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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 03/13/2026 has been entered.
Status of Amendments
Claims 1-16 and 18-20 are currently pending in this case and have been
examined and addressed below. This communication is a Non-Final Rejection in response to the Amendment to the Claims and Remarks filed on 03/13/2026.
• Claims 1, 11, 18, 19, and 20 are amended claims.
• Claims 7 and 14-16 are original claims.
• Claims 2-6, 8-10, and 12-13 are previously presented.
• Claims 17 have been cancelled and will not be considered at this time.
Claim Rejections - 35 USC § 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 1-16 and 18-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to a judicial exception (i.e. an abstract idea) without significantly more.
Step 1 – Statutory Categories of Invention:
Claims 1 and 18-20 are drawn to methods, a system, and an article of manufacture, which are statutory categories of invention.
Step 2A – Judicial Exception Analysis, Prong 1:
Independent claim 1 recite a method comprising: forming an individual patient model based on the first set of individual parameters; determining a matching level between the individual patient model and each of a plurality of different predefined generic patient models, each of the plurality of different predefined generic patient models having a predefined patient risk score; selecting at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold; determining a risk score for the patient based on the selected at least one generic patient model; assigning, based on the risk score, a risk category selected from a plurality of predefined risk categories each associated with a range of risk scores; generating, based on the risk category, record that includes a treatment recommendation specific to the assigned risk category; calculating, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and second set of individual parameters, a patient health progression; and comparing the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model.
Independent claim 18 recite a method comprising forming an individual patient model based on the first set of individual parameters; determining a matching level between the individual patient model and each of a plurality of different predefined generic patient models, each of the plurality of different predefined generic patient models having a predefined patient risk score; selecting at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold; determining a risk score for the patient based on the selected at least one generic patient model; assigning, based on the risk score, a risk category to the patient by comparing the determined risk score for the patient with predefined risk score ranges for each of a low risk category, a medium risk category, and a high-risk category; generating, based on the risk category, record that includes a treatment recommendation specific to the assigned risk category; calculating, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and second set of individual parameters, a patient health progression; and comparing the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model.
Independent claim 19 recite a system comprising forming an individual patient model based on the first set of individual parameters; determining a matching level between the individual patient model and each of a plurality of different predefined generic patient models, each of the plurality of different predefined generic patient models having a predefined patient risk score; selecting at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold; determining a risk score for the patient based on the selected at least one generic patient model; assigning , based on the risk score, a risk category selected from a plurality of predefined risk categories each associated with a range of risk scores; generating, based on the risk category, record that includes a treatment recommendation specific to the assigned risk category; calculating, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and second set of individual parameters, a patient health progression; and compare the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model.
Independent claim 20 recite a method comprising forming an individual patient model based on the first set of individual parameters; determining a matching level between the individual patient model and each of a plurality of different predefined generic patient models, each of the plurality of different predefined generic patient models having a predefined patient risk score; selecting at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold; determining a risk score for the patient based on the selected at least one generic patient model; assigning , based on the risk score, a risk category selected from a plurality of predefined risk categories each associated with a range of risk scores; generating, based on the risk category, record that includes a treatment recommendation specific to the assigned risk category; calculating, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and second set of individual parameters, a patient health progression; and comparing the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model.
These steps amount to certain methods of organizing human activity which includes functions relating to managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions) (MPEP § 2106.04(a)(2)(II)(C) citing the abstract idea grouping for methods of organizing human activity for managing personal behavior or relationships or interactions between people – also note MPEP § 2106.04(a)(2)(II) stating certain activity between a person and a computer may fall within the “certain methods of organizing human activity” grouping).
Step 2A – Judicial Exception Analysis, Prong 2:
This judicial exception is not integrated into a practical application because the additional elements within the claims only amount to instructions to implement the judicial exception using a computer [MPEP 2106.05(f)].
The claims recite a computing device, stored in the memory, a digital record, computer system, computer program product, and the non-transitory computer readable medium.
These elements are recited at a high-level of generality such that it amounts to mere instructions to apply the exception because this is an example of applying the abstract idea by use of general-purpose computer which does not integrate the abstract idea into a practical application.
Claims 1 and 18-20 recite receiving, at a computing device, a first set of
individual parameters indicative of a present or a previous state of a patient and
receiving, at the computing device, a second set of individual parameters indicative of a
state of the patient after administration of the recommended treatment. The limitations
are only recited as a tool which only serves to input data for use by the abstract idea
(MPEP § 2106.05(g) - insignificant pre/post-solution activity that amounts to mere data
gathering to obtain input) and is therefore not a practical application of the recited
judicial exception.
Claims 1 and 18-20 recite updating, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models. This limitation amounts to mere instructions to apply the exception because a mathematical algorithm applied on a general-purpose computer has been found by the courts to be mere instructions to apply as in MPEP 2106.05(f)(2).
The above claims, as a whole, are therefore directed to an abstract idea.
Step 2B – Additional Elements that Amount to Significantly More:
The present claims do not include additional elements that are sufficient to amount to more than the abstract idea because the additional elements or combination of elements amount to no more than a recitation of instructions to implement the abstract idea on a computer.
As discussed above with the respect to integration of the abstract idea into a
practical application, the additional elements of a computing device, stored in the memory, updating, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models. computer system, computer program product, and the non-transitory computer readable medium amounts to no more than mere instructions to apply the exception using a generic computing component.
Claims 1 and 18-20 recite receiving, at a computing device, a first set of
individual parameters indicative of a present or a previous state of a patient and
receiving, at the computing device, a second set of individual parameters indicative of a
state of the patient after administration of the recommended treatment. The courts have decided that receiving or transmitting data over a network as well-understood, routine, conventional activity when claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity (MPEP § 2106.05(d)(II) other types of activities example i. receiving or transmitting data over a network, OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network).
Thus, taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. Their collective functions merely provide conventional computer implementation to amount to significantly more than the recited judicial exception.
For the reasons stated, these claims are consequently rejected under 35 U.S.C. § 101.
Analysis of Dependent Claims
Dependent claim 2 merely describes wherein selecting the at least one generic patient model of the plurality of different predefined generic patient models having the matching level above the predetermined threshold comprises selecting the at least one generic patient model having a highest matching level.
Dependent claim 3 merely describes wherein the risk score is determined based on a combination of at least two selected generic patient models of the plurality of different predefined generic patient models.
Dependent claim 4 merely describes where each of the at least two selected generic patient models have a weight to be applied when determining the risk score.
Dependent claim 5 merely describes wherein the first set of individual parameters comprise a plurality of the patient's clinical data collected over a predetermined time period.
Dependent claim 6 merely describes wherein the plurality of the patient's clinical data comprises at least patient vitals, number of hospitalizations, laboratory results, and prescribed medications.
Dependent claim 7 merely describes wherein the patient vitals comprise at least one of heart rate data, electrocardiograph (EKG/ECG) data, respiration rate data, patient temperature data, pulse oximetry data, and blood pressure data.
Dependent claim 10 recites wherein the recommended treatment for the patient is only formed if the patient has been assigned the high-risk category.
Dependent claim 11 recites wherein, based on the result of the comparison indicating that the patient health progression deviates from the predefined health progression defined for the selected at least one generic patient model, the updating comprises forming a new generic patient model of the plurality of different predefined generic patient models, the new generic patient model being based on the patient health progression.
Dependent Claim 12 merely describes updating a predefined generic patient model of the plurality of different predefined generic patient models based on a combination of the determined individual patient model and a result of the predefined health progression comparison.
Each of these steps of the preceding dependent claims 2-12 only serve to further limit or specify the features of independent claims 1 accordingly, and hence are nonetheless directed towards fundamentally the same abstract idea as the independent claim.
Dependent claim 8 merely describes defining, using the computing device, a low-risk category, a medium risk category, and a high-risk category, and determining, using the computing device, the risk category by comparing the determined risk score for the patient with predefined risk score ranges for the each of the low-risk category, the medium risk category and the high-risk category. The computing device is an additional element, which is mere instructions to apply the exception and does not provide a practical application or significantly more for the same reasons.
