DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Claims
The status of the claims as of the response filled 09/10/2025: Claims 1-20 were initially pending.
Claim 1, 8, 11, 17, and 20 were amended and have been considered below.
Response to Arguments 35 U.S.C. § 101
Applicant’s arguments with respect to the rejection of claims 1-20 under 35 U.S.C. § 101 page 14-16, filed on 09/10/2025, have been fully considered but are not persuasive. The amendments to claims 1, 8, 11, 17, and 20 have been entered. However, the § 101 rejection of all claims is maintained.
Applicant Argument Regarding the Mental Process Exception
Applicant argues that the claims are not directed to a mental process because they describe a "computer-implemented clinical-trial simulator" involving "substantive data transformations" and "specialized models" that "cannot reasonably be performed in the human mind."
Examiner's Response
Examiner respectfully disagrees. While Applicant characterizes the invention as a complex simulator, the claims, under their Broadest Reasonable Interpretation (MPEP § 2111), are not so limited. The claim language recites steps such as "generating...a cohort...based on correlations," "separating," and "determining an effect," which are fundamental analytical and cognitive steps. As defined in MPEP § 2106.04(a)(2), a mental process includes "concepts performed in the human mind (including an observation, evaluation, judgment, opinion)." The amended claims do not recite a specific particularity in the "patient-specific metabolic model" that would preclude a human from conceptually performing these analytical steps, even if it were tedious. Therefore, the argument that these steps cannot be performed in the human mind is not persuasive, as it attempts to import limitations from the specification that are not recited in the claims, contrary to MPEP § 2111.01.
Applicant Argument Regarding Practical Application and "Significantly More"
Applicant argues that even if the claims recite an abstract idea, they are directed to "something significantly more" that results in a "practical application" by yielding a "concrete, computer-generated output (e.g., a 'representative effect')" which provides a "real-world technological benefit" by forecasting cohort-level efficacy in silico.
Examiner's Response
Examiner respectfully disagrees. The production of a "concrete, computer-generated output" is not, by itself, sufficient to confer patent eligibility. Per MPEP § 2106.04(d), the claim as a whole must integrate the abstract idea into a practical application that imposes a "meaningful limit on the judicial exception." The "representative effect" is the direct, logical result of performing the abstract mental process of collecting and analyzing data. The claimed benefit—previewing clinical trial performance is an advantage of the abstract idea itself, not the result of a specific technological improvement recited in the claims. The claims do not describe a specific improvement to how computers function or to another field of technology; they merely use generic computer components to achieve the abstract idea's output more efficiently, which does not constitute "significantly more" under the Alice/Mayo framework.
Applicant Argument Regarding Iterative Refinement of Trial Parameters
Applicant contends that the simulator allows investigators to "iteratively refine trial parameters in ways that are impossible through mental reasoning alone," thereby transforming static records into "optimized trial protocols" and demonstrating a practical, technology-driven improvement.
Examiner's Response
Examiner respectfully disagrees because this argument relies on functionalities not recited in the claims. As stated in MPEP § 2111.01, it is improper to import limitations from the specification into the claims. The amended claims do not include any limitations directed to "iteratively refining trial parameters" or "rerunning the population models." Furthermore, the argument that this process is "impossible through mental reasoning alone" appears to be based on the speed and processing power of a computer. Using a computer for its inherent speed and efficiency to automate a known process does not constitute a patent-eligible technological improvement (see MPEP § 2106.05(a)). Therefore, this argument does not overcome the rejection.
Applicant Argument Regarding Advancement of Patient Safety
Applicant argues that the process "advances patient safety and ethical stewardship" by identifying and excluding at-risk subpopulations, thereby providing a "tangible public-health benefit that far transcends any abstract mental calculation" and anchoring the claims in a practical application.
Examiner's Response
Examiner respectfully disagrees. While the claimed invention may provide a tangible public health benefit, merely limiting an abstract idea to a particular field of use—in this case, healthcare and clinical trial simulation—is not sufficient to confer patent eligibility. As explained in MPEP § 2106.05(h), "Generally linking the use of a judicial exception to a particular technological environment or field of use" does not amount to an inventive concept. The claimed steps for identifying and categorizing patients are still abstract data analysis steps. The benefit to patient safety flows from the application of the abstract idea in a specific field, not from an inventive concept in the claims that improves computer technology or transforms the abstract idea into something patentably distinct. The claims lack limitations specifying a non-conventional or non-generic technological process to achieve this benefit, and therefore, the argument is not persuasive.
Response to Arguments 35 U.S.C. § 103
Applicant’s arguments, see pages 16-18 of the response filed on 09/10/2025 with respect to amended Claims 1, 8, 11, 17, and 20 have been fully considered and are not persuasive.
