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 .
This communication is in response to the amendment received on 04/14/2026. Claims 1-19 remain pending in this application.
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 1-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
Claims 1-15 are drawn to a method which is within the four statutory categories (i.e. process). Claims 16-19 are drawn to a system which is within the four statutory categories (i.e. machine).
Step 2A, Prong 1:
Claims 1 and 16 have been amended to recite:
“receiving a first feature dataset and at least one second feature dataset, wherein each feature dataset comprises values of one or more features, and wherein each feature represents a property of the target subject, wherein the first feature dataset comprises values of genomic features, and wherein the at least one second feature dataset comprises values of clinical features of the target subjects;
applying a first non-linear Machine Learning (ML) based model on the first feature dataset, to obtain a first preliminary risk score, representing a first assessed probability of the target subject in manifesting the disease;
applying a second non-linear ML based model on the at least one second feature dataset, to obtain at least one respective, second preliminary risk score, representing a second assessed probability of the target subject in manifesting the disease;
selecting a subset of features from the first feature dataset and at least one second feature dataset; and
applying a linear ML-based model on (i) the first preliminary risk score, (ii) the at least one second preliminary risk score, and (iii) the subset of features, to determine a disease risk score, representing an overall probability of the target subject in manifesting the disease”.
These limitations correspond to an abstract idea of “certain methods of organizing human activity”. This is a method of managing interactions between people, such as user following rules and instructions. The mere nominal recitation of a generic processor does not take the claims out of the methods of organizing human interactions grouping. Thus, the claims recite an abstract idea.
The current specification describes the processor as a generic computing component, such as in [0060], the specification recites “Computing device 1 may include a processor or controller 2 that may be, for example, a central processing unit (CPU) processor, a chip or any suitable computing or computational device, an operating system 3, a memory 4, executable code 5, a storage system 6, input devices 7 and output devices 8. Processor 2 (or one or more controllers or processors, possibly across multiple units or devices) may be configured to carry out methods described herein, and/or to execute or act as the various modules, units, etc. More than one computing device 1 may be included in, and one or more computing devices 1 may act as the components of, a system according to embodiments of the invention.”.
The limitations of “applying a first non-linear Machine Learning (ML) based model on the first feature dataset, to obtain a first preliminary risk score”, “applying a second non-linear ML based model on the at least one second feature dataset, to obtain at least one respective, second preliminary risk score” and “applying a linear ML-based model on (i) the first preliminary risk score, (ii) the at least one second preliminary risk score, and (iii) the subset of features, to determine a disease risk score” also are directed to an abstract idea of mathematical relationships, which falls within the “mathematical concepts” grouping of abstract ideas.
The limitations of claims 9-11, 14, 18 are directed to an abstract idea of “certain methods of organizing human activity”, such as “receiving a first training dataset, comprising a plurality of first feature datasets, each pertaining to a respective subject of a first cohort of subjects; obtaining a first set of annotations, each labeling a condition of a corresponding subject of the first cohort of subjects; and using the first set of annotations as supervisory data, to train the first non-linear ML model, so as to predict the first preliminary risk score of subjects of the first cohort of subjects, based on the first training dataset”-claim 9, “receiving a second training dataset, comprising a plurality of second feature datasets, each pertaining to a respective subject of a second cohort of subjects; obtaining a second set of annotations, each labeling a condition of a corresponding subject of the second cohort of subjects; and using the second set of annotations as supervisory data, to train the second non-linear ML model, so as to predict the second preliminary risk score of subjects of the second cohort of subjects, based on the second training dataset”-claim 10, “selecting the subset of features from the first dataset and/or second dataset, wherein the subset of features pertains to a specific subject of the first cohort and/or second cohort; and using at least one of the (i) first set of annotations and (ii) second set of annotations as supervisory data, to train the linear ML-based model to produce an initial prediction of a disease risk score of the specific subject, wherein said initial prediction is a linear combination of the subset of features of the specific subject, and (a) the first preliminary risk score of the specific subject and/or (b) the at least one second preliminary risk score of the specific subject”-claim 11, “receiving, via a Graphical User Interface (GUI) a perturbation of a value of at least one feature of the subset of features; applying the linear ML-based model on the subset of features having the perturbed feature value, to determine a simulated disease risk score, representing a simulated probability of the target subject in manifesting the disease; and presenting the simulated disease risk score via the GUI as a result of said perturbation”-claim 14, “receive, via a GUI, a perturbation of a value of at least one feature of the subset of features; apply the linear ML-based model on the subset of features having the perturbed feature value, to determine a simulated disease risk score, representing a simulated probability of the target subject in manifesting the disease; and present the simulated disease risk score via the GUI as a result of said perturbation”-claim 18.