Dependent claim 9 recites forming, using the computing device, the recommended treatment for the patient, wherein the recommended treatment is different for the each of the low risk category, the medium risk category and the high-risk category. The computing device is an additional element, which is mere instructions to apply the exception and does not provide a practical application or significantly more for the same reasons.
Dependent claim 13 merely describes updating the predefined generic patient model of the plurality of different predefined generic patient models comprises applying a machine learning process. The applying a machine learning process is an additional element, which is mere instructions to apply the exception and does not provide a practical application or significantly more for the same reasons.
Dependent claim 14 merely describes wherein the machine learning process is an unsupervised machine learning process. The unsupervised machine learning process is an additional element, which is mere instructions to apply the exception and does not provide a practical application or significantly more for the same reasons.
Dependent claim 15 merely describes wherein the machine learning process is a supervised machine learning process. The supervised machine learning process is an additional element, which is mere instructions to apply the exception and does not provide a practical application or significantly more for the same reasons.
Dependent claim 16 merely describes wherein the machine learning process is based on a convolutional neural network (CNN) or a recurrent neural network (RNN). The convolutional neural network (CNN) or a recurrent neural network (RNN) is an additional element, which is mere instructions to apply the exception and does not provide a practical application or significantly more for the same reasons.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-2, 5, 8, and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Swartz (US 20180165418 A1) in view of Yu (US 20200126636 A1) in view of Schmidt (US 20180075207 A1) in view of Albright (US 20190272922 A1).
As per Claim 1, Swartz teaches a method comprising:
receiving, at a computing device, a first set of individual parameters indicative of a present or a previous state of a patient, ([Para. 0012] Certain data collected by the system relate to factors that directly characterize the current or past health of an individual. For example, the collected data may be objective measures of the individual's heart rate, blood pressure, blood sugar level, length of sleep, etc. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. Examiner interprets the data processor to be indicative of the control unit. [Para. 0046] The environment may include one or more client computing devices 205.)
forming, using the computing device, an individual patient model based on the first set of individual parameters, ([Para. 0012] Data about the different types of factors monitored by the system, whether direct or contextual, are captured by the system over time and used to generate the health vector that characterizes the individual. Examiner interprets health vector to be indicative of individual patient model. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
determining, using the computing device, a matching level between the individual patient model and each of a plurality of different predefined generic patient models stored in a memory, each of the plurality of different predefined generic patient models having a predefined patient risk score, ([Para. 0055] the system retrieves population cohorts. Each cohort is characterized by a cohort health vector and includes health vectors and health score trends of the population members of the cohort. [Para. 0056] The system identifies the cohorts for which the associated cohort health vectors are within a certain proximity to the received individual health vector. Such a comparison may be made, for example, by calculating a sum total of the squares of the distance or difference between each of the factors making up the health vector. In making such calculation, each of the factor ranges may be normalized to a scale that allows a comparison between factors. [Para. 0058] For the evaluated factors, the proximity check determines whether the aggregate distance between each of the cohort health vectors and the individual health vector falls within a threshold distance. The system may identify a cohort health vector as satisfying the proximity check when all of its evaluated factors, when summed, are within a threshold distance from the evaluated factors of the individual health vector. [Para. 0060] every population cohort includes the health score trends (i.e. predefined patient risk score) of the cohort members. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
selecting, using the computing device, at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold, ([Para. 0058] For the evaluated factors, the proximity check determines whether the aggregate distance between each of the cohort health vectors and the individual health vector falls within a threshold distance. The system may identify a cohort health vector as satisfying the proximity check when all of its evaluated factors, when summed, are within a threshold distance from the evaluated factors of the individual health vector. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
determining, using the computing device, a risk score for the patient based on the selected at least one generic patient model; ([Para. 0033] The health assessment model generates an indication of an individual's level of healthiness or unhealthiness (e.g., on a spectrum from very healthy to very unhealthy) based on one or more of the individual's health vector, the individual's health vector change and the health vectors of the members in the cohorts associated with the individual. The health score of an individual may be represented by a value, such as from +100 to −100, that corresponds to strongly healthy and strongly unhealthy, respectively. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
Swartz does not explicitly teach, however Yu teaches
receiving, at the computing device, a second set of individual parameters indicative of a state of the patient after administration of the recommended treatment; ([Para. 0022] determining second concentrations of multiple clinicopathological markers (i.e. second set of individual parameters) of the patient. [Para. 0029] execution by a computing device.)
calculating, using the computing device, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and the second set of individual parameters, a patient health progression. ([Para. 0022] providing, to a gradient boosting machine learning model, the determined second concentrations of the multiple clinicopathological markers; g) receiving, from the gradient boosting machine learning model, a second prediction of whether the patient has poor immune fitness; and h) administering an anticancer therapeutic to the patient if the prediction indicates that the patient does not have poor immune fitness. [Para. 0029] execution by a computing device. Examiner interprets the patient health progression to be indicated by the administering of the anticancer therapeutic because it is only given when the patient does not have poor immune fitness.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, with the motivation of better informing the appropriate treatment for their individual clinical state (Yu Para. 0005).
Swartz/ Yu do not explicitly teach, however Schmidt teaches
assigning, using the computing device based on the risk score, a risk category selected from a plurality of predefined risk categories each associated with a range of risk scores; ([Para. 0025] a processor (i.e. computing device). [Para. 0037] an assignment of a wellness score for each new candidate in the group, and classifying the candidates into a hierarchy of risk levels based on the wellness scores. [Para. 0114] patient risk stratification can include processing a group of clinical factors, lifestyle factors, and medication compliance factors, for each patient of a population; classifying the population of patients into a hierarchy of risk levels; and assigning a health risk status (a wellness score) to each patient of the population, which is based on the group of factors.[Para. 0145] The integrator computer module 908 can be configured to perform triage on a large group of new candidates, which can include the steps of performing a health risk assessment for each new candidate in the group, which results in an assignment of a wellness score for each new candidate in the group; and classifying the group of new candidates into a hierarchy of risk levels based on the wellness score for each candidate.)
generating, based on the risk category, a digital record that includes a treatment recommendation specific to the assigned risk category; ([Para. 0032] determining an optimum DPP and/or DPP provider for which the candidate is likely to succeed, from among many DPP providers with essentially the same content, based on matching a candidate's success metrics with ideal participant profiles associated with various DPP providers and programs. [Para. 0145] The integrator computer module 908 can be configured to perform triage on a large group of new candidates, which can include the steps of performing a health risk assessment for each new candidate in the group, which results in an assignment of a wellness score for each new candidate in the group; and classifying the group of new candidates into a hierarchy of risk levels based on the wellness score for each candidate. [Para. 0176-177] The method can include accessing the wellness score of the patient; accessing medical records of the patient; combining the wellness score and the medical record with demographic and socioeconomic characteristics for the patient; and creating a comprehensive patient profile. The method can include mapping the comprehensive patient profile over a group of disease prevention program providers qualified to deliver the disease prevention program; determining the optimal disease prevention program provider for the patient; and enrolling the patient with the optimal disease prevention program provider.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, with the motivation of provides a risk stratification system to prioritize chronic disease and lifestyle interventions for patients with multiple risk factors (Schmidt Para. 0009).
Swartz/ Yu/ Schmidt do not explicitly teach, however Albright teaches
comparing, using the computing device, the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model; ([Para. 0031] a machine-learning algorithm that uses current and past clinical data in order to accurately and precisely predict the future onset of MCI and dementia for individual patients, thus enabling early identification of those having high risk for Alzheimer's disease, and who are therefore also good candidates for clinical trials for Alzheimer's disease therapeutics. That is, current and past clinical data from patients may be obtained (e.g., from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database) and processed using a novel “All-Pairs” technique, which compares all possible pairs of temporal data points for each patient. This data can then be used to train various machine learning models. (Notably, the models were evaluated using 7-fold cross-validation on the training dataset and confirmed using data from a separate testing dataset—A neural network model was effective (mAUC=0.866) at predicting the progression of Alzheimer's disease on a month-by-month basis, both in patients who were initially cognitively normal and in patients suffering from mild cognitive impairment.))
updating, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models; ([Para. 0034] Machine learning techniques have been applied to the diagnosis of Alzheimer's disease patients with great success. For example, using 3D convolutional neural networks to diagnose Alzheimer's disease achieved an accuracy of 94.1% on a dataset with 841 patients. [Para. 0059] The training and testing of neural networks, as well as the cross-validation process, relies to some extent on algorithms that utilize random numbers, the scores in the table below will change slightly each time that the models are subjected to cross-validation.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, and incorporate machine-learning based forecasting of disease progression as taught by Albright, with the motivation of providing ways to treat the disease, delay its onset, and prevent it from developing (Albright Para. 0004).