Applicant Arguments Regarding Claim 1
Applicant's Argument: Applicant argues that the combined prior art of Schaeffer (US 2022/0044826 A1) and Constantin does not disclose or suggest the claim limitations of “determining a representative effect of the treatment recommendation for the test cohort based on the generated individual predicted effects for the test cohort,” and “comparing the representative effect for the cohort to representations of metabolic states in the control cohort.” Applicant contends that Schaeffer is a generic, oncology-focused tool used only for creating cohorts, not analyzing them, and that Constantin’s model is not applied in a cohort context.
Examiner's Response
The Examiner respectfully disagrees. The applicant’s arguments unduly narrow the teachings of the prior art and misinterpret the standard for obviousness, in addition contrary to Applicant's assertion, no agreement was reached during the interview regarding the prior art (see Interview summary mailed 07/01/2025). The arguments are addressed as follows:
Regarding "determining a representative effect": This argument is not persuasive as it fails to consider the Broadest Reasonable Interpretation (BRI) of the claim language, as required by MPEP § 2111. The amended claim recites determining a "representative effect." Schaeffer explicitly discloses a system and method "to predict an expected response of a particular patient population or cohort" (Schaeffer, Abstract; see also [0005]). Under its broadest reasonable interpretation, predicting an "expected response" for a cohort is synonymous with determining a "representative effect" for that cohort. Therefore, this limitation is clearly taught by Schaeffer.
Regarding "comparing the representative effect... to... control cohort": This argument is not persuasive because Schaeffer explicitly teaches comparative analysis. Schaeffer describes "comparing a representation of the test patient's biological state to a plurality of cohort definitions" ([0007]) and using control panels to identify outlier groups by comparing them against a central or expected value (see discussion of FIGS. 21-24 at [0139]- [0142]). A control cohort is a standard type of cohort definition or baseline used for such comparison. The claimed comparison is therefore a fundamental aspect of the analytical method taught by Schaeffer.
Regarding the Combination of Schaeffer and Constantin: The applicant's argument that Schaeffer is generic and that Constantin is not used in a cohort context precisely identifies the reason for the combination. The rejection does not assert that Constantin teaches a cohort model, but rather that it would have been obvious to apply Constantin's known technique to Schaeffer's known system. As stated in MPEP § 2143, a primary rationale for an obviousness rejection is "applying a known technique [Constantin's patient-specific metabolic modeling] to a known device... [Schaeffer's cohort analysis framework] ready for improvement to yield predictable results." Schaeffer explicitly states its system is designed to use data from the "metabolome" and "metabolomics" ([0002], [0080], [0093]). This provides a clear motivation for a Person of Ordinary Skill in the Art (PHOSITA) to integrate the specific patient metabolic model of Constantin into Schaeffer’s general analysis framework to improve its predictive accuracy for metabolic diseases.
Applicant Arguments Regarding Claims 11 and 20
Applicant's Argument: Applicant argues that since independent claims 11 (system) and 20 (non-transitory computer-readable medium) were amended to include subject matter similar to claim 1, they should also be found allowable.
Examiner's Response: This argument is considered moot. As independent claim 1 remains unpatentable for the reasons detailed above, claims 11 and 20, which recite the same substantive limitations in different statutory classes, are likewise not allowable over the combination of Schaeffer and Constantin for the same reasons. The rejection of claim 1 is therefore incorporated by reference for claims 11 and 20.
Applicant Arguments Regarding Dependent Claims
Applicant's Argument: Applicant argues that the dependent claims should be found allowable based on their dependency from the now-allowable independent claims.
Examiner's Response: This argument is considered moot. Because the independent claims upon which the dependent claims rely are properly rejected, the dependent claims are not allowable. Further, the additional limitations recited in the dependent claims do not add any patentable weight over the applied prior art combination.
Claim Rejections — 35 U.S.C. § 101
35 U.S.C. 101 reads as follows:
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.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (an abstract idea) without integrating the abstract idea into a practical application, and the claims do not amount to significantly more than the abstract idea itself.
Step 1: Statutory Categories of Invention
Independent claims 1, 11, and 20 fall into the statutory categories of "process," "manufacture," and "machine," respectively. Dependent claims 2-10 and 12-19 further define these categories. Accordingly, the claims satisfy the requirements of Step 1 of the eligibility analysis.
Prong One: Does the claim recite a judicial exception?
Yes. Independent claims 1, 11, and 20 are directed to the abstract idea of a mental process. Specifically, they recite the mental process of collecting and analyzing information to make a prediction. As stated in MPEP § 2106.04(a)(2), "concepts performed in the human mind (including an observation, evaluation, judgment, opinion)" are categorized as mental processes.
The amended independent claim 20 recite:
Claim 20.
