Medicare Program; Inpatient Rehabilitation Facility Prospective Payment System for Federal Fiscal Year 2019

AGENCY:

Centers for Medicare & Medicaid Services (CMS), HHS.

ACTION:

Final rule.

SUMMARY:

This final rule updates the prospective payment rates for inpatient rehabilitation facilities (IRFs) for federal fiscal year (FY) 2019. As required by the Social Security Act (the Act), this final rule includes the classification and weighting factors for the IRF prospective payment system's (PPS) case-mix groups and a description of the methodologies and data used in computing the prospective payment rates for FY 2019. This final rule also alleviates administrative burden for IRFs by removing the Functional Independence Measure (FIM^TM) instrument and associated Function Modifiers from the IRF Patient Assessment Instrument (IRF-PAI) beginning in FY 2020 and revises certain IRF coverage requirements to reduce the amount of required paperwork in the IRF setting beginning in FY 2019. Additionally, this final rule incorporates certain data items located in the Quality Indicators section of the IRF-PAI into the IRF case-mix classification system using analysis of 2 years of data beginning in FY 2020. For the IRF Quality Reporting Program (QRP), this final rule adopts a new measure removal factor, removes two measures from the IRF QRP measure set, and codifies a number of program requirements in our regulations.

DATES:

Effective Dates: These regulations are effective on October 1, 2018.

Applicability Dates: The updated IRF prospective payment rates are applicable for IRF discharges occurring on or after October 1, 2018, and on or before September 30, 2019 (FY 2019). In addition, the revisions to certain IRF coverage requirements to reduce the amount of required paperwork in the IRF setting and the updated measures and reporting requirements under the IRF QRP are applicable for IRF discharges occurring on or after October 1, 2018. The removal of the FIM^TM instrument and associated Function Modifiers from the IRF-PAI and refinements to the case-mix classification system are applicable for IRF discharges occurring on or after October 1, 2019.

FOR FURTHER INFORMATION CONTACT:

Gwendolyn Johnson, (410) 786-6954, for general information.

Catie Kraemer, (410) 786-0179, for information about the IRF payment policies and payment rates.

Kadie Derby, (410) 786-0468, for information about the IRF coverage policies.

Christine Grose, (410) 786-1362, for information about the IRF quality reporting program.

SUPPLEMENTARY INFORMATION:

The IRF PPS Addenda along with other supporting documents and tables referenced in this final rule are available through the internet on the CMS website at http://www.cms.hhs.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/.

To assist readers in referencing sections contained in this document, we are providing the following Table of Contents.

Table of Contents

Executive Summary

A. Purpose

B. Summary of Major Provisions

C. Summary of Impacts

D. Improving Patient Outcomes and Reducing Burden Through Meaningful Measures

I. Background

A. Historical Overview of the IRF PPS

B. Provisions of the PPACA Affecting the IRF PPS in FY 2012 and Beyond

C. Operational Overview of the Current IRF PPS

D. Advancing Health Information Exchange

II. Summary of Provisions of the Proposed Rule

III. Analysis and Responses to Public Comments

IV. Update to the Case-Mix Group (CMG) Relative Weights and Average Length of Stay Values for FY 2019

V. Facility-Level Adjustment Factors

VI. FY 2019 IRF PPS Payment Update

A. Background

B. FY 2019 Market Basket Update and Productivity Adjustment

C. Labor-Related Share for FY 2019

D. Wage Adjustment for FY 2019

E. Description of the IRF Standard Payment Conversion Factor and Payment Rates for FY 2019

F. Example of the Methodology for Adjusting the Prospective Payment Rates

VII. Update to Payments for High-Cost Outliers Under the IRF PPS for FY 2019

A. Update to the Outlier Threshold Amount for FY 2019

B. Update to the IRF Cost-to-Charge Ratio Ceiling and Urban/Rural Averages for FY 2019

VIII. Removal of the FIM^TM Instrument and Associated Function Modifiers From the IRF-PAI Beginning With FY 2020 and Refinements to the Case-Mix Classification System Beginning With FY 2020

A. Removal of the FIM^TM Instrument and Associated Function Modifiers From the IRF-PAI Beginning With FY 2020

B. Refinements to the Case-Mix Classification System Beginning With FY 2020

IX. Revisions to Certain IRF Coverage Requirements Beginning With FY 2019

A. Changes to the Physician Supervision Requirement Beginning With FY 2019

B. Changes to the Interdisciplinary Team Meeting Requirement Beginning With FY 2019

C. Changes to the Admission Order Documentation Requirement Beginning With FY 2019

D. Summary of Comments Regarding Additional Changes to the Physician Supervision Requirement

E. Summary of Comments Regarding Changes to the Use of Non-Physician Practitioners in Meeting the Requirements Under § 412.622(a)(3), (4), and (5)

X. Updates to the IRF Quality Reporting Program (QRP)

A. Background

B. General Considerations Used for Selection of Measures for the IRF QRP

C. New Removal Factor for Previously Adopted IRF QRP Measures

D. Quality Measures Currently Adopted for the FY 2020 IRF QRP

E. Removal of Two IRF QRP Measures

F. IMPACT Act Implementation Update

G. Form, Manner, and Timing of Data Submission Under the IRF QRP

H. Changes to the Reconsideration Requirements Under the IRF QRP

I. Policies Regarding Public Display of Measure Data for the IRF QRP

J. Method for Applying the Reduction to the FY 2019 IRF Increase Factor for IRFs That Fail To Meet the Quality Reporting Requirements

XI. Miscellaneous Comments

XII. Provisions of the Final Regulations

XIII. Request for Information on Promoting Interoperability and Electronic Healthcare Information Exchange Through Possible Revisions to the CMS Patient Health and Safety Requirements for Hospitals and Other Medicare- and Medicaid-Participating Providers and Suppliers

XIV. Collection of Information Requirements

A. Statutory Requirement for Solicitation of Comments

B. Collection of Information Requirements for Updates Related to the IRF PPS

C. Collection of Information Requirements for Updates Related to the IRF QRP

XV. Regulatory Impact Analysis

A. Statement of Need

B. Overall Impacts

C. Anticipated Effects

D. Alternatives Considered

E. Regulatory Review Costs

F. Accounting Statement and Table

G. Conclusion

Regulatory Text

Executive Summary

A. Purpose

This final rule updates the prospective payment rates for IRFs for FY 2019 (that is, for discharges occurring on or after October 1, 2018, and on or before September 30, 2019) as required under section 1886(j)(3)(C) of the Act. As required by section 1886(j)(5) of the Act, this rule includes the classification and weighting factors for the IRF PPS's case-mix groups and a description of the methodologies and data used in computing the prospective payment rates for FY 2019. In addition, this final rule reduces the regulatory burden for IRFs by removing data items from the IRF-PAI and revising certain IRF coverage and paperwork requirements. The final rule also updates requirements for the IRF QRP, including adding a new quality measure removal factor, removing two measures from the measure set, and codifying a number of program requirements in our regulations.

B. Summary of Major Provisions

In this final rule, we use the methods described in the FY 2018 IRF PPS final rule (82 FR 36238) to update the prospective payment rates for FY 2019 using updated FY 2017 IRF claims and the most recent available IRF cost report data, which is FY 2016 IRF cost report data. (Note: In the interest of brevity, the rates previously referred to as the “Federal prospective payment rates” are now referred to as the “prospective payment rates”. No change in meaning is intended.) We are also finalizing our proposals to alleviate administrative burden for IRFs by removing the FIM^TM instrument and associated Function Modifiers from the IRF-PAI and revising certain IRF coverage requirements to reduce the amount of required paperwork in the IRF setting. We are also finalizing updates to requirements for the IRF QRP.

C. Summary of Impacts

D. Improving Patient Outcomes and Reducing Burden Through Meaningful Measures

Regulatory reform and reducing regulatory burden are high priorities for CMS. To reduce the regulatory burden on the healthcare industry, lower health care costs, and enhance patient care, in October 2017, we launched the Meaningful Measures Initiative. This initiative is one component of our agency-wide Patients Over Paperwork Initiative, which is aimed at evaluating and streamlining regulations with a goal to reduce unnecessary cost and burden, increase efficiencies, and improve beneficiary experience. The Meaningful Measures Initiative is aimed at identifying the highest priority areas for quality measurement and quality improvement in order to assess the core quality of care issues that are most vital to advancing our work to improve patient outcomes. The Meaningful Measures Initiative represents a new approach to quality measures that fosters operational efficiencies, and will reduce costs, including collection and reporting burden while producing quality measurement that is more focused on meaningful outcomes.

The Meaningful Measures Framework has the following objectives:

• Address high-impact measure areas that safeguard public health;
• Patient-centered and meaningful to patients;
• Outcome-based where possible;
• Fulfill each program's statutory requirements;
• Minimize the level of burden for health care providers (for example, through a preference for EHR-based measures where possible, such as electronic clinical quality measures);
• Significant opportunity for improvement;
• Address measure needs for population based payment through alternative payment models; and
• Align across programs and/or with other payers.

In order to achieve these objectives, we have identified 19 Meaningful Measures areas and mapped them to six overarching quality priorities as shown in the Table 1:

By including Meaningful Measures in our programs, we believe that we can also address the following cross-cutting measure criteria:

• Eliminating disparities;
• Tracking measurable outcomes and impact;
• Safeguarding public health;
• Achieving cost savings;
• Improving access for rural communities; and
• Reducing burden.

We believe that the Meaningful Measures Initiative will improve outcomes for patients, their families, and health care providers while reducing burden and costs for clinicians and providers, as well as promoting operational efficiencies.

Comment: We received numerous comments from stakeholders regarding the Meaningful Measures Initiative and the impact of its implementation in CMS' quality programs. Many of these comments pertained to specific program proposals, and are discussed in the appropriate program-specific sections of this final rule. However, commenters also provided insights and recommendations for the ongoing development of the Meaningful Measures Initiative generally, including: Ensuring transparency in public reporting and the usability of publicly reported data; evaluating the benefit of individual measures to patients via their use in quality programs versus the burden to providers of collecting and reporting that measure data; and identifying additional opportunities for alignment across CMS quality programs.

Response: We will continue to work with stakeholders to refine and further implement the Meaningful Measures Initiative, and will take commenters' insights and recommendations into account moving forward.

I. Background

A. Historical Overview of the IRF PPS

Section 1886(j) of the Act provides for the implementation of a per-discharge prospective payment system (PPS) for inpatient rehabilitation hospitals and inpatient rehabilitation units of a hospital (collectively, hereinafter referred to as IRFs). Payments under the IRF PPS encompass inpatient operating and capital costs of furnishing covered rehabilitation services (that is, routine, ancillary, and capital costs), but not direct graduate medical education costs, costs of approved nursing and allied health education activities, bad debts, and other services or items outside the scope of the IRF PPS. Although a complete discussion of the IRF PPS provisions appears in the original FY 2002 IRF PPS final rule (66 FR 41316) and the FY 2006 IRF PPS final rule (70 FR 47880), we are providing a general description of the IRF PPS for FYs 2002 through 2018.

Under the IRF PPS from FY 2002 through FY 2005, the prospective payment rates were computed across 100 distinct case-mix groups (CMGs), as described in the FY 2002 IRF PPS final rule (66 FR 41316). We constructed 95 CMGs using rehabilitation impairment categories (RICs), functional status (both motor and cognitive), and age (in some cases, cognitive status and age may not be a factor in defining a CMG). In addition, we constructed five special CMGs to account for very short stays and for patients who expire in the IRF.

For each of the CMGs, we developed relative weighting factors to account for a patient's clinical characteristics and expected resource needs. Thus, the weighting factors accounted for the relative difference in resource use across all CMGs. Within each CMG, we created tiers based on the estimated effects that certain comorbidities would have on resource use.

We established the federal PPS rates using a standardized payment conversion factor (formerly referred to as the budget-neutral conversion factor). For a detailed discussion of the budget-neutral conversion factor, please refer to our FY 2004 IRF PPS final rule (68 FR 45684 through 45685). In the FY 2006 IRF PPS final rule (70 FR 47880), we discussed in detail the methodology for determining the standard payment conversion factor.

We applied the relative weighting factors to the standard payment conversion factor to compute the unadjusted prospective payment rates under the IRF PPS from FYs 2002 through 2005. Within the structure of the payment system, we then made adjustments to account for interrupted stays, transfers, short stays, and deaths. Finally, we applied the applicable adjustments to account for geographic variations in wages (wage index), the percentage of low-income patients, location in a rural area (if applicable), and outlier payments (if applicable) to the IRFs' unadjusted prospective payment rates.

For cost reporting periods that began on or after January 1, 2002, and before October 1, 2002, we determined the final prospective payment amounts using the transition methodology prescribed in section 1886(j)(1) of the Act. Under this provision, IRFs transitioning into the PPS were paid a blend of the federal IRF PPS rate and the payment that the IRFs would have received had the IRF PPS not been implemented. This provision also allowed IRFs to elect to bypass this blended payment and immediately be paid 100 percent of the federal IRF PPS rate. The transition methodology expired as of cost reporting periods beginning on or after October 1, 2002 (FY 2003), and payments for all IRFs now consist of 100 percent of the federal IRF PPS rate.

We established a CMS website as a primary information resource for the IRF PPS which is available at http://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/index.html. The website may be accessed to download or view publications, software, data specifications, educational materials, and other information pertinent to the IRF PPS.

Section 1886(j) of the Act confers broad statutory authority upon the Secretary to propose refinements to the IRF PPS. In the FY 2006 IRF PPS final rule (70 FR 47880) and in correcting amendments to the FY 2006 IRF PPS final rule (70 FR 57166) that we published on September 30, 2005, we finalized a number of refinements to the IRF PPS case-mix classification system (the CMGs and the corresponding relative weights) and the case-level and facility-level adjustments. These refinements included the adoption of the Office of Management and Budget's (OMB) Core-Based Statistical Area (CBSA) market definitions, modifications to the CMGs, tier comorbidities, and CMG relative weights, implementation of a new teaching status adjustment for IRFs, rebasing and revising the market basket index used to update IRF payments, and updates to the rural, low-income percentage (LIP), and high-cost outlier adjustments. Beginning with the FY 2006 IRF PPS final rule (70 FR 47908 through 47917), the market basket index used to update IRF payments was a market basket reflecting the operating and capital cost structures for freestanding IRFs, freestanding inpatient psychiatric facilities (IPFs), and long-term care hospitals (LTCHs) (hereinafter referred to as the rehabilitation, psychiatric, and long-term care (RPL) market basket). Any reference to the FY 2006 IRF PPS final rule in this final rule also includes the provisions effective in the correcting amendments. For a detailed discussion of the final key policy changes for FY 2006, please refer to the FY 2006 IRF PPS final rule (70 FR 47880 and 70 FR 57166).

In the FY 2007 IRF PPS final rule (71 FR 48354), we further refined the IRF PPS case-mix classification system (the CMG relative weights) and the case-level adjustments, to ensure that IRF PPS payments would continue to reflect as accurately as possible the costs of care. For a detailed discussion of the FY 2007 policy revisions, please refer to the FY 2007 IRF PPS final rule (71 FR 48354).

In the FY 2008 IRF PPS final rule (72 FR 44284), we updated the prospective payment rates and the outlier threshold, revised the IRF wage index policy, and clarified how we determine high-cost outlier payments for transfer cases. For more information on the policy changes implemented for FY 2008, please refer to the FY 2008 IRF PPS final rule (72 FR 44284), in which we published the final FY 2008 IRF prospective payment rates.

After publication of the FY 2008 IRF PPS final rule (72 FR 44284), section 115 of the Medicare, Medicaid, and SCHIP Extension Act of 2007 (Pub. L. 110-173, enacted on December 29, 2007) (MMSEA) amended section 1886(j)(3)(C) of the Act to apply a zero percent increase factor for FYs 2008 and 2009, effective for IRF discharges occurring on or after April 1, 2008. Section 1886(j)(3)(C) of the Act required the Secretary to develop an increase factor to update the IRF prospective payment rates for each FY. Based on the legislative change to the increase factor, we revised the FY 2008 prospective payment rates for IRF discharges occurring on or after April 1, 2008. Thus, the final FY 2008 IRF prospective payment rates that were published in the FY 2008 IRF PPS final rule (72 FR 44284) were effective for discharges occurring on or after October 1, 2007, and on or before March 31, 2008, and the revised FY 2008 IRF prospective payment rates were effective for discharges occurring on or after April 1, 2008, and on or before September 30, 2008. The revised FY 2008 prospective payment rates are available on the CMS website at http://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Data-Files.html.

In the FY 2009 IRF PPS final rule (73 FR 46370), we updated the CMG relative weights, the average length of stay values, and the outlier threshold; clarified IRF wage index policies regarding the treatment of “New England deemed” counties and multi-campus hospitals; and revised the regulation text in response to section 115 of the MMSEA to set the IRF compliance percentage at 60 percent (the “60 percent rule”) and continue the practice of including comorbidities in the calculation of compliance percentages. We also applied a zero percent market basket increase factor for FY 2009 in accordance with section 115 of the MMSEA. For more information on the policy changes implemented for FY 2009, please refer to the FY 2009 IRF PPS final rule (73 FR 46370), in which we published the final FY 2009 IRF prospective payment rates.

In the FY 2010 IRF PPS final rule (74 FR 39762) and in correcting amendments to the FY 2010 IRF PPS final rule (74 FR 50712) that we published on October 1, 2009, we updated the prospective payment rates, the CMG relative weights, the average length of stay values, the rural, LIP, teaching status adjustment factors, and the outlier threshold; implemented new IRF coverage requirements for determining whether an IRF claim is reasonable and necessary; and revised the regulation text to require IRFs to submit patient assessments on Medicare Advantage (MA) (formerly called Medicare Part C) patients for use in the 60 percent rule calculations. Any reference to the FY 2010 IRF PPS final rule in this final rule also includes the provisions effective in the correcting amendments. For more information on the policy changes implemented for FY 2010, please refer to the FY 2010 IRF PPS final rule (74 FR 39762 and 74 FR 50712), in which we published the final FY 2010 IRF prospective payment rates.

After publication of the FY 2010 IRF PPS final rule (74 FR 39762), section 3401(d) of the Patient Protection and Affordable Care Act (Pub. L. 111-148, enacted on March 23, 2010), as amended by section 10319 of the same Act and by section 1105 of the Health Care and Education Reconciliation Act of 2010 (Pub. L. 111-152, enacted on March 30, 2010) (collectively, hereinafter referred to as “PPACA”), amended section 1886(j)(3)(C) of the Act and added section 1886(j)(3)(D) of the Act. Section 1886(j)(3)(C) of the Act requires the Secretary to estimate a multifactor productivity (MFP) adjustment to the market basket increase factor, and to apply other adjustments as defined by the Act. The productivity adjustment applies to FYs from 2012 forward. The other adjustments apply to FYs 2010 to 2019.

Sections 1886(j)(3)(C)(ii)(II) and 1886(j)(3)(D)(i) of the Act defined the adjustments that were to be applied to the market basket increase factors in FYs 2010 and 2011. Under these provisions, the Secretary was required to reduce the market basket increase factor in FY 2010 by a 0.25 percentage point adjustment. Notwithstanding this provision, in accordance with section 3401(p) of the PPACA, the adjusted FY 2010 rate was only to be applied to discharges occurring on or after April 1, 2010. Based on the self-implementing legislative changes to section 1886(j)(3) of the Act, we adjusted the FY 2010 federal prospective payment rates as required, and applied these rates to IRF discharges occurring on or after April 1, 2010, and on or before September 30, 2010. Thus, the final FY 2010 IRF prospective payment rates that were published in the FY 2010 IRF PPS final rule (74 FR 39762) were used for discharges occurring on or after October 1, 2009, and on or before March 31, 2010, and the adjusted FY 2010 IRF prospective payment rates applied to discharges occurring on or after April 1, 2010, and on or before September 30, 2010. The adjusted FY 2010 prospective payment rates are available on the CMS website at http://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Data-Files.html.

In addition, sections 1886(j)(3)(C) and (D) of the Act also affected the FY 2010 IRF outlier threshold amount because they required an adjustment to the FY 2010 RPL market basket increase factor, which changed the standard payment conversion factor for FY 2010. Specifically, the original FY 2010 IRF outlier threshold amount was determined based on the original estimated FY 2010 RPL market basket increase factor of 2.5 percent and the standard payment conversion factor of $13,661. However, as adjusted, the IRF prospective payments are based on the adjusted RPL market basket increase factor of 2.25 percent and the revised standard payment conversion factor of $13,627. To maintain estimated outlier payments for FY 2010 equal to the established standard of 3 percent of total estimated IRF PPS payments for FY 2010, we revised the IRF outlier threshold amount for FY 2010 for discharges occurring on or after April 1, 2010, and on or before September 30, 2010. The revised IRF outlier threshold amount for FY 2010 was $10,721.

Sections 1886(j)(3)(C)(ii)(II) and 1886(j)(3)(D)(i) of the Act also required the Secretary to reduce the market basket increase factor in FY 2011 by a 0.25 percentage point adjustment. The FY 2011 IRF PPS notice (75 FR 42836) and the correcting amendments to the FY 2011 IRF PPS notice (75 FR 70013) described the required adjustments to the FY 2010 and FY 2011 IRF PPS prospective payment rates and outlier threshold amount for IRF discharges occurring on or after April 1, 2010, and on or before September 30, 2011. It also updated the FY 2011 prospective payment rates, the CMG relative weights, and the average length of stay values. Any reference to the FY 2011 IRF PPS notice in this final rule also includes the provisions effective in the correcting amendments. For more information on the FY 2010 and FY 2011 adjustments or the updates for FY 2011, please refer to the FY 2011 IRF PPS notice (75 FR 42836 and 75 FR 70013).

In the FY 2012 IRF PPS final rule (76 FR 47836), we updated the IRF prospective payment rates, rebased and revised the RPL market basket, and established a new quality reporting program (QRP) for IRFs in accordance with section 1886(j)(7) of the Act. We also consolidated, clarified, and revised existing policies regarding IRF hospitals and IRF units of hospitals to eliminate unnecessary confusion and enhance consistency. For more information on the policy changes implemented for FY 2012, please refer to the FY 2012 IRF PPS final rule (76 FR 47836), in which we published the final FY 2012 IRF prospective payment rates.

The FY 2013 IRF PPS notice (77 FR 44618) described the required adjustments to the FY 2013 prospective payment rates and outlier threshold amount for IRF discharges occurring on or after October 1, 2012, and on or before September 30, 2013. It also updated the FY 2013 prospective payment rates, the CMG relative weights, and the average length of stay values. For more information on the updates for FY 2013, please refer to the FY 2013 IRF PPS notice (77 FR 44618).

In the FY 2014 IRF PPS final rule (78 FR 47860), we updated the prospective payment rates, the CMG relative weights, and the outlier threshold amount. We also updated the facility-level adjustment factors using an enhanced estimation methodology, revised the list of diagnosis codes that count toward an IRF's 60 percent rule compliance calculation to determine “presumptive compliance,” revised sections of the inpatient rehabilitation facility patient assessment instrument (IRF-PAI), revised requirements for acute care hospitals that have IRF units, clarified the IRF regulation text regarding limitation of review, updated references to previously changed sections in the regulations text, and updated requirements for the IRF QRP. For more information on the policy changes implemented for FY 2014, please refer to the FY 2014 IRF PPS final rule (78 FR 47860), in which we published the final FY 2014 IRF prospective payment rates.

In the FY 2015 IRF PPS final rule (79 FR 45872), we updated the prospective payment rates, the CMG relative weights, and the outlier threshold amount. We also revised the list of diagnosis codes that count toward an IRF's 60 percent rule compliance calculation to determine “presumptive compliance,” revised sections of the IRF-PAI, and updated requirements for the IRF QRP. For more information on the policy changes implemented for FY 2015, please refer to the FY 2015 IRF PPS final rule (79 FR 45872) and the FY 2015 IRF PPS correction notice (79 FR 59121).

In the FY 2016 IRF PPS final rule (80 FR 47036), we updated the prospective payment rates, the CMG relative weights, and the outlier threshold amount. We also adopted an IRF-specific market basket that reflects the cost structures of only IRF providers, a blended 1-year transition wage index based on the adoption of new OMB area delineations, a 3-year phase-out of the rural adjustment for certain IRFs due to the new OMB area delineations, and updates for the IRF QRP. For more information on the policy changes implemented for FY 2016, please refer to the FY 2016 IRF PPS final rule (80 FR 47036).

In the FY 2017 IRF PPS final rule (81 FR 52056), we updated the prospective payment rates, the CMG relative weights, and the outlier threshold amount. We also updated requirements for the IRF QRP. For more information on the policy changes implemented for FY 2017, please refer to the FY 2017 IRF PPS final rule (81 FR 52056) and the FY 2017 IRF PPS correction notice (81 FR 59901).

In the FY 2018 IRF PPS final rule (82 FR 36238), we updated the prospective payment rates, the CMG relative weights, and the outlier threshold amount. We also revised the International Classification of Diseases, 10th Revision, Clinical Modification (ICD-10-CM) diagnosis codes that are used to determine presumptive compliance under the “60 percent rule,” removed the 25 percent payment penalty for IRF-PAI late transmissions, removed the voluntary swallowing status item (Item 27) from the IRF-PAI, summarized comments regarding the criteria used to classify facilities for payment under the IRF PPS, provided for a subregulatory process for certain annual updates to the presumptive methodology diagnosis code lists, adopted the use of height/weight items on the IRF-PAI to determine patient body mass index (BMI) greater than 50 for cases of single-joint replacement under the presumptive methodology, and updated requirements for the IRF QRP. For more information on the policy changes implemented for FY 2018, please refer to the FY 2018 IRF PPS final rule (82 FR 36238).

B. Provisions of the PPACA Affecting the IRF PPS in FY 2012 and Beyond

The PPACA included several provisions that affect the IRF PPS in FYs 2012 and beyond. In addition to what was previously discussed, section 3401(d) of the PPACA also added section 1886(j)(3)(C)(ii)(I) of the Act (providing for a “productivity adjustment” for fiscal year 2012 and each subsequent fiscal year). The productivity adjustment for FY 2019 is discussed in section VI.B. of this final rule. Section 3401(d) of the PPACA requires an additional 0.75 percentage point adjustment to the IRF increase factor for each of FYs 2017, 2018, and 2019. The applicable adjustment for FY 2019 is discussed in section VI.B. of this final rule. Section 1886(j)(3)(C)(ii)(II) of the Act provides that the application of these adjustments to the market basket update may result in an update that is less than 0.0 for a fiscal year and in payment rates for a fiscal year being less than such payment rates for the preceding fiscal year.

Sections 3004(b) of the PPACA and section 411(b) of the Medicare Access and CHIP Reauthorization Act of 2015 (Pub. L. 114-10, enacted on April 16, 2015) (MACRA) also addressed the IRF PPS. Section 3004(b) of PPACA reassigned the previously designated section 1886(j)(7) of the Act to section 1886(j)(8) of the Act and inserted a new section 1886(j)(7) of the Act, which contains requirements for the Secretary to establish a QRP for IRFs. Under that program, data must be submitted in a form and manner and at a time specified by the Secretary. Section 411(b) of MACRA amended section 1886(j)(3)(C) of the Act by adding clause (iii), which required us to apply for FY 2018, after the application of section 1886(j)(3)(C)(ii) of the Act, an increase factor of 1.0 percent to update the IRF prospective payment rates. Beginning in FY 2014, section 1886(j)(7)(A)(i) of the Act requires the application of a 2 percentage point reduction to the market basket increase factor otherwise applicable to an IRF (after application of subparagraphs (C)(iii) and (D) of section 1886(j)(3) of the Act) for a fiscal year if the IRF does not comply with the requirements of the IRF QRP for that fiscal year. Application of the 2 percentage point reduction may result in an update that is less than 0.0 for a fiscal year and in payment rates for a fiscal year being less than such payment rates for the preceding fiscal year. Reporting-based reductions to the market basket increase factor are not cumulative; they only apply for the FY involved.

C. Operational Overview of the Current IRF PPS

As described in the FY 2002 IRF PPS final rule (66 FR 41316), upon the admission and discharge of a Medicare Part A Fee-for-Service (FFS) patient, the IRF is required to complete the appropriate sections of a patient assessment instrument (PAI), designated as the IRF-PAI. In addition, beginning with IRF discharges occurring on or after October 1, 2009, the IRF is also required to complete the appropriate sections of the IRF-PAI upon the admission and discharge of each Medicare Advantage (MA) patient, as described in the FY 2010 IRF PPS final rule (74 FR 39762 and 74 FR 50712). All required data must be electronically encoded into the IRF-PAI software product. Generally, the software product includes patient classification programming called the Grouper software. The Grouper software uses specific IRF-PAI data elements to classify (or group) patients into distinct CMGs and account for the existence of any relevant comorbidities.

The Grouper software produces a five-character CMG number. The first character is an alphabetic character that indicates the comorbidity tier. The last four characters are numeric characters that represent the distinct CMG number. Free downloads of the Inpatient Rehabilitation Validation and Entry (IRVEN) software product, including the Grouper software, are available on the CMS website at http://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Software.html.

Once a Medicare Part A FFS patient is discharged, the IRF submits a Medicare claim as a Health Insurance Portability and Accountability Act of 1996 (Pub. L. 104-191, enacted on August 21, 1996) (HIPAA) compliant electronic claim or, if the Administrative Simplification Compliance Act of 2002 (Pub. L. 107-105, enacted on December 27, 2002) (ASCA) permits, a paper claim (a UB-04 or a CMS-1450 as appropriate) using the five-character CMG number and sends it to the appropriate Medicare Administrative Contractor (MAC). In addition, once a MA patient is discharged, in accordance with the Medicare Claims Processing Manual, chapter 3, section 20.3 (Pub. 100-04), hospitals (including IRFs) must submit an informational-only bill (Type of Bill (TOB) 111), which includes Condition Code 04 to their MAC. This will ensure that the MA days are included in the hospital's Supplemental Security Income (SSI) ratio (used in calculating the IRF LIP adjustment) for fiscal year 2007 and beyond. Claims submitted to Medicare must comply with both ASCA and HIPAA.

Section 3 of the ASCA amended section 1862(a) of the Act by adding paragraph (22), which requires the Medicare program, subject to section 1862(h) of the Act, to deny payment under Part A or Part B for any expenses for items or services for which a claim is submitted other than in an electronic form specified by the Secretary. Section 1862(h) of the Act, in turn, provides that the Secretary shall waive such denial in situations in which there is no method available for the submission of claims in an electronic form or the entity submitting the claim is a small provider. In addition, the Secretary also has the authority to waive such denial in such unusual cases as the Secretary finds appropriate. For more information, see the “Medicare Program; Electronic Submission of Medicare Claims” final rule (70 FR 71008). Our instructions for the limited number of Medicare claims submitted on paper are available at http://www.cms.gov/manuals/downloads/clm104c25.pdf.

Section 3 of the ASCA operates in the context of the administrative simplification provisions of HIPAA, which include, among others, the requirements for transaction standards and code sets codified in 45 CFR, parts 160 and 162, subparts A and I through R (generally known as the Transactions Rule). The Transactions Rule requires covered entities, including covered health care providers, to conduct covered electronic transactions according to the applicable transaction standards. (See the CMS program claim memoranda at http://www.cms.gov/ElectronicBillingEDITrans/ and listed in the addenda to the Medicare Intermediary Manual, Part 3, section 3600).

The MAC processes the claim through its software system. This software system includes pricing programming called the “Pricer” software. The Pricer software uses the CMG number, along with other specific claim data elements and provider-specific data, to adjust the IRF's prospective payment for interrupted stays, transfers, short stays, and deaths, and then applies the applicable adjustments to account for the IRF's wage index, percentage of low-income patients, rural location, and outlier payments. For discharges occurring on or after October 1, 2005, the IRF PPS payment also reflects the teaching status adjustment that became effective as of FY 2006, as discussed in the FY 2006 IRF PPS final rule (70 FR 47880).

D. Advancing Health Information Exchange

The Department of Health and Human Services (HHS) has a number of initiatives designed to encourage and support the adoption of interoperable health information technology and to promote nationwide health information exchange to improve health care. The Office of the National Coordinator for Health Information Technology (ONC) and CMS work collaboratively to advance interoperability across settings of care, including post-acute care.

The Improving Medicare Post-Acute Care Transformation Act of 2014 (Pub. L. 113-185, enacted on October 6, 2014) (IMPACT Act) requires assessment data to be standardized and interoperable to allow for exchange of the data among post-acute providers and other providers. To further interoperability in post-acute care, CMS is developing a Data Element Library to serve as a publically available centralized, authoritative resource for standardized data elements and their associated mappings to health IT standards. These interoperable data elements can reduce provider burden by supporting the use and reuse of healthcare data, support provider exchange of electronic health information for care coordination, person-centered care, and support real-time, data driven, clinical decision making. Once available, standards in the Data Element Library can be referenced on the CMS website and in the ONC Interoperability Standards Advisory (ISA).

The 2018 Interoperability Standards Advisory (ISA) is available at https://www.healthit.gov/isa/.

Most recently, the 21st Century Cures Act (Pub. L. 114-255, enacted on December 13, 2016) (Cures Act), requires HHS to take new steps to enable the electronic sharing of health information ensuring interoperability for providers and settings across the care continuum. Specifically, Congress directed ONC to “develop or support a trusted exchange framework, including a common agreement among health information networks nationally.” This framework ( https://beta.healthit.gov/topic/interoperability/trusted-exchange-framework-and-common-agreement ) outlines a common set of principles for trusted exchange and minimum terms and conditions for trusted exchange in order to enable interoperability across disparate health information networks. In another important provision, Congress defined “information blocking” as practices likely to interfere with, prevent, or materially discourage access, exchange, or use of electronic health information, and established new authority for HHS to discourage these practices. We invite providers to learn more about these important developments and how they are likely to affect IRFs.

II. Summary of Provisions of the Proposed Rule

In the FY 2019 IRF PPS proposed rule (83 FR 20972), we proposed to update the IRF prospective payment rates for FY 2019 and to alleviate administrative burden for IRFs by removing the FIM^TM instrument and associated Function Modifiers from the IRF-PAI in accordance with section 1886(j)(2)(D) of the Act and revise certain IRF coverage requirements to reduce the amount of required paperwork in the IRF setting. In addition, we solicited comments on removing the face-to-face requirement for rehabilitation physician visits and expanding the use of non-physician practitioners (that is, nurse practitioners and physician assistants) in meeting the IRF coverage requirements. For the IRF QRP, we proposed to add a new quality measure removal factor, remove two quality measures from the measure set, and codify in our regulations a number of requirements.