As per Claim 2, Swartz/ Yu/ Schmidt/ Albright teach the method according to claim 1, Swartz further teaches wherein selecting the at least one generic patient model of the plurality of different predefined generic patient models having the matching level above the predetermined threshold comprises selecting the at least one generic patient model having a highest matching level. ([Para. 0015] The health recommendations system uses the health vector of an individual to identify cohorts of similar people. On a periodic or continuous basis the system constructs population cohorts of individuals monitored by the system. The different population cohorts may be constructed, for example, based on unsupervised clustering of the individual health vectors of the population. [Para. 0037] the system constructs population cohorts periodically, and separately identifies the cohorts most closely associated with the individual when the individual's health vector is extended.)
As per Claim 5, Swartz/ Yu/ Schmidt/ Albright teach the method according to claim 1, Swartz further teaches wherein the first set of individual parameters comprise a plurality of the patient's clinical data collected over a predetermined time period. ([Para. 0012] Certain data collected by the system relate to factors that directly characterize the current or past health of an individual. For example, the collected data may be objective measures of the individual's heart rate, blood pressure, blood sugar level, length of sleep, etc. Data about the different types of factors monitored by the system, whether direct or contextual, are captured by the system over time and used to generate the health vector that characterizes the individual. The size of the health vector increases over time, as additional data characterizing the user is continuously obtained by the system.)
As per Claim 8, Swartz/ Yu/ Schmidt/ Albright teach the method according to claim 1, Schmidt further teaches further comprising defining, using the computing device, a low-risk category, a medium risk category, and a high-risk category, ([Para. 0025] a processor (i.e. computing device) [Para. 0037] The hierarchy of risk levels can include a high health risk level, a medium health risk, and a low health risk. [Para. 0040] Using the wellness score having a range of 1-150 points, the health risk levels of a population can be stratified by risk as follows: high risk level is in the range of 101 to 150 points, medium risk level is in the range of 51 to 100, and a low risk level is in the range of 0 to 50. A wellness score of 150 is the highest possible score and indicates the highest health risk for a patient.)
and determining , using the computing device, the risk category to the patient by comparing the determined risk score for the patient with predefined risk score ranges for the each of the low-risk category, the medium risk category and the high-risk category. ([Para. 0025] a processor (i.e. computing device) [Para. 0114] patient risk stratification can include processing a group of clinical factors, lifestyle factors, and medication compliance factors, for each patient of a population; classifying the population of patients into a hierarchy of risk levels; and assigning a health risk status (a wellness score) to each patient of the population, which is based on the group of factors.[Para. 0145] The integrator computer module 908 can be configured to perform triage on a large group of new candidates, which can include the steps of performing a health risk assessment for each new candidate in the group, which results in an assignment of a wellness score for each new candidate in the group; and classifying the group of new candidates into a hierarchy of risk levels based on the wellness score for each candidate. [Para. 0025] an integrator system including an integrator computer module having a processor. Examiner interprets a processor to be indicative of a control unit.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, machine-learning based forecasting of disease progression as taught by Albright, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, with the motivation of provides a risk stratification system to prioritize chronic disease and lifestyle interventions for patients with multiple risk factors (Schmidt Para. 0009).
As per Claim 18, Swartz teaches a method comprising:
receiving, at a computing device, a first set of individual parameters indicative of a present or a previous state of a patient, ([Para. 0012] Certain data collected by the system relate to factors that directly characterize the current or past health of an individual. For example, the collected data may be objective measures of the individual's heart rate, blood pressure, blood sugar level, length of sleep, etc. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. Examiner interprets the data processor to be indicative of the control unit. [Para. 0046] The environment may include one or more client computing devices 205.)
forming, using the computing device, an individual patient model based on the first set of individual parameters, ([Para. 0012] Data about the different types of factors monitored by the system, whether direct or contextual, are captured by the system over time and used to generate the health vector that characterizes the individual. Examiner interprets health vector to be indicative of individual patient model. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
determining, using the computing device, a matching level between the individual patient model and each of a plurality of different predefined generic patient models, each of the plurality of different predefined generic patient models having a predefined patient risk score, ([Para. 0055] the system retrieves population cohorts. Each cohort is characterized by a cohort health vector and includes health vectors and health score trends of the population members of the cohort. [Para. 0056] the system identifies the cohorts for which the associated cohort health vectors are within a certain proximity to the received individual health vector. Such a comparison may be made, for example, by calculating a sum total of the squares of the distance or difference between each of the factors making up the health vector. In making such calculation, each of the factor ranges may be normalized to a scale that allows a comparison between factors. [Para. 0058] For the evaluated factors, the proximity check determines whether the aggregate distance between each of the cohort health vectors and the individual health vector falls within a threshold distance. The system may identify a cohort health vector as satisfying the proximity check when all of its evaluated factors, when summed, are within a threshold distance from the evaluated factors of the individual health vector. [Para. 0060] every population cohort includes the health score trends (i.e. predefined patient risk score) of the cohort members. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
selecting, using the computing device, at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold, ([Para. 0058] For the evaluated factors, the proximity check determines whether the aggregate distance between each of the cohort health vectors and the individual health vector falls within a threshold distance. The system may identify a cohort health vector as satisfying the proximity check when all of its evaluated factors, when summed, are within a threshold distance from the evaluated factors of the individual health vector. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
determining, using the computing device, a risk score for the patient based on the selected at least one generic patient model, ([Para. 0033] The health assessment model generates an indication of an individual's level of healthiness or unhealthiness (e.g., on a spectrum from very healthy to very unhealthy) based on one or more of the individual's health vector, the individual's health vector change and the health vectors of the members in the cohorts associated with the individual. The health score of an individual may be represented by a value, such as from +100 to −100, that corresponds to strongly healthy and strongly unhealthy, respectively. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
Swartz does not explicitly teach, however Yu teaches
receiving, at the computing device, a second set of individual parameters indicative of a state of the patient after receiving the recommended treatment; ([Para. 0022] determining second concentrations of multiple clinicopathological markers (i.e. second set of individual parameters) of the patient. [Para. 0029] execution by a computing device.)
calculating, using the computing device, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and the second set of individual parameters, a patient health progression ([Para. 0022] providing, to a gradient boosting machine learning model, the determined second concentrations of the multiple clinicopathological markers; g) receiving, from the gradient boosting machine learning model, a second prediction of whether the patient has poor immune fitness; and h) administering an anticancer therapeutic to the patient if the prediction indicates that the patient does not have poor immune fitness. [Para. 0029] execution by a computing device. Examiner interprets the patient health progression to be indicated by the administering of the anticancer therapeutic because it is only given when the patient does not have poor immune fitness.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, with the motivation of better informing the appropriate treatment for their individual clinical state (Yu Para. 0005).