A system comprising: one or more processors;
and a non-transitory computer readable medium storing instruction encoded thereon that, when executed by the one or more processors, cause the one or more processors to:
identify an intervention parameter in a treatment recommendation for causing a target improvement in metabolic state, the treatment recommendation comprising instructions for adjusting the intervention parameter to cause the target improvement;
generate, from a population of patients, a cohort of patients sensitive to the intervention parameter based on correlations between changes in the metabolic state of each patient of the population and adjustments to the intervention parameter, the sensitivity of a patient representing a likelihood that adjustments to the intervention parameter will affect the metabolic state of the patient;
separate the cohort of patients into a control cohort comprising a first subset of patients and a test cohort comprising a second subset of patients;
and determine an effect of the treatment recommendation on the cohort of patients, the instructions for determining the effect of the treatment recommendation further comprise instructions that cause the processor to:
for each patient of the test cohort, inputting the treatment recommendation into a patient-specific metabolic model to generate an individual predicted effect of the treatment on the patient;
determining a representative effect of the treatment recommendation for the test cohort based on the generated individual predicted effects for the test cohort;
and comparing the representative effect for the test cohort to representations of metabolic states in the control cohort.
Under the broadest reasonable interpretation, these claims recite steps for identifying an intervention parameter, generating a cohort based on correlations, separating into control/test groups, and comparing predicted effects—all of which are fundamental concepts that can be performed in the human mind. The specification itself describes these operations in abstract, analytical terms. For example, the process involves generating a cohort "based on correlations between changes in the metabolic state ... and adjustments to the intervention parameter" (Spec., Para. [0010]), where sensitivity represents a "likelihood" of an effect (Spec., Para. [0010]). These are cognitive operations involving observation, evaluation, and judgment.
A clinician could perform these steps mentally or with pen and paper. For instance, a doctor could:
Review patient medical records (identifying intervention parameters and metabolic states).
Observe correlations between an intervention (e.g., a diet change) and metabolic outcomes, manually grouping patients who seem "sensitive" into a cohort.
Divide this group into a "test" group (for whom a new recommendation is considered) and a "control" group.
Mentally predict the effect on the test group using their medical knowledge (a "patient-specific model") and then compare that prediction to the observed states of the control group. This human-driven, logical reasoning process directly parallels the claimed steps and falls squarely into the "mental process" category of abstract ideas (MPEP § 2106.04(a)(2)).
Dependent claims 2-10 and 12-19 merely refine this core mental process. Claims 2, 3, 4, 12, and 13 add steps of labeling patient sensitivity based on historical data or thresholds, which are data-sorting tasks. Claims 5 and 14 involve filtering patients based on a metabolic state threshold, another analytical step. Claims 6 and 15 consider long-term effects, which is an extension of the same predictive reasoning. Amended claim 8, for example, further limits the cohort generation to "categorizing the population... into categories... with a shared metabolic state," "determining an overall sensitivity of the category," and "generating the cohort of patients based on the category... most sensitive." These added steps—categorizing, determining sensitivity, and comparing—are all pure mental processes of data analysis. Similarly, claims 9 and 18 involve deciding if an improvement is sufficient, and claims 10 and 19 use feature vectors, a standard data representation technique. In all cases, the core operations remain activities that can be performed by human thought, thus falling within the "mental process" abstract idea.
Because the claims recite a judicial exception, the analysis proceeds to Prong Two.
Prong Two: Does the claim integrate the judicial exception into a practical application?
No. The claims do not integrate the abstract mental process into a practical application. The additional elements merely use generic computer components to perform the abstract idea, which does not transform the claim into a patent-eligible application. As stated in MPEP § 2106.04(d), "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." The additional elements here fail to impose such a limit.
The additional elements beyond the abstract idea are the use of a "patient-specific metabolic model," "one or more processors," and a "non-transitory computer readable medium."
Patient-Specific Metabolic Model: This limitation does not add a practical application because it is merely a generic term for applying mathematical analysis to patient data. The specification describes this as a "digital model capturing the biology and metabolism of the patient’s body" (Spec., Para. [0029]) and states that it "implements one or more machine-learned models" (Spec., Para. [0055]). This indicates the "model" is a mathematical concept used for its intended abstract purpose of calculation and prediction. It does not improve computer functionality or any other technology but is simply a tool to execute the abstract analysis.
Non-Transitory Computer Readable Medium / One or More Processors: These limitations recite generic computer components that are invoked merely as a tool to perform the abstract idea. The specification describes these elements in purely conventional terms, such as a "storage device 230 representing a non-volatile memory, such as a hard drive, compact disk read-only memory (CD-ROM), DVD, or a solid-state memory device" (Spec., Paras. [0042]- [0043]) and a "chipset 210 coupled to at least one processor 205" (Spec., Para. [0041]). Reciting generic computer components to perform generic computer functions (like processing and storing data) amounts to "mere instructions to implement an abstract idea on a computer" and does not constitute a practical application (MPEP § 2106.05(f)).