The limitations of claims 12, 13, 15, 17, 19 are directed to an abstract idea of “mathematical concepts”, such as, “applying a feature selection algorithm, to identify a first group of features from the first feature dataset, as prominent contributors in predicting the first preliminary risk score; applying the feature selection algorithm, to identify a second group of features from the second feature dataset, as prominent contributors in predicting the second preliminary risk score; and selecting the subset of features of the plurality of features based on the first, and second groups of features”-claim 12, “calculating one or more disease-specific statistical properties, characterizing manifestation of the disease in a population of the first cohort and/or second cohort, based on at least one of the first and second sets of annotations; obtaining, from the linear ML-based model, an initial value of the disease risk score for the target subject; and fine-tuning the initial value of the disease risk score, based on the disease-specific statistical properties, to determine the disease risk score of the target subject”-claim 13, “automatically perturbing a value of one or more features of the subset of features; applying the linear ML-based model on the subsets of features, each having at least one perturbed feature value, to determine corresponding simulated disease risk scores, wherein each simulated disease risk score represents a simulated probability of the target subject in manifesting the disease, as a result of the corresponding at least one perturbation; and presenting the simulated disease risk scores via a GUI, as recommendations for diminishing the target subject’s probability of manifesting the disease”-claim 15, “apply a feature selection algorithm, to identify a first group of features from the first feature dataset, as prominent contributors in predicting the first preliminary risk score; apply the feature selection algorithm, to identify a second group of features from the second feature dataset, as prominent contributors in predicting the second preliminary risk score; and select the subset of features of the plurality of features based on the first, and second groups of features-claim 17, “automatically perturb a value of one or more features of the subset of features; applying the linear ML-based model on the subsets of features, each having at least one perturbed feature value, to determine corresponding simulated disease risk scores, wherein each simulated disease risk score represents a simulated probability of the target subject in manifesting the disease, as a result of the corresponding at least one perturbation; and presenting the simulated disease risk scores via a GUI, as recommendations for diminishing the target subject’s probability of manifesting the disease”-claim 19.
Claims 2-8 are ultimately dependent from claim 1 and include all the limitations of claim 1. Therefore, claims 2-8 recite the same abstract idea. Claims 2-8 describe a further limitation regarding the basis for determining the disease risk score for the target subject. These are all just further describing the abstract idea recited in claim 1, without adding significantly more.
After considering all claim elements, both individually and in combination and in ordered combination, it has been determined that the claims do not amount to significantly more than the abstract idea itself.
Step 2A, Prong 2:
This judicial exception is not integrated into a practical application. In particular, claims recite the additional elements of “a non-linear machine learning model”, “a linear machine learning model”, using a processor to perform the steps of receiving first and second feature datasets, applying machine learning models, “a graphical user interface (GUI)”, which are hardware and software elements, these limitations are not enough to qualify as “practical application” being recited in the claims along with the abstract idea since these elements are merely invoked as a tool to apply instructions of the abstract idea in a particular technological environment, and mere instructions to apply/implement/automate an abstract idea in a particular technological environment and merely limiting the use of an abstract idea to a particular field or technological environment do not provide practical application for an abstract idea (MPEP 2106.05(f) & (h)).
Claims also recite other additional limitations beyond abstract idea, including functions such as receiving data from a database, presenting data are insignificant extra-solution activities (see MPEP 2106.05 (g)), which do not provide a practical application for the abstract idea.
Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
Step 2B:
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor to perform the determining steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept.
The claims are not patent eligible.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-19 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by McGovern et al. (hereinafter McGovern) (US 2020/0342958 A1).
