Shahram Ebadollahi et al.

Patent Trials and Appeals Board

Jan 20, 2022

2021002845 (P.T.A.B. Jan. 20, 2022)

UNITED STATES PATENT AND TRADEMARK OFFICE UNITED STATES DEPARTMENT OF COMMERCE United States Patent and Trademark Office Address: COMMISSIONER FOR PATENTS P.O. Box 1450 Alexandria, Virginia 22313-1450 www.uspto.gov APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO. 12/855,060 08/12/2010 Shahram Ebadollahi YOR920100439US1 (163-357) 9132 49267 7590 01/20/2022 Tutunjian & Bitetto, P.C. 401 Broadhollow Road Suite 402 Melville, NY 11747 EXAMINER COBANOGLU, DILEK B ART UNIT PAPER NUMBER 3626 NOTIFICATION DATE DELIVERY MODE 01/20/2022 ELECTRONIC Please find below and/or attached an Office communication concerning this application or proceeding. The time period for reply, if any, is set in the attached communication. Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the following e-mail address(es): docketing@tb-iplaw.com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE ____________________ BEFORE THE PATENT TRIAL AND APPEAL BOARD ____________________ Ex parte SHAHRAM EBADOLLAHI, JIANYING HU, ROBERT K. SORRENTINO, DABY M. SOW, and JIMENG SUN __________________ Appeal 2021-002845 Application 12/855,060 Technology Center 3600 ____________________ Before JAMES P. CALVE, NINA L. MEDLOCK, and BRADLEY B. BAYAT, Administrative Patent Judges. CALVE, Administrative Patent Judge. DECISION ON APPEAL STATEMENT OF THE CASE Pursuant to 35 U.S.C. § 134(a), Appellant1 appeals from the decision of the Examiner to reject claims 1, 3-14, 16-23, and 27, which are all of the pending claims.2 See Appeal Br. 1. We have jurisdiction under 35 U.S.C. § 6(b). We AFFIRM. 1 “Appellant” refers to “applicant” as defined in 37 C.F.R. § 1.42. Appellant identifies International Business Machines Corporation as the real party in interest. See Appeal Br. 3. 2 Claims 2, 15, and 24-26 are cancelled. See Appeal Br. 30, 33, 36 (Claims App). Appeal 2021-002845 Application 12/855,060 2 CLAIMED SUBJECT MATTER Claims 1, 8, and 17 are independent. Claim 1 recites: 1. A system for selecting a treatment plan based on a predicted patient prognosis, comprising: a database having stored patient data; a similarity module configured in program storage media to construct at least two similarity functions from a plurality of customized quantitative measurement data sources to compute similarity scores on each data source reflecting a similarity measure between a query patient and historical patient data based on the patient data and physician feedback, the similarity module acquiring quantitative measurement data using patient sensors and historical lab results, wherein different similarity functions are applied to compute the similarity scores for each different type of data source based on physical characteristics of each of the different types of data sources, wherein each data source is customized by a weighting coefficient to automatically adjust importance of each of a plurality of numeric features, from the data sources, of one or more patients based on user input, and retrieve at least one similar patient to the query patient based on the computed similarity scores; and wherein the data sources include lab results, sensor measurements, diagnosis information, medication information, and demographic information; an alignment module configured to compute a dynamic time warping distance and perform longitudinal alignment to align the at least one similar patient to a current time of the query patient so that a comparison between the query patient and the at least one similar patient is provided to enable a best match of current events of the query patient to the at least one similar patient in real-time; a prediction module configured to predict at least one long-term outcome measure of each of a plurality of treatment plans generated for the query patient based on data from the at least one similar patient; and Appeal 2021-002845 Application 12/855,060 3 a model analyzer configured to identify one or more treatment plans with positive outcome estimates by taking treatment parameters for each of the plurality of treatment plans and information of the query patient as input and testing an outcome measure of each of the one or more treatment plans on the query patient; and selecting a treatment plan with a best predicted outcome estimate for the query patient from the identified treatment plans with positive outcome estimates. Appeal Br. 29-30 (Claims App.). REJECTIONS Claim 1 is rejected under 35 U.S.C. § 112(b) as being indefinite. Claims 1, 3-14, 16-23, and 27 are rejected under 35 U.S.C. § 101 as directed