The dependent claims similarly fail to integrate the abstract idea. The limitations regarding accessing data, labeling, comparing to thresholds (claims 2–4, 12–13), identifying patient subsets (claims 5, 14), and determining long-term effects (claims 6, 15) are all generic data manipulation steps. Even amended claim 8, which adds steps for categorizing patients and determining sensitivity, represents conventional data segmentation and analysis, not a specific technical application.
Considered individually and as a whole, the additional elements do not transform the abstract mental process into a practical application. They simply use a general-purpose computer to automate the abstract analysis. Therefore, the claims are "directed to" the abstract idea (Step 2A: YES), and the analysis must proceed to Step 2B.
Step 2B: Inventive Concept (Significantly More)
The claims do not recite additional elements that amount to "significantly more" than the abstract idea itself. This inquiry looks for an "inventive concept" by considering whether the additional elements transform the claim into a patent-eligible application by adding something more than what is well-understood, routine, and conventional in the field (MPEP § 2106.05).
The additional elements identified in Step 2A are analyzed here to determine if they constitute an inventive concept.
Patient-Specific Metabolic Model: This element lacks an inventive concept. The specification describes it broadly as a "digital twin" that "implements one or more machine-learned [models]" (Spec., Para. [0055]) for the purpose of "simulating ... clinical trials using personalized digital twins" (Spec., Para. [0028]). Using machine-learned models for prediction and simulation is a well-understood, routine, and conventional activity in data science and healthcare analytics Refer to US20210202098- Bostic par. 0026, US20210202107-Bostic par. 0026, US20190005200, par.0078. The specification provides no details on a specific, unconventional modeling technique or algorithm that would constitute an improvement in computer technology or medical modeling itself.
One or More Processors / Non-Transitory Computer Readable Medium: These elements are conventional. As quoted previously, the specification at paragraphs [0041]- [0043] describes a generic computer architecture, including a "chipset 210," "processor 205," "memory controller 211," and "storage device 230." These are fundamental, off-the-shelf components used for their basic functions, representing nothing more than well-understood, routine, and conventional computer hardware.
Dependent Claims: The limitations added by the dependent claims also fail to provide an inventive concept.
Cohort Generation (Claims 2-8, 12-17): These claims add limitations regarding how patients are selected. This includes accessing data where "patient data sent through the network 150 is received by the patient health management platform 130…where it is analyzed" (Spec., Para. [0033]); determining historical changes where the "patient cohort generator 920 analyzes an individual patient's historical changes" (Spec., Para. [0137]); and comparing to a threshold where, "If the historical change(s) satisfies the threshold change, the patient cohort generator 920 labels the patient as sensitive" (Spec., Para. [0138]). Amended claim 8 adds categorizing patients "based on current metabolic states" (Spec., Para. [0141]). These are all abstracts’ steps data-filtering and analysis techniques.
Physical Experiment & Data Input (Claims 9-10, 18-19): These claims add steps such as generating instructions for a physical experiment, where the "physical experiment generator 950 generates a shortlist of candidate treatment recommendations" (Spec., Para. [0154]), and encoding data into a feature vector, where "inputs…may be encoded into a vector representation" (Spec., Para. [0099]). These are routine pre- and post-processing steps in data analysis and experimental design.
In summary, the additional elements, both individually and as an ordered combination, do not supply an inventive concept. They amount to nothing more than the performance of well-understood, routine, and conventional activities in the field of data analysis, performed on a generic computer. The claims therefore do not amount to "significantly more" than the abstract idea of collecting, analyzing, and predicting information.
Conclusion
For the foregoing reasons, claims 1-20 are directed to patent-ineligible subject matter under 35 U.S.C. 101.
Claim Rejections - 35 USC § 103
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over US20220044826A1-Schaeffer, and further in view of US20190252079A1-Constantin.
Claims:
1.
Schaeffer teaches, A method comprising:
, identifying an intervention parameter in a treatment recommendation for causing a target improvement in ; (See at least, par. 0238), Schaeffer teaches a treatment with an intervention parameter rule as anastrozal with lotinib medication therapy to improve probability PFS in 12 months.
based on correlations between changes generating, from a population of patients, a cohort of patients sensitive to the intervention parameter, in the ; Schaeffer, teaches in par. 0005 and par. 0238 a cohort according to certain treatment.
separating the cohort of patients into a control cohort comprising a first subset of patients and a test cohort comprising a second subset of patients; (See at least, 00303, 0005, 0008), Schaeffer teaches a control and treatment cohort.