The proposed updates to the IRF prospective payment rates for FY 2019 are as follows:

• Update the IRF PPS relative weights and average length of stay values for FY 2019 using the most current and complete Medicare claims and cost report data in a budget-neutral manner, as discussed in section III. of the FY 2019 IRF PPS proposed rule (83 FR 20972, 20978 through 20981).
• Describe the continued use of FY 2014 facility-level adjustment factors, as discussed in section IV. of the FY 2019 IRF PPS proposed rule (83 FR 20972 at 20981).
• Update the IRF PPS payment rates for FY 2019 by the market basket increase factor, based upon the most current data available, with a 0.75 percentage point reduction as required by sections 1886(j)(3)(C)(ii)(II) and 1886(j)(3)(D)(v) of the Act and a productivity adjustment required by section 1886(j)(3)(C)(ii)(I) of the Act, as described in section V. of the FY 2019 IRF PPS proposed rule (83 FR 20972 at 20982).
• Update the FY 2019 IRF PPS payment rates by the FY 2019 wage index and the labor-related share in a budget-neutral manner, as discussed in section V. of the FY 2019 IRF PPS proposed rule (83 FR 20972, 20982 through 20984).
• Describe the calculation of the IRF standard payment conversion factor for FY 2019, as discussed in section V. of the FY 2019 IRF PPS proposed rule (83 FR 20972, 20984 through 20985).
• Update the outlier threshold amount for FY 2019, as discussed in section VI. of the FY 2019 IRF PPS proposed rule (83 FR 20972 at 20987).
• Update the cost-to-charge ratio (CCR) ceiling and urban/rural average CCRs for FY 2019, as discussed in section VI. of the FY 2019 IRF PPS proposed rule (83 FR 20972, 20987 through 20988).
• Remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI beginning with FY 2020 to reduce administrative burden for IRFs, as discussed in section VII. of the FY 2019 IRF PPS proposed rule (83 FR 20972, 20988 through 20995).
• Revise certain IRF coverage requirements to reduce administrative burden for IRFs beginning with FY 2019, as discussed in section VIII. of the FY 2019 IRF PPS proposed rule (83 FR 20972, 20995 through 20997).
• Solicit comments on removing the face-to-face requirement for rehabilitation physician visits, as discussed in section VIII. of the FY 2019 IRF PPS proposed rule (83 FR 20972, 20997 through 20998).
• Solicit comments on expanding the use of non-physician practitioners (that is, nurse practitioners and physician assistants) in meeting the IRF coverage requirements, as discussed in section VIII. of the FY 2019 IRF PPS proposed rule (83 FR 20972, 20998 through 20999).
• Update the requirements for the IRF QRP, as discussed in section IX. of the FY 2019 IRF PPS proposed rule (83 FR 20972, 20999 through 21004).

III. Analysis and Response to Public Comments

We received 109 timely responses from the public, many of which contained multiple comments on the FY 2019 IRF PPS proposed rule (83 FR 20972). We received comments from various trade associations, inpatient rehabilitation facilities, individual physicians, therapists, clinicians, health care industry organizations, and health care consulting firms. The following sections, arranged by subject area, include a summary of the public comments that we received, and our responses.

IV. Update to the Case-Mix Group (CMG) Relative Weights and Average Length of Stay Values for FY 2019

As specified in § 412.620(b)(1), we calculate a relative weight for each CMG that is proportional to the resources needed by an average inpatient rehabilitation case in that CMG. For example, cases in a CMG with a relative weight of 2, on average, will cost twice as much as cases in a CMG with a relative weight of 1. Relative weights account for the variance in cost per discharge due to the variance in resource utilization among the payment groups, and their use helps to ensure that IRF PPS payments support beneficiary access to care, as well as provider efficiency.

In the FY 2019 IRF PPS proposed rule (83 FR 20972, 20978 through 20981), we proposed to update the CMG relative weights and average length of stay values for FY 2019. As required by statute, we always use the most recent available data to update the CMG relative weights and average lengths of stay. For FY 2019, we proposed to use the FY 2017 IRF claims and FY 2016 IRF cost report data. These data are the most current and complete data available at this time. We note that, as we typically do, we updated our data between the FY 2019 IRF PPS proposed and final rules to ensure that we use the most recent available data in calculating IRF PPS payments. This updated data reflects a more complete set of claims for FY 2017 and additional cost report data for FY 2016.

In the FY 2019 IRF PPS proposed rule, we proposed to apply these data using the same methodologies that we have used to update the CMG relative weights and average length of stay values each fiscal year since we implemented an update to the methodology to use the more detailed CCR data from the cost reports of IRF subprovider units of primary acute care hospitals, instead of CCR data from the associated primary care hospitals, to calculate IRFs' average costs per case, as discussed in the FY 2009 IRF PPS final rule (73 FR 46372). In calculating the CMG relative weights, we use a hospital-specific relative value method to estimate operating (routine and ancillary services) and capital costs of IRFs. The process used to calculate the CMG relative weights for this final rule is as follows:

Step 1. We estimate the effects that comorbidities have on costs.

Step 2. We adjust the cost of each Medicare discharge (case) to reflect the effects found in the first step.

Step 3. We use the adjusted costs from the second step to calculate CMG relative weights, using the hospital-specific relative value method.

Step 4. We normalize the FY 2019 CMG relative weights to the same average CMG relative weight from the CMG relative weights implemented in the FY 2018 IRF PPS final rule (82 FR 36238).

Consistent with the methodology that we have used to update the IRF classification system in each instance in the past, we proposed to update the CMG relative weights for FY 2019 in such a way that total estimated aggregate payments to IRFs for FY 2019 are the same with or without the changes (that is, in a budget-neutral manner) by applying a budget neutrality factor to the standard payment amount. To calculate the appropriate budget neutrality factor for use in updating the FY 2019 CMG relative weights, we use the following steps:

Step 1. Calculate the estimated total amount of IRF PPS payments for FY 2019 (with no changes to the CMG relative weights).

Step 2. Calculate the estimated total amount of IRF PPS payments for FY 2019 by applying the changes to the CMG relative weights (as discussed in this final rule).

Step 3. Divide the amount calculated in step 1 by the amount calculated in step 2 to determine the budget neutrality factor (0.9981) that would maintain the same total estimated aggregate payments in FY 2019 with and without the changes to the CMG relative weights.

Step 4. Apply the budget neutrality factor (0.9981) to the FY 2018 IRF PPS standard payment amount after the application of the budget-neutral wage adjustment factor.

In section VI.E. of this final rule, we discuss the use of the existing methodology to calculate the standard payment conversion factor for FY 2019.

In Table 2, “Relative Weights and Average Length of Stay Values for Case-Mix Groups,” we present the CMGs, the comorbidity tiers, the corresponding relative weights, and the average length of stay values for each CMG and tier for FY 2019. The average length of stay for each CMG is used to determine when an IRF discharge meets the definition of a short-stay transfer, which results in a per diem case level adjustment.

Generally, updates to the CMG relative weights result in some increases and some decreases to the CMG relative weight values. Table 3 shows how we estimate that the application of the revisions for FY 2019 would affect particular CMG relative weight values, which would affect the overall distribution of payments within CMGs and tiers. Note that, because we proposed to implement the CMG relative weight revisions in a budget-neutral manner (as previously described), total estimated aggregate payments to IRFs for FY 2019 would not be affected as a result of the CMG relative weight revisions. However, the revisions would affect the distribution of payments within CMGs and tiers.

As Table 3 shows, 99.3 percent of all IRF cases are in CMGs and tiers that would experience less than a 5 percent change (either increase or decrease) in the CMG relative weight value as a result of the revisions for FY 2019. The largest estimated increase in the CMG relative weight values that affects the largest number of IRF discharges would be a 3.4 percent change in the CMG relative weight value for CMG 0806 Replacement of lower extremity joint, with a motor score less than 22.05 —with no tier adjustment. In the FY 2017 claims data, 1,593 IRF discharges (0.4 percent of all IRF discharges) were classified into this CMG and tier.

The largest estimated decrease in a CMG relative weight value affecting the largest number of IRF cases would be a 2.1 percent decrease in the CMG relative weight for CMG 0304—Non-traumatic brain injury, with a motor score less than 26.5—with no tier adjustment. In the FY 2017 IRF claims data, this change would have affected 3,388 cases (0.8 percent of all IRF cases).

The proposed changes in the average length of stay values for FY 2019, compared with the FY 2018 average length of stay values, are small and do not show any particular trends in IRF length of stay patterns.

We received 1 comment on the proposed update to the CMG relative weights and average length of stay values for FY 2019, which is summarized below.

Comment: The commenter was supportive of our proposal to use the most recent data available to update the relative weights and average length of stays values for FY 2019. The commenter also requested that CMS make available any reports and analyses that we used to update the relative weights and average length of stay values.

Response: We appreciate the commenter's support of our proposal to use the most recent data available to update the relative weights and average length of stays values for FY 2019. For reports on the methodology that we use annually to update the relative weights and average length of stay values, we refer stakeholders to reports issued by the RAND Corporation (RAND) for the implementation of the IRF PPS, which can be downloaded from RAND's website at https://www.rand.org/pubs/drafts/DRU2309.html and at https://www.rand.org/pubs/monograph_reports/MR1500.html. We also refer stakeholders to a report that was issued by RAND in 2005 that specifically discusses the methodology for construction of the CMGs and the relative weights associated with the CMGs, which can be downloaded from RAND's website at https://www.rand.org/pubs/technical_reports/TR207.html. We used the same methodology, with one exception, that RAND used in these reports to calculate the CMG relative weights and average length of stay values. For a specific discussion of the change in our methodology that we implemented in FY 2009, we refer stakeholders to the FY 2009 IRF PPS final rule (73 FR 46372).

Final Decision: After consideration of the public comments, we are finalizing our proposal to update the CMG relative weight and average length of stay values for FY 2019, as shown in Table 2 of this final rule. These updates are effective October 1, 2018.

V. Facility-Level Adjustment Factors

Section 1886(j)(3)(A)(v) of the Act confers broad authority upon the Secretary to adjust the per unit payment rate by such factors as the Secretary determines are necessary to properly reflect variations in necessary costs of treatment among rehabilitation facilities. Under this authority, we currently adjust the prospective payment amount associated with a CMG to account for facility-level characteristics such as an IRF's LIP, teaching status, and location in a rural area, if applicable, as described in § 412.624(e).

Based on the substantive changes to the facility-level adjustment factors that were adopted in the FY IRF PPS 2014 final rule (78 FR 47860, 47868 through 47872), in the FY 2015 IRF PPS final rule (79 FR 45872, 45882 through 45883), we froze the facility-level adjustment factors at the FY 2014 levels for FY 2015 and all subsequent years (unless and until we propose to update them again through future notice-and-comment rulemaking). For FY 2019, we will continue to hold the adjustment factors at the FY 2014 levels as we continue to monitor the most current IRF claims data available and continue to evaluate and monitor the effects of the FY 2014 changes.

VI. FY 2019 IRF PPS Payment Update

A. Background

Section 1886(j)(3)(C) of the Act requires the Secretary to establish an increase factor that reflects changes over time in the prices of an appropriate mix of goods and services included in the IRF PPS payment, which is referred to as a market basket index. According to section 1886(j)(3)(A)(i) of the Act, the increase factor shall be used to update the IRF prospective payment rates for each FY. Section 1886(j)(3)(C)(ii)(I) of the Act requires the application of a productivity adjustment. In addition, sections 1886(j)(3)(C)(ii)(II) and 1886(j)(3)(D)(v) of the Act require the application of a 0.75 percentage point reduction to the market basket increase factor for FY 2019. Thus, in the FY 2019 IRF proposed rule (83 FR 20981), we proposed to update the IRF PPS payments for FY 2019 by a market basket increase factor as required by section 1886(j)(3)(C) of the Act, with a productivity adjustment as required by section 1886(j)(3)(C)(ii)(I) of the Act, and a 0.75 percentage point reduction as required by sections 1886(j)(3)(C)(ii)(II) and 1886(j)(3)(D)(v) of the Act.

Beginning with the FY 2016 IRF PPS, we created and adopted a stand-alone IRF market basket, which was referred to as the 2012-based IRF market basket, reflecting the operating and capital cost structures for freestanding IRFs and hospital-based IRFs. The FY 2016 IRF PPS final rule (80 FR 47046 through 47068) contains a complete discussion of the development of the 2012-based IRF market basket.

B. FY 2019 Market Basket Update and Productivity Adjustment

For FY 2018, we applied an increase factor of 1.0 percent to update the IRF prospective payment rates in accordance with section 1886(j)(3)(C)(iii) of the Act, as added by section 411(b) of MACRA. However, as discussed previously, for FY 2019, we proposed to update the IRF PPS payments by a market basket increase factor as required by section 1886(j)(3)(C) of the Act, with a productivity adjustment as required by section 1886(j)(3)(C)(ii)(I) of the Act, and a 0.75 percentage point reduction as required by sections 1886(j)(3)(C)(ii)(II) and 1886(j)(3)(D)(v) of the Act. For FY 2019, we proposed to use the same methodology described in the FY 2017 IRF PPS final rule (81 FR 52071) to compute the FY 2019 market basket increase factor to update the IRF PPS base payment rate.

Consistent with historical practice, we proposed to estimate the market basket update for the IRF PPS based on the most up-to-date forecast of price indexes used in the market basket as forecasted by IHS Global Inc. (IGI). IGI is a nationally recognized economic and financial forecasting firm with which we contract to forecast the components of the market baskets and MFP. Based on IGI's first quarter 2018 forecast with historical data through the fourth quarter of 2017, we proposed that the projected 2012-based IRF market basket increase factor for FY 2019 would be 2.9 percent. We also proposed that if more recent data were subsequently available (for example, a more recent estimate of the market basket update), we would use such data to determine the FY 2019 market basket update in the final rule. Incorporating the most recent data available, based on IGI's second quarter 2018 forecast with historical data through the first quarter of 2018, the projected 2012-based IRF market basket increase factor for FY 2019 is 2.9 percent.

According to section 1886(j)(3)(C)(i) of the Act, the Secretary shall establish an increase factor based on an appropriate percentage increase in a market basket of goods and services. Section 1886(j)(3)(C)(ii) of the Act then requires that, after establishing the increase factor for a FY, the Secretary shall reduce such increase factor for FY 2012 and each subsequent FY, by the productivity adjustment described in section 1886(b)(3)(B)(xi)(II) of the Act. Section 1886(b)(3)(B)(xi)(II) of the Act sets forth the definition of this productivity adjustment. The statute defines the productivity adjustment to be equal to the 10-year moving average of changes in annual economy-wide private nonfarm business multifactor productivity (MFP) (as projected by the Secretary for the 10-year period ending with the applicable FY, year, cost reporting period, or other annual period) (the “MFP adjustment”). The BLS publishes the official measure of private nonfarm business MFP. Please see http://www.bls.gov/mfp for the BLS historical published MFP data. A complete description of the MFP projection methodology is available on the CMS website at https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/MedicareProgramRatesStats/MarketBasketResearch.html.

Using IGI's first quarter 2018 forecast, the projected MFP adjustment for FY 2019 (the 10-year moving average of MFP for the period ending FY 2019) was 0.8 percent. We proposed that if more recent data were subsequently available, we would use such data to determine the FY 2019 MFP adjustment in the final rule. Incorporating the most recent data available, based on IGI's second quarter 2018 forecast, the projected MFP adjustment for FY 2019 is 0.8 percent.

Thus, in accordance with section 1886(j)(3)(C) of the Act, we proposed to base the FY 2019 market basket update, which is used to determine the applicable percentage increase for the IRF payments, on the most recent estimate of the 2012-based IRF market basket. We proposed to then reduce this percentage increase by the most recent estimate of the MFP adjustment for FY 2019. Following application of the MFP adjustment, we proposed to further reduce the applicable percentage increase by 0.75 percentage point, as required by sections 1886(j)(3)(C)(ii)(II) and 1886(j)(3)(D)(v) of the Act. Therefore, the proposed FY 2019 IRF update was 1.35 percent (2.9 percent market basket update, less 0.8 percentage point MFP adjustment, less 0.75 percentage point statutorily required adjustment). Furthermore, we proposed that if more recent data were subsequently available (for example, a more recent estimate of the MFP adjustment), we would use such data to determine the FY 2019 MFP adjustment in the final rule. Incorporating the most recent data, the current estimate of the FY 2019 IRF update is 1.35 percent (2.9 percent market basket update, less 0.8 percentage point MFP adjustment, less 0.75 percentage point statutorily required adjustment).

For FY 2019, the Medicare Payment Advisory Commission (MedPAC) recommends that we reduce IRF PPS payment rates by 5 percent. As discussed, and in accordance with sections 1886(j)(3)(C) and 1886(j)(3)(D) of the Act, the Secretary proposed to update the IRF PPS payment rates for FY 2019 by an adjusted market basket increase factor of 1.35 percent, as section 1886(j)(3)(C) of the Act does not provide the Secretary with the authority to apply a different update factor to IRF PPS payment rates for FY 2019. As noted above, incorporating the most recent data, the current estimate of the FY 2019 IRF update is 1.35 percent.

We received 4 comments on the proposed market basket increase update and productivity adjustment, which are summarized below.

Comment: One commenter noted that they generally concur with the methodology CMS has used to arrive at the proposed net market basket update of 1.35 percent and encouraged CMS to use the latest available information to update this market basket percentage in the final rule.

Response: We appreciate the commenter's support for the proposed payment update for FY 2019 and, as proposed, have used more recent data to determine the market basket percentage for the final rule.

Comment: One commenter requested CMS provide access to the analyses done by contractors to calculate the market basket update each year.

Response: The market basket update is derived using (1) the market basket base year cost weights as finalized by CMS through rulemaking and (2) the most up-to-date forecast of the price proxies used in the market basket as forecasted by IGI. As stated previously, IGI is a nationally recognized economic and financial forecasting firm, with which we contract to forecast the components of the market baskets and MFP. To determine the market basket update, for each cost category in the market basket (for example, Wages and Salaries, Pharmaceuticals), the level of each of these price forecasts are multiplied by the cost weight for that cost category. The sum of these products (that is, weights multiplied by proxied index levels) for all cost categories yields the composite index level in the market basket in a given year. The most recent forecast of each market basket is available on the CMS website at https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/MedicareProgramRatesStats/MarketBasketData.html.

More detailed forecasts are readily available by request; please send an email to CMSDNHS@cms.hhs.gov to be added to the mailing list for detailed market basket forecasts.

Comment: Several commenters recommended that CMS carefully monitor the impact productivity adjustments have on the rehabilitation hospital sector, provide feedback to Congress as appropriate, and utilize any authority the agency has to reduce the productivity adjustment. One commenter stated their concern that IRFs will not have the ability to generate additional productivity gains at a pace matching the productivity of the economy at large on an ongoing, consistent basis as currently contemplated by the PPACA. The commenter further noted the difficulties in achieving productivity gains in the IRF setting due to the labor intensive nature of the care and unchanging labor-intensive standards such as the 3-hour therapy rule. One commenter specifically requested that CMS provide feedback to Congress, which would include a proposal to end the productivity adjustment effective with the end of the mandated PPACA Market Basket reductions.

Response: We acknowledge the commenters' concerns regarding MFP growth at the economy-wide level and its application to IRFs. As stated above, section 1886(j)(3)(C)(ii)(I) of the Act requires the application of a productivity adjustment to the IRF PPS market basket increase factor.

We will continue to monitor the impact of the payment updates, including the effects of the productivity adjustment, on IRF provider margins as well as beneficiary access to care. We note that each year, MedPAC makes an annual update recommendation to Congress based on a variety of measures related to payment adequacy, including analysis that showed freestanding IRF Medicare margins have been above 10 percent since 2011.

Comment: One commenter (MedPAC) noted that while they understand that CMS is required to implement the statutory update for IRF payment for FY 2019, the commenter continue to recommend that IRF payment rates be reduced by 5 percent for FY 2019. The commenter noted that this recommendation is based on a review of many factors—including indicators of beneficiary access to rehabilitative services, the supply of providers, and aggregate IRF Medicare margins, which have been above 10 percent since 2011. The commenter also noted their appreciation that CMS cited their recommendation, even though the Secretary does not have the authority to deviate from statutorily mandated updates.

Response: As discussed, in accordance with section 1886(j)(3)(C) of the Act, the increase factor for FY 2019 must be set equal to the FY 2019 projected market basket increase factor, reduced by the productivity adjustment, and further reduced by a 0.75 percent statutorily required adjustment. Section 1886(j)(3)(C) of the Act does not provide the Secretary with the authority to apply a different update factor to IRF PPS payment rates for FY 2019.

Final Decision: After careful consideration of comments, we are finalizing the FY 2019 IRF update of 1.35 percent.

C. Labor-Related Share for FY 2019

Section 1886(j)(6) of the Act specifies that the Secretary is to adjust the proportion (as estimated by the Secretary from time to time) of rehabilitation facilities' costs which are attributable to wages and wage-related costs of the prospective payment rates computed under section 1886(j)(3) of the Act for area differences in wage levels by a factor (established by the Secretary) reflecting the relative hospital wage level in the geographic area of the rehabilitation facility compared to the national average wage level for such facilities. The labor-related share is determined by identifying the national average proportion of total costs that are related to, influenced by, or vary with the local labor market. We continue to classify a cost category as labor-related if the costs are labor-intensive and vary with the local labor market.

Based on our definition of the labor-related share and the cost categories in the 2012-based IRF market basket, we proposed to calculate the labor-related share for FY 2019 as the sum of the FY 2019 relative importance of Wages and Salaries, Employee Benefits, Professional Fees: Labor-Related, Administrative and Facilities Support Services, Installation, Maintenance, and Repair Services, All Other: Labor-related Services, and a portion of the Capital-Related cost weight from the 2012-based IRF market basket. For more details regarding the methodology for determining specific cost categories for inclusion in the 2012-based IRF labor-related share, see the FY 2016 IRF final rule (80 FR 47066 through 47068).

Using this method and IGI's first quarter 2018 forecast for the 2012-based IRF market basket, the proposed IRF labor-related share for FY 2019 was 70.6 percent. We also proposed that if more recent data were subsequently available (for example, a more recent estimate of the labor-related share), we would use such data to determine the FY 2019 IRF labor-related share in the final rule.

Incorporating the most recent estimate of the 2012-based IRF market basket based on IGI's second quarter 2018 forecast with historical data through the first quarter of 2018, the sum of the relative importance for FY 2019 operating costs (Wages and Salaries, Employee Benefits, Professional Fees: Labor-related, Administrative and Facilities Support Services, Installation Maintenance & Repair Services, and All Other: Labor-related Services) using the 2012-based IRF market basket is 66.7 percent. We proposed that the portion of Capital-Related Costs that are influenced by the local labor market was estimated to be 46 percent. Incorporating the most recent estimate of the FY 2019 relative importance of Capital-Related costs from the 2012-based IRF market basket based on IGI's second quarter 2018 forecast with historical data through the first quarter of 2018, which is 8.2 percent, we take 46 percent of 8.2 percent to determine the labor-related share of Capital for FY 2019. We proposed to then add this amount (3.8 percent) to the sum of the relative importance for FY 2019 operating costs (66.7 percent) to determine the total labor-related share for FY 2019 of 70.5 percent.

Final Decision: As we did not receive any comments on the proposed labor-related share for FY 2019, we are finalizing the FY 2019 labor-related share of 70.5 percent.

D. Wage Adjustment for FY 2019

1. Background

Section 1886(j)(6) of the Act requires the Secretary to adjust the proportion of rehabilitation facilities' costs attributable to wages and wage-related costs (as estimated by the Secretary from time to time) by a factor (established by the Secretary) reflecting the relative hospital wage level in the geographic area of the rehabilitation facility compared to the national average wage level for those facilities. The Secretary is required to update the IRF PPS wage index on the basis of information available to the Secretary on the wages and wage-related costs to furnish rehabilitation services. Any adjustment or updates made under section 1886(j)(6) of the Act for a FY are made in a budget-neutral manner.

For FY 2019, we proposed to maintain the policies and methodologies described in the FY 2018 IRF PPS final rule (82 FR 36238, 36249 through 36250) related to the labor market area definitions and the wage index methodology for areas with wage data. Thus, we proposed to use the CBSA labor market area definitions and the FY 2018 pre-reclassification and pre-floor hospital wage index data. In accordance with section 1886(d)(3)(E) of the Act, the FY 2018 pre-reclassification and pre-floor hospital wage index is based on data submitted for hospital cost reporting periods beginning on or after October 1, 2013, and before October 1, 2014 (that is, FY 2014 cost report data).

The labor market designations made by the OMB include some geographic areas where there are no hospitals and, thus, no hospital wage index data on which to base the calculation of the IRF PPS wage index. We proposed to continue to use the same methodology discussed in the FY 2008 IRF PPS final rule (72 FR 44299) to address those geographic areas where there are no hospitals and, thus, no hospital wage index data on which to base the calculation for the FY 2019 IRF PPS wage index.

We received 9 public comments on the proposed wage index adjustment and related policies for FY 2019, which are summarized below.

Comment: Commenters suggested that we should use the FY 2019 IPPS pre-reclassified acute care hospital wage index in the calculation of the FY 2019 IRF PPS wage index, as we do for the IPPS, the long-term care hospital PPS, the skilled nursing facility PPS, and the home health PPS, rather than using the FY 2018 IPPS pre-reclassified acute care hospital wage index, as we do in the IRF PPS, the inpatient psychiatric facility PPS, and the hospice PPS. Commenters indicated that using the same wage index data for the IRF PPS that is used in other post-acute and acute care settings would eliminate one difference between Medicare payments for IRFs and Medicare payments for other post-acute and acute care providers, thereby allowing IRFs to demonstrate their cost-effectiveness relative to other post-acute care service providers. By demonstrating their cost-effectiveness relative to other post-acute care service providers, IRFs would have more of an opportunity to participate successfully in alternative payment models currently being tested by Medicare, which generally provide financial incentives for cost effectiveness.

Response: Consistent with historical practice and to ensure the stability and predictability of Medicare payments under the IRF PPS, we proposed to update the IRF wage index for FY 2019 using the FY 2018 pre-reclassification and pre-floor acute care hospital wage index (that is, using a one-year lag of the hospital wage index). The FY 2018 pre-reclassification and pre-floor hospital wage index values are based on data collected from the Medicare cost reports submitted by hospitals for cost reporting periods beginning in FY 2014. We use FY 2014 cost reporting period data to determine the applicable IRF PPS wage index values because, at the point we use these data, the values are more stable and do not tend to change. We do not believe that our continued use of the one-year lag of the hospital wage index for the IRF PPS hinders the ability of IRFs to demonstrate their cost effectiveness. However, we will continue to analyze these issues for future policy development.

Comment: One commenter requested that, until a new wage index system is implemented, we should establish a smoothing variable to be applied to the current IRF wage index to reduce the fluctuations IRFs experience annually.

Response: As stated above, under section 1886(j)(6) of the Act, we adjust IRF PPS rates to account for differences in area wage levels. Any perceived volatility in the wage index is predicated upon volatility in actual wages in that area and reflects real differences in area wage levels. As we believe that the application of a smoothing variable would make the wage index values less reflective of the area wage levels, we do not believe it would be appropriate to implement such a change to the IRF wage index policy.

As we most recently discussed in the FY 2018 IRF PPS final rule (82 FR 36238, 36250), section 3137(b) of the PPACA required us to submit a report to the Congress by December 31, 2011 that included a plan to reform the hospital wage index system. This report describes the concept of a Commuting Based Wage Index as a potential replacement to the current Medicare wage index methodology. While this report addresses the goals of broad based Medicare wage index reform, no consensus has been achieved regarding how best to implement a replacement system. This concern will be taken into consideration while we continue to explore potential wage index reforms. The report that we submitted is available online at https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/AcuteInpatientPPS/Wage-Index-Reform.html.

Comment: One commenter requested that CMS implement a wage index floor of 1.00 for IRFs located in frontier states.

Response: As we do not have an IRF-specific wage index, we are unable to determine if a rural floor policy under the IRF PPS would be appropriate. The rationale for our current wage index policies is fully described in the FY 2006 IRF PPS final rule (70 FR 47880, 47926 through 47928).

Additionally, as most recently noted in the FY 2017 IRF PPS Final rule (81 FR 52075) MedPAC's June 2007 report to the Congress, titled “Report to Congress: Promoting Greater Efficiency in Medicare” (available at http://www.medpac.gov/-/documents/-/reports ), recommends that Congress “repeal the existing hospital wage index statute, including reclassification and exceptions, and give the Secretary authority to establish a new wage index systems.” We continue to believe it would not be appropriate, at this time, to adopt wage index policies afforded to acute care hospitals into the IRF PPS, such as a rural floor policy. Therefore, we will continue to use the CBSA labor market area definitions and the pre-reclassification and pre-floor hospital wage index data based on 2014 cost report data.

Final Decision: After careful consideration of the comments, we are finalizing our proposal to use the CBSA labor market area definitions and the FY 2018 pre-reclassification and pre-floor hospital wage index data for areas with wage data. We are also finalizing our proposal to continue to use the same methodology discussed in the FY 2008 IRF PPS final rule (72 FR 44299) to address those geographic areas where there are no hospitals and, thus, no hospital wage index data.

2. Core-Based Statistical Areas (CBSAs) for the Proposed FY 2019 IRF Wage Index

The wage index used for the IRF PPS is calculated using the pre-reclassification and pre-floor acute care hospital wage index data and is assigned to the IRF on the basis of the labor market area in which the IRF is geographically located. IRF labor market areas are delineated based on the CBSAs established by the OMB. The current CBSA delineations (which were implemented for the IRF PPS beginning with FY 2016) are based on revised OMB delineations issued on February 28, 2013, in OMB Bulletin No. 13-01. OMB Bulletin No. 13-01 established revised delineations for Metropolitan Statistical Areas, Micropolitan Statistical Areas, and Combined Statistical Areas in the United States and Puerto Rico based on the 2010 Census, and provided guidance on the use of the delineations of these statistical areas using standards published on June 28, 2010, in the Federal Register (75 FR 37246 through 37252). We refer readers to the FY 2016 IRF PPS final rule (80 FR 47068 through 47076) for a full discussion of our implementation of the OMB labor market area delineations beginning with the FY 2016 wage index.

Generally, OMB issues major revisions to statistical areas every 10 years, based on the results of the decennial census. However, OMB occasionally issues minor updates and revisions to statistical areas in the years between the decennial censuses. On July 15, 2015, OMB issued OMB Bulletin No. 15-01, which provides minor updates to and supersedes OMB Bulletin No. 13-01 that was issued on February 28, 2013. The attachment to OMB Bulletin No. 15-01 provides detailed information on the update to statistical areas since February 28, 2013. The updates provided in OMB Bulletin No. 15-01 are based on the application of the 2010 Standards for Delineating Metropolitan and Micropolitan Statistical Areas to Census Bureau population estimates for July 1, 2012 and July 1, 2013. The complete list of statistical areas incorporating these changes is provided in OMB Bulletin No. 15-01. In the FY 2018 IRF PPS final rule (82 FR 36250 through 36251), we adopted the updates set forth in OMB Bulletin No. 15-01 effective October 1, 2017, beginning with the FY 2018 wage index. For a complete discussion of the adoption of the updates set forth in OMB Bulletin No. 15-01, we refer readers to the FY 2018 IRF PPS final rule.

For FY 2019, we proposed to continue using the OMB delineations that we adopted beginning with FY 2016 to calculate the area wage indexes, with the updates set forth in OMB Bulletin No. 15-01 that we adopted beginning with the FY 2018 wage index.

We invited public comment on our proposal to continue using the OMB delineations that we adopted beginning with FY 2016 to calculate the area wage indexes for FY 2019. We received one comment on the use of these OMB delineations, which is summarized below.

Comment: One commenter requested that CMS extend the transition period that was afforded to rural IRFs that transitioned to urban status due to the adoption of updated OMB delineations that were finalized in the FY 2016 IRF PPS final rule. This commenter requested that CMS extend the transition period to at least 5 years or allow the affected facilities to apply for reclassification back to rural status for a 5-year period.

Response: We believe the 3-year transition was sufficient to mitigate any adverse payment impacts for these IRFs while also ensuring that payment rates for all IRF providers are set accurately and appropriately. As the wage index is a relative measure of the value of labor in prescribed labor market areas, we do not believe it is appropriate to expand the transition wage index beyond than what was finalized. We believe extending the transition would further delay the use of what we believe are accurate wage index rates. As we did not propose any such changes, this comment is out of scope of the proposed rule.

Final Decision: After careful consideration of the comment we received on the proposal to continue using the OMB delineations that we adopted beginning with FY 2016 to calculate the area wage indexes for FY 2019, we are finalizing this policy for FY 2019.

3. Codes for Constituent Counties in CBSAs

CBSAs are made up of one or more constituent counties. Each CBSA and constituent county has its own unique identifying codes. There are two different lists of codes associated with counties: Social Security Administration (SSA) codes and Federal Information Processing Standard (FIPS) codes. Historically, we have used SSA and FIPS county codes to identify and crosswalk counties to CBSA codes for purposes of the IRF wage index. We have learned that SSA county codes are no longer being maintained and updated. However, the FIPS codes continue to be maintained by the U.S. Census Bureau. The Census Bureau's most current statistical area information is derived from ongoing census data received since 2010; the most recent data are from 2015. For purposes of cross-walking counties to CBSA codes, we proposed to discontinue the use of SSA county codes and continue using only the FIPS county codes. We proposed to use the FIPS county codes to calculate area wage indexes in a manner that is generally consistent with the CBSA-based methodologies finalized in the FY 2006 IRF final rule (70 FR 47880) and the FY 2016 IRF final rule (80 FR 47036). The use of the FIPS codes for cross-walking counties to CBSAs does not result in any changes to the constituent counties of any CBSA. Thus, there is no impact or change for any IRF due to the use of the FIPS county codes. We believe that using the latest FIPS codes will allow us to maintain a more accurate and up-to-date payment system that reflects the reality of population shifts and labor market conditions.

As discussed in the FY 2018 Inpatient prospective payment system (IPPS) and Long-Term Care Hospital (LTCH) PPS final rule (82 FR 38130), this change was implemented under the IPPS beginning on October 1, 2017. Therefore, we proposed to implement this revision for the IRF PPS beginning October 1, 2018, consistent with our historical practice of modeling IRF PPS adoption of updates to labor market areas after IPPS adoption of these changes.

We invited public comments on this proposal. However, we did not receive any comments on the proposed revisions to the CBSA codes.

Final Decision: As we did not receive any comments on our proposal to discontinue the use of SSA county codes and continue using only the FIPS County codes for purposes of cross-walking counties to CBSA codes, we are finalizing these changes for FY 2019.

4. Wage Adjustment

The wage index applicable to FY 2019 is available on the CMS website at http://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Data-Files.html. Table A is for urban areas, and Table B is for rural areas.

To calculate the wage-adjusted facility payment for the payment rates set forth in this final rule, we multiply the unadjusted federal payment rate for IRFs by the FY 2019 labor-related share based on the 2012-based IRF market basket (70.5 percent) to determine the labor-related portion of the standard payment amount. A full discussion of the calculation of the labor-related share is located in section VI.C of this final rule. We then multiply the labor-related portion by the applicable IRF wage index from the tables in the addendum to this final rule. These tables are available on the CMS website at http://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Data-Files.html.

Adjustments or updates to the IRF wage index made under section 1886(j)(6) of the Act must be made in a budget-neutral manner. We proposed to calculate a budget-neutral wage adjustment factor as established in the FY 2004 IRF PPS final rule (68 FR 45689), codified at § 412.624(e)(1), as described in the steps below. We proposed to use the listed steps to ensure that the FY 2019 IRF standard payment conversion factor reflects the update to the wage indexes (based on the FY 2014 hospital cost report data) and the labor-related share in a budget-neutral manner:

Step 1. Determine the total amount of the estimated FY 2018 IRF PPS payments, using the FY 2018 standard payment conversion factor and the labor-related share and the wage indexes from FY 2018 (as published in the FY 2018 IRF PPS final rule (82 FR 36238)).