Swartz/ Yu do not explicitly teach, however Schmidt teaches
assigning, using the computing device based on the risk score, a risk category to the patient by comparing the determined risk score for the patient with predefined risk score ranges for the each of the low-risk category, the medium risk category and the high-risk category; ([Para. 0025] a processor (i.e. computing device) [Para. 0114] patient risk stratification can include processing a group of clinical factors, lifestyle factors, and medication compliance factors, for each patient of a population; classifying the population of patients into a hierarchy of risk levels; and assigning a health risk status (a wellness score) to each patient of the population, which is based on the group of factors.[Para. 0145] The integrator computer module 908 can be configured to perform triage on a large group of new candidates, which can include the steps of performing a health risk assessment for each new candidate in the group, which results in an assignment of a wellness score for each new candidate in the group; and classifying the group of new candidates into a hierarchy of risk levels based on the wellness score for each candidate. [Para. 0025] an integrator system including an integrator computer module having a processor.)
generating, based on the risk category, a digital record that includes a treatment recommendation specific to the assigned risk category; ([Para. 0032] determining an optimum DPP and/or DPP provider for which the candidate is likely to succeed, from among many DPP providers with essentially the same content, based on matching a candidate's success metrics with ideal participant profiles associated with various DPP providers and programs. [Para. 0145] The integrator computer module 908 can be configured to perform triage on a large group of new candidates, which can include the steps of performing a health risk assessment for each new candidate in the group, which results in an assignment of a wellness score for each new candidate in the group; and classifying the group of new candidates into a hierarchy of risk levels based on the wellness score for each candidate. [Para. 0176-177] The method can include accessing the wellness score of the patient; accessing medical records of the patient; combining the wellness score and the medical record with demographic and socioeconomic characteristics for the patient; and creating a comprehensive patient profile. The method can include mapping the comprehensive patient profile over a group of disease prevention program providers qualified to deliver the disease prevention program; determining the optimal disease prevention program provider for the patient; and enrolling the patient with the optimal disease prevention program provider.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, with the motivation of provides a risk stratification system to prioritize chronic disease and lifestyle interventions for patients with multiple risk factors (Schmidt Para. 0009).
Swartz/ Yu/ Schmidt do not explicitly teach, however Albright teaches
comparing, using the computing device, the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model; ([Para. 0031] a machine-learning algorithm that uses current and past clinical data in order to accurately and precisely predict the future onset of MCI and dementia for individual patients, thus enabling early identification of those having high risk for Alzheimer's disease, and who are therefore also good candidates for clinical trials for Alzheimer's disease therapeutics. That is, current and past clinical data from patients may be obtained (e.g., from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database) and processed using a novel “All-Pairs” technique, which compares all possible pairs of temporal data points for each patient. This data can then be used to train various machine learning models. (Notably, the models were evaluated using 7-fold cross-validation on the training dataset and confirmed using data from a separate testing dataset—A neural network model was effective (mAUC=0.866) at predicting the progression of Alzheimer's disease on a month-by-month basis, both in patients who were initially cognitively normal and in patients suffering from mild cognitive impairment.))
updating, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models; ([Para. 0034] Machine learning techniques have been applied to the diagnosis of Alzheimer's disease patients with great success. For example, using 3D convolutional neural networks to diagnose Alzheimer's disease achieved an accuracy of 94.1% on a dataset with 841 patients. [Para. 0059] The training and testing of neural networks, as well as the cross-validation process, relies to some extent on algorithms that utilize random numbers, the scores in the table below will change slightly each time that the models are subjected to cross-validation.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, and incorporate machine-learning based forecasting of disease progression as taught by Albright, with the motivation of providing ways to treat the disease, delay its onset, and prevent it from developing (Albright Para. 0004).
As per Claim 19, Swartz teaches a computer system adapted for determining a risk score for a patient, the computer system adapted to:
receive a first set of individual parameters indicative of a present or a previous state of the patient, ([Para. 0012] Certain data collected by the system relate to factors that directly characterize the current or past health of an individual. For example, the collected data may be objective measures of the individual's heart rate, blood pressure, blood sugar level, length of sleep, etc. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. Examiner interprets the data processor to be indicative of the control unit. [Para. 0046] The environment may include one or more client computing devices 205.)
form an individual patient model based on the first set of individual parameters, ([Para. 0012] Data about the different types of factors monitored by the system, whether direct or contextual, are captured by the system over time and used to generate the health vector that characterizes the individual. Examiner interprets health vector to be indicative of individual patient model. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
determine a matching level between the individual patient model and each of a plurality of different predefined generic patient models, each of the plurality of different predefined generic patient models having a predefined patient risk score, ([Para. 0055] the system retrieves population cohorts. Each cohort is characterized by a cohort health vector and includes health vectors and health score trends of the population members of the cohort. [Para. 0056] the system identifies the cohorts for which the associated cohort health vectors are within a certain proximity to the received individual health vector. Such a comparison may be made, for example, by calculating a sum total of the squares of the distance or difference between each of the factors making up the health vector. In making such calculation, each of the factor ranges may be normalized to a scale that allows a comparison between factors. [Para. 0058] For the evaluated factors, the proximity check determines whether the aggregate distance between each of the cohort health vectors and the individual health vector falls within a threshold distance. The system may identify a cohort health vector as satisfying the proximity check when all of its evaluated factors, when summed, are within a threshold distance from the evaluated factors of the individual health vector. [Para. 0060] every population cohort includes the health score trends (i.e. predefined patient risk score) of the cohort members. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
select at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold, ([Para. 0058] For the evaluated factors, the proximity check determines whether the aggregate distance between each of the cohort health vectors and the individual health vector falls within a threshold distance. The system may identify a cohort health vector as satisfying the proximity check when all of its evaluated factors, when summed, are within a threshold distance from the evaluated factors of the individual health vector. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
determine the risk score for the patient based on the selected at least one generic patient model; ([Para. 0033] The health assessment model generates an indication of an individual's level of healthiness or unhealthiness (e.g., on a spectrum from very healthy to very unhealthy) based on one or more of the individual's health vector, the individual's health vector change and the health vectors of the members in the cohorts associated with the individual. The health score of an individual may be represented by a value, such as from +100 to −100, that corresponds to strongly healthy and strongly unhealthy, respectively. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
Swartz does not explicitly teach, however Yu teaches
receive a second set of individual parameters indicative of a state of the patient after administration of the recommended treatment; ([Para. 0022] determining second concentrations of multiple clinicopathological markers (i.e. second set of individual parameters) of the patient. [Para. 0029] execution by a computing device.)
calculate, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and the second set of individual parameters, a patient health progression ([Para. 0022] providing, to a gradient boosting machine learning model, the determined second concentrations of the multiple clinicopathological markers; g) receiving, from the gradient boosting machine learning model, a second prediction of whether the patient has poor immune fitness; and h) administering an anticancer therapeutic to the patient if the prediction indicates that the patient does not have poor immune fitness. [Para. 0029] execution by a computing device. Examiner interprets the patient health progression to be indicated by the administering of the anticancer therapeutic because it is only given when the patient does not have poor immune fitness.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, with the motivation of better informing the appropriate treatment for their individual clinical state (Yu Para. 0005).
Swartz/ Yu do not explicitly teach, however Schmidt teaches
assign, based on the risk score, a risk category to the patient by comparing the determined risk score for the patient with predefined risk score ranges for the each of the low-risk category, the medium risk category and the high-risk category; ([Para. 0025] a processor (i.e. computing device). [Para. 0037] an assignment of a wellness score for each new candidate in the group, and classifying the candidates into a hierarchy of risk levels based on the wellness scores. [Para. 0114] patient risk stratification can include processing a group of clinical factors, lifestyle factors, and medication compliance factors, for each patient of a population; classifying the population of patients into a hierarchy of risk levels; and assigning a health risk status (a wellness score) to each patient of the population, which is based on the group of factors.[Para. 0145] The integrator computer module 908 can be configured to perform triage on a large group of new candidates, which can include the steps of performing a health risk assessment for each new candidate in the group, which results in an assignment of a wellness score for each new candidate in the group; and classifying the group of new candidates into a hierarchy of risk levels based on the wellness score for each candidate.)
generate, based on the risk category, a digital record that includes a treatment recommendation specific to the assigned risk category; ([Para. 0032] determining an optimum DPP and/or DPP provider for which the candidate is likely to succeed, from among many DPP providers with essentially the same content, based on matching a candidate's success metrics with ideal participant profiles associated with various DPP providers and programs. [Para. 0145] The integrator computer module 908 can be configured to perform triage on a large group of new candidates, which can include the steps of performing a health risk assessment for each new candidate in the group, which results in an assignment of a wellness score for each new candidate in the group; and classifying the group of new candidates into a hierarchy of risk levels based on the wellness score for each candidate. [Para. 0176-177] The method can include accessing the wellness score of the patient; accessing medical records of the patient; combining the wellness score and the medical record with demographic and socioeconomic characteristics for the patient; and creating a comprehensive patient profile. The method can include mapping the comprehensive patient profile over a group of disease prevention program providers qualified to deliver the disease prevention program; determining the optimal disease prevention program provider for the patient; and enrolling the patient with the optimal disease prevention program provider.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, with the motivation of provides a risk stratification system to prioritize chronic disease and lifestyle interventions for patients with multiple risk factors (Schmidt Para. 0009).