Claim 1 has been amended to recite a method of predicting, by at least one processor, a probability of a target subject in manifesting a disease, the method comprising:
receiving a first feature dataset and at least one second feature dataset, wherein each feature dataset comprises values of one or more features, and wherein each feature represents a property of the target subject (McGovern discloses “…assaying biological sample of the subject…genomic loci…blood sample…” in [0004]-[0005]), wherein the first feature dataset comprises values of genomic features, and wherein the at least one second feature dataset comprises values of clinical features of the target subjects (McGovern discloses “…the method further comprises applying the deep learning prediction model ( e.g. , a deep learning classifier ) to a set of clinical health data of the subject . In some embodiments, the set of clinical health data comprises one or more of familial history of an inflammatory disease or disorder, age, hypertension or pre - hypertersion, diabetes or pre - diabetes, overweight or obesity, environmental exposure, lifestyle risk factors (e.g., smoking , alcohol consumption , or drug use ) , or presence of other risk factors …” in [0009]);
applying a first non-linear Machine Learning (ML) based model on the first feature dataset, to obtain a first preliminary risk score, representing a first assessed probability of the target subject in manifesting the disease (McGovern discloses “…Deep Learning algorithm may be used to process one or more of the feature sets …” in [0118]);
applying a second non-linear ML based model on the at least one second feature dataset, to obtain at least one respective, second preliminary risk score, representing a second assessed probability of the target subject in manifesting the disease (McGovern discloses “…Deep Learning algorithm may be used to process one or more of the feature sets …” in [0118]);
selecting a subset of features from the first feature dataset and at least one second feature dataset (McGovern discloses “…selecting subsets …” in [0143]); and
applying a linear ML-based model on (i) the first preliminary risk score, (ii) the at least one second preliminary risk score, and (iii) the subset of features, to determine a disease risk score, representing an overall probability of the target subject in manifesting the disease (McGovern discloses “…using logistic regression with adjustment for principal com ponents from population stratification analysis …” in [0195], “…A linear prediction model in the training set was built with those variants using step - wise logistic regression , …” in [0213]).
Claim 2 recites the method of claim 1, wherein the first feature dataset and the at least one second feature dataset overlap in one or more features (McGovern; [0004]-[0005]).
Claim 3 recites the method of claim 1, wherein the first non-linear ML model comprises a Deep learning Neural Network (DNN), having at least 4 neural layers (McGovern; [0190]).
Claim 4 recites the method of claim 3, wherein the first feature dataset comprises values of genomic features, selected from a list consisting of: a Polygenic Risk Score (PRS), representing polygenic risk in manifesting the disease, monogenic data, representing traits of the target subject that are influenced by a single gene, and pharmacogenomic data, representing the target subject’s response to drugs (McGovern; [0028]).
Claim 5 recites the method of claim 1 wherein the at least one second non-linear ML model is selected from a list consisting of a decision tree model, a k-Nearest Neighbors model, a non-linear Support Vector Machine (SVM) model, and a Naive Bayes model, having non-linear transformations (McGovern; [0120]).
Claim 6 has been amended to recite the method of claim 5, wherein the at least one second feature dataset comprises values of clinical features pertaining to a first group of blood measurements, selected from: a blood pressure (BP) level, a total cholesterol level, a High Density Lipoprotein (HDL) level, a Low Density Lipoprotein (LDL) level, a Lipoprotein A level (McGovern; [0005], [0070], [0009]).
Claim 7 has been amended to recite the method of claim 6, wherein the at least one second feature dataset comprises values of clinical features pertaining to a second group of blood measurements, selected from: a testosterone level, a C-reactive protein level, a basophil count, a cystatin-C level, and a mean corpuscular hemoglobin value (McGovern; [0005], [0070], [0009]).
Claim 8 has been amended to recite the method of claim 5, wherein the at least one second feature dataset further comprises values of features of the subject, selected from a list consisting of: an age, a gender, an ethnicity, a prior diagnosis, a status of drug treatment, a lifestyle factor, and a feature related to mental health (McGovern; [0009]).
Claim 9 recites the method of claim 1, further comprising: receiving a first training dataset, comprising a plurality of first feature datasets, each pertaining to a respective subject of a first cohort of subjects; obtaining a first set of annotations, each labeling a condition of a corresponding subject of the first cohort of subjects; and using the first set of annotations as supervisory data, to train the first non-linear ML model, so as to predict the first preliminary risk score of subjects of the first cohort of subjects, based on the first training dataset (McGovern; [0125], [0140]).