Step 2. Calculate the total amount of estimated IRF PPS payments using the FY 2019 standard payment conversion factor and the FY 2019 labor-related share and CBSA urban and rural wage indexes.

Step 3. Divide the amount calculated in step 1 by the amount calculated in step 2. The resulting quotient is the FY 2019 budget-neutral wage adjustment factor of 1.0000.

Step 4. Apply the FY 2019 budget-neutral wage adjustment factor from step 3 to the FY 2018 IRF PPS standard payment conversion factor after the application of the increase factor to determine the FY 2019 standard payment conversion factor.

We discuss the calculation of the standard payment conversion factor for FY 2019 in section VI.E. of this final rule.

We invited public comments on this proposal. However, we did not receive any comments on the proposed methodology for calculating the budget-neutral wage index.

Final Decision: As we did not receive any comments on the proposed methodology for calculating the budget-neutral wage index, we are finalizing this policy for FY 2019.

E. Description of the IRF Standard Payment Conversion Factor and Payment Rates for FY 2019

To calculate the standard payment conversion factor for FY 2019, as illustrated in Table 5, we begin by applying the increase factor for FY 2019, as adjusted in accordance with sections 1886(j)(3)(C) and (D) of the Act, to the standard payment conversion factor for FY 2018 ($15,838). Applying the 1.35 percent increase factor for FY 2019 to the standard payment conversion factor for FY 2018 of $15,838 yields a standard payment amount of $16,052. Then, we apply the budget neutrality factor for the FY 2019 wage index and labor-related share of 1.0000, which results in a standard payment amount of $16,052. We next apply the budget neutrality factor for the revised CMG relative weights of 0.9981, which results in the standard payment conversion factor of $16,021 for FY 2019.

We received 1 comment on the proposed FY 2019 standard payment conversion factor.

Comment: The commenter noted that the FY 2019 standard payment conversion factor does not include any additional payment to IRFs for the time and resources needed to complete assessments for quality reporting.

Response: Section 1886(j)(3) of the Act does not provide the Secretary with the authority to adjust payments to reflect increases in costs due to time and resources needed to complete assessments for quality reporting. We will continue to monitor the impact of the FY 2019 payment updates and quality reporting requirements on IRF providers.

Final Decision: After careful consideration of the comment we received, we are finalizing the IRF standard payment conversion factor of $16,021 for FY 2019.

After the application of the CMG relative weights described in section IV of this final rule to the FY 2019 standard payment conversion factor ($16,021), the resulting unadjusted IRF prospective payment rates for FY 2019 are shown in Table 6.

F. Example of the Methodology for Adjusting the Prospective Payment Rates

Table 7 illustrates the methodology for adjusting the federal prospective payments (as described in section VI. of this final rule). The following examples are based on two hypothetical Medicare beneficiaries, both classified into CMG 0110 (without comorbidities). The unadjusted prospective payment rate for CMG 0110 (without comorbidities) appears in Table 6.

Example: One beneficiary is in Facility A, an IRF located in rural Spencer County, Indiana, and another beneficiary is in Facility B, an IRF located in urban Harrison County, Indiana. Facility A, a rural non-teaching hospital has a Disproportionate Share Hospital (DSH) percentage of 5 percent (which would result in a LIP adjustment of 1.0156), a wage index of 0.8088, and a rural adjustment of 14.9 percent. Facility B, an urban teaching hospital, has a DSH percentage of 15 percent (which would result in a LIP adjustment of 1.0454 percent), a wage index of 0.8689, and a teaching status adjustment of 0.0784.

To calculate each IRF's labor and non-labor portion of the prospective payment, we begin by taking the unadjusted prospective payment rate for CMG 0110 (without comorbidities) from Table 6. Then, we multiply the labor-related share for FY 2019 (70.5 percent) described in section VI.C. of this final rule by the unadjusted prospective payment rate. To determine the non-labor portion of the prospective payment rate, we subtract the labor portion of the federal payment from the unadjusted prospective payment.

To compute the wage-adjusted prospective payment, we multiply the labor portion of the federal payment by the appropriate wage index located in Tables A and B. These tables are available on the CMS website at http://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Data-Files.html. The resulting figure is the wage-adjusted labor amount. Next, we compute the wage-adjusted federal payment by adding the wage-adjusted labor amount to the non-labor portion of the federal payment.

Adjusting the wage-adjusted federal payment by the facility-level adjustments involves several steps. First, we take the wage-adjusted prospective payment and multiply it by the appropriate rural and LIP adjustments (if applicable). Second, to determine the appropriate amount of additional payment for the teaching status adjustment (if applicable), we multiply the teaching status adjustment (0.0784, in this example) by the wage-adjusted and rural-adjusted amount (if applicable). Finally, we add the additional teaching status payments (if applicable) to the wage, rural, and LIP-adjusted prospective payment rates. Table 7 illustrates the components of the adjusted payment calculation.

Thus, the adjusted payment for Facility A would be $34,090.95, and the adjusted payment for Facility B would be $34,438.89.

VII. Update to Payments for High-Cost Outliers Under the IRF PPS for FY 2019

A. Update to the Outlier Threshold Amount for FY 2019

Section 1886(j)(4) of the Act provides the Secretary with the authority to make payments in addition to the basic IRF prospective payments for cases incurring extraordinarily high costs. A case qualifies for an outlier payment if the estimated cost of the case exceeds the adjusted outlier threshold. We calculate the adjusted outlier threshold by adding the IRF PPS payment for the case (that is, the CMG payment adjusted by all of the relevant facility-level adjustments) and the adjusted threshold amount (also adjusted by all of the relevant facility-level adjustments). Then, we calculate the estimated cost of a case by multiplying the IRF's overall CCR by the Medicare allowable covered charge. If the estimated cost of the case is higher than the adjusted outlier threshold, we make an outlier payment for the case equal to 80 percent of the difference between the estimated cost of the case and the outlier threshold.

In the FY 2002 IRF PPS final rule (66 FR 41362 through 41363), we discussed our rationale for setting the outlier threshold amount for the IRF PPS so that estimated outlier payments would equal 3 percent of total estimated payments. For the 2002 IRF PPS final rule, we analyzed various outlier policies using 3, 4, and 5 percent of the total estimated payments, and we concluded that an outlier policy set at 3 percent of total estimated payments would optimize the extent to which we could reduce the financial risk to IRFs of caring for high-cost patients, while still providing for adequate payments for all other (non-high cost outlier) cases.

Subsequently, we updated the IRF outlier threshold amount in the FYs 2006 through 2018 IRF PPS final rules and the FY 2011 and FY 2013 notices (70 FR 47880, 71 FR 48354, 72 FR 44284, 73 FR 46370, 74 FR 39762, 75 FR 42836, 76 FR 47836, 76 FR 59256, 77 FR 44618, 78 FR 47860, 79 FR 45872, 80 FR 47036, 81 FR 52056, and 82 FR 36238, respectively) to maintain estimated outlier payments at 3 percent of total estimated payments. We also stated in the FY 2009 final rule (73 FR 46370 at 46385) that we would continue to analyze the estimated outlier payments for subsequent years and adjust the outlier threshold amount as appropriate to maintain the 3 percent target.

To update the IRF outlier threshold amount for FY 2019, we proposed to use FY 2017 claims data and the same methodology that we used to set the initial outlier threshold amount in the FY 2002 IRF PPS final rule (66 FR 41316 and 41362 through 41363), which is also the same methodology that we used to update the outlier threshold amounts for FYs 2006 through 2018. The outlier threshold is calculated by simulating aggregate payments and using an iterative process to determine a threshold that results in outlier payments being equal to 3 percent of total payments under the simulation. To determine the outlier threshold for FY 2019, we estimate the amount of FY 2019 IRF PPS aggregate and outlier payments using the most recent claims available (FY 2017) and the FY 2019 standard payment conversion factor, labor-related share, and wage indexes, incorporating any applicable budget-neutrality adjustment factors. The outlier threshold is adjusted either up or down in this simulation until the estimated outlier payments equal 3 percent of the estimated aggregate payments. Based on an analysis of the preliminary data used for the proposed rule, we estimated that IRF outlier payments as a percentage of total estimated payments would be approximately 3.4 percent in FY 2018. Therefore, we proposed to update the outlier threshold amount from $8,679 for FY 2018 to $10,509 for FY 2019 to maintain estimated outlier payments at approximately 3 percent of total estimated aggregate IRF payments for FY 2019.

We note that, as we typically do, we updated our data between the FY 2019 IRF PPS proposed and final rules to ensure that we use the most recent available data in calculating IRF PPS payments. This updated data includes a more complete set of claims for FY 2017. Based on our analysis using this updated data, we now estimate that IRF outlier payments as a percentage of total estimated payments are approximately 3.1 percent in FY 2018. Therefore, we will update the outlier threshold amount from $8,679 for FY 2018 to $9,402 for FY 2019 to account for the increases in IRF PPS payments and estimated costs and to maintain estimated outlier payments at approximately 3 percent of total estimated aggregate IRF payments for FY 2019.

We received 5 comments on the proposed update to the FY 2019 outlier threshold amount to maintain estimated outlier payments at approximately 3 percent of total estimated IRF payments, which are summarized below.

Comment: Some commenters were supportive of maintaining estimated payments for outlier payments at approximately 3 percent and requested that CMS update the outlier threshold amount in the final rule using the latest available data. One commenter reiterated their recommendation to expand the outlier pool from 3 to 5 percent to redistribute payments within the IRF PPS and to reduce the impact of misalignments between IRF payments and costs. Specifically, the commenter suggested that expanding the outlier pool would help to ameliorate the financial burden on IRFs that have a relatively high share of costly cases. However, this same commenter noted that such an expansion in the outlier pool could inappropriately reward some facilities for inefficiencies. Another commenter suggested that CMS should lower the outlier pool below 3 percent.

Response: We agree that we should use the most recent data available to calculate the outlier threshold. Therefore, as previously stated, we updated the data used to calculate the outlier threshold between the FY 2019 IRF PPS proposed and final rule.

We refer readers to the 2002 IRF PPS final rule (66 FR 41316, 41362 through 41363), for a discussion of the rationale for setting the outlier threshold amount for the IRF PPS so that estimated outlier payments would equal 3 percent of total estimated payments. For the 2002 IRF PPS final rule, we analyzed various outlier policies using 3, 4, and 5 percent of the total estimated payments, and we concluded that an outlier policy set at 3 percent of total estimated payments would optimize the extent to which we could reduce the financial risk to IRFs of caring for high-cost patients, while still providing for adequate payments for all other (non-high cost outlier) cases. We continue to believe that the outlier policy of 3 percent of total estimated aggregate payments accomplishes this objective. Increasing the outlier pool would leave less money available to cover the costs of non-outlier cases, due to the fact that we would implement such a change in a budget-neutral manner. We believe that our current outlier policy, to set outlier payments at 3 percent of total estimated aggregate payments, is consistent with the statute and the goals of the IRF PPS.

Comment: Several commenters stated that CMS should ensure that the full 3 percent outlier pool is paid out to providers, as the commenters indicated that CMS has paid out less than the estimated 3 percent in the past. Some commenters suggested implementing a forecast error correction if the full amount of the outlier pool is not paid out.

Response: We appreciate the commenters' analyses and suggestions regarding the outlier threshold calculations. Our analysis of recent data shows that IRF outlier payments as a percentage of total estimated aggregate payments are approximately 3.1 percent in FYs 2017 and 2018, thus indicating that we paid out more than 3 percent, not less, in the 2 most recent fiscal years. Thus, we have not found that our outlier threshold calculations show any tendency to underpay on outlier payments.

However, we will continue to monitor our IRF outlier policies to ensure that they continue to compensate IRFs appropriately for treating unusually high-cost patients and do not limit access to care for patients who are likely to require unusually high-cost care. As we most recently noted in the FY 2018 IRF PPS final rule (82 FR 36255), we do not make adjustments to IRF PPS payment rates for the sole purpose of accounting for differences between projected and actual outlier payments. We use the best available data at the time to establish an outlier threshold for IRF PPS payments prior to the beginning of each fiscal year to help ensure that estimated outlier payments for that fiscal year will equal 3 percent of total estimated IRF PPS payments. We analyze expenditures annually, and if there is a difference from our projection, that information is used to make a prospective adjustment to lower or raise the outlier threshold for the upcoming fiscal year. We believe a retrospective adjustment would not be appropriate to recoup or make excess payments to hospitals.

If outlier payments for a given year turn out to be greater than projected, we do not recoup money from hospitals; if outlier payments for a given year are lower than projected, we do not make an adjustment to account for the difference. Payments for a given discharge in a given fiscal year are generally intended to reflect or address the prospective average costs of that discharge in that year; that goal would be undermined if we adjusted IRF PPS payments to account for “underpayments” or “overpayments” in IRF outliers in previous years.

Comment: Several commenters suggested that we consider implementing a cap on the amount of outlier payments an individual IRF can receive under the IRF PPS to ensure that outliers are fairly distributed.

Response: As we did not propose to implement a cap on the amount of outlier payments an individual IRF can receive under the IRF PPS, these comments are outside the scope of this rule. However, we note that any future consideration given to imposing a limit on outlier payments would have to carefully analyze and take into consideration the effect on access to IRF care for certain high-cost populations.

Comment: One commenter expressed concern that the proposal to increase the outlier threshold amount from $8,679 to $10,509 was too large an increase and suggested that we increase the threshold by no more than 5 or 10 percent.

Response: We note that, as is our standard practice, we have used updated data to calculate the FY 2019 IRF outlier threshold for this final rule, which results in us finalizing a lower outlier threshold amount ($9,402) than we proposed ($10,509) for FY 2019. We believe that this decrease between the proposed and final outlier threshold amount for FY 2019 should at least partially address the commenter's stated concerns. We note, however, that our methodology is designed to maintain estimated outlier payments at 3 percent of total estimated payments, and we do not adjust the outlier threshold amount beyond what is required to meet the target percentage.

Final Decision: Having carefully considered the public comments received and also taking into account the most recent available data, we are finalizing the outlier threshold amount of $9,402 to maintain estimated outlier payments at approximately 3 percent of total estimated aggregate IRF payments for FY 2019.

B. Update to the IRF Cost-to-Charge Ratio Ceiling and Urban/Rural Averages for FY 2019

Cost-to-charge ratios are used to adjust charges from Medicare claims to costs and are computed annually from facility-specific data obtained from Medicare cost reports. IRF specific cost-to-charge ratios are used in the development of the CMG relative weights and the calculation of outlier payments under the IRF prospective payment system. In accordance with the methodology stated in the FY 2004 IRF PPS final rule (68 FR 45674, 45692 through 45694), we proposed to apply a ceiling to IRFs' CCRs. Using the methodology described in that final rule, we proposed to update the national urban and rural CCRs for IRFs, as well as the national CCR ceiling for FY 2019, based on analysis of the most recent data that is available. We apply the national urban and rural CCRs in the following situations:

• New IRFs that have not yet submitted their first Medicare cost report.
• IRFs whose overall CCR is in excess of the national CCR ceiling for FY 2019, as discussed below in this section.
• Other IRFs for which accurate data to calculate an overall CCR are not available.

Specifically, for FY 2019, we proposed to estimate a national average CCR of 0.518 for rural IRFs, which we calculated by taking an average of the CCRs for all rural IRFs using their most recently submitted cost report data. Similarly, we proposed to estimate a national average CCR of 0.414 for urban IRFs, which we calculated by taking an average of the CCRs for all urban IRFs using their most recently submitted cost report data. We apply weights to both of these averages using the IRFs' estimated costs, meaning that the CCRs of IRFs with higher total costs factor more heavily into the averages than the CCRs of IRFs with lower total costs. For this final rule, we have used the most recent available cost report data (FY 2016). This includes all IRFs whose cost reporting periods begin on or after October 1, 2015, and before October 1, 2016. If, for any IRF, the FY 2016 cost report was missing or had an “as submitted” status, we used data from a previous fiscal year's (that is, FY 2004 through FY 2015) settled cost report for that IRF. We do not use cost report data from before FY 2004 for any IRF because changes in IRF utilization since FY 2004 resulting from the 60 percent rule and IRF medical review activities suggest that these older data do not adequately reflect the current cost of care. Using updated FY 2016 cost report data for this final rule, we estimate a national average CCR of 0.515 for rural IRFs, and a national average CCR of 0.412 for urban IRFs.

In accordance with past practice, we proposed to set the national CCR ceiling at 3 standard deviations above the mean CCR. Using this method, we proposed a national CCR ceiling of 1.31 for FY 2019. This means that, if an individual IRF's CCR were to exceed this ceiling of 1.31 for FY 2019, we would replace the IRF's CCR with the appropriate proposed national average CCR (either rural or urban, depending on the geographic location of the IRF). We calculated the proposed national CCR ceiling by:

Step 1. Taking the national average CCR (weighted by each IRF's total costs, as previously discussed) of all IRFs for which we have sufficient cost report data (both rural and urban IRFs combined).

Step 2. Estimating the standard deviation of the national average CCR computed in step 1.

Step 3. Multiplying the standard deviation of the national average CCR computed in step 2 by a factor of 3 to compute a statistically significant reliable ceiling.

Step 4. Adding the result from step 3 to the national average CCR of all IRFs for which we have sufficient cost report data, from step 1.

Using the updated FY 2016 cost report data for this final rule, we estimate a national average CCR ceiling of 1.32, using the same methodology. We did not receive any comments on the proposed update to the IRF CCR ceiling and the urban/rural averages for FY 2019.

Final Decision: As we did not receive any comments on the proposed update to the IRF CCR ceiling and the urban/rural averages for FY 2019, we are finalizing the national average urban CCR at 0.412, the national average rural CCR at 0.515, and the national average CCR ceiling at 1.32 for FY 2019.

VIII. Removal of the FIM^TM Instrument and Associated Function Modifiers From the IRF-PAI Beginning With FY 2020 and Refinements to the Case-Mix Classification System Beginning With FY 2020

A. Removal of the FIM ^TM Instrument and Associated Function Modifiers From the IRF-PAI Beginning With FY 2020

Under section 1886(j)(2)(D) of the Act, the Secretary is authorized to require rehabilitation facilities that provide inpatient hospital services to submit such data as the Secretary deems necessary to establish and administer the IRF PPS. In the FY 2002 IRF PPS final rule (66 FR 41324 through 41328), we finalized the use of the IRF-PAI, through which IRFs are now required to collect and electronically submit patient data for all Medicare Part A FFS and Medicare Part C (Medicare Advantage) patients. Data collected in the IRF-PAI is used to classify patients into distinct payment groups based on clinical characteristics and expected resource needs as well as to monitor the quality of care furnished in IRFs.

The IRF-PAI currently in use under the IRF PPS (IRF-PAI version 2.0) was originally developed based on a modified version of the Uniform Data System for medical rehabilitation (UDSmr) patient assessment instrument, commonly referred to as the FIM^TM. Item 39 of the IRF-PAI version 2.0 contains 18 of the FIM^TM data elements and the FIM^TM measurement scale that are used to score both motor and cognitive functioning at admission and discharge. The FIM^TM data elements and measurement scale are collectively referred to as the FIM^TM instrument. Additionally, items 29 through 38 of the IRF-PAI version 2.0 contain Function Modifiers associated with the FIM^TM instrument. The FIM^TM instrument and associated Function Modifiers are currently used to assign a patient into a CMG for payment purposes under the IRF PPS based on the patient's ability to perform specific activities of daily living and, in some cases, the patient's cognitive ability.

In the FY 2012 IRF PPS final rule (76 FR 47873 through 47883), we established the IRF QRP in accordance with section 1886(j)(7) of the Act and finalized revisions to the IRF-PAI to begin collecting data items under the IRF QRP. Under the IRF QRP, the following data items are collected in the Quality Indicators section of the IRF-PAI:

• GG0130A1 Eating.
• GG0130B1 Oral hygiene.
• GG0130C1 Toileting hygiene.
• GG0130E1 Shower/bathe self.
• GG0130F1 Upper-body dressing.
• GG0130G1 Lower-body dressing.
• GG0130H1 Putting on/taking off footwear.
• GG0170A1 Roll left and right.
• GG0170B1 Sit to lying.
• GG0170C1 Lying to sitting on side of bed.
• GG0170D1 Sit to stand.
• GG0170E1 Chair/bed-to-chair transfer.
• GG0170F1 Toilet transfer.
• GG0170I1 Walk 10 feet.
• GG0170J1 Walk 50 feet with two turns.
• GG0170K1 Walk 150 feet.
• GG0170M1 One step curb.
• H0350 Bladder continence.
• H0400 Bowel continence.
• BB0700 Expression of ideas and wants.
• BB0800 Understanding verbal content.
• C0500 Brief Interview for Mental Status (BIMS) summary score.

Because these data items collect data that are similar in nature to, and overlap with, data collected through the FIM^TM instrument and associated Function Modifiers, we proposed to remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI beginning with FY 2020 to reduce administrative burden on IRFs.

Currently, data elements in the FIM^TM instrument and associated Function Modifiers capture data on eating, grooming, bathing, dressing upper body, dressing lower body, toileting, bladder management, bowel management, transfer to bed/chair/wheelchair, transfer to toilet, transfer to tub/shower, walking or wheelchair use, stair climbing, comprehension, expression, social interaction, problem solving, and memory. The Function Modifiers are used to assist in the scoring of the related FIM^TM instrument data elements and provide additional information as to how the FIM^TM instrument data element score has been determined. For example, item 29 (Bladder Level of Assistance) and item 30 (Bladder Frequency of Accidents) are used to determine the score for the item 39G, the Bladder data element contained in the FIM^TM instrument.

Data items in the Quality Indicators section of the IRF-PAI capture data on functional status, cognitive function, and changes in function and cognitive function among other elements used for quality reporting. For example, the data items in the Quality Indicators section of the IRF-PAI capture data on eating, oral hygiene, toileting hygiene, shower/bathing, dressing upper body, dressing lower body, bowel continence, bladder continence, chair/bed-to-chair transfer, toilet transfer, walking, stair climbing, expression of ideas and wants, understanding verbal and non-verbal content, temporal orientation, and memory/recall ability. As the data elements in the FIM^TM instrument (item 39 of the IRF-PAI) and associated Function Modifiers (items 29 through 38 of the IRF-PAI) overlap, directly or indirectly, with data items in the Quality Indicators section of the IRF-PAI, and as we can now use data items in the Quality Indicators section of the IRF-PAI to assign patients to CMGs for payment under the IRF PPS, we believe that the collection of the FIM^TM instrument and associated Function Modifiers is no longer necessary. Accordingly, we believe that continuing to collect the FIM^TM instrument and associated Function Modifiers places undue burden on IRFs. Additionally, the removal of the FIM^TM instrument and associated Function Modifiers from the IRF-PAI would support the broader goal to standardize data collection across PAC settings as several of the data items we proposed to incorporate into the IRF case-mix system in place of the FIM^TM instrument and associated Function Modifiers are similar to data elements that are also collected on Skilled Nursing Facility (SNF) and LTCH assessment instruments. In support of our goal to reduce administrative burden on providers, we proposed to remove the FIM^TM instrument (item 39) and associated Function Modifiers (items 29 through 38) from the IRF-PAI beginning with FY 2020, that is, for all IRF discharges beginning on or after October 1, 2019. This decrease in burden will be accounted for in the information collection under OMB control number (0938-0842).

We invited public comment on our proposal to remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI beginning with FY 2020, that is, for all IRF discharges beginning on or after October 1, 2019. We summarize and respond to the comments received on this proposal and discuss our final decision on this proposal in section VIII.B.4 of this final rule.

In section VIII.B of this final rule, we discuss the proposed CMG case-mix classification revisions that are necessary to replace our use of the FIM^TM items in assigning CMGs with use of data items located in the Quality Indicators section of the IRF-PAI.

B. Refinements to the Case-Mix Classification System Beginning With FY 2020

1. IRF Classification System Overview

Section 1886(j)(2) of the Act requires the Secretary to establish case-mix groups for payment under the IRF PPS. Under section 1886(j)(2)(B) of the Act, the Secretary must assign each case-mix group a weighting factor that reflects the relative facility resources used for patients classified within the group as compared to patients classified within other groups. Additionally, section 1886(j)(2)(C)(i) of the Act requires the Secretary from time to time to adjust the classifications and weighting factors as appropriate to reflect changes in treatment patterns, technology, case-mix, number of payment units for which payment is made under title XVIII of the Act, and other factors which may affect the relative use of resources. Such adjustments must be made in a manner so that changes in aggregate payments under the classification system are a result of real changes and are not a result of changes in coding that are unrelated to real changes in case mix.

In the FY 2002 IRF PPS final rule (66 FR 41316), we established a case-mix classification system for IRFs under the IRF PPS. Under the case-mix classification system, a patient's principal diagnosis or impairment is used to classify the patient into a RIC. The patient is then placed into a CMG within the RIC, based on the patient's functional status (motor and cognitive scores) and sometimes age. Other special circumstances, such as the occurrence of very short stays, or cases where the patient expired, are also considered in determining the appropriate CMG. CMGs are further divided into tiers based on the presence of certain comorbidities. These tiers reflect the differential cost of care compared with the average beneficiary in a CMG. We refer readers to the FY 2002 final rule (66 FR 41316) and the FY 2006 IRF final rule (70 FR 47886) for a detailed discussion of the development of, and refinements to, the IRF case-mix classification system.

As discussed in section VIII.A of this final rule, we proposed to remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI beginning with FY 2020, that is, for all IRF discharges beginning on or after October 1, 2019. This would necessitate the incorporation of the data items collected on admission and located in the Quality Indicators section of the IRF-PAI version 2.0 into the CMG classification system, as the FIM^TM data would no longer be available to assign patients to CMGs for purposes of payment under the IRF PPS. In accordance with section 1886(j)(2)(C)(i) of the Act and as specified in § 412.620(c) we proposed to replace our use of the FIM^TM items in assigning CMGs with use of data items located in the Quality Indicators section of the IRF-PAI. In addition, to ensure that IRF payments are accurately calculated using the data items located in the Quality Indicators section of the IRF-PAI, we also proposed to update the functional status scores used in the case-mix system and to revise the CMGs and update the relative weights and average length of stay values associated with the revised CMGs. We proposed to implement these revisions to the case-mix classification system in a budget neutral manner.

We proposed to make these changes effective beginning with FY 2020, that is, for discharges occurring on or after October 1, 2019, as they require extensive systems changes. That is, we proposed to implement these changes with a one-year delayed effective date to allow adequate time for providers and vendors to make the necessary systems changes. These proposed changes are discussed in detail below. We did not propose any changes to the methodology used to update the CMGs, relative weights and average length of stay values for FY 2019, that is, for discharges occurring on or after October 1, 2018, and on or before September 30, 2019. For information on the updates to the CMG relative weights and average length of stay values for FY 2019, please refer to section IV of this final rule.

2. Changes to the Functional Status Scores Beginning With FY 2020

As discussed in the FY 2006 IRF final rule (70 FR 47886), under the CMG case-mix classification system, a patient's principal diagnosis or impairment is used to classify the patient into a RIC. After using the RIC to define the first division among the inpatient rehabilitation groups, a patient's motor and cognitive scores and age are used to partition the cases further. To classify a patient into a CMG, IRFs use the admission assessment data from the IRF-PAI to score a patient's functional status. Currently, the functional status scores consist of what are termed “motor” items and “cognitive” items. In addition to the functional status scores, the patient's age may also influence the patient's CMG classification. The motor items are generally indications of the patient's physical functioning level. The cognitive items are generally indications of the patient's mental functioning level, and are related to the patient's ability to process and respond to empirical factual information, use judgment, and accurately perceive what is happening. Under the current case-mix system, the motor and cognitive scores are derived from a combination of data elements in the FIM^TM instrument (item 39 of the IRF-PAI). Eating, grooming, bathing, dressing upper body, dressing lower body, toileting, bladder management, bowel management, transfer to bed/chair/wheelchair, transfer to toilet, walking or wheelchair use, and stair climbing are the data elements collected through the FIM^TM instrument that are currently used to compute a patient's weighted motor score. Comprehension, expression, social interaction, problem solving, and memory are the data elements collected through the FIM^TM instrument that are used to compute a patient's cognitive score. Each data element is recorded on the IRF-PAI and scored on a scale of 1 to 7, with a 7 indicating complete independence in this area of functioning, and a one indicating that a patient is very impaired in this area of functioning. Additionally, a value of zero is used to indicate that an activity did not occur. The scores for each data element above are then used to determine the patient's weighted motor score and cognitive score, which may be used to group a patient into a CMG for payment purposes under the IRF PPS.

As discussed in section VIII.A of this final rule, we proposed to remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI beginning with FY 2020. As the data in the FIM^TM instrument section will no longer be available to determine the motor and cognitive scores used to assign patients to CMGs, we proposed to use data items collected on admission and located in the Quality Indicators section of the IRF-PAI to derive the functional status scores used to assign patients to a CMG for payment purposes under the IRF PPS. The Quality Indicators section of the IRF-PAI includes data items that are similar to the data elements located in the FIM^TM instrument, in addition to new data elements that capture additional functional status information.

In the summer of 2013, we contracted with Research Triangle Institute, International (RTI) to explore use of the data items collected in the Quality Indicators section of the IRF-PAI in setting IRF PPS payments. Some of the data items collected in the Quality Indicators section of the IRF-PAI were originally developed and tested as part of the Post-Acute Care Payment Reform Demonstration (PAC-PRD) version of the Continuity Assessment Record and Evaluation (CARE) Item Set. The CARE item set was developed in response to a mandate in section 5008 of the Deficit Reduction Act of 2005 (Pub. L. 109-171, enacted on February 8, 2006) (DRA) to develop a uniform patient assessment instrument to assess patients across all types of acute and PAC providers.

In the first stage of this analysis, RTI hosted a Technical Expert Panel (TEP) on September 18, 2014, which brought together researchers, clinicians, and representatives from provider associations to discuss exploratory research on the potential to incorporate the CARE data items in the current case-mix system utilized in the IRF PPS. We received helpful feedback on the exploratory research including clinicians' views of the importance and significance of various findings, input on the methodology used to incorporate the CARE items, and potential limitations of the analysis. RTI's analysis of the original CARE data set, along with guidance from the TEP, suggested the need to derive different functional status measures from the data collected in the Quality Indicators section of the IRF-PAI. The data items from the Quality Indicators section of the IRF-PAI contain slightly different information and utilize a different rating system than the items collected on the FIM^TM instrument. Thus, we proposed to modify the IRF case-mix classification system to calculate IRF PPS payments correctly using the admission data items from the Quality Indicators section of the IRF-PAI. RTI considered a broad range of the data items in the Quality Indicators section of the IRF-PAI to identify the best predictors of IRF costs. These analyses examined all motor, cognitive, and additional items collected at admission to predict costs. The regression analysis indicated that the components of functional status that were found to best predict costs were the patient's motor function, a memory function, a communication function based on comprehension and expression, and age.

The motor items used to derive the additive motor score are eating, oral hygiene, toileting hygiene, shower bathe/self, upper body dressing, lower body dressing, putting on/taking off footwear, bladder continence, bowel continence, roll left and right, sit to lying, lying to sitting on side of bed, sit to stand, chair/bed-to-chair transfer, toilet transfer, walk 10 feet, walk 50 feet with two turns, walk 150 feet, and 1 step (curb). The item used to derive the memory score is the BIMS summary score, which is based on the repetition of three words, temporal orientation, and recall. The communication score is derived from the hearing, speech, and vision items including expression of ideas and wants and understanding verbal and non-verbal content. We proposed to incorporate a motor score, a memory score, a communication score, and age into the IRF case-mix classification system. Currently, the IRF case-mix system uses a weighted motor score and an unweighted cognitive score. We did not propose to apply a weighting methodology to the motor score at this time. We proposed to derive the scores for each respective group of the functional status items described above by calculating the sum of the items that constitute each functional status component. For a more detailed discussion of these analyses, please refer to the technical report, “Analyses to Inform the Potential Use of Standardized Patient Assessment Data Elements in the Inpatient Rehabilitation Facility Prospective Payment System,” available at https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Research.html.

As noted in the proposed rule, we believe that it is appropriate to utilize the admission data items located in the Quality Indicators section of the IRF-PAI, as described above, in place of the FIM^TM items to determine functional status, as the data items located in the Quality Indicators section are now available and collected by all IRF providers for purposes of the IRF QRP. We believed the proposed motor score, a memory score, a communication score, and age should compose the functional status scores in the IRF case-mix classification system, as our analysis determined these to be the best predictors of cost. The removal of the FIM^TM instrument and the incorporation of certain items from the Quality Indicators section of the IRF-PAI to assign patients to CMGs support our efforts to reduce burden on providers. Additionally, the removal of the FIM^TM instrument and the incorporation of certain items from the Quality Indicators section of the IRF-PAI into the CMG case-mix system support our broader goal of standardizing assessment data collection across PAC settings.

We proposed to utilize certain data items located in the Quality Indicators section of the IRF-PAI, as described above, to generate the functional status scores that will be used to group patients into CMGs for payment purposes under the IRF PPS beginning in FY 2020.

We invited public comments on the proposed use of certain data items located in the Quality Indicators section of the IRF-PAI, as described above, for payment purposes under the IRF PPS beginning with FY 2020, that is, for all IRF discharges beginning on or after October 1, 2019. We summarize and respond to the comments received on this proposal and discuss our final decision on this proposal in section VIII.B.4 of this final rule.

3. Updates to the Score Reassignment Methodology Beginning With FY 2020

As previously noted, the data items located in the Quality Indicators section of the IRF-PAI utilize a different rating system than the FIM^TM instrument. There are several important differences to note regarding the rating systems for the data items from the Quality Indicators section of the IRF-PAI and the data contained in the FIM^TM instrument. First, the data items from the Quality Indicators section of the IRF-PAI are assessed based on a patient's usual performance during the assessment period in contrast to the FIM^TM items, which are assessed based on the patient's lowest functional score during the assessment period. The data items from the Quality Indicators section of the IRF-PAI are generally assessed using a 6 level rating scale for the self-care and mobility elements and a 4 level scale for the cognitive elements. The FIM^TM data items use a 7 level scale. Additionally, the FIM^TM scale includes a value of zero to indicate an activity did not occur or was not observed. The data items from the Quality Indicators section of the IRF-PAI utilize the following four codes to indicate why an activity did not occur: the patient refused to complete an activity (code 07), the patient did not perform this activity (code 09), the activity was not attempted due to environmental limitations (code 10), or the activity was not attempted due to a medical condition or safety concern (code 88).