to a judicial exception without significantly more. ANALYSIS Indefiniteness of Claim 1 The Examiner interprets the following limitations of claim 1 as means-plus-function limitations that invoke 35 U.S.C. § 112(f): (1) “a similarity module configured to construct . . .”; (2) “an alignment module configured to computer . . .”; (3) “a prediction module configured to . . .”; and “a model analyzer configured to predict . . . .” Non-Final Act. 4. The Examiner determines that the Specification does not describe corresponding structure, material, or acts for performing the entire claimed function to clearly link the structure, material, or acts to the function so it is unclear which structure performs the entire claimed function. Id. at 5-6. Appellant does not present arguments for this rejection. See Appeal Br. 11-27. Therefore, we summarily sustain this rejection. Appeal 2021-002845 Application 12/855,060 4 Eligibility of Claims 1, 3-14, 16-23, and 27 Appellant argues the claims as a group. See Appeal Br. 14-27. We select claim 1 as representative. 37 C.F.R. § 41.37(c)(1)(iv) (2019). The Examiner determines that claim 1 recites a system for selecting a treatment plan based on a predicted patient prognosis by functions that recite mental processes and mathematical calculations. Non-Final Act. 7-8; Ans. 3-4. The Examiner determines that constructing similarity functions from plural quantitative measurement data sources, customizing the data sources by weighting each data source, predicting an outcome measure of each treatment plan, identifying treatment plans with positive outcome estimates by taking treatment parameters of each plan and information of a query patient as input, testing an outcome measure of each plan, and selecting a treatment plan with a best predicted outcome estimate can be performed as mental processes. Non-Final Act. 7-8. The Examiner also determines that computing a time warping distance from longitudinal events in a timeline of a query patient to a history of a similar patient for longitudinal alignment recites mathematical calculations. Id. at 8; Ans. 4. The Examiner further determines that using a generic computer processor to compute similarity scores based on data sources, combine the scores into an overall similarity score, retrieve at least one similar patient to a query patient based on the computed similarity scores, and align the similar patient to a current time of the query patient does not impose a meaningful limit. Non-Final Act. 8. In addition, the Examiner determines that using a generic computer to perform such functions does not amount to significantly more than the abstract idea, and using a patient sensor and sensor measurements recites well-understood, routine, and conventional activities. Id. at 8-9. Appeal 2021-002845 Application 12/855,060 5 Principles of Law Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. 35 U.S.C. § 101. Laws of nature, natural phenomena, and abstract ideas are not patentable. See Alice Corp. v. CLS Bank Int’l, 573 U.S. 208, 216 (2014). To distinguish patents that claim laws of nature, natural phenomena, and abstract ideas from those that claim patent-eligible applications, we first determine whether the claims are directed to a patent-ineligible concept. Id. at 217. If they are, we consider the claim elements, individually and as an ordered combination, to determine if any additional elements provide an inventive concept sufficient to ensure that the claims in practice amount to significantly more than a patent on the ineligible concept. Id. at 217-18. The USPTO has issued guidance about this framework. 2019 Revised Patent Subject Matter Eligibility Guidance, 84 Fed. Reg. 50 (Jan. 7, 2019) (“Revised Guidance”). To determine if a claim is “directed to” an abstract idea, we evaluate whether the claim recites: (1) any judicial exceptions, including certain groupings of abstract ideas listed in the Revised Guidance (i.e., mathematical concepts, certain methods of organizing human activities such as a fundamental economic practice, or mental processes); and (2) additional elements that integrate the judicial exception into a practical application.3 Id. at 52-55. 