Swartz/ Yu/ Schmidt do not explicitly teach, however Albright teaches
compare the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model; ([Para. 0031] a machine-learning algorithm that uses current and past clinical data in order to accurately and precisely predict the future onset of MCI and dementia for individual patients, thus enabling early identification of those having high risk for Alzheimer's disease, and who are therefore also good candidates for clinical trials for Alzheimer's disease therapeutics. That is, current and past clinical data from patients may be obtained (e.g., from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database) and processed using a novel “All-Pairs” technique, which compares all possible pairs of temporal data points for each patient. This data can then be used to train various machine learning models. (Notably, the models were evaluated using 7-fold cross-validation on the training dataset and confirmed using data from a separate testing dataset—A neural network model was effective (mAUC=0.866) at predicting the progression of Alzheimer's disease on a month-by-month basis, both in patients who were initially cognitively normal and in patients suffering from mild cognitive impairment.))
update, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models; ([Para. 0034] Machine learning techniques have been applied to the diagnosis of Alzheimer's disease patients with great success. For example, using 3D convolutional neural networks to diagnose Alzheimer's disease achieved an accuracy of 94.1% on a dataset with 841 patients. [Para. 0059] The training and testing of neural networks, as well as the cross-validation process, relies to some extent on algorithms that utilize random numbers, the scores in the table below will change slightly each time that the models are subjected to cross-validation.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, and incorporate machine-learning based forecasting of disease progression as taught by Albright, with the motivation of providing ways to treat the disease, delay its onset, and prevent it from developing (Albright Para. 0004).
As per Claim 20, Swartz teaches a computer program product comprising a non-transitory computer readable medium having stored thereon computer program means for operating a computer system adapted for determining a risk score for a patient, the computer system comprising a computing device, wherein the computer program product comprises: ([Para. 0045] non-transitory computer-readable media. )
code for receiving, at the computing device, a first set of individual parameters indicative of a present or a previous state of the patient, ([Para. 0012] Certain data collected by the system relate to factors that directly characterize the current or past health of an individual. For example, the collected data may be objective measures of the individual's heart rate, blood pressure, blood sugar level, length of sleep, etc. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. Examiner interprets the data processor to be indicative of the control unit. [Para. 0046] The environment may include one or more client computing devices 205.)
code for forming, using the computing device, an individual patient model based on the first set of individual parameters, ([Para. 0012] Data about the different types of factors monitored by the system, whether direct or contextual, are captured by the system over time and used to generate the health vector that characterizes the individual. Examiner interprets health vector to be indicative of individual patient model. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
code for determining, using the computing device, a matching level between the individual patient model and each of a plurality of different predefined generic patient models, each of the plurality of different predefined generic patient models having a predefined patient risk score, ([Para. 0055] the system retrieves population cohorts. Each cohort is characterized by a cohort health vector and includes health vectors and health score trends of the population members of the cohort. [Para. 0056] the system identifies the cohorts for which the associated cohort health vectors are within a certain proximity to the received individual health vector. Such a comparison may be made, for example, by calculating a sum total of the squares of the distance or difference between each of the factors making up the health vector. In making such calculation, each of the factor ranges may be normalized to a scale that allows a comparison between factors. [Para. 0058] For the evaluated factors, the proximity check determines whether the aggregate distance between each of the cohort health vectors and the individual health vector falls within a threshold distance. The system may identify a cohort health vector as satisfying the proximity check when all of its evaluated factors, when summed, are within a threshold distance from the evaluated factors of the individual health vector. [Para. 0060] every population cohort includes the health score trends (i.e. predefined patient risk score) of the cohort members. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
code for selecting, using the computing device, at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold, ([Para. 0058] For the evaluated factors, the proximity check determines whether the aggregate distance between each of the cohort health vectors and the individual health vector falls within a threshold distance. The system may identify a cohort health vector as satisfying the proximity check when all of its evaluated factors, when summed, are within a threshold distance from the evaluated factors of the individual health vector. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
code for determining, using the computing device, the risk score for the patient based on the selected at least one generic patient model;([Para. 0033] The health assessment model generates an indication of an individual's level of healthiness or unhealthiness (e.g., on a spectrum from very healthy to very unhealthy) based on one or more of the individual's health vector, the individual's health vector change and the health vectors of the members in the cohorts associated with the individual. The health score of an individual may be represented by a value, such as from +100 to −100, that corresponds to strongly healthy and strongly unhealthy, respectively. [Para. 0044] system can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computer-executable instructions. [Para. 0046] The environment may include one or more client computing devices 205.)
Swartz does not explicitly teach, however Yu teaches
code for receiving, at the computing device, a second set of individual parameters indicative of a state of the patient after administration of the recommended treatment; ([Para. 0022] determining second concentrations of multiple clinicopathological markers (i.e. second set of individual parameters) of the patient. [Para. 0029] execution by a computing device.)
and code for calculating, using the computing device, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and the second set of individual parameters, a patient health progression. ([Para. 0022] providing, to a gradient boosting machine learning model, the determined second concentrations of the multiple clinicopathological markers; g) receiving, from the gradient boosting machine learning model, a second prediction of whether the patient has poor immune fitness; and h) administering an anticancer therapeutic to the patient if the prediction indicates that the patient does not have poor immune fitness. [Para. 0029] execution by a computing device. Examiner interprets the patient health progression to be indicated by the administering of the anticancer therapeutic because it is only given when the patient does not have poor immune fitness.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, with the motivation of better informing the appropriate treatment for their individual clinical state (Yu Para. 0005).
Swartz/ Yu do not explicitly teach, however Schmidt teaches
code for assigning, using the computing device based on the risk score, a risk category to the patient by comparing the determined risk score for the patient with predefined risk score ranges for the each of the low-risk category, the medium risk category and the high-risk category; ([Para. 0025] a processor (i.e. computing device). [Para. 0037] an assignment of a wellness score for each new candidate in the group, and classifying the candidates into a hierarchy of risk levels based on the wellness scores. [Para. 0114] patient risk stratification can include processing a group of clinical factors, lifestyle factors, and medication compliance factors, for each patient of a population; classifying the population of patients into a hierarchy of risk levels; and assigning a health risk status (a wellness score) to each patient of the population, which is based on the group of factors.[Para. 0145] The integrator computer module 908 can be configured to perform triage on a large group of new candidates, which can include the steps of performing a health risk assessment for each new candidate in the group, which results in an assignment of a wellness score for each new candidate in the group; and classifying the group of new candidates into a hierarchy of risk levels based on the wellness score for each candidate.)
code for generating, based on the risk category, a digital record that includes a treatment recommendation specific to the assigned risk category; ([Para. 0032] determining an optimum DPP and/or DPP provider for which the candidate is likely to succeed, from among many DPP providers with essentially the same content, based on matching a candidate's success metrics with ideal participant profiles associated with various DPP providers and programs. [Para. 0145] The integrator computer module 908 can be configured to perform triage on a large group of new candidates, which can include the steps of performing a health risk assessment for each new candidate in the group, which results in an assignment of a wellness score for each new candidate in the group; and classifying the group of new candidates into a hierarchy of risk levels based on the wellness score for each candidate. [Para. 0176-177] The method can include accessing the wellness score of the patient; accessing medical records of the patient; combining the wellness score and the medical record with demographic and socioeconomic characteristics for the patient; and creating a comprehensive patient profile. The method can include mapping the comprehensive patient profile over a group of disease prevention program providers qualified to deliver the disease prevention program; determining the optimal disease prevention program provider for the patient; and enrolling the patient with the optimal disease prevention program provider.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, with the motivation of provides a risk stratification system to prioritize chronic disease and lifestyle interventions for patients with multiple risk factors (Schmidt Para. 0009).