As the rating scale for the data items in the Quality Indicators section of the IRF-PAI captures multiple reasons an activity did not occur, we proposed to modify the methodology currently used to reassign values indicating an activity did not occur or was not observed, when they are recorded on an item used for payment, beginning with FY 2020. Currently, when a code of 0 appears for one of the FIM^TM items on the IRF-PAI used to determine payment, the item is reassigned another value to determine the appropriate payment for the patient. In the FY 2002 IRF PPS final rule (66 FR 41316), we finalized a methodology to assign a code of 1 (indicating the patient needed total assistance) whenever the recorded code indicated that the activity did not occur. Subsequently, in the FY 2006 IRF PPS final rule, we revised this methodology to assign a value of 2 when the transfer to toilet item was coded with a zero value. For more information on the rationale behind this decision we refer readers to the 2006 IRF PPS final rule (70 FR 47896 through 47902). As the data items from the Quality Indicators section of the IRF-PAI now utilize 4 values to indicate an activity did not occur and a dash to indicate “no information”, we proposed to modify the reassignment methodology to incorporate the new codes. For the self-care and mobility items identified above, we proposed to recode values of 07, 09, 10, 88, and the presence of a dash (“-”) to 1, the most dependent level, except the toilet transfer item, which is recoded to 2. These recodes are consistent with the current reassignment methodology rules. We also proposed to change the way we treat specific values for the bowel continence and bladder continence items, as our analysis of these items and current coding guidelines indicate these changes are necessary. The bladder continence and bowel continence items utilize a different scale than the other function items and may capture clinical information that is not necessarily reflective of a patient's functional ability. For instance, the bladder continence scale includes the options “no urine output” or “not applicable” for cases where a patient may have renal failure or an indwelling catheter. A clinical review of these cases determined that patients for whom these values are coded are similar in terms of resource needs and costliness to patients for whom functional ability is captured. Based on this review, we proposed to recode these values to be able to score the functional status of a patient when these values are coded on the IRF-PAI. For the bladder continence item, we proposed to reassign a value of 1 (stress incontinence only) to 0 (always continent), a value of 5 (no urine output) to 0 (always continent), and a value of 9 (not applicable) to 4 (always incontinent). For the bowel continence item, we proposed to reassign a value of 9 (not rated) to 2 (frequently incontinent). For both items, we proposed to reassign a missing score to 0 (always continent). As noted in the proposed rule, we believe these changes are necessary to update the score reassignment methodology used to derive the functional status scores to reflect use of the new data items from the Quality Indicators section of the IRF-PAI and to accurately assign payments based on a patients' expected costliness.

We invited public comments on the proposed updates to the score reassignment methodology beginning with FY 2020, that is, for all IRF discharges beginning on or after October 1, 2019. We summarize and respond to the comments received on this proposal and discuss our final decision on this proposal in section VIII.B.4 of this final rule.

4. Refinements to the CMGs Beginning With FY 2020

As previously noted, we proposed to modify the methodology used to update the CMGs used to classify IRF patients for purposes of establishing payment amounts, beginning with FY 2020. We proposed to implement revisions to the CMGs in a budget-neutral manner. As discussed in the FY 2006 IRF PPS final rule (70 FR 47886 through 47887), the current CMGs were derived through Classification and Regression Trees (CART) analysis that incorporated a patient's functional status (motor score and cognitive score) and age into the construction of the CMGs. Under the IRF case-mix classification system, a patient's principal diagnosis or impairment is used to classify the patient into a RIC. Currently, there are 21 diagnosis-based RICs. The RICs are then further subdivided into 92 CMGs. Of the 92 CMGs, patients are assigned to 87 of the CMGs based on the patient's primary reason for rehabilitation care, age and functional status. There are also five special CMGs to account for very short stays and for patients who expire in the IRF.

The CART method is useful in identifying statistical relationships among data and, using these relationships, constructing a predictive model for organizing and separating a large set of data into smaller, similar groups. CART ensures that the proposed CMGs recognize that patients with clinically distinct resource needs are appropriately grouped in the case-mix classification system. CART is an iterative process that creates initial groups of patients then searches for ways to split the initial groups to further decrease the clinical and cost variances within a group and increase the explanatory power of the CMGs.

As noted previously, the data items from the Quality Indicators section of the IRF-PAI contain slightly different information and utilize a different rating system than the items collected on the FIM^TM instrument. Thus, we proposed to update the IRF case-mix classification system to ensure that IRF PPS payments reflect as closely as possible the costs of care when we convert to using the admission data items from the Quality Indicators section of the IRF-PAI. To convert from using the FIM^TM items to using the data items from the Quality Indicators section of the IRF-PAI, RTI first had to identify which quality indicator data items would be the best predictors of cost, as previously discussed. Then, RTI used CART analysis to modify the CMG definitions to reflect the use of the different assessment items.

To develop CMGs based on the data items from the Quality Indicators section of the IRF-PAI, RTI used CART analysis to divide patients into payment groups based on similarities in their clinical characteristics and relative costs. As part of this analysis, RTI imposed certain restraints on these groupings to decrease the resulting number of CMGs (to ensure that the payment system did not become unduly complicated). For a more detailed discussion of these analyses or for more information on the development of the CMGs, we refer readers to the technical report, “Analyses to Inform the Potential Use of Standardized Patient Assessment Data Elements in the Inpatient Rehabilitation Facility Prospective Payment System”, available at https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Research.html.

In developing the revised CMGs, RTI's analysis indicated that RIC 16 and RIC 17 should incorporate the CMGs shown in Table 8, based on motor score and cognitive function, derived from the memory and communication scores.

We considered proposing to revise the CMGs for RIC 16 and RIC 17 as shown above. However, these CMGs indicate higher costs for patients with no cognitive impairment as compared to those with any level of impairment. As this unexpected result may be driven by small sample size, we proposed to combine CMG 03 and 04 for RIC 16 and to combine CMG 05 and 06 for RIC 17 as shown in Table 9.

Table 9 contains the proposed CMGs and their respective descriptions, including the functional status scores and age that we proposed to use to classify discharges into CMGs. Table 9 also contains the CMG relative weights and average length of stay values for the CMGs. We did not propose any changes to methodology used to determine the CMG relative weights that was finalized in the FY 2002 IRF final rule (66 FR 41351 through 41357) and revised in the FY 2009 IRF final rule (73 FR 46372 through 46374). For more information on the methodology used to calculate the CMG relative weights please refer to section IV. of this final rule.

The following would be the most significant differences between the current CMGs and the revised CMGs:

• There would be fewer CMGs than before (88 instead of 92 currently).
• There would be fewer CMGs in RICs 1, 2, 5, 8, 11, and 19, while there would be more CMGs in RICs 3, 4, 10, 13, 15, 17, and 18.
• A patient's age would affect assignment for CMGs in RICs 1, 3, 4, and 13 whereas it currently affects assignment for CMGs in RICs 1, 4, and 8.

We proposed to utilize the CMGs based on the data items from the Quality Indicators section of the IRF-PAI to classify IRF patients for purposes of establishing payment under the IRF PPS beginning with FY 2020. We proposed to implement these revisions in a budget neutral manner. For more information on the specific impacts of this change, we refer readers to Table 10. We also proposed to update the CMG relative weights and average length of stay values associated with the CMGs based on the data items from the Quality Indicators section of the IRF-PAI. We believe it is appropriate to update the CMGs and relative weights for FY 2020 to better align IRF payments with the costs of caring for IRF patients, given the new information that is captured by the data items from the Quality Indicators section of the IRF-PAI. Additionally, changes in treatment patterns, technology, case-mix, and other factors affecting the relative use of resources in IRFs since the current CMGs were last revised, likely require an update to the classification system.

Table 10 shows how we estimate that the application of the revisions to the case-mix system for FY 2020 would affect particular groups. Table 10 categorizes IRFs by geographic location, including urban or rural location, and location for CMS's 9 Census divisions of the country. In addition, the table divides IRFs into those that are separate rehabilitation hospitals (otherwise called freestanding hospitals in this section), those that are rehabilitation units of a hospital (otherwise called hospital units in this section), rural or urban facilities, ownership (otherwise called for-profit, non-profit, and government), by teaching status, and bed size. The changes to the case-mix classification system are expected to affect the overall distribution of payments across CMGs. Note that, because we proposed to implement the revisions to the case-mix classification system in a budget-neutral manner, total estimated aggregate payments to IRFs would not be affected as a result of the revisions to the CMGs. However, these revisions may affect the distribution of payments across CMGs.

We received 94 comments on our proposals to remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI beginning with FY 2020 and to incorporate certain data items located in the Quality Indicators section of the IRF-PAI in the IRF case-mix classification system, which are summarized below.

Comment: Several commenters expressed support for the removal of the FIM^TM and associated Function Modifier items from the IRF-PAI. One commenter stated that collection of both sets of data items is inefficient and takes time away from patient care and also noted that they prefer the data items located in the Quality Indicators section of the IRF-PAI as they are easier to score and are better understood. Another commenter was fully supportive of this proposal, noting that it would remove the requirement of having to report on similar data twice, which providers have indicated is a substantial burden. This commenter stated that they believe this proposal would result in only minor changes to the payment system because of the similarities between the FIM^TM and Quality Indicators data items and noted that there would not be any changes to the RICs used in the IRF PPS. Additionally, this commenter stated that the removal of the FIM^TM instrument is responsive to the IMPACT Act requirement to remove duplicative or overlapping data as soon as practicable.

Response: We appreciate the commenters' support for our proposal to remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI and agree with the one commenter's assessment that this proposal will not result in major changes to the IRF case-mix classification system. We also agree with the commenter that the proposal to remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI aligns with the overall goals of the IMPACT Act.

Comment: While many commenters were appreciative of efforts to reduce burden and generally supportive of future post-acute care payment reform efforts, most commenters did not support the removal of the FIM^TM instrument and associated Function Modifiers from the IRF-PAI, citing concerns over the incorporation of the data items located in the Quality Indicators section of the IRF-PAI into the IRF PPS. Several commenters stated that too little is known about the accuracy, consistency and clinical efficacy of these data items. Many commenters expressed concern that these items have not been meaningfully evaluated and have not been found to be valid and reliable measures of patients' functional status. Additionally, many commenters stated that the data items in the Quality Indictors section of the IRF-PAI have not been sufficiently studied, understood, or validated to be used as the basis for a new budget neutral case-mix system. Many commenters noted they were supportive of the objective to eliminate duplicative data elements, and some were supportive of potentially removing the FIM^TM in the future, but many commenters stated that finalizing the removal of the FIM^TM data would be premature at this time. Commenters expressed concerns that the data items that we had proposed to replace the FIM^TM data items have not been proven reliable or valid for payment purposes and requested to continue reporting data through the FIM^TM instrument.

Response: We disagree with the commenters that the data items in the Quality Indicators section of the IRF-PAI have not been meaningfully evaluated and have not been proven reliable and valid. The data items and response codes located in the Quality Indicators section of the IRF-PAI that were proposed to be incorporated into the IRF case-mix classification system were derived from a subset of items within the CARE Tool that were extensively tested for validity and reliability in the IRF setting as part of the Post-Acute Care Payment Reform Demonstration (PAC PRD). These items were developed to accurately measure the functional and cognitive status of patients across PAC settings and were found to be reliable and valid. A description of the reliability and validity testing methodology and results are available in several reports, including The Development and Testing of the Continuity Assessment Record and Evaluation (CARE) Item Set, the Final Report On Reliability Testing, and the Final Report on CARE Item Set and Current Assessment Comparisons. These reports are available at http://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/Post-Acute-Care-Quality-Initiatives/CARE-Item-Set-and-B-CARE.html.

Additionally, these data items were extensively tested for payment purposes under the IRF PPS as part of the PAC PRD. These data items were developed in response to a mandate in Section 5008 of the Deficit Reduction Act of 2005 and were collected for analysis under the PAC PRD from 2008 to 2010. Analyses conducted through the PAC PRD found that the elements of the CARE tool include proven predictors of health care costs and utilization across PAC prospective payment systems. More information on the PAC PRD is available on the CMS website at https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/Reports/Research-Reports-Items/PAC_Payment_Reform_Demo_Final.html.

In addition to this, we conducted reliability and validity testing of the data items associated with the four IRF QRP functional outcome measures when these measures were submitted for NQF endorsement as discussed in the FY 2016 IRF PPS final rule (80 FR 47096 through 47120). The testing of the data elements, the scale and facility-level data showed very good reliability and validity. We will update the reliability and validity testing of the data items associated with the four IRF QRP functional outcome measures, as these outcome measures are due for maintenance of NQF endorsement in 2019.

In addition to the work conducted under the PAC PRD, RTI conducted analysis to identify the best predictors of cost and then used CART analysis to modify the CMG definitions to reflect the use of the different assessment items. RTI found that the model predicting costs using CMGs derived from the items located in the Quality Indicators section of the IRF-PAI, based on data from FY 2017, had a slightly higher R-squared value than models using the current CMGs which are derived from items in the FIM^TM instrument, thus indicating that the revised CMGs more accurately predict costs than the CMGs that are currently utilized.

Additionally, we disagree with the commenters' characterization of this proposal as the construction of a new budget neutral case-mix system. Instead, we proposed revisions to the case-mix system solely to incorporate the data items from the Quality Indicators section instead of the FIM^TM instrument. We note that that we did not propose any changes to the RICs, comorbidity tiers, or the relative weight methodology that are currently in place, and we believe the proposed revisions to the case-mix groups would result in minor changes to the structure of the CMGs.

Comment: A number of commenters expressed concerns that the removal of the FIM^TM instrument could, paradoxically, increase burden on providers and potentially worsen patient outcomes. Many commenters noted that providers would need to invest in system changes due to these proposals. Several commenters stated that facilities need adequate lead time, measured in years, to change electronic medical record systems, financial tracking and reporting systems, quality measurement recording, and program improvement purposes and that any regulatory burden reduction derived from eliminating duplicative reporting would be offset by having to adapt to major changes in the payment system. Additionally, several commenters suggested that eliminating the FIM^TM instrument to reduce burden may have the opposite effect in light of ongoing confusion and uncertainty in proper coding of section GG items, which are the data items in the Quality Indicators section, and suggested that burden would increase from education and training activities.

Response: We disagree with the suggestion that the proposed removal of the FIM^TM instrument and associated Function Modifiers would increase administrative burden associated with Medicare data reporting requirements or have an adverse effect on patient outcomes. This proposal would simply remove data items from the IRF-PAI and was proposed with a one year delayed effective date of October 1, 2019 to allow providers time to make necessary system changes. We note that with each assessment release, we provide free software to providers that allows for the completion and submission of any required assessment data. Free downloads of the Inpatient Rehabilitation Validation and Entry (IRVEN) software product are available on the CMS website at http://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Software.html. Additionally, we disagree with the commenters' suggestions that the proposal would create additional burden on providers from training activities, as these data items have been collected nationally for almost 2 years. We do not believe providers will experience additional burden from the continued reporting and collection of this subset of Quality Indicator data items.

Comment: Several commenters supported the continued collection of FIM^TM data because the commenters said that they did not believe that the Quality Indicator items accurately capture burden of care. Multiple commenters noted that the Quality Indicators data items use a different scale, and that this compressed scale may limit the ability to capture the complexity of the sickest IRF patients. Commenters stated that they believe the scale used for the data items located in the Quality Indicators section of the IRF-PAI is less sensitive than the scale used for the FIM^TM items and expressed concern that the scale does not capture a patient's true severity of impairment. Several commenters stated the scale for the Quality Indicator items does not have the specificity or predictability of the FIM^TM scale and expressed concern that the scale for these items does not reflect progress between admission and discharge in a similar manner as the FIM^TM scale.

Response: We disagree with the commenters and believe that the data items located in the Quality Indicators section of the IRF-PAI accurately capture the functional and cognitive status of patients and can also be used to accurately assess changes in patients' functional status. We believe that the six level scale utilized for the data items located in the Quality Indicators section of the IRF-PAI better distinguishes change at the highest and lowest levels of patient function by documenting minimal change from no change at the low end of the scale. This is important for measuring progress in some of the most complex cases treated in PAC settings. Additionally, we note that these data items were developed with input from the clinical therapy communities to better measure the change in function, regardless of the severity of the individual's impairment. The self-care and mobility data elements included on the IRF-PAI were selected to represent a wide range of activity difficulty, and cover a wide range of patient functioning, from low to high functioning. At admission, activities in the areas of toileting hygiene, dressing, bed mobility, bed and toilet transfers, and walking distinguish patient ability. Several data elements are activities that are very challenging for patients to complete and are frequently coded using the “activity not attempted codes” at admission. Thus, these more challenging data elements may not contribute as much to identify differences in patient ability at admission beyond the included data elements. These more challenging activities (for example, car transfers and 12 steps) are important to assess at discharge as they represent daily activities that are important for a person living in the community and are important in differentiating patient abilities at discharge when most patients have gained function. Overall, the inclusion of these items allows the patient the opportunity to demonstrate gains in a variety of functional activities and tasks. Rehabilitation care typically focuses on several aspects of functioning, and patients may be expected to make varying amounts of improvement, from minimal to substantial improvement, across different functional activities.

Comment: A number of commenters noted they use the FIM^TM data for various purposes and that removing the FIM^TM instrument from the IRF-PAI would not reduce burden as providers would still need to collect this data for internal purposes. Other commenters indicated that FIM^TM scores are sent to insurance companies for approval of continued treatment, are used in other acute settings, and are used by private payers to make determinations about IRF coverage.

Response: We appreciate the commenters' concerns regarding the various uses of the FIM^TM data items outside of their use for Medicare payment, but we note that these concerns are specific to business decisions of individual IRF providers. For Medicare payment purposes, we believe that the Quality Indicator items represent an improved and more standardized way of collecting functional assessment data on patients in the IRF setting and across PAC settings, and we therefore also believe that collecting both the FIM^TM instrument and the Quality Indicator items on the same IRF-PAI form is unnecessarily burdensome for providers. We certainly have no issues with IRF providers choosing to continue to continue to collect the FIM^TM instrument data on their own, but this choice has no bearing on our decision to remove the FIM^TM items from the IRF-PAI to minimize regulatory burden on providers.

Comment: One commenter noted that FIM^TM items are universally understood across PAC settings and suggested that we should continue to collect the FIM^TM items. This commenter also suggested that we make the FIM^TM instrument the standard throughout all PAC areas to describe motor and cognitive function.

Response: As certain Quality Indicator data items collect data that are similar in nature to data collected through the FIM^TM instrument and these items are currently collected in multiple PAC settings, we believe that these items are understood by providers in the settings in which they are currently collected and that they will be well understood in settings in which they may be collected in the future. We disagree with the commenter and do not believe that the FIM^TM instrument is the best instrument to use to collect standardized patient assessment data across all PAC settings. As noted above, the data items collected in the Quality Indicators section of the IRF-PAI are a subset of items derived from the original CARE tool item set that was specifically developed to measure the clinical complexity of patients in acute care hospitals and across all four types of PAC providers. We continue to believe that the data items located in the Quality Indicators section of the IRF-PAI are the most appropriate data for assessing functional status in the IRF setting and across all PAC settings.

Comment: Several commenters suggested that we utilize a demonstration or establish a model through CMS' Center for Medicare and Medicaid Innovation to test the revisions to the IRF-PAI, inform future policy recommendations, and gather additional data before making IRFs invest in system changes for revisions to the IRF-PAI.

Response: We do not believe there is any need to test the collection of IRF-PAI data as it would not have any impact on, or fundamentally change, the current IRF-PAI submission process. The Quality Indicator data items that we proposed to use to determine Medicare payment to IRFs are already being collected on the IRF-PAI and were originally developed and tested as part of the PAC PRD version of the CARE item set. These items have undergone extensive testing and validation and have been found to be accurate and valid to use for payment purposes under the IRF PPS.

Comment: One commenter stated they were concerned that the discontinued use of the FIM^TM instrument could stymy research and advancements in treatment and care management, as most rehabilitation research and other Physical Medicine and Rehabilitation (PM&R) academic papers use FIM^TM data to assess function and intervention outcomes.

Response: As noted previously, the FIM^TM data items and the Quality Indicator data items are very similar, and we therefore do not believe that the proposed removal of the FIM^TM instrument and replacement with the Quality Indicator data will have a substantial impact on the research being conducted in this area. Researchers may choose to continue to use the FIM^TM data items, subject to obtaining any necessary permissions, or alternatively, utilize the Quality Indicator data items.

Comment: One commenter inquired if preadmission screening requirements would be updated to utilize Quality Indicator item scoring.

Response: We do not currently require FIM^TM scoring on the preadmission screening documentation, and we will not require the Quality Indicator item scoring on the preadmission screening documentation either.

Comment: Several commenters expressed concerns that there are no certification requirements and no clinician-level certification materials for section GG items and inquired if there would be a certification process developed for this in the future.

Response: There is currently no plan to require any certification process for completion of the IRF-PAI. Patient assessments must be completed in accordance with applicable federal requirements.

Comment: Commenters stated that transitioning from the FIM^TM instrument to the Quality Indicators items will take time and sufficient training to ensure the industry understands and consistently applies the new definitions and standards. Commenters stated that we have not provided enough guidance to ensure the accuracy of this data and noted that guidance received during training on the CARE tool was inconsistent and that additional training with the CARE tool is needed. Commenters requested that we clarify the new rules for section GG patient assessment items, revise the IRF-PAI training manual to reflect these clarifications, and provide more opportunities for education and outreach to IRF providers. One commenter did not object to the proposed removal of the FIM^TM, but requested that we develop decision trees to assist clinical teams in accurately coding the Quality Indicators data items.

Response: We disagree with the commenters' assertions that we have provided insufficient guidance on the proper coding of this data. We are committed to providing information and support that will allow providers to accurately interpret and complete quality reporting items. We believe we have provided adequate training opportunities for IRFs on coding the Quality Indicator data items, including in-person training, webinars, on-line training and help desk emails. We will continue to provide these types of opportunities to the IRF community and plan to provide training and updated educational resources regarding the Quality Indicators items before the data items are used for payment purposes beginning on October 1, 2019.

We finalized the collection of the Quality Indicators data items in the FY 2016 IRF PPS final rule (80 FR 47036, 47100 through 47120). Prior to October 1, 2016, the data collection start date, we hosted two in-person training programs for IRFs that included coding guidance for the Quality Indicators items followed by practice examples and a case study so IRF clinicians could practice applying the guidance. Additionally, we offered an IRF QRP Refresher Webinar in August 2017, which covered coding guidance and examples for this data, and then hosted an additional in-person training in May 2018, which also covered coding guidance and new examples for coding this data.

The 2016, 2017, and 2018 training materials (for example, slides and case study) are available at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/IRF-Quality-Reporting-Training.html. Video recordings of previous trainings can be accessed at CMS YouTube channel at https://www.youtube.com/user/CMSHHSgov. Search for “IRF QRP” on the CMS You Tube channel.

A web-based training program focused on the coding of the Quality Indicators items was published on the CMS website in December 2017. This training module can be accessed at https://www.cms.gov/medicare/Quality-Initiatives-Patient-Assessment-Instruments/NursingHomeQualityInits/gg-training/.

We also note that we receive questions about coding the items via the IRF QRP help desk email (IRF.questions@cms.hhs.gov), and we encourage providers to reach out to us with any questions.

We have updated the Quality Indicators section of the IRF-PAI Training Manual in 2016, 2017, and 2018 and incorporated coding tips based on the questions we have received via the help desk and during training programs. We also post on the CMS website “Post-training Question and Answer” documents and “Frequently-Asked Questions” so that all providers can learn from questions requested by their colleagues. These resources are available on the IRF QRP website at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/.

We thank the commenters for their suggestion to improve training materials by incorporating more decision trees. We will work to incorporate this approach into our training materials.

Comment: Several commenters stated that there is considerable confusion and uncertainty among many rehabilitation hospital clinicians as to how to accurately and consistently score a patient's “usual performance” under the Quality Indicator items and expressed concern that the data may not be accurate due to duplication and discrepancies in the definitions of the term “usual performance”. One commenter indicated that CMS has not adequately defined what it means to assess a patient's “usual performance” on a Section GG item or activity and requested that CMS clarify the definition for “usual performance” with specific examples.

Response: We disagree with the commenters on this point. Usual performance has been the approach used since the development and testing of the data elements, starting in 2006, and we believe that IRF clinicians are able to accurately assess patients' “usual performance” on the Quality Indicator items, as we have undertaken numerous training efforts and developed comprehensive training materials to assist providers in accurately coding these data items. We have been pleased with the participation of IRF clinicians at the in-person training programs and via the IRF QRP help desk since the introduction of the Quality Indicator data elements. Our responses to questions from the IRF QRP help desk have reflected more specific guidance and examples related to coding usual performance. In an effort to share this information widely with the IRF industry, we have updated Section GG of the IRF-PAI Training Manual in 2016, 2017 and 2018 and incorporated coding tips based on the questions we have received via the help desk and during training programs. The IRF-PAI manual and change tables can be found in the Download section on the IRF QRP website at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/IRF-PAI-and-IRF-QRP-Manual.html.

We also post on the CMS website “Post-training Question and Answer” documents and “Frequently-Asked Questions” so that all providers can learn from questions requested by their colleagues. These resources are available on the IRF QRP website at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/ .

In addition, we refer readers to the most recent IRF QRP Providers Training, held May 9-10, 2018 in Baltimore, MD. Training materials and video recordings are available at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/IRF-Quality-Reporting-Training.html.

We thank the commenters for the suggestions to improve training materials by including specific examples and appreciate the feedback on the types of training materials that are most helpful to providers. We will continue to offer training sessions and will work to incorporate these approaches into our training materials. We also plan to offer these training sessions and update training materials and educational resources before the refinements to the case-mix classification take effect on October 1, 2019.

Comment: One commenter sought additional information on the expectations for capturing patient level of care and what role nursing staff has in capturing the patient's usual performance.

Response: As noted above, the data items located in the Quality Indicators section of the IRF-PAI and the revised CMGs have been found to accurately reflect the relative resources needs and costliness of patients. With regard to the expectations and role of nursing staff in capturing patient level of care, we believe it is the responsibility of each IRF to ensure that any staff, including nurses, that complete the IRF-PAI assessments adhere to the coding instructions and specifications identified in the IRF-PAI training manual for coding the data items located in the Quality Indicators section of the IRF-PAI.

Comment: One commenter requested that we clarify how cognitive abilities for stroke patients should be reported under the Quality Indicator items.

Response: The reporting of cognitive ability for stroke patients should follow the coding guidelines outlined in the IRF-PAI Training Manual. The IRF-PAI Training Manual can be accessed on the CMS IRF QRP website at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment- Instruments/IRF-Quality-Reporting/IRF-PAI-and-IRF-QRP-Manual.html.

Comment: Several commenters requested that we better clarify the instructions for completing the Quality Indicator items on the IRF-PAI. Specifically, these commenters requested that we clarify any differences between the reporting of the FIM^TM instrument and the Section GG items, including the timing of the data collection (that is, the first 3 days of admission), and that we explain how Section GG items align with other IRF requirements.

Response: We refer these commenters to Section GG in the IRF-PAI Training Manual on the CMS IRF QRP website at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/IRF-PAI-and-IRF-QRP-Manual.html for additional information about completing the Section GG items. As we do not understand from the comments exactly what questions these commenters have about the Section GG items, we also encourage them to send specific questions that they may have regarding how to report the Section GG items or how these items align with other IRF regulations to us at IRF.Questions@cms.hhs.gov. We will be happy to try to answer the commenters' questions directly. We also plan to provide training and updated educational resources regarding the Quality Indicators items before the data items are used for payment purposes beginning on October 1, 2019.

Comment: Several commenters specifically expressed concern with the new cognitive function items in Section GG, stating that they believe these items lack the appropriate sensitivity and do not capture a complete picture of cognition, especially when compared to the legacy cognition items from the FIM^TM instrument. These commenters said that using the new items and excluding the legacy cognitive FIM^TM items may produce an inadequate picture of patient severity, level of impairment, and the resources needed to care for patients. Several commenters expressed concerns with the BIMS item, stating that the item cannot measure progress, social interaction, or problem solving, which can lead to unsafe discharges, repeat re-admissions, and higher SNF placement and that the item cannot define critical deficits within cognitive domains that are useful for care planning such as social interaction, levels of supervision, safety considerations, and the need and use of medications. Commenters noted that CMS is still testing these data items and recommended that these items not be utilized until they are found to be sufficiently reliable and valid. Another commenter indicated that work is underway to develop better function and cognition measures and encouraged us to incorporate the improved cognition measures into the IRF-PAI as they become available to ensure that the breadth of cognition is captured in patient assessment.

Response: We believe that the cognitive items including the expression of ideas and wants, understanding verbal and non-verbal content, and the BIMS items have been tested and have been shown to be sensitive and valid. The reliability of these communication items was tested in the IRF setting and results are reported in the report entitled The Development and Testing of the Continuity Assessment Record and Evaluation (CARE) Item Set: Final Report on Reliability Testing Volume 2 of 3 (available at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/Post-Acute-Care-Quality-Initiatives/Downloads/The-Development-and-Testing-of-the-Continuity-Assessment-Record-and-Evaluation-CARE-Item-Set-Final-Report-on-Reliability-Testing-Volume-2-of-3.pdf ).

This analysis indicated that the data element focused on understanding verbal and non-verbal content and had very good reliability with unweighted and weighted kappa values that ranged from 0.677 to 0.777. The data element focused on expression of needs also showed very good reliability with unweighted and weighted kappa values between 0.656-0.789.

We examined the reliability of the BIMS items in post-acute care providers and found very good agreement with weighted kappas ranging from 0.71 to 0.91 and unweighted kappas ranging from 0.62 to 0.86. The kappas were highest for the “Temporal orientation” items at 0.86 and above and “Recall of three words” at 0.89 or above for the second recall item. The first memory item, “Repetition of 3 words,” was slightly lower with kappas of 0.71.

We would also like to note that the cognitive items that were used in RTI's CART analysis only emerged as potential splits in two RICs. As we proposed to merge the CMGs within these RICs, these cognitive items were not included in the proposed revised CMG definitions. We appreciate the commenter's suggestion to incorporate improved cognition measures into the IRF-PAI if and when they become available and will take this into consideration in future analyses.

Comment: Several commenters expressed concerns that we have not adequately evaluated how clinicians across the nation have been scoring and assessing the Quality Indicators data items and suggested that we conduct new inter-rater reliability studies to validate practice consistency in the field before finalizing these proposals.

Response: We agree with the commenters about the importance of reliability testing on these items to ensure that they are being scored consistently across all IRF providers. For this reason, we examined reliability using two distinct methods. Our initial testing focused on within-facility testing. We requested two clinicians to assess the same patient at the same time and independently report the patient's ability. Our subsequent testing focused on using “standardized patients” by using videotapes of persons completing daily activities and being interviewed by a clinician. By showing the same videos to multiple clinicians, we were able to examine the agreement of data element coding across all the providers and across disciplines and with coding experts. We report on the “standardized patient” reliability testing in a report entitled “Continuity Assessment Record and Evaluation (CARE) Item Set: Video Reliability Testing” which is available at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/Post-Acute-Care-Quality-Initiatives/Downloads/Continuity-Assessment-Record-and-Evaluation-CARE-Item-Set-Video-Reliability-Testing.pdf.

When we submitted the four functional outcome measures for NQF endorsement consideration, our NQF applications included reliability and validity testing of the data elements, the scale and facility-level data. The testing of the data elements, the scale and facility-level data showed very good reliability and validity. The NQF applications can be found at http://www.qualityforum.org/QPS/2633 and http://www.qualityforum.org/QPS/2634 and http://www.qualityforum.org/QPS/2635 and http://www.qualityforum/QPS/2636 . We note that these four functional outcome measures are due for maintenance of NQF endorsement in 2019 and that we will submit NQF applications with updated reliability and validity testing for the data elements, scale and provider-level data, which will be reviewed by the NQF methods panel, person- and family-centered care committee and the public.

Comment: Several commenters suggested that because the data items in the FIM^TM instrument and the data items collected in the Quality Indicators section of the IRF-PAI use different scales, there is a need to crosswalk future performance to historical performance to ensure continuity in ongoing care improvement activities. Several commenters noted there are no available tools to crosswalk the FIM^TM data items to the CARE data items set and requested that CMS make such a tool available so that providers can study and compare patient functional outcomes if the FIM^TM instrument is removed. A number of commenters indicated they use national and regional benchmark data to measure clinical outcomes and improvement efforts and recommend that CMS delay the removal of the FIM^TM instrument until benchmark data is available for the data items located in the Quality Indicators section of the IRF-PAI.

Response: Although the data items collected in the Quality Indicators section of the IRF-PAI utilize different reporting guidelines and a different scale than the FIM^TM items, we believe that the FIM^TM and the Quality Indicator items are similar enough to facilitate ongoing care improvement activities. The items do not lend themselves to a specific cross-walk, but we do provide national IRF Medicare data for the Functional Outcome Measures derived from the data items located in the Quality Indicators section of the IRF PAI in Confidential QM Reports and Provider Preview Reports to IRFs in CASPER, so that the providers have the ability to compare their patients' functional outcomes with those of other IRFs. The data items located in the Quality Indicators section of the IRF-PAI have been collected since October 1, 2016, so IRFs may use this data to compare functional outcomes over time. By October 1, 2019, 2 years (24 months) of this data will be available. The methods used to calculate the functional outcome measures using this data are provided in the IRF Quality Measures User's Manual, which is available at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/IRF-Quality-Reporting-Program-Measures-Information-.html.

Comment: Several commenters stated that 1 year of data is too little to be used as the basis for a new case-mix system. Many commenters noted that providers have limited experience using the assessment items in the Quality Indicators section of the IRF-PAI and suggested that the data may not be accurate and valid and therefore the revised case-mix groups may not accurately reflect patients' nursing, therapy, cognitive and other needs. Commenters suggested that CMS should study and evaluate the accuracy of the data before basing any changes on it and noted CMS has not audited this data to determine if providers are reporting the Quality Indicator items appropriately and accurately. Many of these commenters noted that there was a 4-year baseline of data used when the FIM^TM instrument was incorporated into the IRF PPS and that the same baseline is not present for the analysis used to incorporate the Quality Indicators items into the IRF PPS. Commenters suggested that we should consider delaying this proposal until multiple years of data are available for analysis. Other commenters suggested excluding 1 or more years of the initial data collected from the analysis to provide a more stable foundation to support this proposed policy change. Commenters encouraged CMS to monitor any shifts in this data and update the model to reflect these changes.

Response: We note that the data items in the Quality Indicators section of the IRF-PAI have been collected for close to 2 years, and we believe the data to be accurate and valid at this time. Additionally, we note that we do not generally audit the FIM^TM data that is used for payment and believe it is the responsibility of the IRF to submit accurate and valid data that adheres to the coding guidelines detailed in the IRF-PAI training manual.

As published in the aforementioned technical report, “Analyses to Inform the Potential Use of Standardized Patient Assessment Data Elements in the Inpatient Rehabilitation Facility Prospective Payment System,” RTI found that the model predicting costs using CMGs derived from the items located in the Quality Indicators section of the IRF-PAI, based on data from FY 2017, had a slightly higher R-squared value than models using the current CMGs which are derived from items in the FIM^TM instrument, thus indicating that the revised CMGs more accurately predict costs than the CMGs that are currently utilized.

We also note that the data items and response codes located in the Quality Indicators section of the IRF-PAI have been collected nationally for all IRFs since October 1, 2016. As such, the proposed revised CMGs reflect data collected from the entire universe of Medicare-covered inpatient rehabilitation patients, allowing for greater precision in the analysis compared to the analysis used in the construction of the original CMGs. The original CMGs that were implemented at the inception of the IRF PPS were based on data from just a sample of hospitals, which was the best available data at the time and which contributed to the use of multiple years of data in those analyses. As the most recently available year of national data portrays the most recent and complete picture of patients under the IRF PPS, we believe it was sufficient and appropriate to utilize in this analysis.