and determining an effect of the treatment recommendation on the cohort of patients, the determination comprising:
for each patient of the test cohort, inputting the treatment recommendation into a patient-specific ; (Schaeffer, par. 0005-0008, 0157-0158, 0172-0173)
Schaeffer describes a prediction framework that analyzes individual patients within a defined population, using a model that processes patient-specific data, including treatments, to forecast an expected outcome such as survival or response for each patient. This is disclosed where Schaeffer describes a system to predict an expected response of a particular patient population or cohort when provided with a certain treatment and performs operations for each of the plurality of patients (for each patient of the test cohort). Schaeffer further details using a prediction model implemented based on information about the patients' medical history and treatments (inputting the treatment recommendation into a patient-specific model). Finally, Schaeffer states an objective is determining the likelihood of each patient surviving longer than Y years, which constitutes an individual predicted effect (to generate an individual predicted effect of the treatment on the patient).
determining a representative effect of the treatment recommendation for the test cohort based on the generated individual predicted effects for the test cohort; (Schaeffer, par. 0005-0008, 0126, 0129)
Schaeffer discloses calculating an aggregate outcome for a patient group that is derived from the individual data points of the patients within that group. This is taught where Schaeffer’s system is designed to predict an expected response of a particular patient population or cohort when provided with a certain treatment, which constitutes determining a representative effect for the test cohort. This representative effect is based on individual predicted effects, as Schaeffer further describes processes such as calculating an average survival rate for the cohort of patients and generating time until event… curves… for sub-groups of the filtered cohort of interest, both of which are aggregate metrics (representative effects) necessarily derived from the individual outcomes and data of each patient constituting the cohort.and comparing the representative effect for the test cohort to representations of (Scheffer, par. 0005-0007, 0126, 0139-0142, 0303)
This limitation is explicitly taught by Schaeffer, which describes multiple ways of comparing a specific cohort's results against a baseline or control group.
In summarize Schaeffer teaches all limitations of evaluating treatment efficacy through comparative analysis of predicted treatment outcomes against a control group, except for the specificity of metabolic status and model. However, Constantin invention is for diabetic a metabolic health disease (refer to abstract Constantin) and by first real-time datum associated with a patient, determining a state of the patient (Refer to par. 0010, 0532). Therefore, describe a model that predictive a metabolic state for a patient. It therefore would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to add in Schaeffer invention the Constantin specificity metabolic state and model to provide support for treatment decision-making (refer to par. 0002 Constantin). Schaeffer also speak about metabolic panels paragraph 0391, that is a rational to combine Schaeffer with Constantin to develop a specific in a metabolic state improvement.
2.
Schaeffer in further view of Constantin teaches, The method of claim 1, wherein generating the cohort of patients further comprises: accessing patient data for the population of patients, the patient data comprising labels describing the sensitivity of each patient of the population of patients to the intervention parameter; (See at least, [par.0125, 0324], Schaeffer describes retrieving patient data that includes pre-categorized disease response information. The combination of retrieving pre-categorized data and selecting based on that data describes the limitation.) and generating the cohort of patients based on patients sensitive to the intervention parameter in the treatment recommendation based on the accessed patient data. (See at least, [abstract, 0005, 0324, 0358], Schaeffer describes the way to select the patients, based on specific feature that could be easy substitute with treatment for example and sensitivity.)
3.
Schaeffer in further view of Constantin teaches, The method of claim 2, wherein assigning the label describing the sensitivity of a patient to the intervention parameter to the patient comprises: determining historical changes in a metabolic state of the patient caused by previous adjustments to the intervention parameter; (See at least, [0251, 0324, 0152], Schaeffer describes the uses historical patient data, specifically “disease response” labels derived from physician notes and medical records, to categorize patients based on their sensitivity to past treatments. ) and assigning the patient to either a first subset of patients sensitive to the intervention parameter or a second subset of patients insensitive to the intervention parameter based the historical changes. (See at least, [0152, 0324]-Schaeffer)
4.
Schaeffer in further view of Constantin teaches, The method of claim 3, further comprising: comparing the historical changes in the metabolic state to a threshold change; (See at least, [0152, 0136], Schaeffer describe a threshold-based comparison “survival time to a particular time” to assign patients to one of two subgroups.)
5.
Schaeffer in further view of Constantin teaches, The method of claim 1, wherein generating the cohort of patients further comprises: identifying, from the population of patients, a subset of patients whose metabolic state is below a threshold metabolic state; (See at least, [0152, 0358, 0324], The Schaeffer paragraphs describe selecting patient who did not survive with a particular time (Threshold). This “not surviving” is a below a threshold. This selection forms a subgroup which, is equivalent to a cohort that are generated based on specific features and values. and generating the cohort of patients from the identified subset of the population of patients. (See at least, [0324-Schaeffer])
6.