Swartz/ Yu/ Schmidt do not explicitly teach, however Albright teaches
code for comparing, using the computing device, the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model; ([Para. 0031] a machine-learning algorithm that uses current and past clinical data in order to accurately and precisely predict the future onset of MCI and dementia for individual patients, thus enabling early identification of those having high risk for Alzheimer's disease, and who are therefore also good candidates for clinical trials for Alzheimer's disease therapeutics. That is, current and past clinical data from patients may be obtained (e.g., from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database) and processed using a novel “All-Pairs” technique, which compares all possible pairs of temporal data points for each patient. This data can then be used to train various machine learning models. (Notably, the models were evaluated using 7-fold cross-validation on the training dataset and confirmed using data from a separate testing dataset—A neural network model was effective (mAUC=0.866) at predicting the progression of Alzheimer's disease on a month-by-month basis, both in patients who were initially cognitively normal and in patients suffering from mild cognitive impairment.))
code for updating, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models; ([Para. 0034] Machine learning techniques have been applied to the diagnosis of Alzheimer's disease patients with great success. For example, using 3D convolutional neural networks to diagnose Alzheimer's disease achieved an accuracy of 94.1% on a dataset with 841 patients. [Para. 0059] The training and testing of neural networks, as well as the cross-validation process, relies to some extent on algorithms that utilize random numbers, the scores in the table below will change slightly each time that the models are subjected to cross-validation.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, and incorporate machine-learning based forecasting of disease progression as taught by Albright, with the motivation of providing ways to treat the disease, delay its onset, and prevent it from developing (Albright Para. 0004).
Claim(s) 3 and 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Swartz (US 20180165418 A1) in view of Yu (US 20200126636 A1) in view of Schmidt (US 20180075207 A1) in view of Albright (US 20190272922 A1) in view of Patel (US 20120179480 A1).
As per Claim 3, Swartz/ Yu/ Schmidt/ Albright teach the method according to claim 1, however Patel teaches wherein the risk score is determined based on a combination of at least two selected generic patient models of the plurality of different predefined generic patient models. ([Para. 0007] determining a health risk assessment score for the patient who did not complete the health risk assessment based on health risk assessment scores of multiple patients who did respond to the health risk assessment, the multiple patients having behavior prediction scores that correspond to the behavior prediction score of the patient who did not complete the health risk assessment, the health risk assessment score indicating a risk being assessed by the health risk assessment.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz, methods for determining treatments for cancer patients as taught by Yu, calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, machine-learning based forecasting of disease progression as taught by Albright, and incorporate systems and techniques for determining a health risk assessment score for a patient as taught by Patel, with the motivation of determining a health risk assessment score for a patient (Patel Abstract).
As per Claim 4, Swartz/ Yu/ Schmidt/ Albright/ Patel teach the method according to claim 3, Patel further teaches where each of the at least two selected generic patient models have a weight to be applied when determining the risk score. ([Para. 0035] A model can include a set of one or more model profiles (i.e. at least two selected generic models) where each model profile has an associated model score. In addition, each model profile can have one or more model attributes, where each model attribute has a model value. [Para. 0064] A modifier algorithm can include weights for various attributes depending on the application. In some examples, a modifier algorithm can include weights for various attributes for determining a modifier for a specific application. The modifier can be used to modify an adherence score into an enhanced adherence score (e.g., for a specific disease, for a specific patient population etc.), a cost score, a risk score, an intervention score, or a score for clinical trial completion.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz, methods for determining treatments for cancer patients as taught by Yu, calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, machine-learning based forecasting of disease progression as taught by Albright, and incorporate systems and techniques for determining a health risk assessment score for a patient as taught by Patel, with the motivation of determining a health risk assessment score for a patient (Patel Abstract).
Claim(s) 6 and 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Swartz (US 20180165418 A1) in view of Yu (US 20200126636 A1) in view of Schmidt (US 20180075207 A1) in view of Albright (US 20190272922 A1) in view of Spurlock (US 20190108912 A1).
As per Claim 6, Swartz/ Yu/ Schmidt/ Albright teach the method according to claim 5, Swartz further teaches wherein the plurality of the patient's clinical data comprises at least patient vitals, ([Para. 0012] Certain data collected by the system relate to factors that directly characterize the current or past health of an individual. For example, the collected data may be objective measures of the individual's heart rate, blood pressure, blood sugar level, length of sleep, etc.)
Swartz does not explicitly teach, however Spurlock teach
number of hospitalizations, laboratory results, and prescribed medications. ([Para. 0026] Health records, or medical records, generally include electronic clinical data which is obtained at the point of care at a medical facility, hospital, clinic or practice. Often referred to as the electronic medical record (EMR), the EMR typically includes administrative and demographic information, diagnosis, treatment, prescription drugs, laboratory tests, physiologic monitoring data, hospitalization (i.e. number of hospitalizations), patient insurance, etc.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz, methods for determining treatments for cancer patients as taught by Yu, calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, machine-learning based forecasting of disease progression as taught by Albright, and incorporate number of patient medical data as taught by Spurlock, with the motivation of continuously accumulating health related data from various sources and analyzes such data to assist clinicians in making timely and accurate diagnoses, assessing outcomes, stratifying the severity of a disease, predicting treatment compliance, and providing a patient with a prognosis of disease, so as to properly counsel and treat a patient (Spurlock Para. 0006).
As per Claim 7, Swartz/ Yu/ Schmidt/ Albright/ Spurlock teach the method according to claim 6, Swartz further teaches wherein the patient vitals comprise at least one of heart rate data, electrocardiograph (EKG/ECG) data, respiration rate data, patient temperature data, pulse oximetry data, and blood pressure data. ([Para. 0012] Certain data collected by the system relate to factors that directly characterize the current or past health of an individual. For example, the collected data may be objective measures of the individual's heart rate, blood pressure, blood sugar level, length of sleep, etc.)
Claim(s) 9-13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Swartz (US 20180165418 A1) in view of Yu (US 20200126636 A1) in view of Schmidt (US 20180075207 A1) in view of Albright (US 20190272922 A1) in view of Bernard (US 20060167721 A1).
As per Claim 9, Swartz/ Yu/ Schmidt/ Albright teach the method according to claim 8, however Bernard teaches further comprising forming, using the computing device, the recommended treatment for the patient based on the selected patient risk category, wherein the recommended treatment is different for the each of the low-risk category, the medium risk category and the high-risk category. ([Para. 0060] To determine the appropriate level of post-treatment service, a scoring process may be performed. For each category, the patient is assessed, and based on the assessment, a rating is determined. In other words, for each column, a selection (e.g., selecting a level) is made and a rating, the corresponding numerical value, is recorded. After determining a selection for each column, the ratings are totaled and a recommended level of care will be obtained. Referring to FIG. 2B, a range of totaled ratings, the acuity level, and the recommended discharge recommendation is provided. For patients with a total rating (e.g., score) of greater than 18, the acute discharge recommendation would be home and/or outpatient care. For patients with a total rating ranging from between 14 and 17, a sub-acute level of care may be recommended. For patients with a total of less than 13, a medical rehabilitation center may be recommended. [Para. 0031] a processor. Examiner interprets a processor to be indicative of the computing device.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz, methods for determining treatments for cancer patients as taught by Yu, calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, machine-learning based forecasting of disease progression as taught by Albright, and incorporate determining a post-acute level of care for a patient as taught by Bernard, with the motivation of determining a post-acute level of care for a patient (Bernard Abstract).
As per Claim 10, Swartz/ Yu/ Schmidt/ Albright/ Bernard teach the method according to claim 9, Schmidt further teach wherein the recommended treatment for the patient is only formed if the patient has been assigned the high-risk category. ([Para. 0037] The triage can prioritize the new candidates in the high health risk level for enrollment in a disease prevention program (DPP) (i.e. treatment). [Para. 0031] The health risk status of a patient can be used to direct the patient to a DPP designed to improve the patient's health, modify behavior, and delay or prevent the onset of a chronic disease. [Para. 0163] Various examples of DPP programs include, inter alia, the following categories: i) lifestyle/prevention (pre-chronic); ii) chronic disease (e.g., congestive heart failure (“CHF”), coronary artery disease (“CAD”), type-2 diabetes, depression, chronic obstructive pulmonary disease (“COPD”), hypertension, and hyperlipidemia.); iii) behavioral health (e.g., addiction, domestic violence, anger management, depression, anxiety); and iv) pharmaceuticals, including compliance and dosage protocols.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz, the methods for determining treatments for cancer patients as taught by Yu, machine-learning based forecasting of disease progression as taught by Albright, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, with the motivation of provides a risk stratification system to prioritize chronic disease and lifestyle interventions for patients with multiple risk factors (Schmidt Para. 0009).
As per Claim 11, Swartz/ Yu/ Schmidt/ Bernard/ Albright teach the method according to claim 9, Albright teaches wherein, based on the result of the comparison indicating that the patient health progression deviates from the predefined health progression defined for the selected at least one generic patient model, the updating comprises forming a new generic patient model of the plurality of different predefined generic patient models, the new generic patient model being based on the patient health progression. ([Para. 0128] FIG. 9 shows a schematic of how the databases are used in combination with the patient-specific virtual cohorts to determine dynamically optimized treatment strategies. The outcome database (scattered dots in each panel) is populated to cover the entire space of possible patient data. When a patient enters the system, their patient-specific data defines the patient-specific virtual cohort (gray rectangle of panel (a)), determining a subspace of optimization. Layer 3 produces an optimized therapy for the patient (large dot in panel (a)). Immediately, Phase 4 commences. Temporal data for the patient-specific virtual cohort is generated (organized series of dots in panel (b)) and stored. When the patient returns for follow-up, the newly collected patient data is compared to the predictions of the temporal database. Simulations are weighted based on how well they predicted the patient progression, leading to a refined patient-specific virtual cohort (lighter area of the PSVC in panel (c)). This new cohort (i.e. new generic patient model) is optimized for therapy, leading to a new treatment prediction (large dot in panel (c)). The process repeats with each follow-up visit, so that therapy recommendations are adapted based on each new collection of data from the patient.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz and incorporate the methods for determining treatments for cancer patients as taught by Yu, and incorporate calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, and incorporate machine-learning based forecasting of disease progression as taught by Albright, with the motivation of provides decision support that evolves with increasing data collected on a given patient by refining weights and models used to determine recommended therapies (Albright Para. 0004).
As per Claim 12, Swartz/ Yu/ Schmidt/ Albright/ Bernard teach the method according to claim 11, Swartz teaches further comprising updating a predefined generic patient model of the plurality of different predefined generic patient models based on a combination of the determined individual patient model and a result of the predefined health progression comparison. ([Para. 0054] The process 325 begins at a block 330, where the system receives an updated health vector for an individual. The health vector characterizes various factors, pertaining to health, associated with the individual over time. The health vector is “extended” as it is updated to encompass more recent data for the various factors. The retrieval of the individual's health vector may be triggered by various conditions. For example, the health vector may be retrieved when the system determines that new factor data has been received and the health vector has therefore been recently extended. As another example, the system may determine that the occurrence of an event (e.g., a breaking news item, the completion of a health program by the individual, a medical event, an injury, etc.) has triggered the need for new recommendations for the user. As an additional example, the system may determine that cohorts need to be newly associated the individual, such as when the individual is new to the system and no cohorts have been associated, or when a previously-associated cohort for the individual has sufficiently aged such that the data it contains is now considered stale. As yet another example, the system may periodically associate cohorts for an individual, in order to ensure that the cohorts associated with the individual will always contain the most recent set of population members that might be relevant to the individual.)
As per Claim 13, Swartz/ Yu/ Schmidt/ Albright/ Bernard teach the method according to claim 12, Swartz teaches wherein updating the predefined generic patient model of the plurality of different predefined generic patient models comprises applying a machine learning process. ([Para. 0033] The system generates the health assessment model using machine learning techniques. The system relies upon a training dataset made up of health vectors and corresponding health scores for known population members. The training dataset is used by the system to train the health assessment model to automatically evaluate new health vectors that are analyzed using the model. Over time the system may re-train the health assessment model based on observed population data. For example, the observed population health vectors may include subsequent health assessments performed by medical professionals or provided by the associated population members (e.g., a self-assessment provided by a member). When a sufficient threshold of new health vectors/health scores is detected, the system re-trains the model to help identify new correlations between health vectors and health scores.)
Claim(s) 14-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Swartz (US 20180165418 A1) in view of Yu (US 20200126636 A1) in view of Schmidt (US 20180075207 A1) in view of Albright (US 20190272922 A1) in view of Bernard (US 20060167721 A1) in view of Spurlock (US 20190108912 A1).
As per Claim 14, Swartz/ Yu/ Schmidt/ Albright/ Bernard teach the method according to claim 13, however Spurlock teaches wherein the machine learning process is an unsupervised machine learning process. ([Para. 0059] Deep learning neural networks (also known as deep structured learning, hierarchical learning or deep machine learning) include a class of machine learning operations that use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). Certain embodiments are based on unsupervised learning of multiple levels of features or representations of the data.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz, methods for determining treatments for cancer patients as taught by Yu, calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, machine-learning based forecasting of disease progression as taught by Albright, determining a post-acute level of care for a patient as taught by Bernard, and incorporate the use of machine learning to discover within clinical data patterns that are predictive of disease as taught by Spurlock, with the motivation of continuously accumulating health related data from various sources and analyzes such data to assist clinicians in making timely and accurate diagnoses, assessing outcomes, stratifying the severity of a disease, predicting treatment compliance, and providing a patient with a prognosis of disease, so as to properly counsel and treat a patient (Spurlock Para. 0006).
As per Claim 15, Swartz/ Yu/ Schmidt/ Albright/ Bernard teach the method according to claim 13, however Spurlock teach wherein the machine learning process is a supervised machine learning process. ([Para. 0059] Deep learning neural networks (also known as deep structured learning, hierarchical learning or deep machine learning) include a class of machine learning operations that use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). Certain embodiments are based on unsupervised learning of multiple levels of features or representations of the data.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz, methods for determining treatments for cancer patients as taught by Yu, calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, machine-learning based forecasting of disease progression as taught by Albright, determining a post-acute level of care for a patient as taught by Bernard, and incorporate the use of machine learning to discover within clinical data patterns that are predictive of disease as taught by Spurlock, with the motivation of continuously accumulating health related data from various sources and analyzes such data to assist clinicians in making timely and accurate diagnoses, assessing outcomes, stratifying the severity of a disease, predicting treatment compliance, and providing a patient with a prognosis of disease, so as to properly counsel and treat a patient (Spurlock Para. 0006).
As per Claim 16, Swartz/ Yu/ Schmidt/ Albright/ Bernard teach the method according to claim 13, however Spurlock teaches wherein the machine learning process is based on a convolutional neural network (CNN) or a recurrent neural network (RNN). ([Para. 0058] include any neural network that facilitates machine learning. The system may include a known neural network architecture, such as GoogLeNet (Szegedy, et al. Going deeper with convolutions, in CVPR 2015, 2015); AlexNet (Krizhevsky, et al. Imagenet classification with deep convolutional neural networks, in Pereira, et al. Eds., Advances in Neural Information Processing Systems 25, pages 1097-3105, Curran Associates, Inc., 2012); VGG16 (Simonyan & Zisserman, Very deep convolutional networks for large-scale image recognition, CoRR, abs/3409.1556, 2014); or FaceNet (Wang et al., Face Search at Scale: 80 Million Gallery, 2015). Examiner interprets the known neural network architecture to be indicative of convolutional neural networks.)
Therefore, it would be prima facie obvious to one of ordinary skill in the art, at the time of filing, to modify the health recommendations system as taught by Swartz, methods for determining treatments for cancer patients as taught by Yu, calculating wellness scores for individual patents and assigning a risk level to each patient as taught by Schmidt, machine-learning based forecasting of disease progression as taught by Albright, determining a post-acute level of care for a patient as taught by Bernard, and incorporate the use of machine learning to discover within clinical data patterns that are predictive of disease as taught by Spurlock, with the motivation of continuously accumulating health related data from various sources and analyzes such data to assist clinicians in making timely and accurate diagnoses, assessing outcomes, stratifying the severity of a disease, predicting treatment compliance, and providing a patient with a prognosis of disease, so as to properly counsel and treat a patient (Spurlock Para. 0006).
Response to Arguments
Applicant's arguments, see pgs. 9-19 “I. Rejection of Claims under 35 U.S.C. 101” filed 03/13/2026 have been fully considered but they are not persuasive.
Applicant argues that the claims do not recite a judicial exception and the claims as amended cannot practically be performed in the human mind or by following a series of rules. Examiner respectfully disagrees. Examiner would note that none of the previous correspondence cited mental process as the bases of the 101 rejection. Examiner submits that the identified claim elements represent a series of rules or instructions that a person or persons, with or without the aid of a computer, would follow to determine a risk score of a patient. The claims recite forming an individual patient model based on the first set of individual parameters; determining a matching level between the individual patient model and each of a plurality of different predefined generic patient models, each of the plurality of different predefined generic patient models having a predefined patient risk score; selecting at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold; determining a risk score for the patient based on the selected at least one generic patient model; assigning, based on the risk score, a risk category selected from a plurality of predefined risk categories each associated with a range of risk scores; generating, based on the risk category, record that includes a treatment recommendation specific to the assigned risk category; calculating, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and second set of individual parameters, a patient health progression; and comparing the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model - these behaviors are best categorized as human task. Because the claim elements fall under a series of rules or instructions that a person or person would follow to obtain and extract medical data, the claimed invention is directed to an abstract idea.
The computing device, stored in the memory, a digital record, computer system, computer program product, and the non-transitory computer readable medium are additional elements that amount to mere instructions to apply the exception because this is an example of applying the abstract idea by use of general-purpose computer which does not integrate the abstract idea into a practical application. Claims 1 and 18-20 recite receiving, at a computing device, a first set of individual parameters indicative of a present or a previous state of a patient and receiving, at the computing device, a second set of individual parameters indicative of a state of the patient after administration of the recommended treatment. The limitations are only recited as a tool which only serves to input data for use by the abstract idea (MPEP § 2106.05(g) - insignificant pre/post-solution activity that amounts to mere data gathering to obtain input) and is therefore not a practical application of the recited judicial exception. Claims 1 and 18-20 recite updating, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models. This limitation amounts to mere instructions to apply the exception because a mathematical algorithm applied on a general-purpose computer has been found by the courts to be mere instructions to apply as in MPEP 2106.05(f)(2).
Applicant argues that the claims integrate the alleged judicial exception into a practical application because they provide a closed-loop feedback mechanism in which the stored population models are validated and refined based on how actual patient outcomes compare against expected outcomes, thereby improving the accuracy of future risk determinations for subsequent patients and amounts to an improvement to technology. Examiner respectfully disagrees. An improvement to the abstract idea of improving the accuracy of future risk determinations for subsequent patients does not amount to an improvement to technology or a technical field (see MPEP § 2106.05(a)(III) stating “it is important to keep in mind that an improvement in the abstract idea itself (e.g. a recited fundamental economic concept) is not an improvement in technology. For example, in Trading Technologies Int’l v. IBG,921 F.3d 1084, 1093-94, 2019 USPQ2d 138290 (Fed. Cir. 2019), the court determined that the claimed user interface simply provided a trader with more information to facilitate market trades, which improved the business process of market trading but did not improve computers or technology.”). There is no indication in the instant disclosure that the involvement of a computer assists in improving the technology for the outlined problem statement. Here, the improvement is to comparing data of the determined patient health progression with a predefined health progression, which are categorized best as human behaviors. The instant application and claim language fail to detail how a computer aids the method, the extent to which the computer aids the method, or the significance of a computer to the performance of the method. Merely adding generic computer components to perform the method is not sufficient.
The limitation of updating, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models. This limitation amounts to mere instructions to apply the exception because a mathematical algorithm applied on a general-purpose computer has been found by the courts to be mere instructions to apply as in MPEP 2106.05(f)(2).
Applicant argues that the claims include additional elements that amount to significantly more than the judicial exception itself. The claim requires: “determining, using the computing device, a matching level between the individual patient model and each of a plurality of different predefined generic patient models stored in a memory, each of the plurality of different predefined generic patient models having a predefined patient risk score," "selecting, using the computing device, at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold," "calculating, using the computing device, based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and the second set of individual parameters, a patient health progression," "comparing, using the computing device, the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model," and "updating, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models". This arrangement is not a mere recitation of data collection and display. Accordingly, when considered as a whole, the additional elements of amended claim 1, including the population model architecture, the threshold-based selection mechanism, the post- treatment progression calculation, the comparison of the determined patient health progression with a predefined health progression for the selected model, and the neural network-based updating of stored models conditioned on "a result of the comparison of the determined patient health progression and the predefined health progression," provide an inventive concept that amounts to significantly more than any alleged abstract idea. These features improve the functioning of the underlying computer-based patient modeling technology in a manner that satisfies Step 2B of the eligibility analysis under BASCOM, McRO, and Berkheimer, and thus the claim is patent-eligible. Examiner respectfully disagrees.
The Examiner has identified the limitations of ‘determining a matching level between the individual patient model and each of a plurality of different predefined generic patient models stored in a memory, each of the plurality of different predefined generic patient models having a predefined patient risk score; selecting at least one generic patient model of the plurality of different predefined generic patient models having the matching level above a predetermined threshold; calculating based on the at least one generic patient model of the plurality of different predefined generic patient models and based on the first and the second set of individual parameters, a patient health progression; and comparing the determined patient health progression with a predefined health progression defined for the selected at least one generic patient model’ as part of the abstract idea.
The consideration under Step 2B is if the additional elements, alone or in combination, are well-understood, routine, and conventional in the field – the novelty of the abstract idea is not considered relevant under the Step 2B analysis. Here, the additional elements of Claim 1 and 18-20 reciting a computing device and a digital record, alone or in combination, amount to instruction to implement the abstract idea using a general-purpose computer.
The limitation of updating, using a neural network-based machine learning model, based on the patient health progression and a result of the comparison of the determined patient health progression and the predefined health progression, at least one of the at least one generic patient model of the plurality of different predefined generic patient models amounts to mere instructions to apply the exception because a mathematical algorithm applied on a general-purpose computer has been found by the courts to be mere instructions to apply as in MPEP 2106.05(f)(2).
Applicant's arguments, see pgs. 19-24 “II. Rejections of Claims under 35 U.S.C. 103” filed 03/13/2026 have been fully considered but they are not persuasive.
Applicant argues that the combination of Swartz, Yu, and Schmidt are designed for different purposes and operate on different data structures, and therefore the combination of references is not properly supported. Examiner respectfully disagrees. Swartz teaches A health recommendations system that collects data about multiple factors pertaining to an individual's health and uses such data to recommend contextual changes that are likely to have a positive health impact on the individual. Yu teaches determining treatments for cancer patients using multiple clinicopathological markers of the patient. Schmidt teaches the automated processing of patient risk stratification for a patient population, calculating wellness scores for individual patents, assigning a risk level to each patient, and enrolling high risk patients in appropriate disease prevention programs. Therefore, the combination of these references would be obvious because all the references analyze patient data to determine risk and determine optimal treatment options based of the assigned or calculated risk.
However, Applicant’s argument that the cited prior art does not teach the are persuasive regarding the newly added limitations. Therefore, the rejection has been withdrawn. However, upon further consideration, a new grounds of rejection is made in view of Albright, as per the rejection above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Patricia K Edouard whose telephone number is (571)272-6084. The examiner can normally be reached Monday - Friday 7:30 AM - 5:00 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Peter H Choi can be reached at 469-295-9171. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/P.K.E./Examiner, Art Unit 3681
/PETER H CHOI/Supervisory Patent Examiner, Art Unit 3681
Prosecution Insights