However, we appreciate the commenters' concerns and suggestions to incorporate multiple years of data into this analysis and conduct monitoring activities and we will therefore ensure that we use multiple years of data in our analysis when we incorporate the Quality Indicator data items into the IRF case-mix classification system on October 1, 2019. We will incorporate an additional year of data into the analysis used to update the revised CMG definitions to reflect the use of the different assessment items. Any changes to the revised CMG definitions will be addressed in future rulemaking prior to their implementation beginning in FY 2020.

Comment: Several commenters requested clarifications and further detail on how cognitive function would play a role in defining the CMGs. Other commenters noted that current CMGs incorporate cognition and expressed concern that cognition does not factor into the revised CMGs. Commenters suggested that cognition is an important factor in determining how costly a patient will be in the IRF and indicated that not reflecting a patient's cognitive score in the CMG definitions misses an important factor in predicting patient costs. Another commenter recommended that we investigate whether there are floor or ceiling effects with the proposed cognitive function items. Commenters also requested that we allow and recognize additional cognitive research to consider impacts on costs of care before finalizing this policy and suggested that we conduct further study into the relationship between cognitive function and resource use in the inpatient rehabilitation setting. One commenter requested that the FIM^TM cognitive items be included in the CMGs to account for the cost and impact of cognitive deficits.

Response: To clarify, a cognitive score was identified in the early stages of the analysis for inclusion in the proposed revised CMG definitions as a potential split for CMGs in both RIC 16 and RIC 17, presented separately in Table 8 of the FY 2019 IRF PPS proposed rule (83 FR 20992). Ultimately, however, we decided to propose to combine the CMGs within these RICs because, in both cases, higher patient cognitive deficits would have led to lower IRF payments, which we believed would be inappropriate. Also, we were concerned about this result because it was based on a relatively small number of patients that could be inappropriately skewing our results. As the CMGs we proposed to combine within these RICs were only differentiated by a cognitive score, our decision to consolidate the CMGs in these 2 RICs, resulted in the exclusion of a cognitive score from the definitions of the revised CMGs presented in Table 9 of the FY 2019 IRF PPS proposed rule.

We believe that the fact that patients' cognitive scores do not show up as significant in the CART analysis in any other RICs may be due in large part to the limitations with the cognitive items that were proposed to be incorporated into the revised case-mix system. The cognitive items that we used for this analysis are the best ones that we have for use at the present time, but we will certainly consider the incorporation of revised cognitive data items into the CMG definitions if and when they become available in the future. We also note that, while a cognitive score is not included in the revised CMG definitions, the motor score may capture aspects of cognitive status as the scale measures the need for assistance, including supervision. We will take the commenters' concerns into consideration in future analysis.

Comment: Several commenters noted particular concerns that they had with the proposed motor score, including concerns with the exclusion of certain items from the score's calculation, general concerns with the structure of the data items that were proposed for inclusion in the motor score, and concerns with the definition of the score response codes utilized by the data items that were proposed for inclusion in the motor score. Commenters also requested additional information on the predictive ability of the items that were included in the proposed motor score. One commenter specifically requested additional information on why item “GG017O1—12 Steps” was not included in the motor score.

Response: We appreciate the commenters' concerns with the proposed motor score. We note that RTI analyzed a range of available data to identify the variables that were most predictive of costs in the IRF setting. RTI's analysis shows that the correlation between the standardized item motor score and the FIM^TM motor score was between 0.76 and 0.90 across all RICs. In addition, each of the proposed Quality Indicators data items that were included in the motor score were found to have statistically significant correlation with IRF costs.

RTI's analysis of the variables that were most predictive of costs found a higher use of “activity not attempted codes” for more challenging items such as GG017O1 and found that there was less variability overall in the score for these items across all patients on admission, which may be due to discretion in the assessment of these activities. Based on this finding, the more challenging items including stairs and car transfers were not included in the motor score.

Comment: A number of commenters disagreed with the omission of wheelchair locomotion from the motor score items that were found to best predict costs and sought additional information on how patients that are wheelchair dependent would be accounted for in the proposed CMGs and what impact this would have on wheelchair-dependent patients. One commenter noted that omitting wheelchair locomotion items from the motor score would underestimate a patient's functional ability at admission if the patient is more functional in a wheelchair than walking and recommended including “wheels 50 feet with 2 turns” and “wheels 150 feet” into the motor score. One commenter noted that omitting wheelchair items from the motor score would inappropriately produce a higher facility payment for some patients that may be more functional in a wheelchair than walking, as these patients' functional ability would be underestimated based on walking items alone.

Response: We appreciate the commenters' concerns about wheelchair-dependent patients. Patients that are considered wheelchair dependent or are otherwise unable to walk would be accounted for in the proposed motor score through the “not attempted” response codes captured through some of the other items, especially some of the walking items that are incorporated in the proposed motor score. We proposed to recode any “not attempted” response codes to 1, the most dependent status, because RTI's analysis of the items “wheel 50 with two turns” and “wheel 150 feet with two turns” indicated that the majority of these items are currently coded as 1, “dependent” or utilized an “activity was not attempted code”. We do not believe that the omission of these items from the motor score would have any impact on wheelchair dependent patients. We thank the commenters for their suggestions and will consider the incorporation of the data items identified above into the motor score in the future.

Comment: Commenters requested that we explain why we proposed to use an unweighted motor score when RAND previously found that a weighted motor score using the FIM^TM items improved the explanation of variance within each RIC.

Response: We proposed to use an unweighted motor score as our analysis at this time does not identify any benefit from weighting the items in the motor score. Additionally, the unweighted motor score facilitates greater understanding among the provider community, as it is less complex. We will take these comments into consideration in future analysis.

Comment: Several commenters expressed concerns with the number of claims used in the analysis and questioned if we were using statistically sound data. Some of these commenters also suggested that it would be more appropriate to utilize multiple years of data for this analysis.

Response: We believe that the data utilized in this analysis was sufficient and statistically sound. The exclusion criteria utilized in the analysis and outlined in the technical report aligned with the approach used by RAND when revisions to the current CMGs were finalized in the FY 2006 IRF PPS final rule (70 FR 47892 through 47896). We appreciate the commenter's suggestion to incorporate multiple years of data into the analysis and will use 2 years of data (FYs 2017 and 2018) to revise the CMG definitions prior to implementing the proposed changes in FY 2020.

Comment: We received several comments on the proposed score recoding methodology that was discussed in the proposed rule and in the technical report. One commenter supported the proposed score recoding methodology. Another commenter recommended that a value of 10 be recoded to a 6 for the bladder continence item, and suggested that a non-response items for the bladder item should be recoded to “0” instead of “1”, noting that recoding it to “1” would overestimate a patient's bladder function at admission. Another commenter stated that they did not support the proposed score recoding methodology, and requested that we provide additional rationale and explanation for the methodology. Some commenters also requested that we conduct further regression analysis to test the proposed score recoding methodology. Additionally, one commenter expressed concern that the proposed score recoding methodology could have significant operational impacts on providers.

Response: We thank the commenters for these suggestions and will take them into consideration in the future. We note that the proposed methodology for recoding the “non-response” values aligns with the current recoding methodology, and reflects both findings from regression analysis and clinical input. We also note that we do not believe that the proposed score recoding methodology could have a significant operational impact on providers as it does not impact the data collection or submission process of IRF-PAI data.

Comment: One commenter noted that the bladder continence and bowel continence items use a scoring methodology where higher scores indicate more impairment which does not align with the scoring methodology used for the other motor items where lower scores indicate higher impairment.

Response: As outlined in the aforementioned technical report, available at https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Research.html,, we proposed to reverse the bladder continence and bowel continence responses for purposes of determining the motor score so that the higher response codes would reflect less impairment to be consistent with the scale used for the other proposed motor items.

Comment: One commenter disagreed with the use of the response code “10- the activity was not attempted due to environmental limitations” and suggested that allowing a facility to not assess a patient due to environmental limitations would reduce the quality of care for patients.

Response: We appreciate the commenter's concerns but have no reason to believe that ability to indicate why an activity was not attempted would reduce the quality of care for patients. We note that responses indicating an activity did not occur or was not attempted are currently used on the IRF-PAI for items in both the FIM^TM Instrument and items located in the Quality Indicators section of the IRF PAI. The addition of this code allows for the collection of additional data indicating why an activity was not attempted.

Comment: One commenter was generally supportive of the proposed refinements to the CMGs but expressed concern about the proposal to combine CMGs within RIC 16 and RIC 17, stating that fewer CMGs within RICs may degrade the ability to quantify burden of care in sufficient detail. Another commenter did not support the proposal to combine certain CMGs and requested that we increase the sample size of the data on which the analysis was conducted.

Response: As noted in the aforementioned technical report, RTI's analysis indicated that the CMGs generated by the CART analysis for RIC 16 and RIC 17 attributed considerably higher costs for what could amount to a small level of impairment. Given the high threshold for the splits, the inconsistency with clinical expectations, and the low number of observations in these RICs, we proposed to remove these splits from the final CMG definitions. Specifically, these splits went against clinical expectations by attributing higher payments to beneficiaries with less impairment than to those with greater impairment, which we believed would be inappropriate. As noted above, we will incorporate an additional year of data into our analysis and will revisit any changes in this proposal due to the incorporation of additional data into the analysis in future notice and comment rulemaking prior to implementing the revised CMG definitions beginning in FY 2020. We appreciate the commenter's concerns and will take them into consideration for future analysis.

Comment: Several commenters expressed concern that the new CMGs may not accurately reflect the severity of illness of some of the most clinically complex IRF patients, noting that there were fewer CMGs in some RICs, thereby creating less specificity in payment determinations for some patients. Commenters also suggested that these changes will impact access to and quality of care for medically complex patients and suggested that we assess the impact of these proposed changes on patient outcomes.

Response: While the commenters are correct that, in certain RICs, there are fewer proposed CMGs than under the current IRF case-mix classification system, there are more proposed CMGs in other RICs. We disagree with the commenters' concerns that the revised CMGs may not accurately reflect resource needs for clinically complex patients. As noted in the FY 2019 IRF PPS proposed rule (83 FR 20991 through 20992) and the accompanying technical report, RTI utilized CART analysis on FY 2017 Medicare claims to determine the revised CMG definitions. As such, we believe the revised CMGs reflect the severity or distinct resource needs of the current Medicare IRF population. We believe that, if anything, the revised CMGs will have a neutral or positive impact on access to and quality of care for IRF patients by increasing the accuracy of IRF payments to providers. We appreciate the commenters' concerns and will continue to monitor the IRF data closely to ensure that IRF payments are appropriately aligned with costs of care and that Medicare patients continue to have appropriate access to IRF services.

Comment: Several commenters expressed concern that utilizing a patient's usual performance instead of lowest function will make IRF patients appear “less severe” and that the revised CMG definitions will result in decreased lengths of stay and decreased payments.

Response: We agree with commenters that the scales and coding instructions are slightly different between the data sets and that coding a patient's usual performance instead of the patient's lowest function may result in higher functional scores for some patients. As noted above, we believe that the scale for the data items located in the Quality Indicators section of the IRF-PAI is sensitive and may more accurately reflect the costs of caring for patients.

Regarding the commenters' assertion that this proposal will lead to shorter lengths of stay, we disagree with the commenters that the proposal will have any substantial or long-term impact on the average lengths of stay in the IRFs. First, we believe that these commenters have misunderstood the purpose of the published average lengths of stay values in the IRF PPS proposed and final rules. We note that the average length of stay values are not prescribed lengths of stay for patients admitted to IRFs and should not considered to be target lengths of stay. IRFs generally have the flexibility to treat patients for as few or as many days as they deem medically appropriate. We encourage IRFs to admit patients for the length of time that results in the best quality of care for the patient. The average length of stay values are used to determine when an IRF discharge meets the definition of a short-stay transfer.

Additionally, we believe that commenters may have been inappropriately comparing the average lengths of stay published for the proposed revised CMGs to the average lengths of stay for the current CMGs. As the definitions for the proposed revised CMGs are different than those for the current CMGs, the average length of stay values cannot be directly compared between the two. The proposed revised CMGs group patients differently, and therefore result in different average length of stays for the new patient groupings. We do not believe that the proposed revised CMGs would result in any systematic changes in average length of stay in the IRF setting since, as noted above, the average length of stay values should not considered to be target lengths of stay.

Comment: Several commenters expressed concern that the proposed CMGs may not, in fact, be budget neutral as proposed and requested that we reevaluate our budget neutrality adjustment. One commenter noted that they anticipated lower payments due to this proposal and therefore, the proposal was not budget neutral.

Response: We disagree with the commenters' suggestions that the proposed budget neutrality adjustment was incorrect. As stated in the FY 2019 IRF PPS proposed rule, the proposed revisions to the IRF case-mix classification were to be implemented in a budget neutral manner. Thus, we proposed to apply a budget-neutrality adjustment to payments to ensure that aggregate payments to IRFs due to the implementation of these proposals would neither increase nor decrease overall. However, the proposed changes would result in some redistribution of payments among providers.

Comment: One commenter stated that we have not adequately determined the impact of these proposed changes on patient outcomes, including medically complex, low functioning patients and that these types of analyses should be an essential component of the IMPACT Act's eventual research framework before moving forward.

Response: As noted previously, the Quality Indicator data items have been extensively tested for reliability, accuracy, and sensitivity and were found to be reliable, accurate, and sensitive for use in the IRF PPS. As these items are more sensitive and more accurately reflect patients' functional status in the IRF, we believe that IRF payments based on these items will do a better job of reflecting patients' costs than payments based on the FIM^TM items. Therefore, we disagree with the commenter and believe that, if anything, the proposed changes will have a neutral or positive impact on access to care and outcomes for more medically complex, low-functioning patients by paying more accurately for these patients' care in the IRF.

Comment: One commenter requested that we adjust the classifications and weighting factors to reflect the special care and complex medical needs of oncology patients in the rehabilitation setting. This commenter suggested adding additional codes to the list of impairment group codes to better define patients with impairments due to cancer under the RIC classification system and noted that without these specific classifications, cancer patients may not be admitted to IRFs due to the high costs of care for these patients.

Response: As we did not propose any changes to the RICs or comorbidity tiers, this comment is outside the scope of the proposed rule.

Comment: Several commenters requested more information about how comorbid conditions will be reported for the revised case-mix classification system and requested that we review and update the comorbid condition code listings.

Response: As we did not propose any changes to how comorbid conditions are to be reported or any changes to the list of comorbid condition codes, these comments are out of scope of the proposed rule.

Comment: Many commenters noted that they were supportive of policies in the IMPACT Act and of future Medicare payment reforms that would move Medicare in the direction of unified post-acute care payment. However, several of these commenters suggested that the proposed revisions to the CMGs are inconsistent with the intent of the IMPACT ACT. Multiple commenters noted that the IMPACT Act's core premise is to develop a complete evidentiary basis, inform broad post-acute care payment and delivery reform, and provide recommendations for replacing existing payment policies based on the incorporation of standardized patient assessment data. These commenters suggested that finalizing the proposed policies now would be premature and recommended that we refrain from finalizing the proposed changes at this time. Commenters stated that because the proposal would be implemented in a budget neutral manner, there is no financial rationale or budgetary impact that supports moving faster than the IMPACT Act mandates. Many commenters also stated that the functional assessment data items located in the Quality Indicators section of the IRF-PAI were designed for quality purposes and should not be used to develop a new payment system.

Response: We disagree with the commenters' suggestion that these proposals are inconsistent with the intent of the IMPACT Act and would like to note that these policies were proposed under the authority of section 1886(j)(2)(D), 1886(j)(2)(B), and 1886(j)(2)(C) of the Act. We believe that the proposed policies align with the overall goals of the IMPACT Act and are a necessary step toward a potential unified PAC PPS in the future. We would like to note that the data items that we proposed to incorporate into the IRF case-mix system were tested for use in all PAC settings under the PAC PRD, and were found to be appropriate to use for payment purposes.

We also disagree with the commenters' suggestions that the data items located in the Quality Indicators section of the IRF-PAI were developed for quality purposes and are therefore not suitable for use in payment because they were developed for quality reporting purposes. Many of these data items were derived from the original CARE Tool data item set. The CARE Tool's development was based on certain guiding principles, including the ability to measure the needs and clinical characteristics of patients that were predictive of resource intensity and that could be used to inform payment policy. While we agree with commenters that the IMPACT Act imposed new data reporting requirements for the purposes of the quality reporting program, it does not preclude the use of these items for payment purposes. As noted above, these items were developed and tested for payment purposes and were found to be appropriate for incorporation in the IRF case-mix system. We would also like to reiterate that we disagree with the commenter's assessment of the proposed revisions to the CMGs as the development of a new payment system. We believe these proposals would generate minor changes to the current IRF case-mix classification system.

Comment: Several commenters stated that they believe that the proposed incorporation of data items located in the Quality Indicators section of the IRF-PAI into the IRF case-mix system conflicts with the timelines specified in the IMPACT Act. Commenters noted that CMS and MEDPAC are directed to submit a report to Congress by 2021 on the findings of the IMPACT Act and to provide recommendations for replacing existing PAC payment systems. Several commenters stated that, if we were to move forward with finalizing the proposed changes, it would be in direct conflict with the timelines in the IMPACT Act.

Response: We believe commenters may have misinterpreted the reporting requirements and associated deadlines stipulated in the IMPACT Act, as these requirements are not applicable to the proposed removal of the FIM^TM instrument and associated Function Modifiers from the IRF-PAI or the proposed incorporation of data items located in the Quality Indicators section of the IRF-PAI into the IRF case-mix system at this time. While these proposals are generally consistent with the broad goal of standardizing patient assessment data collection across PAC settings and aligning the IRF PPS with other PAC payment systems, they do not implement or conflict with any specific provision of the IMPACT Act.

Comment: Several commenters noted that they did not believe that we have performed the thorough data analyses, testing, and engagement with the provider community that are necessary prior to making significant changes to the IRF-PAI and the IRF PPS. Many commenters did not support the proposed revisions to the IRF PPS and noted they would be willing to work with us to develop appropriate changes to payment policies in the future. One commenter specifically expressed concern that CMS did not seek stakeholder input through an advanced notice of public rulemaking, similar to the process used in proposing the new SNF case-mix classification system. Several commenters requested that we solicit additional feedback from the stakeholder community, including convening a technical advisory panel, to assist us in developing the proposed changes to the IRF case-mix classification system.

Response: We are committed to engaging with the provider community and providing information that will support a clear understanding of our proposals and the potential impacts on providers. We would like to note that RTI hosted a TEP in 2014 to discuss their initial research and findings on the potential incorporation of the CARE data items into the IRF case-mix system. Through the TEP, we received helpful feedback on the initial research that was taken into consideration in the development of these proposals. We appreciate the offers from stakeholders to assist in the development of future revisions to payment policies and we recognize the value from these partnerships. We appreciate the request for increased engagement and will continue to engage stakeholders in future development of payment policies. However, we do not believe an advanced notice of proposed rulemaking would have been necessary or that a technical advisory panel is needed at this time as the proposed changes to the case-mix system are minor.

Comment: Several commenters expressed concern that providers needed more time or information to model the impact of a new case-mix classification system. Multiple commenters requested that we provide additional information, including the algorithms and CART trees used in the analysis to better understand how we arrived at the proposed revisions to the CMG definitions. One commenter requested that we make available all standardized data being collected from providers across all settings of care. Another commenter requested that we make all data utilized in the analysis, including the Medicare Inpatient National Claims History, IRF-PAI data, and IRF cost reports available in full to enable IRFs to replicate our analyses. Some commenters indicated that, without additional data, they would not be able to provide meaningful input on the proposed significant changes to the IRF case-mix classification system.

Response: We believe that we released sufficient information in the proposed rule and the accompanying technical report to enable stakeholders to model impacts and submit meaningful comments. The technical report, entitled “Analyses to Inform the Potential Use of Standardized Patient Assessment Data Elements in the Inpatient Rehabilitation Facility Prospective Payment System,” was released contemporaneously with the proposed rule and describes, in detail, the data and analysis used to construct the revised CMGs. This technical report included the methodology used to calculate the revised functional scores and the CMG relative weights for the revised CMG definitions, which would allow providers to model impacts. Additionally, the FY 2019 IRF PPS proposed rule included an impact analysis for IRFs at a group level based on IRF provider characteristics.

Regarding the request for additional data, we note that the release of all standardized data being collected from providers in other settings of care is outside the scope of the proposed rule. Additionally, the FY 2017 IRF claims and IRF-PAI data utilized in this analysis contain information that can be used to identify individual Medicare beneficiaries and therefore cannot be made publicly available.

Final Decision: After careful consideration of the comments received, we are finalizing our proposal, as discussed in section VIII.A of this final rule, to remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI beginning in FY 2020 that is, for all discharges occurring on or after October 1, 2019.

We are also finalizing our proposal to incorporate certain data items from the Quality Indicators section of the IRF-PAI into the IRF case-mix classification system for payment purposes beginning in FY 2020. Specifically, we are finalizing our proposal to use the Quality Indicator data items identified in section VIII.B.2 of this final rule, to construct the functional status scores for use in the IRF case-mix classification system and to derive the scores for each respective group of the functional status items by calculating the sum of the items that constitute each functional status component.

Additionally, we are finalizing our proposal to update the score reassignment methodology, as discussed in section VIII.B.3 of this final rule, beginning with FY 2020, that is, for all IRF discharges beginning on or after October 1, 2019.

We are also finalizing our proposal, as discussed in section VIII.B.4 of this final rule, to utilize CMGs based on the data items from the Quality Indicators section of the IRF-PAI to classify IRF patients for purposes of establishing payment under the IRF PPS beginning with FY 2020. However, based on public comments, we are not finalizing the revised CMG definitions as proposed and as identified in table 9 of this final rule. Instead, we have noted the commenters' concerns regarding the use of one year of data and will incorporate two full years of data (FY 2017 and FY 2018) into our analyses used to revise the CMG definitions that will be implemented beginning in FY 2020. Any changes to the proposed CMG definitions resulting from the incorporation of an additional year of data (FY 2018) into the analysis will be addressed in future rulemaking prior to their implementation beginning in FY 2020. Additionally, we will also update the relative weights and average length of stay values associated with the revised CMG definitions in future rulemaking. We also plan to provide training and educational resources on the data items in the Quality Indicators section of the IRF-PAI before this finalized policy takes effect on October 1, 2019.

IX. Revisions to Certain IRF Coverage Requirements Beginning With FY 2019

We are committed to transforming the health care delivery system, and the Medicare program, by putting an additional focus on patient-centered care and working with providers and physicians to improve patient outcomes. As an agency, we recognize it is imperative that we develop and implement policies that allow providers and physicians to focus the majority of their time treating patients rather than completing paperwork. Moreover, we believe it is essential for us to reexamine current regulations and administrative requirements, to assure that we are not placing unnecessary burden on providers.

We believe the agency initiative of treating patients over paperwork will improve patient outcomes, decrease provider costs, and ensure that patients and providers are making the best health care choices possible. In the FY 2018 IRF PPS proposed rule (82 FR 20743), we included a request for information (RFI) to solicit comments from stakeholders requesting information on CMS flexibilities and efficiencies. The purpose of the RFI was to receive feedback regarding ways in which we could reduce burden for hospitals and physicians, improve quality of care, decrease costs and ensure that patients receive the best care. We received comments from IRF industry associations, state and national hospital associations, industry groups representing hospitals, and individual IRF providers in response to the solicitation. We are appreciative of the feedback. As discussed in more detail below, we in some cases used the commenters' specific suggestions to propose changes to regulatory requirements to alleviate provider burden. In other cases, however, we proposed additional changes to the regulatory requirements that we believed would be responsive to stakeholder feedback and helpful to providers in reducing administrative burden.

In the FY 2010 IRF PPS final rule (74 FR 39788 through 39798), we updated the IRF coverage criteria requirements to reflect changes that had occurred in medical practice since the IRF PPS was first implemented in 2002. IRF care is only considered by Medicare to be reasonable and necessary under section 1862(a)(1) of the Act if the patient meets all of the IRF coverage requirements outlined in § 412.622(a)(3), (4), and (5). Failure to meet the IRF coverage criteria in a particular case will result in denial of the IRF claim. The IRF coverage requirements have not been updated since they became effective on January 1, 2010. To reduce unnecessary burden on IRF providers and physicians, we proposed to revise the current IRF coverage criteria as suggested by some of the comments received in response to the RFI. Specifically, we focused on reducing medical record documentation requirements that we believe have become overly burdensome to IRF providers over time.

A. Changes to the Physician Supervision Requirement Beginning With FY 2019

In response to the RFI, several commenters suggested that we consider decreasing the number of required weekly face-to-face visits that the rehabilitation physician must complete and document in the IRF medical record. Commenters suggested that the decrease in visits would not only assist with reducing the medical record documentation burden on rehabilitation physicians, but it would also afford the rehabilitation physician more time to focus on higher-acuity, more complex patients resulting in improved outcomes and lower readmission rates. Additionally, we received comments suggesting that we consider either eliminating the requirement to document post-admission physician evaluation in the IRF medical record altogether in an effort to reduce paperwork and duplicative requirements or that we allow the post-admission physician evaluation to count as one of the required face-to-face visits completed and documented by the rehabilitation physician in the IRF medical record. We agreed with the commenters and proposed a combination of these two suggested ideas in order to reduce unnecessary burden on rehabilitation physicians.

Under § 412.622(a)(3)(iv), for an IRF claim to be considered reasonable and necessary under section 1862(a)(1) of the Act, there must be a reasonable expectation at the time of the patient's admission to the IRF that the patient requires physician supervision by a rehabilitation physician, defined as a licensed physician with specialized training and experience in inpatient rehabilitation. The requirement for medical supervision means that the rehabilitation physician must conduct face-to-face visits with the patient at least 3 days per week throughout the patient's stay in the IRF to assess the patient both medically and functionally, as well as modify the course of treatment as needed to maximize the patient's capacity to benefit from the rehabilitation process. Under § 412.622(a)(4)(ii), to document that each patient for whom the IRF seeks payment is reasonably expected to meet all of the requirements in § 412.622(a)(3) at the time of admission, the patient's medical record at the IRF must contain a post-admission physician evaluation that meets all of the requirements specified in the regulation. For more information, we refer readers to the Medicare Benefit Policy Manual, chapter 1, sections 110.1.2 and 110.2.4 (Pub. 100-02), which can be downloaded from the CMS website at https://www.cms.gov/Regulations-and-Guidance/Guidance/Manuals/Internet-Only-Manuals-IOMs.html.

While the purpose of the physician supervision requirement is to ensure that the patient's medical and functional statuses are being continuously monitored as the patient's overall plan of care is being carried out, the purpose of the post-admission physician evaluation is to document (in the IRF medical record) the patient's status on admission, identify any relevant changes that may have occurred since the preadmission screening, and provide the rehabilitation physician with the necessary information to begin development of the patient's overall plan of care. When the coverage criteria were initially implemented, we believed that the post-admission physician evaluation should not be used as a way to fulfill one of the face-to-face visits required under § 412.622(a)(3)(iv) because we considered them to be different types of assessments. We also believed it was in the patient's best interest to be seen by a rehabilitation physician at least four times in the first week of the IRF admission when the patient is in the most critical phase of their recovery process.

While we continue to believe that the post-admission physician evaluation and the face-to-face physician visits are two different types of assessments, after reevaluating these coverage criteria, we believe that the rehabilitation physician should have the flexibility to assess the patient and conduct the post-admission physician evaluation during one of the three face-to-face physician visits required in the first week of the IRF admission. Additionally, based on the comments that we received in response to the RFI, we believe that it should be the responsibility of the rehabilitation physician to use his or her best clinical judgment to determine whether the patient needs to be seen more than three times in the first week of the IRF admission. Therefore, allowing these two requirements to be met (and documented in the IRF medical record) concurrently would reduce redundancy and regulatory burden while still ensuring adequate care to the patient.

Therefore, we proposed to modify § 412.622(a)(3)(iv) to provide that the post-admission physician evaluation required under § 412.622(a)(4)(ii) may count as one of the face-to-face physician visits required under § 412.622(a)(3)(iv) beginning with FY 2019, that is, for all IRF discharges beginning on or after October 1, 2018. To clarify, we did not propose to modify § 412.622(a)(4)(ii), including the 24-hour timeframe within which the post-admission physician evaluation requirement must be completed.

We received 33 comments on the proposal to modify § 412.622(a)(3)(iv) to provide that the post-admission physician evaluation required under § 412.622(a)(4)(ii) (and documented in the IRF medical record) may count as one of the face-to-face physician visits required under § 412.622(a)(3)(iv) beginning with FY 2019, that is, for all IRF discharges beginning on or after October 1, 2018, which are summarized below.

Comment: The majority of commenters supported our proposal. Commenters agreed that the proposed change would provide additional flexibility to rehabilitation physicians and reduce redundancy of documentation requirements and regulatory burden, while still ensuring adequate care to patients. Additionally, some commenters suggested that they believed this proposed change would allow rehabilitation physicians the flexibility to use their clinical judgment to determine the need and frequency of physician visits based on each patient's needs during the first week of admission.

Response: We appreciate the commenters' support for the proposal. We agree that finalizing this proposal will ease administrative and documentation burden for rehabilitation physicians.

Comment: One commenter supported the proposal, but stated that they did not expect the proposal to produce the cost savings in Medicare expenditures as estimated by CMS since many IRF physicians visit patients far more frequently than the minimum three times per week.

Response: We appreciate the commenter's support for the proposal. Based on this comment, we decided to take a more conservative approach when estimating the burden reduction for IRFs. Therefore, we are estimating that the rehabilitation physicians in only about half of the IRFs would adopt this new policy change. While some IRFs may choose not to reduce the number of physician visits, removing the need to specifically document a visit as meeting the requirements at § 412.622(a)(3) increases the flexibility that IRFs have to make these types of decisions in the best interest of their patients and will free up valuable physician time that can be spent on patient care.

Comment: One commenter suggested that CMS should provide greater flexibility for IRFs to complete the post-admission physician evaluation by allowing more lenient timeframes in which the evaluation could be completed or should consider removing the requirement completely. The commenter stated that the post-admission physician evaluation is redundant with other documentation requirements such as the pre-admission screening or the overall plan of care.

Response: We appreciate the commenters' suggestions, but we respectfully disagree with both suggestions, as we continue to believe that the post-admission physician evaluation, as well as the timeframe in which it is currently required to be completed, are integral parts of the patient's care. The purpose of the post-admission physician evaluation is to document in the IRF medical record the patient's status on admission, identify any relevant changes that may have occurred since the preadmission screening, and provide the rehabilitation physician with the necessary information to begin development of the patients overall plan of care. We believe that removing this requirement completely or changing the 24-hour timeframe within which the post-admission physician evaluation must be completed, could jeopardize initial contact with the patient and result in a decrease in quality of care. We believe that evaluating the patient after admission to the IRF in order to confirm that their medical and functional status has not decreased since the pre-admission screening is necessary to ensure the patient is still an appropriate candidate for IRF care.

Comment: Several commenters stated that CMS should more clearly articulate that, although we are proposing to combine the two requirements, three face-to-face rehabilitation physician visits during the first week of a patient's admission serves as a minimum, and patients are entitled to additional physician visits as medically necessary based on their rehabilitation physician's clinical judgment. Another commenter expressed concern that loosening IRF coverage requirements suggests that such high levels of care may not be required by all patients who are cared for in an IRF or that the level of resources needed to provide IRF care has decreased.

Response: To clarify, we are not limiting rehabilitation physicians from seeing patients more than three times in the first week of a patient's admission, nor are we limiting rehabilitation physicians from using their best clinical judgment regarding the frequency in which they believe patients should to be seen. Though we are finalizing our proposal to combine these two requirements, we continue to expect that each rehabilitation physician will exercise his or her best clinical judgment to determine the need and frequency of rehabilitation physician visits for a given patient.

Additionally, we respectfully disagree with the commenter that allowing the post-admission physician evaluation to count as one of the required face-to-face physician visits in any way implies a reduction in the intensity of care required by IRF patients. By allowing the two requirements to be met concurrently, we are decreasing documentation burden on rehabilitation physicians, which will free up valuable physician time that can be spent on patient care and oversight.

Comment: One commenter stated that after both of the requirements were initially implemented, it was clarified through sub-regulatory guidance that the post-admission physician evaluation and the required face-to-face rehabilitation physician visits could not be combined. The commenter suggested that while they support the proposal to allow the post-admission physician evaluation to count as one of the required face-to-face physician visits, it could also be clarified through sub-regulatory guidance and proposing it through rulemaking was not necessary.

Response: We appreciate the commenter's suggestion. However, since both the post-admission physician evaluation requirement and the required face-to-face physician visits were implemented through the rulemaking process, we believe it is appropriate to revise our IRF coverage policies through notice and comment rulemaking. We also want to avoid creating any confusion for stakeholders.

Final Decision: After careful consideration of the comments we received, we are finalizing our proposal to modify § 412.622(a)(3)(iv) to provide that the post-admission physician evaluation required under § 412.622(a)(4)(ii) may count as one of the face-to-face physician visits required under § 412.622(a)(3)(iv) beginning with FY 2019, that is, for all IRF discharges beginning on or after October 1, 2018.

B. Changes to the Interdisciplinary Team Meeting Requirement Beginning With FY 2019

Under § 412.622(a)(5), for an IRF claim to be considered reasonable and necessary under section 1862(a)(1) of the Act, the patient must require an interdisciplinary team approach to care, as evidenced by documentation in the patient's medical record of weekly interdisciplinary team meetings that meet all of the requirements specified in the regulation. Among those requirements are that the team meetings must be led by a rehabilitation physician and that the results and findings of the team meetings, and the concurrence by the rehabilitation physician with those results and findings, are retained in the patient's medical record. For more information, we refer readers to the Medicare Benefit Policy Manual, chapter 1, section 110.2.5 (Pub. 100-02), which can be downloaded from the CMS website at https://www.cms.gov/Regulations-and-Guidance/Guidance/Manuals/Internet-Only-Manuals-IOMs.html.

We understand that it may occasionally be difficult for the rehabilitation physician to be physically present in the team meetings and for that reason we have always instructed providers that the rehabilitation physician may participate in the interdisciplinary team meetings by telephone as long as it is clearly demonstrated in the documentation of the IRF medical record that the meeting was led by the rehabilitation physician. However, with the advancements in technology since the inception of the IRF coverage criteria in 2010, we believe it is appropriate to allow rehabilitation physicians to lead the meeting remotely via another mode of communication, such as video or telephone conferencing. Therefore, we proposed to amend § 412.622(a)(5)(A) to expressly provide that the rehabilitation physician may lead the interdisciplinary meeting remotely without any additional documentation requirements. We believe that other communication modes such as video and telephone conferencing are acceptable ways of leading the interdisciplinary team meeting. We believe this change will allow time management flexibility and convenience for all rehabilitation physicians, especially those located in rural areas who may need to travel greater distances between facilities. We proposed for this change to apply only to the rehabilitation physician and not the other required interdisciplinary team meeting attendees to give IRFs time to adapt to this change. However, we stated that we may consider expanding this policy to include other interdisciplinary team meeting attendees in future rulemaking. Please note that the requirement that the rehabilitation physician must lead the interdisciplinary team meeting will remain the same.

We received 37 comments on the proposal to amend § 412.622(a)(5)(A) to expressly provide that the rehabilitation physician may lead the interdisciplinary team meeting remotely without any additional documentation requirements, which are summarized below.