Claim 10 recites the method of claim 9, further comprising: receiving a second training dataset, comprising a plurality of second feature datasets, each pertaining to a respective subject of a second cohort of subjects; obtaining a second set of annotations, each labeling a condition of a corresponding subject of the second cohort of subjects; and using the second set of annotations as supervisory data, to train the second non-linear ML model, so as to predict the second preliminary risk score of subjects of the second cohort of subjects, based on the second training dataset (McGovern; [0125], [0140]).
Claim 11 recites the method of claim 10, further comprising: selecting the subset of features from the first dataset and/or second dataset, wherein the subset of features pertains to a specific subject of the first cohort and/or second cohort; and using at least one of the (i) first set of annotations and (ii) second set of annotations as supervisory data, to train the linear ML-based model to produce an initial prediction of a disease risk score of the specific subject, wherein said initial prediction is a linear combination of the subset of features of the specific subject, and (a) the first preliminary risk score of the specific subject and/or (b) the at least one second preliminary risk score of the specific subject (McGovern; [0131], [0140]).
Claim 12 recites the method of claim 1, further comprising: applying a feature selection algorithm, to identify a first group of features from the first feature dataset, as prominent contributors in predicting the first preliminary risk score; applying the feature selection algorithm, to identify a second group of features from the second feature dataset, as prominent contributors in predicting the second preliminary risk score; and selecting the subset of features of the plurality of features based on the first, and second groups of features (McGovern; [0131], [0140]).
Claim 13 recites the method of claim 10, further comprising: calculating one or more disease-specific statistical properties, characterizing manifestation of the disease in a population of the first cohort and/or second cohort, based on at least one of the first and second sets of annotations; obtaining, from the linear ML-based model, an initial value of the disease risk score for the target subject; and fine-tuning the initial value of the disease risk score, based on the disease-specific statistical properties, to determine the disease risk score of the target subject (McGovern; [0131], [0140]).
Claim 14 recites the method of claim 1 further comprising receiving, via a Graphical User Interface (GUI) a perturbation of a value of at least one feature of the subset of features; applying the linear ML-based model on the subset of features having the perturbed feature value, to determine a simulated disease risk score, representing a simulated probability of the target subject in manifesting the disease; and presenting the simulated disease risk score via the GUI as a result of said perturbation (McGovern; [0151], [0179]).
Claim 15 recites the method of claim 1 further comprising automatically perturbing a value of one or more features of the subset of features; applying the linear ML-based model on the subsets of features, each having at least one perturbed feature value, to determine corresponding simulated disease risk scores, wherein each simulated disease risk score represents a simulated probability of the target subject in manifesting the disease, as a result of the corresponding at least one perturbation; and presenting the simulated disease risk scores via a GUI, as recommendations for diminishing the target subject’s probability of manifesting the disease (McGovern; [0151], [0179]).
As per claims 16-19, they are system claims which repeat the same limitations of claims 1, 12, 14, 15, the corresponding method claims, as a collection of elements as opposed to a series of process steps. Since the teachings of McGovern disclose the underlying process steps that constitute the methods of claims 1, 12, 14, 15, it is respectfully submitted that they provide the underlying structural elements that perform the steps as well. As such, the limitations of claims 16-19 are rejected for the same reasons given above for claims 1, 12, 14, 15.
Response to Arguments
Applicant's arguments filed 04/14/2026 have been fully considered but they are not persuasive. Applicant’s arguments will be addressed below in the order in which they appear.
Arguments about 35 USC 101 rejection:
Applicant argues that the limitations of claim 1, “applying a first non-linear machine learning model on the first dataset, to obtain a first preliminary risk score”, and “applying a second non-linear machine learning model on the at least one second feature dataset, to obtain at least one respective, second preliminary risk score” are not directed to “certain methods for organizing human activity” or “mathematical concepts”, since these limitations describe technical operations performed by machine learning models on data (Remarks, pages 1-3).