3 “A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, such that the claim is more than a drafting effort designed to monopolize the judicial exception.” Revised Guidance, 84 Fed. Reg. at 54. Appeal 2021-002845 Application 12/855,060 6 If a claim (1) recites a judicial exception and (2) does not integrate that exception into a practical application, we consider whether the claim (3) provides an inventive concept such as by adding a limitation beyond a judicial exception that is not “well-understood, routine, conventional” in the field or (4) appends well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception. Revised Guidance, 84 Fed. Reg. at 56. Step 1 We agree with the Examiner that claim 1 recites a system, which falls within a statutory category of invention of a machine. See 35 U.S.C. § 101; Non-Final Act. 7. Alice Step One Revised Guidance Step 2A, Prong One: Do the Claims Recite a Judicial Exception? We agree with the Examiner that claim 1 recites a system for selecting a treatment plan based on a predicted patient prognosis through limitations that can be performed as mental processes and mathematical calculations. See Non-Final Act. 7-8; Ans. 3-4; Revised Guidance, 84 Fed. Reg. at 52. The focus of the claims is on predicting the long term prognosis of a patient so that an appropriate treatment plan can be selected. Spec. ¶¶ 2, 6, 14, 36-39. The application title reflects this focus on a SYSTEM AND METHOD FOR PREDICTING LONG-TERM PATIENT OUTCOME. As discussed in more detail below, the Specification’s description of the system makes clear that the modules perform data processing functions that can be performed as mental processes and that involve mathematical calculations and concepts. See Spec. ¶¶ 27-39, Figs. 2-5. Appeal 2021-002845 Application 12/855,060 7 The similarity module 106 constructs similarity functions from plural data sources to compute similarity scores for each data source reflecting a similarity measure between a query patient and historical patient data using patient data and physician feedback. Appeal Br. 29 (Claims App.). The Specification describes the similarity module as constructing customizable patient similarity measures that are applied to patient data to find similar patients for each query patient. Spec. ¶ 27. Similarity measures are highly customizable based on the data and physician feedback using an interface. Id. Similarity scores are computed with weighting coefficients that adjust the importance of each data source and combine them into a total score. Id. ¶ 30. Weighting coefficients can be increased or decreased by user input to adjust the importance of a given data source. Id. Similarity measures can be adjusted using localized supervised metric learning to leverage a physician’s assessment of a disease type and stage. Id. ¶ 31. Mathematical equations are used to replicate a physician’s mental processes of determining similarity of patients by computing a distance metric between patients. Id. ¶¶ 32-34. The alignment module 108 compares a pair of similar patients and identifies a longitudinal offset to align pairs of patients so that a meaningful comparison may be made between patients in different stages of disease progression. Id. ¶¶ 28, 35. The module computes a dynamic time-warping distance or Euclidean distance to determine an anchor time that matches the current time of a query patient to the historical patient in time. Longitudinal alignment tries “to best match the query patient’s current events to the other historical patient in time, so that we can compare two patients who are in different stages of the disease.” Id. ¶ 35. Mathematical computations are used to replicate mental processes of physicians. See id. ¶¶ 31-35. Appeal 2021-002845 Application 12/855,060 8 The prediction module 110 forecasts outcome measures for a patient based on health status, lab results, cost, life expectancy, recovery time, and disease progression of similar patients and their outcome measures. Spec. ¶¶ 29, 36. A statistical average is computed for outcome estimates of similar patients so outcome estimates are derived from the actual outcome measures of similar patients. Id. ¶¶ 36, 39. A mean or median of outcome measures of similar patients or statistics models may be used. Id. ¶ 36. The model analyzer 114 tests different treatment options. Id. ¶ 29. It also replicates mental processes of a doctor who “looks at what treatments have been done on the similar patients who had a good or positive outcome and decides to select the corresponding treatment for patient X.” Id. ¶ 37. The description of the similarity, alignment, and prediction modules and model analyzer as using physicians’ mental processes and mathematical calculations confirms their abstract nature. See SAP Am., Inc. v. InvestPic, LLC, 898 F.3d 1161, 1167 (Fed. Cir. 2018) (“The focus of the claims, as reflected in what is quoted above, is on selecting certain information, analyzing it using mathematical techniques, and reporting or displaying the results of the analysis. That is all abstract.”); Elec. Power Grp., LLC v. Alstom S.A., 830 F.3d 1350, 1354 (Fed. Cir. 2016) (“In a similar vein, we have treated analyzing information by steps people go through in their minds, or by mathematical algorithms, without more, as essentially mental processes within the abstract-idea category.”); see also FairWarning IP, LLC v. Iatric Sys., Inc., 839 F.3d 1089, 1093 (Fed. Cir. 2016) (steps of collecting data regarding access of a patient’s personal health information and analyzing that data according to rules to generate a full picture of a user’s activity and detect misuse involve mental processes). Appeal 2021-002845 Application 12/855,060 9 Applying such data collection and analysis functions to medical data does not change the outcome. See Elec. Power, 830 F.3d at 1355 (“[A] large portion of the lengthy claims is devoted to enumerating types of information and information sources available within the power-grid environment. But merely selecting information, by content or source, for collection, analysis, and display does nothing significant to differentiate a process from ordinary mental processes, whose implicit exclusion from § 101 undergirds the information-based category of abstract ideas.”); In re Meyer, 688 F.2d 789, 795-96 (Fed. Cir. 1982) (claims to a mathematical algorithm representing mental processes that a neurologist follows to diagnose a patient’s condition is an abstract idea); SmartGene, Inc. v. Advanced Biological Labs., SA, 555 F. App’x 950, 954-55 (Fed. Cir. 2014) (a method for guiding selection of a therapeutic treatment regimen for a patient with a known disease or medical condition by comparing stored and input data using a set of expert rules to evaluate and select from a stored plurality of different treatment regimens involves mental steps of comparing new and stored information using rules to identify medical options as doctors perform in their heads); see also In re Rosenberg, 813 F. App’x 594, 596-97 (Fed. Cir. 2020) (the claims recite computer-performed mental steps that otherwise are performed in person to assess and respond to performance measures in the field by assessing the consistency of data compared to data previously collected, evaluating changes in data, monitoring data for trends, determining whether procedures or parameters used in conducting a clinical trial or any process should be modified, and providing instructions to modify the procedures or parameters, which is just a process of gathering and analyzing information of a specified content and displaying the results, which is an abstract idea). Appeal 2021-002845 Application 12/855,060 10 Here, the claimed system analyzes stored patient data collected from various sources and computes various parameters and measures to identify and select a treatment plan with the best predicted outcome estimate for a query patient without using any asserted, inventive technology to perform those functions beyond the mental processes and mathematical calculations that are used to perform those functions. See Elec. Power, 830 F.3d at 1354. Appellant contends that the claimed features involve more than predicting patient prognosis. Appeal Br. 16. Appellant also asserts that the claimed subject matter does not fall in any of the enumerated groupings of abstract ideas identified in the Revised Guidance. Id. at 16-17. Appellant further argues that the claims are similar to claims determined to be patent- eligible in McRO, Inc. v. Bandai Namco Games America Inc., 837 F.3d 1299 (Fed. Cir. 2016). Id. at 17. In particular, Appellant asserts claim 1 recites a specific system and specific approach for predicting patient prognosis based on customized quantitative measurements used to apply treatment plans based on a patient’s prognosis and specific rules. Id. at 17-19. The claimed improvement in McRO allowed computers to produce “accurate and realistic lip synchronization and facial expressions in animated characters.” McRO, 837 F.3d at 1313. The claimed rules defined morph weight sets as a function of the timing of phoneme sub-sequences to generate and apply transition parameters to create a final morph weight set to improve computer animation. Id. at 1313-14. The claims were directed to the creation of something physical--the display of lip synchronization and facial expressions of animated characters on screens to produce better quality images for viewing rather than improved mathematical techniques without any improved display mechanism. See SAP, 898 F.3d at 1167. Appeal 2021-002845 Application 12/855,060 11 Here, claim 1 is focused on a system for collecting data of particular content and analyzing that data by performing mathematical computations and data processing activities that involve, or are performable as, mental processes by physicians. The Specification confirms that the functions or rules performed by the modules include mental processes of physicians and other technicians. See Spec. ¶¶ 27, 29, 31, 32, 37, original claims 16 and 25. The claim applies mathematical algorithms or rules to patient data to identify treatment regimens as doctors do. See SmartGene, 555 F. App’x at 954-55. Accordingly, we determine that claim 1 recites the abstract idea identified above. Alice Step One Revised Guidance Step 2A, Prong Two: Is There an Integration into a Practical Application? We next consider whether claim 1 recites additional elements that integrate the abstract idea into a practical application. Revised Guidance, 84 Fed. Reg. at 54. Performing computations using patient data stored in a generic database, acquiring data using generic patient sensors, and using a generic computer to perform the claimed functions are not sufficient for an integration into a practical application. The additional elements are used to perform generic data processing activities without improving computers or other technology, without using a particular machine that is integral to the claim, without transforming or reducing a particular article to a different state or thing, and without effecting a treatment or prophylaxis for a disease or medical condition. See Non-Final Act. 8, 10; Revised Guidance, 84 Fed. Reg. at 55. The claimed functions predict and select a treatment plan with the best outcome by mental processes and mathematical calculations without applying any treatment plan to a patient based on a prognosis. See Ans. 4. Appeal 2021-002845 Application 12/855,060 12 Appellant argues that claim 1 uses a limited set of rules to achieve an improved technological result in a conventional industry practice, and details of the claimed approach would not preempt approaches that use rules of a different structure or different techniques. Appeal Br. 19. Appellant asserts claim 1 is confined to a particular useful application of predicting prognoses from real world customized quantitative measurements of a patient including lab results, sensor measurements, diagnosis information, medication information, and demographic information. See id. at 19-21. Appellant also argues that using determined concrete and quantitative real world patient measurements for a patient’s prognosis is not abstract. Id. at 20-21. Predicting a patient’s prognosis based on customized measurements and a patient’s medical and demographic information to select a treatment plan with the best predicted outcome simply organizes a patient’s medical and health activities and information similar to other concepts that our reviewing court has treated as an abstract idea. See Salwan v. Iancu, 825 F. App’x 862, 865-66 (Fed. Cir. 2020) (claims to communicating patient health information over a generic physician-patient network by requiring the receipt and storage of patient health information data “read on organizing human activity with respect to medical information, i.e., abstract processes that can be performed by an individual.”); see also In re Jobin, 811 F. App’x 633, 637 (Fed. Cir. 2020) (claims directed to the collection, organization, grouping, and storage of data by conducting a survey or crowdsourcing are directed to a method of organizing human activity, a hallmark of abstract ideas); In re Downing, 754 F. App’x 988, 993 (Fed. Cir. 2018) (claims to the concept of personal management, resource planning, and forecasting collect and analyze non-business and business information as an abstract idea). Appeal 2021-002845 Application 12/855,060 13 Providing customized information tailored to unique circumstances of a patient as indicated by their demographic or medical information is another form of this abstract idea. See Affinity Labs of Tex., LLC v. Amazon.com Inc., 838 F.3d 1268, 1271 (Fed. Cir. 2016) (customizing a user interface based on a user’s demographic information is an abstract idea); Intellectual Ventures I LLC v. Capital One Bank (USA), 792 F.3d 1363, 1369 (Fed. Cir. 2015) (customizing information provided to a user using information known about the user and other data is an abstract idea); In re Morsa, 809 F. App’x 913, 917 (Fed. Cir. 2020) (requesting demographic or psychographic information of a user and saving it on a system to match to specific parties relates to customizing information based on information known about the user and other data, which is an abstract idea). Here, the system gathers medical information of a query patent and analyzes that data to match the query patient to an historical patient to predict a long-term outcome measure of various treatment plans and select a customized treatment plan tailored for the best predicted outcome estimate for the query patient. Essentially, the system chooses a treatment plan tailored to the circumstances of the query patient based on information known about the query patient and historical patients with similar demographic and medical information via mathematical computations and processes that replicate the thought processes of doctors and other healthcare providers. See Spec. ¶¶ 2-6, 26-39, Figs. 2-5; see also BSG Tech LLC v. Buyseasons, Inc., 899 F.3d 1281, 1286 (Fed. Cir. 2018) (claims to considering historical usage information while inputting data to a database to ensure users provide more consistent item descriptions is a well- established method of organizing activity; it is not saved from abstraction by reciting a database and components more specific than a generic computer). Appeal 2021-002845 Application 12/855,060 14 Merely determining concrete and quantitative measurements from medical sensors for predicting outcomes and identifying treatments for a patient does not make an abstract idea patent eligible. See CardioNet, LLC v. InfoBionic, Inc., 816 F. App’x 471, 475, 476-77 (Fed. Cir. 2020) (system that collected physiological data, monitored and reported that data to identify arrhythmia events based on predetermined criteria, and correlated the events with events identified by parallel human assessment for validity monitoring did so through generic data analysis; “[e]ven assuming that measuring the atrial fibrillation burden is a new metric as CardioNet claims, it is at most a mathematical computation performed on a general-purpose computing device, which could otherwise be ‘performed by a human, mentally or with pen and paper.’”) (citation omitted); cf. Classen Immunotherapies, Inc. v. Biogen IDEC, 659 F.3d 1057, 1066 (Fed. Cir. 2011) (lowering the risk of chronic immune-mediated disorder by the physical step of immunizing a patient on a determined schedule recited a specific, tangible application). Here, as discussed under Prong One above, the system analyzes collected medical information through mathematical computations and steps that can be performed as mental processes without implementing any treatment. We recognize that “[s]oftware can make non-abstract improvements to computer technology just as hardware improvements can, and . . . the improvements can be accomplished through either route.” Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1335 (Fed. Cir. 2016). “[T]o be directed to a patent-eligible improvement to computer functionality, the claims must be directed to an improvement to the functionality of the computer or network platform itself.” Customedia Techs., LLC v. Dish Network Corp., 951 F.3d 1359, 1365 (Fed. Cir. 2020) (citing Enfish, 822 F.3d at 1336-39). Appeal 2021-002845 Application 12/855,060 15 We find no such improvements in the claimed system. It may be implemented as an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects as a “circuit,” “module,” or “system.” Spec. ¶ 17. Computer program code for carrying out aspects of the invention may be written in any combination of programming languages including object oriented programming language such as Java, Smalltalk, C++, or conventional procedural programming languages such as “C” programming language. Id. ¶ 20. System 100 may include a single processing device such as a computer, a personal digital assistant or other computing device or a plurality of distributed computers in a network environment. Id. ¶ 25. Patient data warehouse 104 stores patient records in a structured format that is searchable for compiling statistics and patient information. Id. ¶ 25. Patient similarity measurements use “sensor measurements.” Id. ¶ 31. This description indicates that the claimed system and database and patient sensors are generic tools that are used to perform the abstract idea without any improvement to computers or other technology. Obtaining measurement data from generic patient sensors does not require a particular machine that is integral to the claim or that improves computers or technology. See Elec. Power, 830 F.3d at 1351-52, 1354 (detecting and analyzing events of an electric power grid from plural data streams based on limits, rates of change of measurements of data streams, and dynamic stability metrics derived from analysis of the measurements, and displaying analysis results and diagnoses of events associated with metrics of different categories of data (i.e., monitoring, tracking, historical, prediction, and summary data) focused on gathering and analyzing data of a specific content without an inventive technology to perform these functions). Appeal 2021-002845 Application 12/855,060 16 “[N]ot every claim that recites concrete, tangible components escapes the reach of the abstract-idea inquiry” such as where physical components “merely provide a generic environment in which to carry out the abstract idea of classifying and storing digital images in an organized manner.” In re TLI Commc’ns LLC Patent Litig., 823 F.3d 607, 611, 613 (Fed. Cir. 2016) (the recitation of a “telephone unit,” a “server,” an “image analysis unit,” and a “control unit” failed to make the abstract idea patent-eligible); Content Extraction & Transmission LLC v. Wells Fargo Bank Nat’l Assn., 776 F.3d 1343, 1348 (Fed. Cir. 2014) (using a scanner or digitizing device to extract data from a document was not a patent-eligible application of the abstract idea); Automated Tracking Solutions, LLC v. Coca-Cola Co., 723 F. App’x 989, 993-94 (Fed. Cir. 2018) (collecting data from sensors, analyzing that data, and determining results recited an abstract idea). Here, “[t]he purely functional nature of the claim confirms that it is directed to an abstract idea, not to a concrete embodiment of that idea.” Affinity Labs, 838 F.3d at 1269; see also Elec. Power, 830 F.3d at 1356 (“[T]he essentially result-focused, functional character of claim language has been a frequent feature of claims held ineligible under § 101 especially in the area of using generic computer and network technology to carry out economic transactions.”). Selecting a treatment plan with the best predicted outcome is extra- solution activity. See Elec. Power, 830 F.3d at 1354 (“[M]erely presenting the results of abstract processes of collecting and analyzing information, without more (such as identifying a particular tool for presentation), is abstract as an ancillary part of such collection and analysis.”). As such, it does not integrate the abstract idea into a practical application. Appeal 2021-002845 Application 12/855,060 17 Furthermore, the limited set of rules used to predict prognoses from real world customized quantitative measurements of a patient (see Appeal Br. 19-21) are aspects of the abstract idea identified under Prong One and cannot serve as additional elements. See Revised Guidance, 84 Fed. Reg. at 55 n.24 (“additional elements” refer to claim features, limitations, and/or steps that are recited in a claim beyond the identified judicial exception); Alice, 573 U.S. at 221 (a claim that recites an abstract idea must include additional features to ensure it does not monopolize the abstract idea). Even if the Specification described particular technical improvements for performing the functions of the similarity module, the alignment module, the prediction module, and the model analyzer, those details are not claimed. Thus, they cannot be relied on for an integration. See Ericsson Inc. v. TCL Commc’n Tech. Holdings Ltd., 955 F.3d 1317, 1325 (Fed. Cir. 2020) (“[T]he specification may be ‘helpful in illuminating what a claim is directed to . . . [but] the specification must always yield to the claim language’ when identifying the ‘true focus of a claim.’”); Accenture Glob. Servs., GmbH v. Guidewire Software, Inc., 728 F.3d 1336, 1345 (Fed. Cir. 2013) (“[T]he complexity of the implementing software or the level of detail in the specification does not transform a claim reciting only an abstract concept into a patent-eligible system or method.”); see also Bancorp Servs., L.L.C. v. Sun Life Assurance Co. of Can. (U.S.), 687 F.3d 1266, 1279 (Fed. Cir. 2012) (“Using a computer to accelerate an ineligible mental process does not make that process patent-eligible.”). Accordingly, we determine that claim 1 lacks additional elements that are sufficient to integrate the abstract idea into a practical application. Appeal 2021-002845 Application 12/855,060 18 Alice, Step Two and Revised Guidance Step 2B: Do the Claims Include an Inventive Concept? We next consider whether claim 1 recites any additional elements, individually or as an ordered combination, to provide an inventive concept. Alice, 573 U.S. at 217-18. This step is satisfied when limitations involve more than well-understood, routine, and conventional activities known in the industry. See Berkheimer v. HP Inc., 881 F.3d 1360, 1367 (Fed. Cir. 2018). Individually, the additional elements perform conventional functions known in the industry. The database stores patient data. The patient sensors measure and provide patient data. No technical improvements are recited. As an ordered combination, the limitations recite no more than when they are considered individually. They recite result-oriented functions rather than technical improvements to computers or technology. See Ericsson, 955 F.3d at 1328 (“Merely claiming ‘those functions in general terms, without limiting them to technical means for performing the functions that are arguably an advance,’ does not make a claim eligible at step one.”) (citations omitted)); SAP, 898 F.3d at 1167-68 (to avoid patent ineligibility, a claim must have the specificity to transform it from one claiming only a result to one claiming a way of achieving the result); Interval Licensing LLC v. AOL, Inc., 896 F.3d 1335, 1343 (Fed. Cir. 2018) (software can make non-abstract improvements to computer technology but software-based inventions that do not pass § 101 muster fail because “they did not recite any assertedly inventive technology for improving computers as tools and/or because the elements of the asserted invention were so result-based that they amounted to patenting the patent-ineligible concept itself.”). Essentially, the claimed functions can be performed by any and all technical means. Appeal 2021-002845 Application 12/855,060 19 “If a claim’s only ‘inventive concept’ is the application of an abstract idea using conventional and well-understood techniques, the claim has not been transformed into a patent-eligible application of an abstract idea.” BSG, 899 F.3d at 1290-91; see Bozeman Fin. LLC v. Fed. Reserve Bank of Atl., 955 F.3d 971, 980-81 (Fed. Cir. 2020) (using well-known computer components to collect and analyze data, present data, and send notifications recites a logical sequence with no inventive concept); SAP, 898 F.3d at 1169-70 (claims to available databases and processors that perform already available basic functions to include generic parallel processing components that are not asserted to be inventive to carry out improved mathematical calculations amounts to reciting what is well-understood, routine, and conventional); Elec. Power, 830 F.3d at 1355 (claims to using off-the-shelf, conventional computer, network, and display technology to gather, send, and present desired information lack an inventive concept). Whether the claim preempts approaches that use different rules or techniques is not determinative. See Appeal Br. 19. “[W]hile preemption may signal patent ineligible subject matter, the absence of complete preemption does not demonstrate patent eligibility.” FairWarning, 839 F.3d at 1098 (quoting Ariosa Diagnostics, Inc. v. Sequenom, Inc., 788 F.3d 1371, 1379 (Fed. Cir. 2015)); see OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1362-63 (Fed. Cir. 2015) (“[T]hat the claims do not preempt all price optimization or may be limited to price optimization in the e-commerce setting do not make them any less abstract.”). Where it is determined that a patent’s claims recite only patent ineligible subject matter, as in this case, preemption concerns are fully addressed and made moot. See Ariosa, 788 F.3d at 1379. Appeal 2021-002845 Application 12/855,060 20 Even if the techniques are groundbreaking, innovative, or brilliant, that is not enough for eligibility. SAP, 898 F.3d at 1163 (“No matter how much of an advance in the finance field the claims recite, the advance lies entirely in the realm of abstract ideas, with no plausibly alleged innovation in the non-abstract application realm. An advance of that nature is ineligible for patenting.”). Combining one abstract idea (mathematical calculations) with another abstract idea (mental processes) is not an inventive concept. See RecogniCorp, LLC v. Nintendo Co., 855 F.3d 1322, 1327 (Fed. Cir. 2017) (“Adding one abstract idea (math) to another abstract idea (encoding and decoding) does not render the claim non-abstract.”); Apple, Inc. v. Ameranth, Inc., 842 F.3d 1229, 1240 (Fed. Cir. 2016) (“An abstract idea can generally be described at different levels of abstraction.”); Synopsys, Inc. v. Mentor Graphics Corp., 839 F.3d 1138, 1151 (Fed. Cir. 2016) (“[A] claim for a new abstract idea is still an abstract idea.”). Accordingly, we sustain the rejection of claims 1, 3-14, 16-23, and 27 as directed to an abstract idea without significantly more. DECISION In summary: Claim(s) Rejected 35 U.S.C. § References/Basis Affirmed Reversed 1, 3-14, 16- 23, 27 101 Eligibility 1, 3-14, 16- 23, 27 TIME PERIOD FOR RESPONSE No time period for taking any subsequent action in connection with this appeal may be extended under 37 C.F.R. § 1.136(a). See 37 C.F.R. § 1.136(a)(1)(iv). Appeal 2021-002845 Application 12/855,060 21 AFFIRMED