Schaeffer in further view of Constantin teaches, The method of claim 1, wherein generating the cohort of patients further comprises: determining a long-term effect of adjustments to the intervention parameter on each patient of the population of patients based on historical changes in the metabolic state of the patient; (See at least, [0002, 0324, 0136, 0152-Schaeffer], Schaeffer analyzes historical patient data, including treatments and outcomes. It identifies features that have a significant impact on prediction, and these features can include past treatments. The system evaluates levels of response and uses time periods in its analysis, indicating an assessment of lasting impact. The disease response categories are direct measures of the impact of treatments of patient data.)
and generating the cohort of patients based on the long-term effect of adjustments to the intervention parameter determined for each patient of the population of patients. (See at least, [0152, 0324, 0136, 0160], Schaeffer describes creating subgroups of patients. This subgroup creation is based on the lasting impact of past events as evidenced by the use of survival time, Disease response categories and survival profile. The system evaluates each patient’s outcome individually to determine a subgroup membership.)
7.
Schaeffer in further view of Constantin teaches, The method of claim 1, wherein the treatment recommendation comprises instructions or adjusting a plurality of intervention parameters and generating the cohort of patients comprises: for each patient of the population of patients, determining a sensitivity of each patient to each intervention parameter of the plurality; (See at least, [0358, 0107, 0369, 0324, 00002, 0363, 0107], Schaeffer allows the user to select multiple criteria and features. These criteria can include various aspects of treatment. Selecting different values for these features is equivalent to “adjusting a plurality of intervention parameters. Also, the outcome category, includes sub-categories.) and determining an overall sensitivity of the patient to the treatment recommendation based on the sensitivity of the patient to each intervention parameter of the plurality; (See at least, [par. 0136, 0160, 0152, 0270]: Schaeffer analyzing how different combinations of factors affect patient outcomes. The process of creating subgroups and determining differences in survival inherently involves combining the effects of multiple factors. The ability to work with unlabeled data and various machine learning algorithms, add flexibility in how this combination is performed and the greatest weight it is implies an overall sensitivity.) and generating the cohort of patients based on the overall sensitivity of each patient of the population of patients. (See at least, [par. 0387, 0152], Schaeffer is designed to generate cohorts based on selected criteria. Overall sensitivity can be established as a criterion as established in previous limitations, then the system can generate a cohort based on it.)
8.
Schaeffer in further view of Constantin teaches, The method of claim 1, wherein generating the cohort of patients comprises: categorizing the population of patients into categories of patients with a shared metabolic state; (See at least, [par. 0233-0234,], Schaeffer categorizes patients using similarity metrics and dimensionality reduction, which aligns with categorizing patients. ) for each category of patients, predicting an effect of the treatment recommendation on each patient of the category by inputting the treatment recommendation to a patient-specific metabolic model of the patient; (See at least, [par. 0218,-0219], Schaeffer describes a predictive model trained on patient-specific features. ) and determining an overall sensitivity of the category of patients to the treatment recommendation based on the predicted effect of the treatment recommendation on each patient of the category; (See at least, [par. 0232], Schaeffer describes measuring patient similarity through decision trees.) and determining a category of patients most sensitive to the treatment recommendation based on a comparison of the overall sensitivity of each category of patients; (See at least, [par. 0228-0230 ], Schaeffer describes selecting features that create the most significant differences between patient groups. ) and generating the cohort of patients based on the category of patients most sensitive to the treatment recommendation. (See at least, [par.0229-0230], Schaeffer describes forming patient subgroups based on distinguishing features, which aligns with generating a patient cohort using the most responsive category)
9.
Schaeffer in further view of Constantin teaches, The method of claim 1, further comprising: determining that the effect of the treatment recommendation on the cohort of patients satisfies a threshold improvement in a metabolic state of each patient of the cohort of patients; (See at least, [0387, 0390-0391, 0394], Schaeffer describes a system that determines a treatment effect by identifying and analyzing patient cohorts based on predefined health criteria, aligning with determining the impact of treatment recommendations. Schaeffer quantifies the effect of genetic variations on disease states, which is analogous to assessing whether a treatment leads to a threshold improvement in health.) and generating instructions for performing a physical experiment to validate the treatment recommendation. (See at least, [par. 0418, 0421, 0436-0437], Schaeffer describes generating reports and patient similarity indicators for clinical trials.)
10.
Schaeffer in further view of Constantin teaches, The method of claim 1, wherein determining the effect of the treatment recommendation on the cohort of patients further comprises: encoding a feature vector representation of the treatment recommendation; (See at least, [par. 0218],Schaeffer describes a system where treatment predictions are generated using machine learning based on structured patient features analogous to feature vector representation of the treatment recommendation.) and inputting the feature vector representation to the patient-specific metabolic model of each patient of the test cohort. (See at least, [0265, 0220], Schaeffer maps medical treatment features into structured categories for predictive analytics, which aligns with inputting a feature vector representation into a patient-specific model.)
11.
Schaeffer in further view of Constantin teaches, A non-transitory computer readable medium storing instructions encoded thereon that, when executed by a processor, cause the one or more processors to:
identify an intervention parameter in a treatment recommendation for causing a target improvement in (See at least, [par. 0434, 0439, 0238], Schaeffer describes a system where processes are executed via computer-readable instructions stored on non-transitory media.) Schaeffer teaches a treatment with an intervention parameter rule as anastrozal with lotinib medication therapy to improve probability PFS in 12 months.
generate, from a population of patients, a cohort of patients sensitive to the intervention parameter based on correlations between changes in the (Schaeffer, teaches in par. 0005 and par. 0238 a cohort according to certain treatment. A person of ordinary skill in the art will be find obviousness to combine Schaeffer with Constantin. Because Constantin has a metabolic modeling see par. 0123 and 0301 where treat is adjustment according to past data and Schaeffer the concept of cohort to improve analyze the data quickly, efficiently, and comprehensively [par.0004-Schaeffer].
separate the cohort of patients into a control cohort comprising a first subset of patients and a test cohort comprising a second subset of patients; Schaeffer teaches a control and treatment cohort in par. 00303.
and determine an effect of the treatment recommendation on the cohort of patients, the instructions for determining the effect of the treatment recommendation further comprise instructions that cause the processor to:
for each patient of the test cohort, inputting the treatment recommendation into a patient-specific metabolic model to generate an individual predicted effect of the treatment on the patient; (Schaeffer, par. 0005-0006, 0008,)
This limitation is explicitly taught by Schaeffer, which describes a system designed for the exact purpose of predicting how a defined group of patients ("cohort") will respond to a specific "treatment."
determining a representative effect of the treatment recommendation for the test cohort based on the generated individual predicted effects for the test cohort; (Schaeffer, par. 0005-0007, 0126)
This limitation is explicitly taught by Schaeffer. The reference states its purpose is to "predict an expected response of a particular patient population or cohort," which is synonymous with determining a "representative effect."
and comparing the representative effect for the test cohort to representations of metabolic states in the control cohort. (Scheffer, par. 0005-0007, 0126, 0139-0142, 0303)
This limitation is explicitly taught by Schaeffer, which describes multiple ways of comparing a specific cohort's results against a baseline or control group.
In summarize Schaeffer teaches all limitations of evaluating treatment efficacy through comparative analysis of predicted treatment outcomes against a control group, except for the specificity of metabolic status and model. However, Constantin invention is for diabetic a metabolic health disease (refer to abstract Constantin) and by first real-time datum associated with a patient, determining a state of the patient (Refer to par. 0010, 0532). Therefore, describe a model that predictive a metabolic state for a patient. It therefore would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to add in Schaeffer invention the Constantin specificity metabolic state and model to provide support for treatment decision-making (refer to par. 0002 Constantin). Schaeffer also speak about metabolic panels paragraph 0391, that is a rational to combine Schaeffer with Constantin to develop a specific in a metabolic state improvement.
12.
Schaeffer in further view of Constantin teaches, The non-transitory computer readable medium of claim 11, wherein instructions for generating the cohort of patients further comprise instructions that cause the processor to: access patient data for the population of patients, the patient data comprising labels describing the sensitivity of each patient of the population of patients to the intervention parameter; (See at least, [par.0125, 0324], Schaeffer describes retrieving patient data that includes pre-categorized disease response information. The combination of retrieving pre-categorized data and selecting based on that data describes the limitation.) and generate the cohort of patients based on patients sensitive to the intervention parameter in the treatment recommendation based on the accessed patient data. (See at least, [abstract, 0005, 0324, 0358], Schaeffer describes the way to select the patients, based on specific feature that could be easy substitute with treatment for example and sensitivity.)
13.
Schaeffer in further view of Constantin teaches, The non-transitory computer readable medium of claim 12, wherein assigning the label describing the sensitivity of a patient to the intervention parameter to the patient further comprise instructions that cause the processor to: determine historical changes in a metabolic state of the patient caused by previous adjustments to the intervention parameter; (See at least, [0251, 0324, 0152], Schaeffer describes the uses historical patient data, specifically “disease response” labels derived from physician notes and medical records, to categorize patients based on their sensitivity to past treatments. ) and assign the patient to either a first subset of patients sensitive to the intervention parameter or a second subset of patients insensitive to the intervention parameter based the historical changes. (See at least, [0152, 0136], Schaeffer describe a threshold-based comparison “survival time to a particular time” to assign patients to one of two subgroups.)
14.
Schaeffer in further view of Constantin teaches, The non-transitory computer readable medium of claim 11, wherein instructions for generating the cohort of patients further comprise instructions that cause the processor to:
identify, from the population of patients, a subset of patients whose metabolic state is below a threshold metabolic state; ((See at least, [0152, 0358, 0324], The Schaeffer paragraphs describe selecting patient who did not survive with a particular time (Threshold). This “not surviving” is a below a threshold. This selection forms a subgroup which, is equivalent to a cohort that are generated based on specific features and values. and generate the cohort of patients from the identified subset of the population of patients. (See at least, [0324-Schaeffer])
15.