In response, Examiner submits that the limitations of applying machine learning models on the datasets correspond to mathematical calculations to iteratively adjust the values to obtain a risk score. The limitations of “receiving feature datasets, obtaining preliminary risk scores, selecting a subset of features and determine a disease risk score” correspond to managing interactions between people, such as user following rules and instructions. Therefore, these features correspond to “certain methods of organizing human activity”.
Applicant argues that the claim limitations are directed to a technical solution to a technical problem and are directed to a practical application. The technical solution is to provide the combination of linear and non-linear models allows the system to address two, seemingly contradicting objectives: On one hand, the employment of complex, non-linear models in an ensemble- learning architecture allows the system to learn complex and non-linear relations between features characterizing a variety of patients, and their respective likelihood of manifesting a disease of interest. On the other hand, the employment of a linear model allows the system to provide an explainable, intuitive, and insightful interface, for understanding the contributors to a subject's condition.
In response, Examiner submits that applying the non-linear machine learning models on different datasets, and applying a linear machine learning model to primary risk scores to obtain a disease risk score may improve the outcome of the risk scores, however, these features are not directed to a technical solution to a technical problem. These limitations only recite the outcome for “risk scores”.
Applicant argues that the experimental results demonstrating that the ensemble model architecture as recited in claim 1 - which integrates genomic features through a first non-linear model, clinical features through a second non-linear model, and selected raw features through a linear model - yields a measurable improvement in diagnostic accuracy over any individual model component.
In response, Examiner submits that yields a measurable improvement in diagnostic accuracy corresponds to an improvement to the outcomes for the diagnostic risk scores and not an improvement to the technology itself.
Applicant argues that the specific ordered combination of elements amounts to significantly more. The claims do not merely recite generic computer implementation of an abstract concept. Instead, claim 1 recites a specific technical architecture: receiving heterogeneous feature datasets, applying a first non- linear ML model to obtain a first preliminary risk score, applying a second non-linear ML model to obtain a second preliminary risk score, selecting a subset of features, and applying a linear ML model on the preliminary risk scores and selected features to determine an overall disease risk score. This specific combination of different ML model types operating on different data types, with feature selection and linear integration, represents an unconventional technical approach that provides the specific technical benefits of both accuracy and interpretability.
In response, Examiner submits that the current specification recites “The first non-linear ML model may include a Deep Learning Neural Network (DNN), having at least four neural layers, adapted to learn complex, and optionally non-linear relations between features of the first feature dataset and the first preliminary risk score.” in [0029], “The at least one second non-linear ML model may be selected from a list of ML based architectures, such as a decision tree model, a k-Nearest Neighbors model, a non-linear Support Vector Machine (SVM) model, a Naive Bayes model, having non-linear transformations, and the like.” in [0033], and “a linear, ML-based classification or regression model 130, such as a logistic regression model” in [0103]. These machine learning models have been applied to the datasets in order to determine the risk scores. Applying these machine learning models are merely invoked as a tool to apply instructions of the abstract idea in a particular technological environment, and mere instructions to apply/implement/automate an abstract idea in a particular technological environment and merely limiting the use of an abstract idea to a particular field or technological environment do not provide practical application for an abstract idea (MPEP 2106.05(f) & (h)).
Therefore, the arguments are not persuasive and claims are rejected under 35 U.S.C. §101 as being directed to non-statutory subject matter.
Argument about 35 USC 102 rejection:
Applicant argues that McGovern does not teach processing two different type of data, but teaches processing all genetic variant data.
In response, Examiner submits that McGovern teaches “…the method further comprises applying the deep learning prediction model ( e.g. , a deep learning classifier ) to a set of clinical health data of the subject . In some embodiments, the set of clinical health data comprises one or more of familial history of an inflammatory disease or disorder, age, hypertension or pre - hypertersion, diabetes or pre - diabetes, overweight or obesity, environmental exposure, lifestyle risk factors (e.g., smoking , alcohol consumption , or drug use ) , or presence of other risk factors …” in [0009].
Therefore, the argument is not persuasive.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DILEK B COBANOGLU whose telephone number is (571)272-8295. The examiner can normally be reached 8:30-5:00 ET.
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, Obeid Mamon can be reached at (571) 270-1813. 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.
/DILEK B COBANOGLU/Primary Examiner, Art Unit 3687
Prosecution Insights