Comment: The majority of commenters agreed with our proposal, stating that it would decrease burdensome documentation requirements and increase time management flexibility for rehabilitation physicians.

Response: We appreciate the support that we received from commenters regarding this proposed change. We agree that this proposed policy will allow rehabilitation physicians the flexibility to use their clinical judgment regarding when it is necessary to conduct the team meeting in-person versus when it can be conducted remotely without hindering patient coordination and care. Additionally, we believe that allowing the rehabilitation physician the flexibility to conduct the interdisciplinary team meeting remotely without additional documentation requirements will free up valuable time for the rehabilitation physician to focus on patient care.

Comment: Some commenters stated that while they agree with allowing the rehabilitation physician to lead the interdisciplinary team meeting remotely without any additional documentation requirements, it should only be allowed on a limited basis as in-person meetings enhance the flow of communication and result in a more clearly articulated plan of care. The commenters expressed that they believe in-person team meetings are more effective and create a positive team involvement.

Response: We believe that each IRF should maintain the flexibility to determine how to appropriately organize their medical staff, as well as how to best implement a protocol for where the rehabilitation physician leads the interdisciplinary team meeting. We are finalizing this policy as proposed. However, we would like to clarify that this policy in no way precludes IRFs from exercising their own discretion in determining how best to organize their medical staff or implementing a protocol for determining when the rehabilitation physician should lead the interdisciplinary team meeting in person or remotely. If IRFs would like to maintain a protocol that their rehabilitation physician must continue to lead the interdisciplinary team meeting in-person, then we believe they should have the flexibility to do so. Likewise, if IRFs believe that they would like to implement a more flexible protocol for their rehabilitation physician, we believe they should have the ability to do so. Our purpose in revising this policy is to give rehabilitation physicians increased flexibility for time management, as well as to reduce documentation requirements that we believe are burdensome and provide limited benefit to patient care and coordination.

Comment: A few commenters were not supportive of this proposal, suggesting that in-person communication is the most effective way for the rehabilitation physician to lead discussions regarding patient care and coordination and that using other forms of communication such as videoconferencing or telephone conferencing could possibly hinder the flow of communication where critical discussions are needed. Commenters also suggested that team members could become more easily distracted during meetings if the rehabilitation physician was conducting the meeting remotely. In addition, commenters suggested that although meetings conducted with the assistance of technology have increased throughout the medical arena, technology is not always cooperative or reliable and could result in ineffective meetings with valuable time lost.

Response: We appreciate the commenters' feedback and understand the concerns that commenters have expressed. To clarify, we have always, and continue to believe, that the role of the rehabilitation physician during the interdisciplinary team meeting is vital to patient coordination and care. We believe that it is of utmost importance for the rehabilitation physician to lead the interdisciplinary team meeting in order to make critical decisions regarding patient care. However, we do not feel that documentation of the rehabilitation physician's physical location during the team meeting in the IRF medical record is needed to ensure that the rehabilitation physician is making the decisions. We also do not believe that removal of this documentation requirement in any way hinders patient coordination and care. For these reasons, we have decided to finalize this policy as proposed. As noted above, however, this policy in no way precludes IRFs from exercising their own discretion in determining how best to organize their medical staff or implementing a protocol for determining when the rehabilitation physician should lead the interdisciplinary team meeting in person or remotely. We support IRFs that want to continue requiring the interdisciplinary team meetings to be led by the rehabilitation physician in-person. Likewise, if IRFs would like to allow the rehabilitation physicians more flexibility to lead the team meetings remotely (for example, during extenuating situations only), we support that decision as well.

Comment: A few commenters suggested that this policy should only apply to IRFs in rural areas or underserved areas, or to small IRFs with few staff. These commenters indicated that physician access is frequently limited in rural and underserved areas and that this proposal would increase access to care for patients in these areas. The commenters suggested that for all other IRFs it should be mandatory that the rehabilitation physician leads the interdisciplinary team meeting in-person.

Response: We appreciate the commenters' suggestion, but we believe that implementing this policy change for some IRFs and not others would be unduly complicated and confusing to administer, and would likely increase administrative burden for providers rather than lessen it.

Comment: Some commenters that agreed with our proposal also suggested that we extend the policy to allow all members of the interdisciplinary team meeting to participate in the meeting remotely if necessary.

Response: We appreciate the commenters' suggestion to allow additional interdisciplinary team meeting members to participate in the meetings remotely, if necessary. After careful consideration of the comments, at this time, we are only applying this policy to rehabilitation physicians. We will monitor the implementation of this new policy and possibly consider applying this policy to other interdisciplinary team meeting members in the future, through notice and comment rulemaking, as appropriate.

Final Decision: After careful consideration of the comments we received, we are finalizing our proposal to amend § 412.622(a)(5)(A) to expressly provide that the rehabilitation physician may lead the interdisciplinary meeting remotely without any additional documentation requirements beginning with FY 2019, that is, for all IRF discharges beginning on or after October 1, 2018. We also note that this policy in no way precludes IRFs from exercising their own discretion in determining how best to organize their medical staff or implementing a protocol for determining when the rehabilitation physician should lead the interdisciplinary team meeting in person or remotely.

C. Changes to the Admission Order Documentation Requirement Beginning With FY 2019

In response to the RFI, several commenters suggest that in general, we should consider eliminating duplicative requirements. Commenters stated that duplicative requirements placed unnecessary administrative burden on facilities trying to make sure they comply with each nuance of each requirement. We agreed with the commenters, and for that reason we proposed to remove § 412.606(a) as we believe that IRFs are already required to fulfill this requirement under §§ 482.12(c), 482.24(c), and 412.3.

Under § 412.606(a), at the time that each Medicare Part A FFS patient is admitted, the IRF must have physician orders for the patient's care during the time the patient is hospitalized. For more information, we refer readers to the Medicare Benefit Policy Manual, chapter 1, section 110.1.4 (Pub. 100-02), which can be downloaded from the CMS website at https://www.cms.gov/Regulations-and-Guidance/Guidance/Manuals/Internet-Only-Manuals-IOMs.html.

Additionally, under § 412.3(a) of the hospital payment requirements, for the purposes of payment under Medicare Part A, an individual is considered an inpatient of a hospital, including a critical access hospital, if formally admitted as an inpatient under an order for inpatient admission by a physician or other qualified practitioner in accordance with §§ 412.3, 482.24(c), 482.12(c), and 485.638(a)(4)(iii) for a critical access hospital.

In an effort to reduce duplicative requirements, we believe that if we remove the admission order documentation requirement at § 412.606(a), this requirement would continue to be appropriately addressed through the enforcement of § 482.12(c) and § 482.24(c) of the hospital conditions of participation (CoPs), as well as the hospital admission order payment requirements at § 412.3. IRFs are responsible for meeting all of the inpatient hospital CoPs and the hospital admission order payment requirements at § 412.3, and, therefore, we believe that by removing the admission order documentation requirement at § 412.606(a), we would be reducing both regulatory redundancy as well as administrative burden.

Therefore, we proposed to amend § 412.606(a) to remove the admission order documentation requirement beginning with FY 2019, that is, for all IRF discharges beginning on or after October 1, 2018. IRFs would continue to meet the requirements at §§ 482.12(c), 482.24(c), and 412.3.

We received 21 comments on the proposal to amend § 412.606(a) to remove the admission order documentation requirement, which are summarized below.

Comment: All of the comments that we received regarding the proposal to amend § 412.606(a) to remove the admission order documentation requirement were supportive. The commenters agreed with our assessment that the regulations currently have duplicative admission order requirements for IRFs. Commenters agreed that, if we remove the admission order documentation requirement at § 412.606(a), the admission order requirement would continue to be addressed through the enforcement of the hospital conditions of participation.

Response: We appreciate the support from the commenters regarding the removal of the admission order documentation requirement at § 412.606(a). We believe that removal of this duplicative requirement will reduce unnecessary administrative burden on IRFs.

Comment: One commenter suggested that CMS remove the reference to § 412.3 as a requirement that IRFs will continue to be required to meet for the purposes of admission orders, as we proposed to revise that requirement in the FY 2019 IPPS/LTCH proposed rule to no longer require a written inpatient admission order to be present in the medical record as a specific condition of Medicare Part A payment.

Response: We respectfully disagree with the commenters' suggestion to remove the reference at § 412.3 as a requirement that IRFs will need to meet. While we proposed revisions to the language at § 412.3 in the FY 2019 IPPS/LTCH proposed rule (83 FR 20447 through 20448), we did not propose to remove the admission order requirement completely. Therefore, IRFs must still meet the requirements at § 412.3 as well as §§ 482.12(c) and 482.24(c). We are finalizing our proposal to remove the admission order requirement at § 412.606(a) because it is duplicative.

Final Decision: After careful consideration of the comments we received, we are finalizing our proposal to amend § 412.606(a) to remove the admission order documentation requirement beginning with FY 2019, that is, for all IRF discharges beginning on or after October 1, 2018. IRFs will continue to meet the requirements at §§ 482.12(c), 482.24(c), and 412.3.

D. Summary of Comments Regarding Additional Changes to the Physician Supervision Requirement

As discussed in section VIII.A of the proposed rule, under § 412.622(a)(3)(iv), for an IRF claim to be considered reasonable and necessary under section 1862(a)(1) of the Act, there must be a reasonable expectation at the time of the patient's admission to the IRF that the patient requires physician supervision by a rehabilitation physician, defined as a licensed physician with specialized training and experience in inpatient rehabilitation. The requirement for medical supervision means that the rehabilitation physician must conduct face-to-face visits with the patient at least 3 days per week throughout the patient's stay in the IRF to assess the patient both medically and functionally, as well as to modify the course of treatment as needed to maximize the patient's capacity to benefit from the rehabilitation process. For more information, we refer readers to the Medicare Benefit Policy Manual, chapter 1, section 110.2.4 (Pub. 100-02), which can be downloaded from the CMS website at https://www.cms.gov/Regulations-and-Guidance/Guidance/Manuals/Internet-Only-Manuals-IOMs.html.

When the IRF coverage criteria were initially implemented in 2010, we believed that the rehabilitation physician visits should be completed face-to-face to ensure that the patient receives the most comprehensive in-person care by a rehabilitation physician throughout the IRF stay.

As part of our efforts to assist in reducing unnecessary regulatory burden on IRFs, this is an issue we would like to further explore. We solicited public comments in the FY 2019 IRF PPS proposed rule (83 FR 20997 through 20998) on whether the rehabilitation physician should have the flexibility to determine that some of the IRF visits can be appropriately conducted remotely via another mode of communication, such as video or telephone conferencing. Given the level of complexity of IRF patients, we had some concerns about whether this approach would have an impact on the quality of care provided to IRF patients. To maintain the hospital level of care that IRF patients require, we would continue to expect that the majority of IRF physician visits would continue to be performed face-to-face. However, we were interested in feedback from stakeholders on whether we should allow a limited number of visits to be conducted remotely. In order to better assist us in balancing the needs of the patient, as well as retaining the hospital level quality of care provided in an IRF with the goal of reducing the regulatory burden on rehabilitation physicians, we sought feedback from stakeholders about potentially amending the face-to-face visit requirement for rehabilitation physicians. Specifically, we sought feedback regarding the following:

• Do stakeholders believe that the rehabilitation physician would be able to fully assess both the medical and functional needs and progress of the patient remotely?
• Would this assist facilities in rural areas where it may be difficult to employ an abundance of physicians?
• Do stakeholders believe that assessing the patient remotely would affect the quality or intensity of the physician visit in any way?
• How many and what types of visits do stakeholders believe should be able to be performed remotely?
• From an operational standpoint, how would the remote visit work?
• What type of clinician would need to be present in the room with the patient while the rehabilitation physician was in a remote location?

Thus, to assist us in generating ideas and information for analyzing potential refinements in this area, we specifically solicited public comments from stakeholders on whether the rehabilitation physician should have the flexibility to determine that some of the IRF visits can be appropriately conducted remotely via another mode of communication, such as video or telephone conferencing, while maintaining a hospital level high quality of care for IRF patients.

We received 22 comments in response to our solicitation. We appreciate the commenters' responses to this solicitation and will take them into consideration for possible future policy development.

E. Summary of Comments Regarding Changes to the Use of Non-Physician Practitioners in Meeting the Requirements Under § 412.622(a)(3), (4), and (5)

Several of the requirements under § 412.622(a)(3), (4), and (5) require documentation that a rehabilitation physician, defined as a licensed physician with specialized training and experience in inpatient rehabilitation, visited each patient admitted to an IRF and performed an assessment of the patient. For example, under § 412.622(a)(3)(iv), for an IRF claim to be considered reasonable and necessary under section 1862(a)(1) of the Act, there must be a reasonable expectation at the time of the patient's admission to the IRF that the patient requires physician supervision by a rehabilitation physician. The requirement for medical supervision means that the rehabilitation physician must conduct face-to-face visits with the patient at least 3 days per week throughout the patient's stay in the IRF to assess the patient both medically and functionally, as well as to modify the course of treatment as needed to maximize the patient's capacity to benefit from the rehabilitation process. For more information, please refer to the Medicare Benefit Policy Manual, chapter 1, section 110.2.4 (Pub. 100-02), which can be downloaded from the CMS website at https://www.cms.gov/Regulations-and-Guidance/Guidance/Manuals/Internet-Only-Manuals-IOMs.html.

In addition, under § 412.622(a)(4)(ii), to document that each patient for whom the IRF seeks payment is reasonably expected to meet all of the requirements in § 412.622(a)(3) at the time of admission, the patient's medical record at the IRF must contain a post-admission physician evaluation that must, among other requirements, be completed by a rehabilitation physician within 24 hours of the patient's admission to the IRF. For more information, we refer readers to the Medicare Benefit Policy Manual, chapter 1, section 110.1.2 (Pub. 100-02), which can be downloaded from the CMS website at https://www.cms.gov/Regulations-and-Guidance/Guidance/Manuals/Internet-Only-Manuals-IOMs.html.

In the feedback that we received in response to the RFI, it was suggested that we consider amending the requirements in § 412.622(a)(3)(iv) and § 412.622(a)(4)(ii) to enable IRFs to expand their use of non-physician practitioners (physician assistants and nurse practitioners) to fulfill some of the requirements that rehabilitation physicians are currently required to complete. The commenters suggested that expanding the use of non-physician practitioners in meeting some of the IRF requirements would ease the documentation burden on rehabilitation physicians.

In exploring this issue, we had questions about whether non-physician practitioners have the specialized training in inpatient rehabilitation that would enable them to adequately assess the interaction between patients' medical and functional care needs in an IRF. Another concern that had been raised regarding this issue, was whether IRF patients will continue to receive the hospital level and quality of care that is necessary to treat such complex conditions.

To better assist us in balancing the needs of the patient with the desire to reduce the regulatory burden on rehabilitation physicians, in the FY 2019 IRF PPS proposed rule (83 FR 20998 through 20999), we specifically solicited public comments from stakeholders about potentially allowing IRFs to expand their use of non-physician practitioners to fulfill some of the requirements that rehabilitation physicians are currently required to complete. Specifically, we sought feedback regarding the following:

• Do non-physician practitioners have the specialized training in rehabilitation that they need to have to assess IRF patients both medically and functionally?
• How would the non-physician practitioner's credentials be documented and monitored to ensure that IRF patients are receiving high quality care?
• Are non-physician practitioners required to do rotations in inpatient rehabilitation facilities as part of their training, or could this be added to their training programs in the future?
• Do stakeholders believe that utilizing non-physician practitioners to fulfill some of the requirements that are currently required to be completed by a rehabilitation physician would have an impact of the quality of care for IRF patients?

Thus, to assist us in generating ideas and information for analyzing potential refinements in this area, we specifically solicited public comments from stakeholders on the ways in which the role of non-physician practitioners could be expanded in the IRF setting while maintaining a hospital level high quality of care for IRF patients.

We received 39 comments in response to our solicitation. We appreciate the commenters' responses to this solicitation and will take them into consideration for future possible policy development.

X. Updates to the IRF Quality Reporting Program (QRP)

A. Background

The Inpatient Rehabilitation Facility Quality Reporting Program (IRF QRP) is authorized by section 1886(j)(7) of the Act, and it applies to freestanding IRFs, as well as inpatient rehabilitation units of hospitals or critical access hospitals (CAHs) paid by Medicare under the IRF PPS. Under the IRF QRP, the Secretary reduces the annual increase factor for discharges occurring during such fiscal year by 2 percentage points for any IRF that does not submit data in accordance with the requirements established by the Secretary. For more information on the background and statutory authority for the IRF QRP, we refer readers to the FY 2012 IRF PPS final rule (76 FR 47873 through 47874), the CY 2013 Hospital Outpatient Prospective Payment System/Ambulatory Surgical Center (OPPS/ASC) Payment Systems and Quality Reporting Programs final rule (77 FR 68500 through 68503), the FY 2014 IRF PPS final rule (78 FR 47902), the FY 2015 IRF PPS final rule (79 FR 45908), the FY 2016 IRF PPS final rule (80 FR 47080 through 47083), the FY 2017 IRF PPS final rule (81 FR 52080 through 52081), and the FY 2018 IRF PPS final rule (82 FR 36269 through 36270).

Although we have historically used the preamble to the IRF PPS proposed and final rules each year to remind stakeholders of all previously finalized program requirements, we have concluded that repeating the same discussion each year is not necessary for every requirement, especially if we have codified it in our regulations. Accordingly, the following discussion is limited as much as possible to a discussion of our proposals, responses to comments on those proposals, and policies we are finalizing for future years of the IRF QRP after consideration of the comments, and represents the approach we intend to use in our rulemakings for this program going forward.

B. General Considerations Used for the Selection of Measures for the IRF QRP

1. Background

For a detailed discussion of the considerations we historically used for the selection of IRF QRP quality, resource use, and other measures, we refer readers to the FY 2016 IRF PPS final rule (80 FR 47083 through 47084).

Comment: Several commenters offered support, suggestions for improvement, and concerns about the implementation of the IMPACT Act. Some commenters requested greater stakeholder engagement, including IRF involvement in the testing of Standardized Patient Assessment Data Elements (SPADE), and that CMS provide publicly available cross-setting data on SPADEs. One commenter recommended that quality measurement (QM) and SPADE development be suspended until QMs are standardized and interoperable for all post-acute care (PAC) sites, measures are NQF endorsed for their setting, SPADE provides evidence that it predicts costs and/or improves quality, and additional training materials and specifications are provided.

Response: We appreciate the comments, and we will take them into account as we engage in future quality measure and SPADE development for the IRF QRP. For a discussion of the IMPACT Act, the selection of IRF QRP measures, and SPADEs, we refer readers to the FY 2016 IRF PPS final rule (80 FR 47083 through 47084) and the FY 2018 IRF PPS final rule (82 FR 36270 through 36276) respectively.

2. Accounting for Social Risk Factors in the IRF QRP

In the FY 2018 IRF PPS final rule (82 FR 36273 through 36274), we discussed the importance of improving beneficiary outcomes including reducing health disparities. We also discussed our commitment to ensuring that medically complex patients, as well as those with social risk factors, receive excellent care. We discussed how studies show that social risk factors, such as being near or below the poverty level as determined by HHS, belonging to a racial or ethnic minority group, or living with a disability, can be associated with poor health outcomes and how some of this disparity is related to the quality of health care. Among our core objectives, we aim to improve health outcomes, attain health equity for all beneficiaries, and ensure that complex patients as well as those with social risk factors receive excellent care. Within this context, reports by the Office of the Assistant Secretary for Planning and Evaluation (ASPE) and the National Academy of Medicine have examined the influence of social risk factors in our value-based purchasing programs. As we noted in the FY 2018 IRF PPS final rule (82 FR 36273 through 36274), ASPE's report to Congress, which was required by the IMPACT Act, found that, in the context of value-based purchasing programs, dual eligibility was the most powerful predictor of poor health care outcomes among those social risk factors that they examined and tested. ASPE is continuing to examine this issue in its second report required by the IMPACT Act, which is due to Congress in the fall of 2019. In addition, as we noted in the FY 2018 IPPS/LTCH PPS final rule (82 FR 38428), the National Quality Forum (NQF) undertook a 2-year trial period in which certain new measures and measures undergoing maintenance review have been assessed to determine if risk adjustment for social risk factors is appropriate for these measures. The trial period ended in April 2017 and a final report is available at http://www.qualityforum.org/SES_Trial_Period.aspx. The trial concluded that “measures with a conceptual basis for adjustment generally did not demonstrate an empirical relationship” between social risk factors and the outcomes measured. This discrepancy may be explained in part by the methods used for adjustment and the limited availability of robust data on social risk factors. NQF has extended the socioeconomic status (SES) trial, allowing further examination of social risk factors in outcome measures.

In the FY/CY 2018 proposed rules for our quality reporting and value-based purchasing programs, we solicited feedback on which social risk factors provide the most valuable information to stakeholders and the methodology for illuminating differences in outcomes rates among patient groups within a provider that would also allow for a comparison of those differences, or disparities, across providers. Feedback we received across our quality reporting programs included encouraging CMS to explore whether factors that could be used to stratify or risk adjust the measures (beyond dual eligibility); to consider the full range of differences in patient backgrounds that might affect outcomes; to explore risk adjustment approaches; and to offer careful consideration of what type of information display would be most useful to the public.

We also sought public comment on confidential reporting and future public reporting of some of our measures stratified by patient dual eligibility. In general, commenters noted that stratified measures could serve as tools for hospitals to identify gaps in outcomes for different groups of patients, improve the quality of health care for all patients, and empower consumers to make informed decisions about health care. Commenters encouraged CMS to stratify measures by other social risk factors such as age, income, and educational attainment. With regard to value-based purchasing programs, commenters also cautioned to balance fair and equitable payment while avoiding payment penalties that mask health disparities or discouraging the provision of care to more medically complex patients. Commenters also noted that value-based payment program measure selection, domain weighting, performance scoring, and payment methodology must account for social risk.

As a next step, we are considering options to improve health disparities among patient groups within and across hospitals by increasing the transparency of disparities, as shown by quality measures. We also are considering how this work applies to other CMS quality programs in the future. We refer readers to the FY 2018 IPPS/LTCH PPS final rule (82 FR 38403 through 38409) for more details where we discuss the potential stratification of certain Hospital Inpatient Quality Reporting Program outcome measures. Furthermore, we continue to consider options to address equity and disparities in our value-based purchasing programs.

We plan to continue working with ASPE, the public, and other key stakeholders on this important issue to identify policy solutions that achieve the goals of attaining health equity for all beneficiaries and minimizing unintended consequences.

Comment: Many commenters supported the future implementation of a strategy to account for social risk factors in the IRF QRP that includes risk stratification by race, ethnicity, geographic area, sex, and disability. The commenters also suggested that CMS consider the role of primary language and family, caregiver and community support in developing this strategy.

Response: We thank the commenters for their comments and will take these comments into account as we further consider how to appropriately account for social risk factors in the IRF QRP. We also refer the reader to the FY 2018 IRF PPS final rule (82 FR 36273 through 36274), where we discussed in depth many of the issues raised by these commenters.

C. New Removal Factor for Previously Adopted IRF QRP Measures

As part of our Meaningful Measures Initiative, discussed in section D.1. of the Executive Summary of this final rule, we strive to put patients first, ensuring that they, along with their clinicians, are empowered to make decisions about their own healthcare using data-driven information that is increasingly aligned with a parsimonious set of meaningful quality measures. We began reviewing the IRF QRP's measures in accordance with the Meaningful Measures Initiative, and we are working to identify how to move the IRF QRP forward in the least burdensome manner possible, while continuing to incentivize improvement in the quality of care provided to patients.

Specifically, we believe the goals of the IRF QRP and the measures used in the program cover most of the Meaningful Measures Initiative priorities, including making care safer, strengthening person and family engagement, promoting coordination of care, promoting effective prevention and treatment, and making care affordable.

We also evaluated the appropriateness and completeness of the IRF QRP's current measure removal factors. We have previously finalized that we would use notice and comment rulemaking to remove measures from the IRF QRP based on the following factors:

• Factor 1. Measure performance among IRFs is so high and unvarying that meaningful distinctions in improvements in performance can no longer be made.
• Factor 2. Performance or improvement on a measure does not result in better patient outcomes.
• Factor 3. A measure does not align with current clinical guidelines or practice.
• Factor 4. A more broadly applicable measure (across settings, populations, or conditions) for the particular topic is available.
• Factor 5. A measure that is more proximal in time to desired patient outcomes for the particular topic is available.
• Factor 6. A measure that is more strongly associated with desired patient outcomes for the particular topic is available.
• Factor 7. Collection or public reporting of a measure leads to negative unintended consequences other than patient harm.

We continue to believe these measure removal factors are appropriate for use in the IRF QRP. However, even if one or more of the measure removal factors applies, we might nonetheless choose to retain the measure for certain specified reasons. Examples of such instances could include when a particular measure addresses a gap in quality that is so significant that removing the measure could in turn result in poor quality, or in the event that a given measure is statutorily required. We note further that, consistent with other quality reporting programs, we apply these factors on a case-by-case basis.

In the FY 2019 IRF PPS proposed rule, we proposed to adopt an additional factor to consider when evaluating measures for removal from the IRF QRP measure set:

Factor 8. The costs associated with a measure outweigh the benefit of its continued use in the program.

As we discussed in section D.1. of the Executive Summary of this final rule, in furtherance of our new Meaningful Measures Initiative, we are engaging in efforts to ensure that the IRF QRP measure set continues to promote improved health outcomes for beneficiaries while minimizing the overall costs associated with the program. We believe these costs are multifaceted and include not only the burden associated with reporting, but also the costs associated with implementing and maintaining the program. We have identified several different types of costs, including, but not limited to: (1) Provider and clinician information collection burden and burden associated with the submitting/reporting of quality measures to CMS; (2) the provider and clinician cost associated with complying with other programmatic requirements; (3) the provider and clinician cost associated with participating in multiple quality programs, and tracking multiple similar or duplicative measures within or across those programs; (4) the cost to CMS associated with the program oversight of the measure including measure maintenance and public display; and (5) the provider and clinician cost associated with compliance to other federal and/or state regulations (if applicable).

For example, it may be needlessly costly and/or of limited benefit to retain or maintain a measure which our analyses show no longer meaningfully supports program objectives (for example, informing beneficiary choice). It may also be costly for health care providers to track confidential feedback, preview reports, and publicly reported information on a measure where we use the measure in more than one program. We may also have to expend unnecessary resources to maintain the specifications for the measure, including the tools needed to collect, validate, analyze, and publicly report the measure data. Furthermore, beneficiaries may find it confusing to see public reporting on the same measure in different programs.

When these costs outweigh the evidence supporting the continued use of a measure in the IRF QRP, we believe it may be appropriate to remove the measure from the program. Although we recognize that one of the main goals of the IRF QRP is to improve beneficiary outcomes by incentivizing health care providers to focus on specific care issues and making public data related to those issues, we also recognize that those goals can have limited utility where, for example, the publicly reported data is of limited use because it cannot be easily interpreted by beneficiaries and used to influence their choice of providers. In these cases, removing the measure from the IRF QRP may better accommodate the costs of program administration and compliance without sacrificing improved health outcomes and beneficiary choice.

We proposed that we would remove measures based on this factor on a case-by-case basis. We might, for example, decide to retain a measure that is burdensome for health care providers to report if we conclude that the benefit to beneficiaries is so high that it justifies the reporting burden. Our goal is to move the program forward in the least burdensome manner possible, while maintaining a parsimonious set of meaningful quality measures and continuing to incentivize improvement in the quality of care provided to patients.

We invited public comment on our proposal to adopt an additional measure removal Factor 8. The costs associated with a measure outweigh the benefit of its continued use in the program.

Comment: Several commenters supported the proposal to add measure removal Factor 8. The costs associated with a measure outweigh the benefit of its continued use in the program. Commenters appreciated the consideration of costs beyond those associated with data collection and submission.

Response: We appreciate the support of the addition of this measure removal factor for the IRF QRP.

Comment: A few commenters had concerns about the new measure removal Factor 8. Some commenters suggested that CMS should involve stakeholders when determining if Factor 8 applies to a measure, to get input about whether clinicians or patients believe a measure is important. One commenter requested clarification about the methods or criteria used to assess when the measure cost or burden outweighs the benefits of retaining it.

Response: We appreciate commenters' concerns about the new measure removal factor. We value transparency in our processes, and continually seek stakeholder input through education and outreach sessions, other webinars, rulemaking, and other collaborative engagements with stakeholders. We agree with commenters that benefits can be difficult to define and that various stakeholders may have different perspectives on these benefits. Because of these challenges, we intend to evaluate each measure on a case-by-case basis, while considering input from a variety of stakeholders, including, but not limited to: Patients, caregivers, patient and family advocates, providers, provider associations, healthcare researchers, data vendors, and other stakeholders with insight into the benefits and costs (financial and otherwise) of maintaining the specific measure in the IRF QRP.

With regard to the request for clarification about criteria used to assess costs and burden, in the FY 2019 IRF PPS proposed rule (83 FR 21000 through 21001), we provided examples of five different costs that could be considered in this proposed measure removal factor. We intend to assess the costs and benefits to all program stakeholders, including but not limited to, those listed above. We intend to balance the costs with the benefits to a variety of stakeholders. These stakeholders include, but are not limited to, patients and their families or caregivers, providers, the healthcare research community, healthcare payers, and patient and family advocates. Because for each measure the relative benefit to each stakeholder may vary, we believe that the benefits to be evaluated for each measure are specific to the measure and the original rationale for including the measure in the program.

Final Decision: After consideration of the public comments, we are finalizing our proposal to add the IRF QRP measure removal Factor 8. The costs associated with a measure outweigh the benefit of its continued use in the program.

We proposed to revise § 412.634(b)(2) of our regulations to codify both the removal factors we have previously finalized for the IRF QRP, as well as the new measure removal factor that we are finalizing in this final rule. We also proposed to remove the reference to the payment impact from the heading of § 412.634(b) and, as discussed more fully in section X.J. of this final rule, remove the language in current § 412.634(b)(2) related to the 2 percentage point payment reduction because that payment reduction is also addressed at § 412.624(c)(4).

We did not receive any public comments on our proposals to update to the IRF QRP regulatory text.

Final Decision: We are finalizing the codification of the IRF QRP measure removal factors at § 412.634(b)(2) and the updates to the regulatory text at § 412.634(b). We are also making minor grammatical edits to the IRF QRP measure removal factor language to align with the language of other programs.

D. Quality Measures Currently Adopted for the FY 2020 IRF QRP

The IRF QRP currently has 18 measures for the FY 2020 program year, which are outlined in Table 11.

While we did not solicit comments on currently adopted or future IRF QRP measures, we received several comments.

Comment: Several commenters suggested additional measures that could be removed from the IRF QRP, including the NHSN Catheter Associated Urinary Tract Infection (CAUTI) Outcome Measure (NQF #0138); the NHSN Facility-wide Inpatient Hospital-onset Clostridium difficile Infection (CDI) Outcome Measure (NQF #1717); Influenza Vaccination among Healthcare Personnel (NQF #0431); Application of Percent of Residents Experiencing one or more falls with major injury; and Application of percent of LTCH patients with an admission and discharge functional assessment and a care plan that addresses function.

Response: We thank the commenters for their comments. We did not propose any changes to our previously finalized measures, nor did we propose additional measure removals from the IRF QRP. We will take these comments into account as we engage in future measure selection activities for the IRF QRP.

Comment: A few commenters suggested future measures for the IRF QRP, including a measure on Pneumococcal Vaccination Coverage, an adult immunization composite measure, and a standardized patient care survey.

Response: While we did not solicit public comment about future measures, we will take these comments into account as we engage in future measure development and selection activities for the IRF QRP.

E. Removal of Two IRF QRP Measures

We proposed to remove two measures from the IRF QRP measure set. Beginning with the FY 2020 IRF QRP, we proposed to remove the National Healthcare Safety Network (NHSN) Facility-wide Inpatient Hospital-onset Methicillin-resistant Staphylococcus aureus (MRSA) Bacteremia Outcome Measure (NQF #1716). We also proposed to remove one measure beginning with the FY 2021 IRF QRP: Percent of Residents or Patients Who Were Assessed and Appropriately Given the Seasonal Influenza Vaccine (Short Stay) (NQF #0680). We discuss these proposals below.

1. Removal of National Healthcare Safety Network (NHSN) Facility-Wide Inpatient Hospital-Onset Methicillin-Resistant Staphylococcus aureus (MRSA) Bacteremia Outcome Measure (NQF #1716) Beginning With the FY 2020 IRF QRP

We proposed to remove the measure, Facility-wide Inpatient Hospital-onset Methicillin-resistant Staphylococcus aureus (MRSA) Bacteremia Outcome Measure (NQF #1716), from the IRF QRP measure set beginning with the FY 2020 IRF QRP under measure removal Factor 8. The costs associated with a measure outweigh the benefit of its continued use in the IRF QRP.

We originally adopted this measure in the FY 2015 IRF PPS final rule (79 FR 45911 through 45913). The measure assesses MRSA infections caused by a strain of MRSA bacteria that has become resistant to antibiotics commonly used to treat MRSA infections. The measure is reported as a Standardized Infection Ratio (SIR) of hospital-onset unique blood source MRSA laboratory-identified events among all inpatients in the facility.

The data on this measure is submitted by IRFs via the National Health Safety Network (NHSN), and we adopted it for use in several quality reporting programs because we believe that MRSA is a serious healthcare associated infection. To calculate a measure rate for an individual IRF, we must be able to attribute to the IRF at least one expected MRSA infection during the reporting period. However, we have found that the number of IRFs with expected MRSA infections during a given reporting period is extraordinarily low. For 99.9 percent of IRFs, the expected MRSA infection incident rate is less than one, which is too low to use for purposes of generating a reliable standardized infection ratio. As a result, we are unable to calculate reliable measure rates and publicly report those rates for almost all IRFs because their expected infection rates during a given reporting period are less than one. Therefore, while we still recognize that MRSA is a serious healthcare associated infection, the benefit of this NHSN Facility-wide Inpatient Hospital-onset MRSA Bacteremia Outcome Measure (NQF #1716) is small. For this reason, we believe that the burden required for data collection and submission on this measure and the costs associated with this measure, which include the costs to maintain and publicly report it for the IRF QRP and the costs for a small number of IRFs to track their rates when reliable rates cannot be calculated for most IRFs, outweigh the benefit of its continued use in the program.

Therefore, we proposed to remove this measure from the IRF QRP, beginning with the FY 2020 IRF QRP.

We proposed that IRFs would no longer be required to submit data on this measure for the purposes of the IRF QRP beginning with October 1, 2018 admissions and discharges.

We invited public comment on this proposal.

Comment: Several commenters supported the proposal to remove this measure from the IRF QRP.

Response: We thank the commenters for their support.

Final Decision: After considering public comment, we are finalizing our proposal to remove the NHSN Facility-wide Inpatient Hospital-onset MRSA Bacteremia Outcome Measure (NQF #1716) from the IRF QRP beginning with the FY 2020 IRF QRP. IRFs will no longer be required to submit data on this measure for the purposes of the IRF QRP beginning with October 1, 2018 admissions and discharges.