Schaeffer in further view of Constantin teaches, The non-transitory computer readable medium of claim 11, wherein instructions for generating the cohort of patients further comprise instructions that cause the processor to: determine a long-term effect of adjustments to the intervention parameter on each patient of the population of patients based on historical changes in the metabolic state of the patient; (See at least, [0002, 0324, 0136, 0152-Schaeffer], Schaeffer analyzes historical patient data, including treatments and outcomes. It identifies features that have a significant impact on prediction, and these features can include past treatments. The system evaluates levels of response and uses time periods in its analysis, indicating an assessment of lasting impact. The disease response categories are direct measures of the impact of treatments of patient data.)
and generate the cohort of patients based on the long-term effect of adjustments to the intervention parameter determined for each patient of the population of patients. (See at least, [0152, 0324, 0136, 0160], Schaeffer describes creating subgroups of patients. This subgroup creation is based on the lasting impact of past events as evidenced by the use of survival time, Disease response categories and survival profile. The system evaluates each patient’s outcome individually to determine a subgroup membership.)
16.
Schaeffer in further view of Constantin teaches, The non-transitory computer readable medium of claim 11, wherein the treatment recommendation comprises instructions or adjusting a plurality of intervention parameters and instructions for generating the cohort of patients further comprise instructions that cause the processor to: for each patient of the population of patients, determine a sensitivity of each patient to each intervention parameter of the plurality; (See at least [par. 0069], The digital twin module 450 uses machine-learned metabolic models to predict the effects of various patient data aspects (symptoms, lifestyle, nutrition) on metabolic state. It aggregates these predictions to create a holistic view of the patient's metabolic state. This anticipates the limitation by determining each patient's sensitivity to multiple intervention parameters and generating a cohort based on overall sensitivity.)
and determine an overall sensitivity of the patient to the treatment recommendation based on the sensitivity of the patient to each intervention parameter of the plurality; (See at least, [par. 0171], "The TAC score generator 1140 computes a numerical TAC score based on a patient's progress completing outlined objectives." This indicates that using all previously determined sensitivity values, the processor calculates an overall responsiveness score for each patient related to the entire treatment recommendation.) and generate the cohort of patients based on the overall sensitivity of each patient of the population of patients (See at least, [par. 0387, 0152], Schaeffer is designed to generate cohorts based on selected criteria. Overall sensitivity can be established as a criterion as established in previous limitations, then the system can generate a cohort based on it.)
17.
Schaeffer in further view of Constantin teaches, The non-transitory computer readable medium of claim 11, wherein instructions for generating the cohort of patients further comprise instructions that cause the processor to: categorize the population of patients into categories of patients with a shared metabolic state; (See at least, [par. 0233-0234,], Schaeffer categorizes patients using similarity metrics and dimensionality reduction, which aligns with categorizing patients. ) for each category of patients, predicting an effect of the treatment recommendation on each patient of the category by inputting the treatment recommendation to a patient-specific metabolic model of the patient; (See at least, [par. 0218,-0219], Schaeffer describes a predictive model trained on patient-specific features. ) and determining an overall sensitivity of the category of patients to the treatment recommendation based on the predicted effect of the treatment recommendation on each patient of the category; (See at least, [par. 0232], Schaeffer describes measuring patient similarity through decision trees.) and determining a category of patients most sensitive to the treatment recommendation based on a comparison of the overall sensitivity of each category of patients; (See at least, [par. 0228-0230 ], Schaeffer describes selecting features that create the most significant differences between patient groups. ) and generating the cohort of patients based on the category of patients most sensitive to the treatment recommendation. (See at least, [par.0229-0230], Schaeffer describes forming patient subgroups based on distinguishing features, which aligns with generating a patient cohort using the most responsive category)
18. Schaeffer in further view of Constantin teaches, The non-transitory computer readable medium of claim 11, wherein instructions for generating the cohort of patients further comprise instructions that cause the processor to: determine that the effect of the treatment recommendation on the cohort of patients satisfies a threshold improvement in a metabolic state of each patient of the cohort of patients; (See at least, [0387, 0390-0391, 0394], Schaeffer describes a system that determines a treatment effect by identifying and analyzing patient cohorts based on predefined health criteria, aligning with determining the impact of treatment recommendations. Schaeffer quantifies the effect of genetic variations on disease states, which is analogous to assessing whether a treatment leads to a threshold improvement in health.) and generating instructions for performing a physical experiment to validate the treatment recommendation. (See at least, [par. 0418, 0421, 0436-0437],