2. Removal of Percent of Residents or Patients Who Were Assessed and Appropriately Given the Seasonal Influenza Vaccine (Short Stay) (NQF #0680) Beginning With the FY 2021 IRF QRP

We proposed to remove the measure, Percent of Residents or Patients Who Were Assessed and Appropriately Given the Seasonal Influenza Vaccine (Short Stay) (NQF #0680), from the IRF QRP beginning with the FY 2021 IRF QRP under measure removal Factor 1. Measure performance among IRFs is so high and unvarying that meaningful distinctions in improvements in performance can no longer be made.

In the FY 2014 IRF PPS final rule (78 FR 47910 through 47911), we adopted the Percent of Residents or Patients Who Were Assessed and Appropriately Given the Seasonal Influenza Vaccine (Short Stay) measure (NQF #0680) to assess vaccination rates among IRF patients because many patients receiving care in the IRF setting are 65 years and older and considered to be the target population for the influenza vaccination.

This process measure reports the percentage of stays in which the patient was assessed and appropriately given the influenza vaccine for the most recent influenza vaccination season. In our evaluation of this measure, we identified that IRF performance has been high and relatively stable, demonstrating nominal improvements across influenza seasons since data collection began. Our analysis of this particular measure revealed that for the 2015-2016 and the 2016-2017 influenza seasons, nearly every IRF patient was assessed and more than 75 percent of IRFs (n = 836) are vaccinating IRF patients who have not already received a flu vaccination at 90 percent or higher. Further, throughout the last two influenza seasons, the number of IRFs who achieved a perfect score (100 percent) on this measure has grown substantially, increasing by approximately 50 percent from 146 IRFs (12.9 percent) in the 2015-2016 influenza season to 210 IRFs (18.8 percent) in the 2016-2017 influenza season.

The Percent of Residents or Patients Who Were Assessed and Appropriately Given the Seasonal Influenza Vaccine (Short Stay) (NQF #0680) measure rates are also unvarying. With respect to the 2015-2016 influenza season, the mean performance score was 91.04 percent, and with respect to the 2016-2017 influenza season, the mean performance score on this measure was 93.88 percent. The proximity of these mean rates to the maximum score of 100 percent suggests a potential ceiling effect and a lack of variation that restricts distinction between facilities. Given that performance among IRFs has remained so high and that no meaningful distinction in performance can be made across the majority of IRFs, we proposed the removal of this measure.

Therefore, we proposed to remove this measure from the IRF QRP beginning with the FY 2021 IRF QRP under measure removal Factor 1. Measure performance among IRFs is so high and unvarying that meaningful distinctions in improvements in performance can no longer be made.

We proposed that IRFs would no longer be required to submit data on this measure for the purposes of the IRF QRP beginning with patients discharged on or after October 1, 2018. We also stated that we plan to remove these data elements from the IRF-PAI version 3.0, effective October 1, 2019, and that beginning with October 1, 2018 discharges, IRFs should enter a dash (-) for O0250A, O0250B, and O0250C until the IRF-PAI version 3.0 is released.

Comment: Several commenters, including MedPAC, supported the proposal to remove the Percent of Residents or Patients Who Were Assessed and Appropriately Given the Seasonal Influenza Vaccine (Short Stay) (NQF #0680) (Patient Influenza Vaccine) measure from the IRF QRP. Several commenters stated that the removal of this measure will allow providers to devote more time to patient care by reducing the burden of collecting and reporting data. A few commenters, including MedPAC, suggested focusing on more meaningful measures, as this measure is no longer effective in improving the quality of care or patient outcomes. A few commenters requested that CMS provide guidance to clarify the appropriateness of dash use for the IRF-PAI influenza vaccine items beginning FY 2019.

Response: We appreciate the support from MedPAC and other commenters for the proposed removal of the Patient Influenza Vaccine measure from the IRF QRP. Due to IRFs effectively assessing and vaccinating patients across the 2015-2016 and 2016-2017 influenza seasons, performance on this measure has remained so high that we are no longer able to make meaningful distinctions in improvements in performance. Removing the Patient Influenza Vaccine measure due to its high and unvarying performance will allow providers to address highest priority issues for improving overall health and focus more on meaningful measures that are most vital to patient outcomes in the IRF setting. We will provide ongoing guidance to IRFs to clarify that use of a dash for IRF-PAI items O0250A, O0250B, and O0250C beginning FY 2019 is appropriate and will not cause a non-compliance determination.

Comment: Some commenters did not support the removal of the Patient Influenza Vaccine measure from the IRF QRP, citing concerns with patient care consequences that could occur as a result of its removal. One commenter stated that the Patient Influenza Vaccine measure is an important safety measure that may be overlooked if providers are no longer required to report data. Another commenter indicated that removing the measure will send the impression that preventative health services, such as immunizations, are not a priority in the inpatient setting, could leave a vulnerable population of Medicare-beneficiaries more susceptible to vaccine-preventable illness, and may generate reporting confusion among providers.

Response: While we understand that assessing and appropriately vaccinating patients are important components of the care process, many patients admitted to IRFs come from an acute care setting where influenza vaccinations are tracked and, due to that tracking, have already been immunized before they are admitted to the IRF. For that reason, the process of assessing IRF patients for influenza vaccination is duplicative of a process that most of these patients have already undergone. In addition, our analysis has shown that IRFs regularly assess and vaccinate their patients when appropriate to do so. As a result, we do not believe that the removal of the measure from the IRF QRP will lead to lower immunization rates in the IRF patient population.

Final decision: After careful consideration of the public comments, we are finalizing our proposal to remove the Percent of Residents or Patients Who Were Assessed and Appropriately Given the Seasonal Influenza Vaccine (Short Stay) (NQF #0680) measure from the IRF QRP beginning with the FY 2021 IRF QRP. IRFs will no longer be required to submit data on this measure for the purposes of the IRF QRP beginning with patients discharged on or after October 1, 2018. We plan to remove these data elements from the IRF-PAI version 3.0, effective October 1, 2019. Beginning with October 1, 2018 discharges, IRFs should enter a dash (-) for O0250A, O0250B, and O0250C until the IRF-PAI version 3.0 is released.

F. IMPACT Act Implementation Update

In the FY 2018 IRF PPS final rule (82 FR 36285 through 36286), we stated that we intended to specify two measures that would satisfy the domain of accurately communicating the existence and provision of the transfer of health information and care preferences under section 1899B(c)(1)(E) of the Act no later than October 1, 2018, and intended to propose to adopt them for the FY 2021 IRF QRP with data collection beginning on or about October 1, 2019.

In the FY 2019 IRF PPS proposed rule (83 FR 21002 through 21003), we stated that, as a result of the input provided during a public comment period between November 10, 2016 and December 11, 2016, input provided by a technical expert panel (TEP), and pilot measure testing conducted in 2017, we are engaging in continued development work on these two measures, including supplementary measure testing and providing the public with an opportunity for comment in 2018. We stated that we would reconvene a TEP for these measures in mid-2018, which occurred in April 2018. We stated that we now intend to specify the measures under section 1899B(c)(1)(E) of the Act no later than October 1, 2019, and intend to propose to adopt the measures for the FY 2022 IRF QRP, with data collection beginning with patients discharged on or after October 1, 2020. For more information on the pilot testing, we refer readers to https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/Post-Acute-Care-Quality-Initiatives/IMPACT-Act-of-2014/IMPACT-Act-Downloads-and-Videos.html.

Comment: A few commenters supported the updated implementation timeline for the transfer of health information and care preference domain measures, allowing additional time for measure development. A commenter further stated that, given the complexity of the draft measures under development for this domain, it is important that CMS prioritize sound measure development to ensure that the measures are implementable, minimally burdensome to providers, and add value beyond current care practices.

Response: We appreciate the commenters' support.

Comment: A few commenters noted the extension of the IMPACT Act measure deadline for the transfer of health information and care preferences domain measures and requested further explanation and clarification for extending quality measure implementation beyond statutory deadlines. Another commenter questions why the agency is delaying these measures, but did not delay the implementation of other measures, such as the Section GG functional assessment items and measures despite multiple requests from stakeholders to delay implementation to facilitate more deliberation, input, and research.

Response: In the FY 2016 proposed and final rules, we described the statutory timeline for measure specification under the IMPACT Act and how that timeline was not feasible in light of operational and other practical constraints. We outlined our historical timeline for developing and adopting quality measures, which pre-dates the IMPACT Act, and how that timeline takes into consideration the time needed to specify and adopt valid and reliable measures, as well as give IRFs enough notice of their new data reporting obligations. We intended to specify the measures required by the IMPACT Act in accordance with our historical timeline in order to ensure that the measures we adopt are developed in a transparent manner that involves stakeholder input, MAP review, and NQF endorsement.

We have largely been able to comply with the implementation timeline we set forth in the FY 2016 proposed and final rules. The measures we have adopted in accordance with that timeline were developed in a transparent manner and incorporate both expert and stakeholder input. They were also reviewed by the MAP and, in many cases, are NQF-endorsed for at least one of the four PAC settings. We also considered the input of stakeholders who requested that we conduct further testing and research before we adopted various measures and determined, based on our own assessment of the evidence, as well as input of experts and other stakeholders, that the measures were valid and reliable enough to be adopted.

The two measures that would satisfy the domain of accurately communicating the existence and provision of the transfer of health information and care preferences that are currently under development do not enjoy a level of support that is akin to the support that we received for other IMPACT Act measures. Results from the pilot test of the original measure concept recommended CMS to continue to further modify the measures to increase the usefulness and feasibility of the constructs for PAC settings. The core concern of the MAP was the measure testing, including incomplete development, and other topics such as what information would be needed at the time of transfer and measure attribution issues. Based on input from the MAP and more recently from stakeholders and our own research, we have determined that the measures are not sufficiently developed at this time to support their use in the four PAC settings, and we have concluded that it is better to delay their implementation while we engage in further development and testing than it would be to adopt the measures prematurely.

G. Form, Manner, and Timing of Data Submission Under the IRF QRP

Under our current policy, IRFs report data on IRF QRP assessment-based measures and standardized patient assessment data by completing applicable sections of the IRF-PAI and submitting the IRF-PAI to CMS through the Quality Improvement Evaluation System (QIES) Assessment Submission and Processing (ASAP) system. For more information on IRF QRP reporting through the Quality Improvement and Evaluation System Assessment Submission and Processing (QIES ASAP) system, refer to the “Related Links” section at the bottom of https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/InpatientRehabFacPPS/Software.html. Data on IRF QRP measures that are also collected by the Centers for Disease Control and Prevention (CDC) for other purposes are reported by IRFs to the CDC through the NHSN, and the CDC then transmits the relevant data to CMS. Information regarding the CDC's NHSN is available at https://www.cdc.gov/nhsn/index.html. We refer readers to the FY 2018 IRF PPS final rule (82 FR 36291 through 36292) for the data collection and submission timeframes that we finalized for the IRF QRP.

We previously codified at § 412.634(b)(1) of our regulations the requirement that IRFs submit data on measures specified under sections 1886(j)(7)(D), 1899B(c)(1), and 1899B(d)(1) of the Act in the form and manner, and at a time, specified by CMS. In the FY 2019 IRF PPS proposed rule (83 FR 21003), we proposed to revise § 412.634(b)(1) to include the policy we previously finalized in the FY 2018 IRF PPS final rule (82 FR 36292 through 36293) that IRFs must also submit standardized patient assessment data required under section 1899B(b)(1) of the Act in the form and manner, and at a time, specified by CMS.

We invited public comment on this proposal.

Comment: One commenter supported the codification of the policy that IRFs must also submit standardized patient assessment data required under section 1899B(b)(1) of the Act in the form and manner, and at a time, specified by CMS.

Response: We appreciate the commenter's support for this proposal.

Comment: Several commenters expressed concern about data submission using the National Healthcare Safety Network (NHSN), including the additional time and effort required to submit data using this method.

Response: We acknowledge the commenters' concerns, but note that we did not propose changes to the data submission requirements related to the NHSN. We refer readers to the IRF NHSN website for IRFs, https://www.cdc.gov/nhsn/inpatient-rehab/index.html,, which contains guidelines and protocols for NHSN submission, along with Frequently Asked Questions and resources for data submission.

Final decision: After careful consideration of the public comments, we are finalizing our proposal to revise § 412.634(b)(1) and codify in our regulations that IRFs must also submit standardized patient assessment data required under section 1899B(b)(1) of the Act in the form and manner, and at a time, specified by CMS.

H. Changes to Reconsideration Requirements Under the IRF QRP

Section 412.634(d)(1) of our regulations states, in part, that IRFs found to be non-compliant with the quality reporting requirements for a particular fiscal year will receive a letter of non-compliance through the Quality Improvement and Evaluation System Assessment Submission and Processing (QIES-ASAP) system, as well as through the United States Postal Service.

In the FY 2019 IRF PPS proposed rule (83 FR 21003), we proposed to revise § 412.634(d)(1) to expand the methods by which we would notify an IRF of non-compliance with the IRF QRP requirements for a program year. Revised § 412.634(d)(1) would state that we would notify IRFs of non-compliance with the IRF QRP requirements via a letter sent through at least one of the following notification methods: The QIES-ASAP system, the United States Postal Service, or via an email from the Medicare Administrative Contractor (MAC). We believe that this change will address feedback from providers who requested additional methods for notification.

We also proposed to revise § 412.634(d)(5) to clarify that we will notify IRFs, in writing, of our final decision regarding any reconsideration request using the same notification process.

We invited public comments on these proposals.

Comment: One commenter was supportive of our proposal to use the same process to notify IRFs of both non-compliance and our final decision on reconsideration requests.

Response: We appreciate the commenter's support.

Comment: Many commenters supported the efforts by CMS to provide more methods of communication for notifying IRFs of IRF QRP non-compliance and reconsideration decisions. A few commenters requested additional details about the logistics of these methods of notification, and a few had concerns that this would add uncertainty to the notification process. Some providers expressed confusion about how many methods of notification would be required. One commenter requested a timeline for this change. Some commenters questioned who in the provider organization would receive the notification or wanted the option to designate one person.

Response: We thank commenters for their support. We will use at least one method of notification, and providers will be notified regarding the specific method of communication that we will use via the IRF QRP Reconsideration and Exception & Extension website at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/IRF-Quality-Reporting-Reconsideration-and-Exception-and-Extension.html and announcements via the PAC listserv. The announcements will be posted annually following the May 15 data submission deadline—prior to the distribution of the initial notices of non-compliance determination in late spring/early summer. Messaging will include method of communication for the notices, instructions for sending a reconsideration request, and the final deadline for submitting the request. This policy would be effective October 1, 2018.

With regard to the point of contact for a specific facility, our notifications are sent to the point of contact on file in the QIES database. This information is populated via ASPEN. It is the responsibility of the facility to ensure that this information is up-to-date. For information regarding how to update provider information in QIES, we refer providers to https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/Downloads/How-to-Update-IRF-Demographic-Data-1-4-18-Final.pdf.

Comment: A few commenters did not support the use of MACs in the notification process, citing concerns that this might cause additional confusion. One commenter noted that MACs do not have prior experience with the IRF QRP, and are too bureaucratically complex for efficient provider communication. Several commenters suggested utilizing the existing QRP Helpdesk contractor to communicate QRP non-compliance.

Response: The MACs have been active in the notification process since the establishment of the IRF QRP. MACs serve as the primary operational contact between the Medicare FFS program and IRFs, and they work with CMS and the agency's other contractors to implement the 2 percent reduction in the annual increase factor within the Fiscal Intermediary Standard System (FISS). They also send to IRFs both the initial notices of non-compliance with the requirements of the IRF QRP and the final decisions on reconsideration requests. We are confident that the MACs will continue to be a valuable addition to the notification process.

Final decision: After careful consideration of the public comments, we are finalizing our proposal to revise § 412.634(d)(1) to state that we will notify IRFs of non-compliance with the IRF QRP requirements via a letter sent through at least one of the following notification methods: The QIES-ASAP system, the United States Postal Service, or via an email from the Medicare Administrative Contractor (MAC). We are also finalizing our proposal to revise § 412.634(d)(5) to clarify that we will notify IRFs, in writing, of our final decision regarding any reconsideration request using the same notification process.

I. Policies Regarding Public Display of Measure Data for the IRF QRP

Section 1886(j)(7)(E) of the Act requires the Secretary to establish procedures for making the IRF QRP data available to the public after ensuring that an IRF has the opportunity to review its data prior to public display. Measure data are currently displayed on the IRF Compare website, an interactive web tool that assists individuals by providing information on IRF quality of care to those who need to select an IRF. For more information on IRF Compare, we refer readers to https://www.medicare.gov/inpatientrehabilitationfacilitycompare/.

In the FY 2019 IRF PPS proposed rule (83 FR 21003), we proposed to begin publicly displaying data on the following four assessment-based measures in CY 2020, or as soon thereafter as technically feasible: (1) Change in Self-Care (NQF #2633); (2) Change in Mobility (NQF #2634); (3) Discharge Self-Care Score (NQF #2635); (4) and Discharge Mobility Score (NQF #2636). Data collection for these four assessment-based measures began with patients discharged on or after October 1, 2016. We proposed to display data for these assessment-based measures based on four rolling quarters of data, initially using discharges from January 1, 2019 through December 31, 2019 (Quarter 1 2019 through Quarter 4 2019). To ensure the statistical reliability of the data for these four assessment-based measures, we also proposed that if an IRF has fewer than 20 cases during any four consecutive rolling quarters of data that we are displaying for any of these measures, then we would note in our public display of that measure that with respect to that IRF the number of cases/patient stays is too small to publicly report.

We sought public comment on these proposals.

Comment: One commenter supported the proposal to begin publicly displaying the four assessment-based measures on the IRF Compare website in CY 2020.

Response: We appreciate the commenter's support.

Comment: A few commenters recommended that CMS provide education for IRFs prior to the public display of the four assessment-based measures. The commenters requested training for providers on the calculation and interpretation of their performance data in the CASPER reports to ensure accurate public reporting. Some commenters also requested increased transparency regarding the statistical methodologies that CMS uses to calculate provider performance.

Response: We recently held provider training in May 2018 on the interpretation of the assessment-based quality measure data on the CASPER reports as well as the data review process prior to public reporting. These and other training materials are posted on the IRF QRP website at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/index.html. We intend to hold additional training programs on this topic and will include information on the calculation of the performance data including for the four assessment-based measures: (1) Change in Self-Care (NQF #2633); (2) Change in Mobility (NQF #2634); (3) Discharge Self-Care Score (NQF #2635); (4) and Discharge Mobility Score (NQF #2636). Information related to measure calculation is currently available in IRF QM User's Manual, available at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/IRF-Quality-Reporting-Program-Measures-Information-.html. We will continue to closely monitor the performance data and assist IRFs on CASPER and public reporting efforts through ongoing stakeholder education, national trainings, IRF provider announcements, website postings, CMS Open Door Forums, and responses to help desk inquiries.

Comment: Some commenters provided recommendations on the public display of the assessment-based measures. One commenter suggested revising the measure names to better distinguish the measures and that CMS provide an explanation of the differences between these assessment-based measures in different post-acute care settings. This commenter further recommended that the data displayed on the IRF Compare website be stratified by clinical conditions to make the data more valuable for patients and their caregivers. Another commenter suggested that the assessment-based measures be divided into two larger categories labeled “Self-Care” and “Mobility” for further clarity, and recommended that the observed, expected, and national values be publicly displayed on the IRF Compare website.

Response: We appreciate commenters' suggestions on the public display of the assessment-based measures on the IRF Compare website, and we will take these suggestions into consideration. We would like to clarify that the measure names that will be displayed on the IRF Compare website will use consumer-friendly language that differs from the technical measure name. A crosswalk between the consumer-friendly name and the technical measure name is available on the IRF Compare website at https://www.medicare.gov/inpatientrehabilitationfacilitycompare/#about/theData.

Comment: MedPAC expressed concern about the functional status and other quality measure data that would be publicly displayed on the IRF Compare website. MedPAC cautioned that because functional status data are gathered through patient observation, there are concerns regarding the objectivity of this data and encouraged CMS to monitor the accuracy of the data and to confirm the inter-rater reliability of the four assessment-based measures to be displayed on the IRF Compare website.

Response: We thank MedPAC for its feedback regarding the public display of the four assessment-based measures. We understand these concerns and will continue to monitor the reliability and validity of all IRF QRP measures, including these measures, by conducting training on how to properly collect and report the measure data, and conducting our own testing as part of our measure monitoring activities.

Comment: Some commenters opposed the public display of the four assessment-based measures on the IRF Compare website in CY 2020. One commenter requested that CMS defer, or suspend, the public display of the assessment-based measures that we proposed to publicly report until providers have been given the opportunity to review the risk adjustment model and evaluate their performance. Other commenters said they do not support the proposal without first receiving more information on the way these measures will be publicly displayed.

A few commenters requested that CMS provide additional information on providers' CASPER reports. Another commenter was concerned that risk adjusted data are not currently available on the CASPER reports, and therefore, IRFs do not have sufficient information to track their performance and ensure that their provider-level performance is accurately represented on IRF Compare. One commenter suggested that CMS provide actionable patient-level data for these measures in the providers' CASPER reports.

Response: We plan to provide IRFs with the intercept and coefficient values needed for risk-adjustment in the fall of 2018. We also plan to include data on the four assessment-based measures, including patient-level data and risk-adjusted data, in the CASPER reports that we provide to IRFs in the fall of 2018, and training to assist IRFs in interpreting those data and how the data will be publicly reported. We believe that this information will allow IRFs to track their performance and ensure that their performance is accurately represented on IRF Compare. Details about the risk adjustment model variables and the calculation of these assessment-based measures can currently be found in the IRF QM User's Manual, available at https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment-Instruments/IRF-Quality-Reporting/IRF-Quality-Reporting-Program-Measures-Information-.html.

Comment: One commenter stated that there is currently no standardization of the beneficiary populations across IMPACT Act measures and recommended that CMS align these patient populations across PAC settings. If this cannot be done, the commenter then suggested using a uniform population, such as on Medicare Part A patients, for the purposes of public reporting for cross-setting comparisons. The commenter further recommended that in the future the data should be stratified by payer status, and that CMS should work with stakeholders to develop appropriate reporting methods for non-Medicare patients. Another commenter expressed concern about the standardization of Section GG functional status data and related measures across PAC settings and about the accurate depiction of differences between settings viewed on public websites.

Response: We thank the commenters for their comments. We would like to note that as we continue to develop and refine all quality measures for purposes of assessment and public reporting, we are working to align Medicare patient populations across the PAC settings. We will take into consideration the suggestion to use a uniform patient population for purposes of reporting cross-setting comparisons. We will ensure that all future development work will be aided by public comment and work with our stakeholders.

Comment: We received comments on a number of other issues related to public display. One commenter recommended implementing consumer testing prior to public reporting. A few commenters recommended that CMS provide patient-level feedback data for their claims-based measures to help IRFs improve their quality of care. One commenter requested that CMS evaluate the use of performance categories on the IRF Compare website and either remove the current performance categories or use a different methodology.

Response: We thank commenters for their comments. We will consider the commenters' suggestions about consumer testing and the use of performance categories, and we will provide the details prior to publicly reporting the four assessment-based measures. We did not propose any changes related to the public display of claims-based or CDC NHSN measures, which currently include performance categories, or to provide patient-level feedback data for their claims-based measures. However, we appreciate the feedback and will consider the commenters' concerns as we continue to monitor and evaluate measure performance and reporting methods.

Final decision: After consideration of the public comments, we are finalizing our proposal to begin publicly displaying data on the following four assessment-based measures in CY 2020, or as soon thereafter as technically feasible: (1) Change in Self-Care (NQF #2633); (2) Change in Mobility (NQF #2634); (3) Discharge Self-Care Score (NQF #2635); (4) and Discharge Mobility Score (NQF #2636) based on four rolling quarters of data, initially using discharges from January 1, 2019 through December 31, 2019 (Quarter 1 2019 through Quarter 4 2019).

J. Method for Applying the Reduction to the FY 2019 IRF Increase Factor for IRFs That Fail To Meet the Quality Reporting Requirements

As previously noted, section 1886(j)(7)(A)(i) of the Act requires the application of a 2-percentage point reduction of the applicable market basket increase factor for payments for discharges occurring during such fiscal year for IRFs that fail to comply with the quality data submission requirements. We proposed to apply a 2-percentage point reduction to the applicable FY 2019 market basket increase factor in calculating an adjusted FY 2019 standard payment conversion factor to apply to payments for only those IRFs that failed to comply with the data submission requirements. As previously noted, application of the 2-percentage point reduction may result in an update that is less than 0.0 for a fiscal year and in payment rates for a fiscal year being less than such payment rates for the preceding fiscal year. Also, reporting-based reductions to the market basket increase factor will not be cumulative; they will only apply for the FY involved.

We invited public comment on the proposed method for applying the reduction to the FY 2019 IRF increase factor for IRFs that fail to meet the quality reporting requirements.

Comment: Some commenters suggested that CMS provide flexibility in its application of the IRF QRP payment penalty for IRFs who make a good-faith effort to comply and submit quality reporting data.

Response: We interpret the commenter's suggestion that CMS take into consideration case by case exceptions and apply leniency for providers have attempted but failed to submit their quality reporting data for the IRF QRP. While we did not seek comment on flexibilities on which the penalty is applied, we note that we have provided flexibility where the failure of the IRF to comply with the requirements of the IRF QRP stemmed from circumstances beyond its control. For example, we have finalized policies that grant exceptions or extensions for IRFs if we determine that a systemic problem with one of our data collection systems affected the ability of IRFs to submit data (79 FR 45920). We have also adopted policies (78 FR 47920) that allow us to grant exemptions or extensions to an IRF if it has experienced an extraordinary circumstance beyond its control. In addition we set the reporting compliance threshold at 95 percent rather than at 100 percent to data to for account for the rare instances when assessment data collection and submission maybe impossible, such as when patients have been discharged emergently, or against medical advice.

Table 12 shows the calculation of the adjusted FY 2019 standard payment conversion factor that will be used to compute IRF PPS payment rates for any IRF that failed to meet the quality reporting requirements for the applicable reporting period.

Our regulations currently address the 2 percentage point payment reduction for failure to meet requirements under the IRF QRP in two places: §§ 412.624(c)(4) and 412.634(b)(2). We believe that these provisions are duplicative and proposed to revise the regulations so that the payment reduction is addressed only in § 412.624(c)(4). As noted in section X.C. of this final rule, we are finalizing our proposal to remove the language regarding the payment reduction that is currently at § 412.634(b)(2) and to codify that section instead the retention and removal policies for the IRF QRP.

We also proposed to revise § 412.624(c)(4)(i) to clarify that an IRF's failure to submit data under the IRF QRP in accordance with § 412.634 will result in the 2 percentage point reduction to the applicable increase factor specified in § 412.624(a)(3).

Finally, we proposed to revise § 412.624(c)(4) for greater consistency with the language of section 1886(j)(7)(A)(i) of the Act. Specifically, we would revise paragraph (i) to clarify that the 2 percentage point reduction is applied “after application of subparagraphs (C)(iii) and (D) of section 1886(j)(3) of the Act.” In addition, we would add a new paragraph (iii) that clarifies that the 2 percentage point reduction required under section 1886(j)(7)(A)(i) of the Act may result in an update that is less than 0.0 for a fiscal year. We sought public comment on these proposals.

We did not receive any public comments on the revision of the regulatory text at § 412.624(c).

Final decision: We are finalizing our proposed revisions to our regulatory text at § 412.624(c).

XI. Miscellaneous Comments

We received several comments that were outside the scope of the FY 2019 IRF PPS proposed rule. Specifically, we received comments regarding the processes for updating the IRF facility-level adjustment factors and the transparency of these updates, transitions for IRFs that are redesignated from rural to urban status due to CBSA updates, the IRF 60 percent rule and ICD-10-CM codes that might be appropriate for addition to the presumptive methodology, coverage of recreational therapy under the IRF PPS, participation of licensed therapy assistants in the interdisciplinary team meetings, requirements for hospitals to publicly report charges on the internet, access to IRF services for beneficiaries in Medicare Advantage plans, hospital-within-hospital requirements for satellite facilities, MedPAC recommendations regarding monitoring of inter-rater reliability concerns with the IRF-PAI, the role of residents in completing IRF documentation requirements, need for the overall plan of care, and the overall need to update rules on an ongoing basis to maintain their relevancy. We thank commenters for bringing these issues to our attention, and we will take these comments into consideration for potential policy refinements.

XII. Provisions of the Final Regulations

In this final rule, we are adopting the provisions set forth in the FY 2019 IRF PPS proposed rule (83 FR 20972). Specifically:

• We will update the FY 2019 IRF PPS relative weights and average length of stay values using the most current and complete Medicare claims and cost report data in a budget-neutral manner, as discussed in section IV. of this final rule.
• The facility-level adjustments will remain frozen at FY 2014 levels for FY 2015 and all subsequent years, as discussed in section V. of this final rule.
• We will update the FY 2019 IRF PPS payment rates by the market basket increase factor, based upon the most current data available, with a 0.75 percentage point reduction as required by sections 1886(j)(3)(C)(ii)(II) and 1886(j)(3)(D)(v) of the Act and a productivity adjustment required by section 1886(j)(3)(C)(ii)(I) of the Act, as described in section VI. of this final rule.
• We will update the FY 2019 IRF PPS payment rates by the FY 2019 wage index and the labor-related share in a budget-neutral manner, as discussed in section VI. of this final rule.
• We will calculate the final IRF standard payment conversion factor for FY 2019, as discussed in section VI. of this final rule.
• We will update the outlier threshold amount for FY 2019, as discussed in section VII. of this final rule.
• We will update the CCR ceiling and urban/rural average CCRs for FY 2019, as discussed in section VII. of this final rule.
• We will remove the FIM^TM Instrument and Associated Function Modifiers from the IRF-PAI beginning with FY 2020 and make refinements to the case-mix classification system using 2 full years of data, beginning with FY 2020, as discussed in section VIII. of this final rule.
• We will revise certain IRF coverage requirements beginning with FY 2019, as discussed in section IX. of this final rule.
• We will adopt updates to the IRF QRP in accordance with sections 1886(j)(7) of the Act, as discussed in section X. of this final rule.

XIII. Request for Information on Promoting Interoperability and Electronic Healthcare Information Exchange Through Possible Revisions to the CMS Patient Health and Safety Requirements for Hospitals and Other Medicare- and Medicaid-Participating Providers and Suppliers

In the FY 2019 IRF PPS proposed rule, we included a Request for Information (RFI) related to promoting interoperability and electronic healthcare information exchange (83 FR 20972 through 21015). We received 15 comments on this RFI, and appreciate the input provided by commenters.

XIV. Collection of Information Requirements

A. Statutory Requirement for Solicitation of Comments

Under the Paperwork Reduction Act of 1995 (PRA), we are required to provide 60-day notice in the Federal Register and solicit public comment before a collection of information requirement is submitted to the OMB for review and approval. To fairly evaluate whether an information collection should be approved by OMB, section 3506(c)(2)(A) of the PRA requires that we solicit comment on the following issues:

• The need for the information collection and its usefulness in carrying out the proper functions of our agency;
• The accuracy of our estimate of the information collection burden;
• The quality, utility, and clarity of the information to be collected; and
• Recommendations to minimize the information collection burden on the affected public, including automated collection techniques.

This final rule makes reference to associated information collections that are not discussed in the regulation text contained in this document.

B. Collection of Information Requirements for Updates Related to the IRF PPS

As discussed in section VIII.A of this final rule, we are removing the FIM^TM instrument and associated Function Modifiers from the IRF-PAI beginning with FY 2020, that is, for all IRF discharges beginning on or after October 1, 2019. The removal of the FIM^TM instrument and associated Function Modifiers from the IRF-PAI would result in the removal of 11 data items. As a result, we estimate the burden and costs associated with the collection of this data will be reduced for IRFs. Specifically, we estimate the removal of the FIM^TM instrument and the associated Function Modifiers will save 25 minutes of nursing/clinical staff time used to report data on both admission and discharge which was the estimated time needed to complete these items when the FIMM^TM instrument was added to the IRF-PAI in the FY 2002 IRF PPS Final Rule (66 FR 41375). We believe that the FIM^TM items we are removing may be completed by social service assistants, Licensed Practical Nurses (LPN), recreational therapists, social workers, dietitians and nutritionists, Registered Nurses (RN), Occupational Therapists (OT), Speech Language Pathologists (SLP) and audiologists, and or Physical Therapists (PT), depending on the item. To estimate the burden associated with the collection of these data items, we obtained mean hourly wages for these staff from the U.S. Bureau of Labor Statistics' May 2017 National Occupational Employment and Wage Estimates ( https://www.bls.gov/oes/current/oes_nat.htm ) and doubled them to account for overhead and fringe benefits. We estimate IRF-PAI preparation and coding costs using a social worker hourly wage rate of $49.64, a social work assistant's hourly wage rate of $34.10, an RN hourly wage rate of $70.72, an LPN hourly wage rate of $43.96, a recreation therapist hourly wage rate of $47.76, a dietitian/nutritionist hourly wage rate of $57.84, a speech-language pathologist hourly wage rate of $76.70, an audiologist hourly wage rate of $76.96, an occupational therapist hourly wage rate of $81.38, and a physical therapist hourly wage rate of $84.68. Using the mean hourly wages (doubled to account for overhead and fringe benefits) for the staffing categories above, we calculate an average rate of $62.37. The $62.37 rate is a blend of all of these categories, and reflects the fact that IRF providers have historically used all of these clinicians for preparation and coding for the IRF-PAI.

To estimate the burden reduction associated with this change, we estimate that there are approximately 403,341 discharges from 1,126 IRFs in FY 2017 resulting in an approximate average of 358 discharges per IRF annually. This equates to a reduction of 168,059 hours for all IRFs (403,341 discharges × 0.416 hours). This is 149 hours (168,059 hours/1,126 IRFs) per IRF annually. We estimate the total cost savings per IRF will be approximately $9,293 (149 hours × $62.37) annually. We estimate that the total cost savings for all IRF providers will be approximately $10.5 million (1,126 IRFs × $9,293) annually.

C. Collection of Information Requirements for Updates Related to the IRF QRP

An IRF that does not meet the requirements of the IRF QRP for a fiscal year will receive a 2 percentage point reduction to its otherwise applicable annual increase factor for that fiscal year. Information is not currently available to determine the precise number of IRFs that will receive less than the full annual increase factor for FY 2019 due to non-compliance with the requirements of the IRF QRP.

We believe that the burden associated with the IRF QRP is the time and effort associated with complying with the requirements of the IRF QRP. As of June 1, 2018, there are approximately 1,126 IRFs reporting quality data to CMS. For the purposes of calculating the costs associated with the collection of information requirements, we obtained mean hourly wages for these staff from the U.S. Bureau of Labor Statistics' May 2017 National Occupational Employment and Wage Estimates ( http://www.bls.gov/oes/current/oes_nat.htm ). To account for overhead and fringe benefits, we have doubled the hourly wage. These amounts are detailed in Table 13.

As discussed in section X.4. of this rule, we are finalizing our proposal to remove two measures from the IRF QRP.

In section X.4.2 of the final rule, we are finalizing our proposal to remove the measure, Percent of Residents or Patients Who Were Assessed and Appropriately Given the Seasonal Influenza Vaccine (Short Stay) (NQF #0680), beginning with the FY 2021 IRF QRP. IRFs will no longer be required to submit data on this measure beginning with patients discharged on October 1, 2018, and the items will be removed from the IRF-PAI V3.0, effective October 1, 2019. As a result, the estimated burden and cost for IRFs for complying with requirements of the FY 2021 IRF QRP will be reduced. Specifically, we believe that there will be a 4.8 minute reduction in clinical staff time to report data per patient stay. We estimate 403,341 discharges from 1,126 IRFs annually. This equates to a decrease of 32,267 hours in burden for all IRFs (0.08 hours per assessment × 403,341 discharges). Given 4.8 minutes of RN time at $71.30 per hour completing an average of 358 sets of IRF-PAI assessments per provider per year, we estimate that the total cost will be reduced by $2,043 per IRF annually, or $2,300,657 for all IRFs annually. This decrease in burden will be accounted for in the information collection under OMB control number (0938-0842).

In addition, we are finalizing our proposal to remove one CDC National Healthcare Safety Network (NHSN) measure, beginning with the FY 2020 IRF QRP, which will result in a decrease in burden and cost for IRFs. Providers will no longer be required to submit data beginning with October 1, 2018 admissions and discharges. We estimate that the removal of the National Healthcare Safety Network (NHSN) Facility-wide Inpatient Hospital-onset Methicillin-resistant Staphylococcus aureus (MRSA) Bacteremia Outcome Measure (NQF #1716) will result in a 3-hour (15 minutes per MRSA submission × 12 estimated submissions IRF per year) reduction in clinical staff time annually to report data which equates to a decrease of 3,378 hours (3 hours burden per IRF per year × 1,126 total IRFs) in burden for all IRFs. Given 10 minutes of RN time at $71.30 per hour, and 5 minutes of Medical Records or Health Information Technician at $37.66 per hour, for the submission of 12 estimated submissions of MRSA data to the NHSN per IRF per year, we estimate that the total cost of complying with requirements of the IRF QRP will be reduced by $180 per IRF annually, or $202,973 for all IRFs annually.

In summary, the finalized IRF QRP measure removals will result in a burden reduction of $2,223 per IRF annually, and $2,503,630 for all IRFs annually.

XV. Regulatory Impact Analysis

A. Statement of Need

This final rule updates the IRF prospective payment rates for FY 2019 as required under section 1886(j)(3)(C) of the Act. It responds to section 1886(j)(5) of the Act, which requires the Secretary to publish in the Federal Register on or before the August 1 that precedes the start of each fiscal year, the classification and weighting factors for the IRF PPS's case-mix groups, and a description of the methodology and data used in computing the prospective payment rates for that fiscal year.

This final rule also implements sections 1886(j)(3)(C) and (D) of the Act. Section 1886(j)(3)(C)(ii)(I) of the Act requires the Secretary to apply a multifactor productivity adjustment to the market basket increase factor, and to apply other adjustments as defined by the Act. The productivity adjustment applies to FYs from 2012 forward. The other adjustments apply to FYs 2010 through 2019.

Furthermore, this final rule also adopts policy changes under the statutory discretion afforded to the Secretary under section 1886(j)(7) of the Act. Specifically, we are removing the FIM^TM instrument and associated Function Modifiers from the IRF-PAI, revising certain IRF coverage requirements, removing two measures from the IRF QRP measure set, and codifying policies that were previously finalized under the IRF QRP.

B. Overall Impact

We have examined the impacts of this rule as required by Executive Order 12866 on Regulatory Planning and Review (September 30, 1993), Executive Order 13563 on Improving Regulation and Regulatory Review (January 18, 2011), the Regulatory Flexibility Act (RFA) (September 19, 1980, Pub. L. 96-354), section 1102(b) of the Act, section 202 of the Unfunded Mandates Reform Act of 1995 (March 22, 1995; Pub. L. 104-4), Executive Order 13132 on Federalism (August 4, 1999), the Congressional Review Act (5 U.S.C. 804(2) and Executive Order 13771 on Reducing Regulation and Controlling Regulatory Costs (January 30, 2017).

Executive Orders 12866 and 13563 direct agencies to assess all costs and benefits of available regulatory alternatives and, if regulation is necessary, to select regulatory approaches that maximize net benefits (including potential economic, environmental, public health and safety effects, distributive impacts, and equity). Section 3(f) of Executive Order 12866 defines a “significant regulatory action” as an action that is likely to result in a rule: (1) Having an annual effect on the economy of $100 million or more in any 1 year, or adversely and materially affecting a sector of the economy, productivity, competition, jobs, the environment, public health or safety, or state, local or tribal governments or communities (also referred to as “economically significant”); (2) creating a serious inconsistency or otherwise interfering with an action taken or planned by another agency; (3) materially altering the budgetary impacts of entitlement grants, user fees, or loan programs or the rights and obligations of recipients thereof; or (4) raising novel legal or policy issues arising out of legal mandates, the President's priorities, or the principles set forth in the Executive Order.

A regulatory impact analysis (RIA) must be prepared for major rules with economically significant effects ($100 million or more in any 1 year). We estimate the total impact of the policy updates described in this final rule by comparing the estimated payments in FY 2019 with those in FY 2018. This analysis results in an estimated $105 million increase for FY 2019 IRF PPS payments. Additionally we estimate that costs associated with the proposals to revise certain IRF coverage requirements and update the reporting requirements under the IRF quality reporting program result in an estimated $23 million reduction in costs in FY 2019 for IRFs. We also estimate that the provisions in this final rule will result in an estimated $18.5 million reduction in Medicare Part B spending from physicians billing one fewer visit to Medicare Part B. We estimate that this rulemaking is “economically significant” as measured by the $100 million threshold, and hence also a major rule under the Congressional Review Act. Also, the rule has been reviewed by OMB. Accordingly, we have prepared a Regulatory Impact Analysis that, to the best of our ability, presents the costs and benefits of the rulemaking.

C. Anticipated Effects

1. Effects on IRFs

The RFA requires agencies to analyze options for regulatory relief of small entities, if a rule has a significant impact on a substantial number of small entities. For purposes of the RFA, small entities include small businesses, nonprofit organizations, and small governmental jurisdictions. Most IRFs and most other providers and suppliers are small entities, either by having revenues of $7.5 million to $38.5 million or less in any 1 year depending on industry classification, or by being nonprofit organizations that are not dominant in their markets. (For details, see the Small Business Administration's final rule that set forth size standards for health care industries, at 65 FR 69432 at http://www.sba.gov/sites/default/files/files/Size_Standards_Table.pdf,, effective March 26, 2012 and updated on February 26, 2016.) Because we lack data on individual hospital receipts, we cannot determine the number of small proprietary IRFs or the proportion of IRFs' revenue that is derived from Medicare payments. Therefore, we assume that all IRFs (an approximate total of 1,120 IRFs, of which approximately 55 percent are nonprofit facilities) are considered small entities and that Medicare payment constitutes the majority of their revenues. The HHS generally uses a revenue impact of 3 to 5 percent as a significance threshold under the RFA. As shown in Table 14, we estimate that the net revenue impact of this final rule on all IRFs is to increase estimated payments by approximately 1.3 percent. The rates and policies set forth in this final rule will not have a significant impact (not greater than 3 percent) on a substantial number of small entities. Medicare Administrative Contractors are not considered to be small entities. Individuals and states are not included in the definition of a small entity. In addition, section 1102(b) of the Act requires us to prepare a regulatory impact analysis if a rule may have a significant impact on the operations of a substantial number of small rural hospitals. This analysis must conform to the provisions of section 604 of the RFA. For purposes of section 1102(b) of the Act, we define a small rural hospital as a hospital that is located outside of a Metropolitan Statistical Area and has fewer than 100 beds. As discussed in detail below in this section, the rates and policies set forth in this final rule will not have a significant impact (not greater than 3 percent) on a substantial number of rural hospitals based on the data of the 137 rural units and 11 rural hospitals in our database of 1,126 IRFs for which data were available.

Section 202 of the Unfunded Mandates Reform Act of 1995 (Pub. L. 104-04, enacted on March 22, 1995) (UMRA) also requires that agencies assess anticipated costs and benefits before issuing any rule whose mandates require spending in any 1 year of $100 million in 1995 dollars, updated annually for inflation. In 2018, that threshold is approximately $150 million. This final rule does not mandate any requirements for State, local, or tribal governments, or for the private sector.

Executive Order 13132 establishes certain requirements that an agency must meet when it issues a proposed rule (and subsequent final rule) that imposes substantial direct requirement costs on state and local governments, preempts state law, or otherwise has federalism implications. As stated, this final rule will not have a substantial effect on state and local governments, preempt state law, or otherwise have a federalism implication.

Executive Order 13771, titled Reducing Regulation and Controlling Regulatory Costs, was issued on January 30, 2017 and requires that the costs associated with significant new regulations “shall, to the extent permitted by law, be offset by the elimination of existing costs associated with at least two prior regulations.” This final rule is considered an E.O. 13771 deregulatory action. We estimate that this rule would generate $27.24 million in annualized cost savings, discounted at 7 percent relative to year 2016, over a perpetual time horizon. Details on the estimated costs savings of this rule can be found in the preceding analyses.

2. Detailed Economic Analysis

This final rule updates to the IRF PPS rates contained in the FY 2018 IRF PPS final rule (82 FR 36238). Specifically, this final rule updates the CMG relative weights and average length of stay values, the wage index, and the outlier threshold for high-cost cases. This final rule applies a MFP adjustment to the FY 2019 IRF market basket increase factor in accordance with section 1886(j)(3)(C)(ii)(I) of the Act, and a 0.75 percentage point reduction to the FY 2019 IRF market basket increase factor in accordance with sections 1886(j)(3)(C)(ii)(II) and (D)(v) of the Act. Further, this final rule contains revisions to remove the FIM^TM instrument and associated Function Modifiers from the IRF-PAI beginning in FY 2020, revise certain IRF coverage requirements, and revises and updates the IRF quality reporting requirements that are expected to result in some additional financial effects on IRFs. In addition, section X.J. of this final rule discusses the implementation of the required 2 percentage point reduction of the market basket increase factor for any IRF that fails to meet the IRF quality reporting requirements, in accordance with section 1886(j)(7) of the Act.

We estimate that the impact of the changes and updates described in this final rule will be a net estimated increase of $105 million in payments to IRF providers. This estimate does not include the implementation of the required 2 percentage point reduction of the market basket increase factor for any IRF that fails to meet the IRF quality reporting requirements (as discussed in section X.J. of this final rule). The impact analysis in Table 14 of this final rule represents the projected effects of the updates to IRF PPS payments for FY 2019 compared with the estimated IRF PPS payments in FY 2018. We determine the effects by estimating payments while holding all other payment variables constant. We use the best data available, but we do not attempt to predict behavioral responses to these changes, and we do not make adjustments for future changes in such variables as number of discharges or case-mix.

We note that certain events may combine to limit the scope or accuracy of our impact analysis, because such an analysis is future-oriented and, thus, susceptible to forecasting errors because of other changes in the forecasted impact time period. Some examples could be legislative changes made by the Congress to the Medicare program that would impact program funding, or changes specifically related to IRFs. Although some of these changes may not necessarily be specific to the IRF PPS, the nature of the Medicare program is such that the changes may interact, and the complexity of the interaction of these changes could make it difficult to predict accurately the full scope of the impact upon IRFs.

In updating the rates for FY 2019, we are adopting standard annual revisions described in this final rule (for example, the update to the wage and market basket indexes used to adjust the federal rates). We are also implementing a productivity adjustment to the FY 2019 IRF market basket increase factor in accordance with section 1886(j)(3)(C)(ii)(I) of the Act, and a 0.75 percentage point reduction to the FY 2017 IRF market basket increase factor in accordance with sections 1886(j)(3)(C)(ii)(II) and (D)(v) of the Act. We estimate the total increase in payments to IRFs in FY 2019, relative to FY 2018, will be approximately $105 million.

This estimate is derived from the application of the FY 2019 IRF market basket increase factor, as reduced by a productivity adjustment in accordance with section 1886(j)(3)(C)(ii)(I) of the Act, and a 0.75 percentage point reduction in accordance with sections 1886(j)(3)(C)(ii)(II) and (D)(v) of the Act, which yields an estimated increase in aggregate payments to IRFs of $110 million. Furthermore, there is an additional estimated $5 million decrease in aggregate payments to IRFs due to the proposed update to the outlier threshold amount. Outlier payments are estimated to decrease from approximately 3.1 percent in FY 2018 to 3.0 percent in FY 2019. Therefore, summed together, we estimate that these updates will result in a net increase in estimated payments of $105 million from FY 2018 to FY 2019.

The effects of the updates that impact IRF PPS payment rates are shown in Table 14. The following updates that affect the IRF PPS payment rates are discussed separately below:

• The effects of the update to the outlier threshold amount, from approximately 3.1 percent to 3.0 percent of total estimated payments for FY 2019, consistent with section 1886(j)(4) of the Act.
• The effects of the annual market basket update (using the IRF market basket) to IRF PPS payment rates, as required by section 1886(j)(3)(A)(i) and sections 1886(j)(3)(C) and (D) of the Act, including a productivity adjustment in accordance with section 1886(j)(3)(C)(i)(I) of the Act, and a 0.75 percentage point reduction in accordance with sections 1886(j)(3)(C)(ii)(II) and (D)(v) of the Act.
• The effects of applying the budget-neutral labor-related share and wage index adjustment, as required under section 1886(j)(6) of the Act.
• The effects of the budget-neutral changes to the CMG relative weights and average length of stay values, under the authority of section 1886(j)(2)(C)(i) of the Act.
• The total change in estimated payments based on the FY 2019 payment changes relative to the estimated FY 2018 payments.

3. Description of Table 14

Table 14 categorizes IRFs by geographic location, including urban or rural location, and location for CMS's 9 Census divisions (as defined on the cost report) of the country. In addition, the table divides IRFs into those that are separate rehabilitation hospitals (otherwise called freestanding hospitals in this section), those that are rehabilitation units of a hospital (otherwise called hospital units in this section), rural or urban facilities, ownership (otherwise called for-profit, non-profit, and government), by teaching status, and by disproportionate share patient percentage (DSH PP). The top row of Table 14 shows the overall impact on the 1,126 IRFs included in the analysis.

The next 12 rows of Table 14 contain IRFs categorized according to their geographic location, designation as either a freestanding hospital or a unit of a hospital, and by type of ownership; all urban, which is further divided into urban units of a hospital, urban freestanding hospitals, and by type of ownership; and all rural, which is further divided into rural units of a hospital, rural freestanding hospitals, and by type of ownership. There are 978 IRFs located in urban areas included in our analysis. Among these, there are 709 IRF units of hospitals located in urban areas and 269 freestanding IRF hospitals located in urban areas. There are 148 IRFs located in rural areas included in our analysis. Among these, there are 137 IRF units of hospitals located in rural areas and 11 freestanding IRF hospitals located in rural areas. There are 389 for-profit IRFs. Among these, there are 349 IRFs in urban areas and 40 IRFs in rural areas. There are 619 non-profit IRFs. Among these, there are 532 urban IRFs and 87 rural IRFs. There are 118 government-owned IRFs. Among these, there are 97 urban IRFs and 21 rural IRFs.

The remaining four parts of Table 14 show IRFs grouped by their geographic location within a region, by teaching status, and by DSH PP. First, IRFs located in urban areas are categorized for their location within a particular one of the nine Census geographic regions. Second, IRFs located in rural areas are categorized for their location within a particular one of the nine Census geographic regions. In some cases, especially for rural IRFs located in the New England, Mountain, and Pacific regions, the number of IRFs represented is small. IRFs are then grouped by teaching status, including non-teaching IRFs, IRFs with an intern and resident to average daily census (ADC) ratio less than 10 percent, IRFs with an intern and resident to ADC ratio greater than or equal to 10 percent and less than or equal to 19 percent, and IRFs with an intern and resident to ADC ratio greater than 19 percent. Finally, IRFs are grouped by DSH PP, including IRFs with zero DSH PP, IRFs with a DSH PP less than 5 percent, IRFs with a DSH PP between 5 and less than 10 percent, IRFs with a DSH PP between 10 and 20 percent, and IRFs with a DSH PP greater than 20 percent.

The estimated impacts of each policy described in this rule to the facility categories listed are shown in the columns of Table 14. The description of each column is as follows:

• Column (1) shows the facility classification categories.
• Column (2) shows the number of IRFs in each category in our FY 2019 analysis file.
• Column (3) shows the number of cases in each category in our FY 2019 analysis file.
• Column (4) shows the estimated effect of the adjustment to the outlier threshold amount.
• Column (5) shows the estimated effect of the update to the IRF labor-related share and wage index, in a budget-neutral manner.
• Column (6) shows the estimated effect of the update to the CMG relative weights and average length of stay values, in a budget-neutral manner.
• Column (7) compares our estimates of the payments per discharge, incorporating all of the policies reflected in this final rule for FY 2019 to our estimates of payments per discharge in FY 2018.

The average estimated increase for all IRFs is approximately 1.3 percent. This estimated net increase includes the effects of the IRF market basket increase factor for FY 2019 of 2.9 percent, reduced by a productivity adjustment of 0.8 percentage point in accordance with section 1886(j)(3)(C)(ii)(I) of the Act, and further reduced by 0.75 percentage point in accordance with sections 1886(j)(3)(C)(ii)(II) and (D)(v) of the Act. It also includes the approximate 0.1 percent overall decrease in estimated IRF outlier payments from the update to the outlier threshold amount. Since we are making the updates to the IRF wage index and the CMG relative weights in a budget-neutral manner, they will not be expected to affect total estimated IRF payments in the aggregate. However, as described in more detail in each section, they will be expected to affect the estimated distribution of payments among providers.

4. Impact of the Update to the Outlier Threshold Amount

The estimated effects of the update to the outlier threshold adjustment are presented in column 4 of Table 14. In the FY 2018 IRF PPS final rule (82 FR 36238), we used FY 2016 IRF claims data (the best, most complete data available at that time) to set the outlier threshold amount for FY 2018 so that estimated outlier payments would equal 3 percent of total estimated payments for FY 2018.

For the FY 2019 IRF PPS proposed rule (83 FR 20987), we used preliminary FY 2017 IRF claims data, and, based on that preliminary analysis, we estimated that IRF outlier payments as a percentage of total estimated IRF payments would be 3.4 percent in FY 2018. As we typically do between the proposed and final rules each year, we updated our FY 2017 IRF claims data to ensure that we are using the most recent available data in setting IRF payments. Therefore, based on updated analysis of the most recent IRF claims data for this final rule, we now estimate that IRF outlier payments as a percentage of total estimated IRF payments are 3.1 percent in FY 2018. Thus, we are adjusting the outlier threshold amount in this final rule to set total estimated outlier payments equal to 3 percent of total estimated payments in FY 2019. The estimated change in total IRF payments for FY 2019, therefore, includes an approximate 0.1 percent decrease in payments because the estimated outlier portion of total payments is estimated to decrease from approximately 3.1 percent to 3 percent.

The impact of this outlier adjustment update (as shown in column 4 of Table 14) is to decrease estimated overall payments to IRFs by about 0.1 percent. We estimate the largest decrease in payments from the update to the outlier threshold amount to be 0.4 percent for rural IRFs in the Pacific region.

5. Impact of the CBSA Wage Index and Labor-Related Share

In column 5 of Table 14, we present the effects of the budget-neutral update of the wage index and labor-related share. The changes to the wage index and the labor-related share are discussed together because the wage index is applied to the labor-related share portion of payments, so the changes in the two have a combined effect on payments to providers. As discussed in section VI.C. of this final rule, we are updating the labor-related share from 70.7 percent in FY 2018 to 70.5 percent in FY 2019.

6. Impact of the Update to the CMG Relative Weights and Average Length of Stay Values

In column 6 of Table 14, we present the effects of the budget-neutral update of the CMG relative weights and average length of stay values. In the aggregate, we do not estimate that these updates will affect overall estimated payments of IRFs. However, we do expect these updates to have small distributional effects.

7. Effects of the Removal of the FIM^TM Instrument and Associated Function Modifiers From the IRF-PAI Beginning in FY 2020

As discussed in section VIII. of this final rule, we are removing the FIM^TM Instrument and Associated Function Modifiers from the IRF-PAI beginning in FY 2020. We estimate that removal of these data items from the IRF-PAI will reduce administrative burden on IRF providers and reduce the costs incurred by IRFs by $10.5 million for FY 2020.

8. Effects of Revisions to Certain IRF PPS Requirements

As discussed in section IX. of this final rule, in response to the RFI, we are removing and amending certain IRF coverage criteria requirements that are overly burdensome on IRF providers beginning in FY 2019, that is, all IRF discharges on or after October 1, 2018.

We estimate the cost savings associated with our change to allow the post-admission physician evaluation to count as one of the required face-to-face physician visits, as discussed in section IX.A of this final rule, in the following way. We first estimate that the post-admission physician evaluation takes approximately 60 minutes to complete and the required face-to-face physician visits take, on average, 30 minutes each to complete. Both of these requirements must be fulfilled by a rehabilitation physician. To estimate the burden reduction of this change, therefore, we obtained the hourly wage rate for a physician (there was not a specific wage rate for a rehabilitation physician) from the Bureau of Labor Statistics ( http://www.bls.gov/ooh/healthcare/home.htm ) to be $100.00. The hourly wage rate including fringe benefits and overhead is $200.00.

In FY 2017, we estimate that there were approximately 1,126 total IRFs and on average 358 discharges per IRF annually. Therefore, there were an estimated seven patients (358 discharges/52 weeks) at the IRF per week. The rehabilitation physician spends 358 hours (60 minutes × 358 discharges) annually completing the post-admission physician evaluation. If on average each IRF has seven patients per week and each face-to-face visit takes an estimated 30 minutes for the rehabilitation physician to complete, annually the rehabilitation physician spends an estimated 546 hours ((7 patients × 3 visits × 0.5 hours) × 52 weeks) completing the required face-to-face physician visits. On average, a rehabilitation physician currently spends 903 hours (357 hours + 546 hours) annually completing post-admission physician evaluations and the required face-to-face physician visits.

If we allow the post-admission physician evaluation to count as one of the face-to-face required physician visits, and to be documented as such in the IRF medical record, we would need to estimate the average time spent on one face-to-face visit ((7 patients × 1 visit × 0.5 hours) × 52 weeks). Removing one of the face-to-face visits required in the first week of the IRF admission will save the rehabilitation physician approximately 182 hours ((7 patients × 1 visit × 0.5 hours) × 52 weeks) annually per IRF. This is a savings of 204,932 hours across all IRFs annually (1,126 IRFs × 182 hours).

To estimate the total cost savings per IRF annually, we multiply 182 hours by $200.00 (average physician's salary doubled to account for fringe and overhead costs). Therefore, we can estimate the total cost savings per IRF will be $36,400 annually. We estimate that the total cost savings for allowing the post-admission physician evaluation to count as one of the required face-to-face physician visits, will be $41 million (1,126 IRFs × $36,400) annually across the IRF setting. As described above, based on stakeholder feedback, we anticipate that rehabilitation physicians in a majority of IRFs will adopt this policy change; because there is some uncertainty, we assume in our burden reduction estimate that rehabilitation physicians in half of all IRFs will change their visiting practices accordingly. Therefore, we now estimate that the total cost savings for allowing the post-admission physician evaluation to count as one of the required face-to-face physician visits will be $20.5 million (563 IRFs × $36,400).

We also note that fewer physician visits will result in Medicare savings from lower Part B payments to physicians under the physician fee schedule. The national average Medicare Part B payment for a 30 minute moderate intensity “subsequent” visit (versus an initial visit) is $93. Therefore, if the estimated number of discharges per IRF is 358 and we multiply that by the estimated cost of one physician visit, then we estimate that the reduction in Part B billing per IRF would be approximately $33,000. Across the Medicare program for all IRFs, we estimate it would be approximately $37 million in Part B savings. However, we reduce this estimate by 50 percent, as we assume that only half of IRFs will adopt this policy. Therefore, we estimate that Medicare Part B payments to rehabilitation physicians in IRFs will be reduced by approximately $18.5 million.

We do not estimate a cost savings in removing the admission order coverage criteria requirements as IRFs are still required to comply with the enforcement of the admission requirements located in §§ 482.24(c), 482.12(c) and 412.3. Any increase in Medicare payments due to the change would be negligible given the anticipated low volume of claims that would be payable under this revised policy that would not have been paid under the current policy. Therefore, we believe that the reduction of burden in this removal is in reducing the redundancy of requirements only.

Therefore, we estimate that the removal and updates to these requirements will reduce unnecessary regulatory and administrative burden on IRF providers and reduce the costs incurred by IRFs by $20.5 million for FY 2019. Additionally, we estimate that the removal and updates to these requirements will also reduce Medicare Part B payments by $18.5 million for FY 2019.

Though we are unsure exactly how many, we recognize that some IRFs may have facility protocols in place that exceed our IRF requirements regarding how many times the rehabilitation physician must visit each patient per week and document these visits in the IRF medical record. While our requirement is a minimum of three face-to-face visits a week, we understand that it is not uncommon for IRFs institute a facility protocol requiring the rehabilitation physician to see the patient daily. To the extent that some IRFs are choosing to exceed our requirements, we recognize that the savings estimate could be lower than what we have projected.

9. Effects of the Requirements for the IRF QRP for FY 2020

In accordance with section 1886(j)(7) of the Act, we will reduce by 2 percentage points the market basket increase factor otherwise applicable to an IRF for a fiscal year if the IRF does not comply with the requirements of the IRF QRP for that fiscal year. In section VII.K of this final rule, we discuss the method for applying the 2 percentage point reduction to IRFs that fail to meet the IRF QRP requirements.

As discussed in section X.4. of this final rule, we are removing two measures from the IRF QRP: Percent of Residents or Patients Who Were Assessed and Appropriately Given the Seasonal Influenza Vaccine (Short Stay) (NQF #0680) and the National Healthcare Safety Network (NHSN) Facility-wide Inpatient Hospital-onset Methicillin-resistant Staphylococcus aureus (MRSA) Bacteremia Outcome Measure (NQF #1716).

We describe the estimated burden and cost reductions for both of these measures in section XIV.C of this rule. In summary, the finalized IRF QRP measure removals will result in a burden reduction of $2,223.26 per IRF annually, and $2,503,629.76 for all IRFs annually.

We intend to continue closely monitoring the effects of the IRF QRP on IRFs and to help perpetuate successful reporting outcomes through ongoing stakeholder education, national trainings, IRF announcements, website postings, CMS Open Door Forums, and general and technical help desks.

D. Alternatives Considered

The following is a discussion of the alternatives considered for the IRF PPS updates contained in this final rule.

Section 1886(j)(3)(C) of the Act requires the Secretary to update the IRF PPS payment rates by an increase factor that reflects changes over time in the prices of an appropriate mix of goods and services included in the covered IRF services. Thus, we did not consider alternatives to updating payments using the estimated IRF market basket increase factor for FY 2019. However, as noted previously in this final rule, section 1886(j)(3)(C)(ii)(I) of the Act requires the Secretary to apply a productivity adjustment to the market basket increase factor for FY 2019, and sections 1886(j)(3)(C)(ii)(II) and 1886(j)(3)(D)(v) of the Act require the Secretary to apply a 0.75 percentage point reduction to the market basket increase factor for FY 2019. Thus, in accordance with section 1886(j)(3)(C) of the Act, we are updating the IRF federal prospective payments in this final rule by 1.35 percent (which equals the 2.9 percent estimated IRF market basket increase factor for FY 2019 reduced by a 0.8 percentage point productivity adjustment as required by section 1886(j)(3)(C)(ii)(I) of the Act and further reduced by 0.75 percentage point).

We considered maintaining the existing CMG relative weights and average length of stay values for FY 2019. However, in light of recently available data and our desire to ensure that the CMG relative weights and average length of stay values are as reflective as possible of recent changes in IRF utilization and case-mix, we believe that it is appropriate to update the CMG relative weights and average length of stay values at this time to ensure that IRF PPS payments continue to reflect as accurately as possible the current costs of care in IRFs.

We considered updating facility-level adjustment factors for FY 2019. However, as discussed in more detail in the FY 2015 final rule (79 FR 45872), we believe that freezing the facility-level adjustments at FY 2014 levels for FY 2015 and all subsequent years (unless and until the data indicate that they need to be further updated) will allow us an opportunity to monitor the effects of the substantial changes to the adjustment factors for FY 2014, and will allow IRFs time to adjust to the previous changes.

We considered maintaining the existing outlier threshold amount for FY 2019. However, analysis of updated FY 2019 data indicates that estimated outlier payments would be higher than 3 percent of total estimated payments for FY 2019, by approximately 0.1 percent, unless we updated the outlier threshold amount. Consequently, we are adjusting the outlier threshold amount in this final rule to reflect a 0.1 percent decrease thereby setting the total outlier payments equal to 3 percent, instead of 3.1 percent, of aggregate estimated payments in FY 2019.

We considered not removing the FIM^TM instrument and associated Function Modifiers from the IRF-PAI in this final rule. However, in light of recently available data located in the Quality Indicators section of the IRF-PAI, we believe that removal of the FIM^TM instrument and associated Function Modifiers is appropriate at this time. As the data items located in the Quality Indicators section of the IRF-PAI are now collected for all IRFs, we believe that the collection of the FIM data is duplicative and creates undue burden on providers. Consequently, we are removing these data items from the IRF-PAI beginning with FY 2020. Additionally, the removal of the FIM^TM Instrument and associated Function Modifiers necessitates the incorporation of the data items from the Quality Indicators section of the IRF-PAI into the CMG classification system. To ensure that the CMGs, relative weights, and average length of stay values are as reflective as possible of recent changes in IRF utilization and case-mix, we believe that it is appropriate to incorporate the data items from the Quality Indicators section of the IRF-PAI into the development of the CMGs beginning with FY 2020.

We considered not revising certain IRF PPS requirements, or revising them partially, in order to reduce burden in this final rule. Specifically, we considered not combining the post-admission physician evaluation with the required face-to-face physician visits, and continuing to require documentation of the post-admission physician evaluation and all three face-to-face physician visits in the IRF medical record in the first week of the patient's IRF stay. However, through the request for information, it was suggested that we focus on removing documentation and administrative burden in IRFs and we wanted to assist by combining two documentation requirements into one, thus reducing the medical record documentation requirements that the rehabilitation physician would need to meet. Additionally, we also considered not removing the admission order requirement from the IRF medical record. However, we felt that the requirement was duplicative and could be met by other requirements that are currently in place. Lastly, we considered not allowing rehabilitation physicians to lead the interdisciplinary team meeting remotely via other forms of communication without additional documentation of this in the IRF medical record. We also considered only relaxing this requirement for rural IRFs, as some of the commenters suggested. However, we believe that this policy change is appropriate and beneficial for all IRFs, not just rural, so we decided to finalize the policy as proposed. As we believe that rehabilitation physicians rarely conduct interdisciplinary team meetings remotely, we do not believe that this policy has significant financial implications for IRFs. However, we believe that it does advance the Agency's goal of placing patients over paperwork.

Therefore, after the response that we received from providers regarding the RFI solicitation and comments that we received from the FY 2019 IRF PPS proposed rule, we believed that these specific coverage requirements were areas in which we could reduce unnecessary regulatory and administrative burden on IRF providers, while ensuring that IRF patients would continue to receive adequate care.

E. Regulatory Review Costs

If regulations impose administrative costs on private entities, such as the time needed to read and interpret this final rule, we should estimate the cost associated with regulatory review. Due to the uncertainty involved with accurately quantifying the number of entities that will review the rule, we assume that the total number of unique commenters on FY 2019 IRF PPS proposed rule will be the number of reviewers of this final rule. We acknowledge that this assumption may understate or overstate the costs of reviewing this final rule. It is possible that not all commenters reviewed the FY 2019 IRF PPS proposed rule in detail, and it is also possible that some reviewers chose not to comment on the proposed rule. For these reasons we thought that the number of past commenters would be a fair estimate of the number of reviewers of this rule.

We also recognize that different types of entities are in many cases affected by mutually exclusive sections of this final rule, and therefore for the purposes of our estimate we assume that each reviewer reads approximately 50 percent of the rule. We sought comments on this assumption.

Using the wage information from the BLS for medical and health service managers (Code 11-9111), we estimate that the cost of reviewing this rule is $107.38 per hour, including overhead and fringe benefits ( https://www.bls.gov/oes/current/oes_nat.htm ). Assuming an average reading speed, we estimate that it would take approximately 2 hours for the staff to review half of this final rule. For each IRF that reviews the rule, the estimated cost is $214.76 (2 hours × $107.38). Therefore, we estimate that the total cost of reviewing this regulation is $23,408.84 ($214.76 × 109 reviewers).

F. Accounting Statement and Table

As required by OMB Circular A-4 (available at http://www.whitehouse.gov/sites/default/files/omb/assets/omb/circulars/a004/a-4.pdf ), in Table 15, we have prepared an accounting statement showing the classification of the expenditures associated with the provisions of this final rule. Table 15 provides our best estimate of the increase in Medicare payments under the IRF PPS as a result of the updates presented in this final rule based on the data for 1,126 IRFs in our database. In addition, Table 15 presents the costs associated with the new IRF quality reporting program requirements for FY 2019.

G. Conclusion

Overall, the estimated payments per discharge for IRFs in FY 2019 are projected to increase by 1.3 percent, compared with the estimated payments in FY 2018, as reflected in column 7 of Table 14.

IRF payments per discharge are estimated to increase by 1.3 percent in urban areas and 1.1 percent in rural areas, compared with estimated FY 2018 payments. Payments per discharge to rehabilitation units are estimated to increase 1.2 percent in urban areas and 1.0 percent in rural areas. Payments per discharge to freestanding rehabilitation hospitals are estimated to increase 1.3 percent in urban areas and increase 1.6 percent in rural areas.

Overall, IRFs are estimated to experience a net increase in payments as a result of the policies in this final rule. The largest payment increase is estimated to be a 3.2 percent increase for rural IRFs located in the New England region. The analysis above, together with the remainder of this preamble, provides a Regulatory Impact Analysis.

In accordance with the provisions of Executive Order 12866, this regulation was reviewed by the Office of Management and Budget.

List of Subjects in 42 CFR Part 412

• Administrative practice and procedure
• Health facilities
• Medicare
• Puerto Rico
• Reporting and recordkeeping requirements

For the reasons set forth in the preamble, the Department of Health and Human Services amends 42 CFR chapter IV as set forth below:

PART 412—PROSPECTIVE PAYMENT SYSTEMS FOR INPATIENT HOSPITAL SERVICES

1. The authority citation for part 412 is revised to read as follows:

Authority: 42 U.S.C. 1302 and 1395hh.

2. Section 412.606 is amended by—

a. Removing paragraph (a); and

b. Redesignating paragraphs (b) and (c) as paragraphs (a) and (b).

3. Section 412.622 is amended by—

a. Revising paragraph (a)(3)(iv);

b. Redesignating paragraphs (a)(5)(A) through (C) as paragraphs (a)(5)(i) through (iii); and

c. Revising newly redesignated paragraph (a)(5)(i).

The revisions read as follows:

4. Section 412.624 is amended by revising paragraph (c)(4)(i) and adding paragraph (c)(4)(iii) to read as follows:

5. Section 412.634 is amended by revising paragraphs (b), (d)(1) and (5) to read as follows: