Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
This office action for the 18/476014 application is in response to the communications filed October 20, 2025.
Claims 1, 8 and 13 were amended October 20, 2025.
Claims 3 and 14 were cancelled October 20, 2025.
Claims 1, 2, 4-13 and 15-22 are currently pending and considered below.
Claim Rejections - 35 USC § 103
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 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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 2, 4-13 and 15-22 are rejected under 35 U.S.C. 103 as being unpatentable over McGovern et al. (US 2020/0342958; herein referred to as McGovern) in view of Seres et al. (US 2019/0240059; herein referred to as Seres).
As per claim 1,
McGovern teaches a computer-implemented method for training a machine learning (ML) model to assess the risk of a human subject for developing at least one disorder, the method comprising:
(Abstract and Paragraphs [0003]-[0011] of McGovern. The teaching describes assessing inflammatory disease or condition in subjects using Deep Learning (DL) prediction models - assaying a biological sample of the subject to generate a dataset comprising genetic data - processing the dataset at a plurality of genomic loci to determine quantitative measures of each genomic locus of the plurality of genomic loci. Applying a deep learning prediction model to the inflammatory disease profile to identify a presence of the inflammatory disease or condition in the subject, or a likelihood that the subject will develop the inflammatory disease or condition. Applying the deep learning prediction model (e.g., a deep learning classifier) to a set of clinical health data of the subject)
McGovern further teaches receiving an input dataset including at least medical claim data corresponding to a plurality of human subjects over a target prediction period:
(Paragraphs [0003]-[0011], [0049]-[0053] and [0084]-[0091] of McGovern. The teaching describes a set of clinical health data comprises one or more of familial history of an inflammatory disease or disorder, age, hypertension or pre-hypertension, 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). Biological samples may be obtained or derived from a human subject - inflammatory disease or condition may comprise a likelihood, risk, or susceptibility of having an inflammatory disease in the future)
McGovern further teaches splitting the input dataset into a first dataset corresponding to a first portion of the plurality of human subjects and a second dataset corresponding to a second portion of the plurality of human subjects:
(Paragraphs [0116]-[0122] of McGovern. The teaching describes that a DeepLearning algorithm may be used to apply a machine learning classifier to a plurality of inflammatory disease-associated genomic loci that are associated with two or more classes of individuals inputted into a machine learning model, in order to classify a subject into one of the two or more classes of individuals. For example, the DeepLearning algorithm may be used to apply a machine learning classifier to a plurality of inflammatory disease-associated genomic loci that are associated with individuals with known conditions (e.g., an inflammatory disease or disorder, such as an IBD) and individuals not having the condition (e.g., healthy individuals, or individuals who do not have an inflammatory disease or disorder, such as an IBD), in order to classify a subject as having the condition (e.g., positive test outcome) or not having the condition (e.g., negative test outcome). The plurality of input variables or features may comprise one or more datasets indicative of the presence (e.g., positive test result) or absence (e.g., negative test result) of one or more inflammatory disease or conditions.)
McGovern further teaches selecting at least one risk factor associated with developing the at least one disorder from the first dataset:
(Paragraphs [0003]-[0011] and [0092]-[0096] of McGovern. The teaching describes that the biological sample may be taken from a subject at risk of developing an inflammatory disease or condition due to factors such as familial history, age, hypertension or pre-hypertension, 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)
McGovern further teaches training a machine learning (ML) model using the first dataset and the at least one risk factor, the ML model including at least one logistic regression model:
(Paragraphs [0003]-[0011] and [0120]-[0126] of McGovern. The teaching describes that a deep learning prediction model is trained using a first set of independent training samples associated with a presence of the inflammatory disease or condition and a second set of independent training samples associated with an absence of the inflammatory disease or condition - applying the deep learning prediction model (e.g., a deep learning classifier) to a set of clinical health data of the subject. DeepLearning algorithm may comprise a classifier, such that each of the one or more output values comprises one of a fixed number of possible values (e.g., a linear classifier, a logistic regression classifier, etc.)
McGovern further teaches providing the second dataset to the ML model to generate a risk prediction for developing the at least one disorder by the end of the target prediction period for each human subject included in the second portion of the plurality of human subjects:
(Paragraphs [0003]-[0011], [0049]-[0053], [0084]-[0091] and [0222]-[0227] of McGovern. The teaching describes that inflammatory disease or condition may comprise a likelihood, risk, or susceptibility of having an inflammatory disease in the future (e.g., within about 1 hour- about 10 years, or more than about 10 years. Prediction model of CD risk was constructed using DeepLearning algorithms using genetic data from the IIBDGC cohort - best performance of risk prediction of complex human diseases using genetic data - DL predicted risk score is also strongly associated with disease clinical phenotypes of CD including disease location, severity and need for surgery.)
McGovern further teaches tuning at least one parameter of the ML model based on the generated risk predictions for the second portion of the plurality of human subjects:
(Paragraphs [0221]-[0227] of McGovern. The teaching describes that intensive tuning of the hyperparameters was performed in the Deep Learning Model, rather than using arbitrarily selected numbers of neurons and/or layers. Tuning of the parameters in Deep Learning Models may have important impact on performance of the models - Deep Learning-based algorithms were effectively utilized to predict CD risk using genetic data. Results demonstrated that this algorithm significantly increased the prediction accuracy, and that the predicted disease risk is associated with disease clinical characteristics)
McGovern further teaches further comprising: creating a third dataset corresponding to a certain human subject over a time period; and providing the third dataset to the ML model with the at least one parameter to generate a risk prediction for developing the at least one disorder over the time period for the certain human subject, wherein the risk predictions score is within a range of values:
(Paragraphs [0003]-[0011], [0084]-[0091 and [0222]-[0227] of McGovern. The teaching describes prediction model of CD risk was constructed using Deep Learning algorithms using genetic data from the IIBDGC cohort - best performance of risk prediction of complex human diseases using genetic data - DL predicted risk score is also strongly associated with disease clinical phenotypes of CD including disease location, severity and need for surgery.)
McGovern further teaches grouping the certain human subject into a cohort comprising a plurality of similar users wherein each similar user of the plurality of similar users has a risk prediction score that is within the range of values:
(Paragraph [0130] of McGovern. The teaching describes that the classifier may be configured to classify samples by assigning an output value of “indeterminate” or 2 if the sample is not classified as “positive”, “negative”, 1, or 0. In this case, a set of two cutoff values is used to classify samples into one of the three possible output values or classes of individuals (e.g., corresponding to outcome groups of individuals having “low risk,” “intermediate risk,” and “high risk” of having one or more inflammatory disease or conditions, such as an inflammatory disease or disorder). Examples of sets of cutoff values may include {1%, 99%}, {2%, 98%}, {5%, 95%}, {10%, 90%}, {15%, 85%}, {20%, 80%}, {25%, 75%}, {30%, 70%}, {35%, 65%}, {40%, 60%}, and {45%, 55%}. Similarly, sets of n cutoff values may be used to classify samples into one of n+1 possible output values or classes of individuals, where n is any positive integer.)
McGovern further teaches providing an activity to the certain human subject and the plurality of similar users:
(Paragraphs [0074], [0148] and [0150] of McGovern. The teaching describes upon identifying a subject as having elevated risk of developing an inflammatory disease with the DeepLeaning model described herein, a primary intervention may be administered to the subject to prevent or delay the onset of the inflammatory disease or condition. The therapeutic intervention may comprise recommending the subject for a secondary clinical test to confirm a diagnosis of the inflammatory disease or condition. This secondary clinical test may comprise a blood test, fetal occult blood test (FOBT), colonoscopy, sigmoidoscopy, endoscopy, enteroscopy, X-ray scan, computerized tomography (CT) scan, positron emission tomography (PET) scan, PET-CT scan, magnetic resonance imaging (MRI), ultrasound scan, or a combination thereof. Progression of an inflammatory disease may be tracked before treatment, after treatment, or during the course of treatment, to determine the treatment's effectiveness. For example, a method as described herein may be performed on a subject prior to, and after, treatment of a subject with an inflammatory disease therapy to measure the subject's disease progression or regression in response to the inflammatory disease therapy.)
McGovern does not explicitly teach facilitating communications between the certain human subject and the plurality of similar users, wherein the communications correspond to the activity.
However, Seres teaches facilitating communications between a certain human subject and a plurality of similar users, wherein the communications correspond to an activity:
(Paragraphs [0044], [0052] and [0053] of Seres. The teaching describes a system that connects patients with inflammatory disease over a communication network. A patient may be paired with a patient coach using a pairing algorithm (such as based on location, gender, age, type of ostomy surgery received, and/or the type of support needed by the patient, for example, technical support, emotional support, and/or others), or select a patient coach based on any one or combination of the aforementioned factors. A psychologist care provider may contact the patient on a regular schedule for a period of time following the procedure, such as weekly or biweekly, and then on an as needed basis. A patient coach may interact with the patient weekly, such as through a support group, and/or interact with the patient on an as needed basis.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the activities recommended by McGovern of their inflammatory disease patients, the support group connections in emotional therapy as taught by Seres. Paragraph [0049] of Seres teaches that the use of communication networks to connect users experiencing inflammatory disease improves the quality of care each individual patient receives in the course of their medical treatment. One of ordinary skill in the art would have added to the teaching of McGovern, the teaching of Seres based on this incentive without yielding unexpected results.
As per claim 2,
The combined teaching of McGovern and Seres teaches the limitations of claim 1.
McGovern further teaches wherein the first dataset is a training dataset and the second dataset is a validation dataset:
(Paragraphs [0110]-[0122], [0182]-[0184] and [0222]-[0232] of McGovern. The teaching describes that after building up different deep learning models in the training dataset, those models may be fitted in the test dataset to obtain the predictions. DeepLearning algorithm may be used to apply a machine learning classifier to a plurality of inflammatory disease-associated genomic loci that are associated with individuals with known conditions (e.g., an inflammatory disease or disorder, such as an IBD} and individuals not having the condition (e.g., healthy individuals, or individuals who do not have an inflammatory disease or disorder, such as an IBD), in order to classify a subject as having the condition (e.g., positive test outcome) or not having the condition (e.g., negative test outcome). Such classifications include training and validation cohorts, and external validation datasets)
As per claim 4,
The combined teaching of McGovern and Seres teaches the limitations of claim 1.
McGovern further teaches further comprising: determining whether each human subject of the plurality of human subjects has developed the at least one disorder by the end of the target prediction period; labeling a portion of the plurality of human subjects who have developed the at least one disorder by the end of the target prediction period as positive for the disorder; and labeling a remaining portion of the plurality of human subjects as healthy:
(Paragraphs [0084]-[0091], [0116]-[0122] and [0131] of McGovern. The teaching describes that an inflammatory disease or condition may comprise a likelihood, risk, or susceptibility of having an inflammatory disease in the future (e.g., within about 1 hour – about 10 years, or more than about 10 years. DeepLearning algorithm may be used to apply a machine learning classifier to a plurality of inflammatory disease-associated genomic loci that are associated with individuals with known conditions (e.g., an inflammatory disease or disorder, such as an IBD) and individuals not having the condition (e.g., healthy individuals, or individuals who do not have an inflammatory disease or disorder, such as an IBD), in order to classify a subject as having the condition (e.g., positive test outcome) or not having the condition (e.g., negative test outcome).)
As per claim 5,
The combined teaching of McGovern and Seres teaches the limitations of claim 4.
McGovern further teaches wherein determining that a human subject has developed the at least one disorder includes detecting at least one identifying factor in a final year of the target prediction period:
(Paragraph [0131] of McGovern. The teaching describes independent training samples may comprise samples and associated datasets and outputs obtained at a plurality of different time points from the same subject (e.g., on a regular basis such as weekly, biweekly, or monthly), as part of a longitudinal monitoring of a subject before, during, and after a course of treatment for one or more inflammatory disease or conditions of the subject)
As per claim 6,
The combined teaching of McGovern and Seres teaches the limitations of claim 4.
McGovern further teaches wherein the first portion of the plurality of human subjects has a first ratio of positive to healthy human subjects and the second portion of the plurality of human subjects has a second ratio of positive to healthy human subjects:
(Paragraphs [0003]-[0011], [0116]-[0122], [0200] and [0222]-[0232] of McGovern. The teaching describes improvement in prediction accuracy from the DL approach led to greatly enriched CD cases in the extreme of the DL score, with an OR of 19.25 in the top 10 percent, and an OR of 26.32 for DL compared to 6.29 for LDPred approach in top 5 percent - By producing such a high Odds Ratio (OR), DL-based approaches may enable cost-effective genetic screening (e.g., to a general population or a high-risk population such as individuals with family history and/or symptoms of CD) in the extremes of DL prediction)
As per claim 7,
The combined teaching of McGovern and Seres teaches the limitations of claim 6.
McGovern further teaches wherein the first ratio and the second ratio are different:
(Paragraphs [0003]-[0011], [0116]-[0122], [0200] and [0222]-[0232] of McGovern. The teaching describes improvement in prediction accuracy from the DL approach led to greatly enriched CD cases in the extreme of the DL score, with an OR of 19.25 in the top 10 percent, and an OR of 26.32 for DL compared to 6.29 for LDPred approach in top 5 percent - By producing such a high Odds Ratio (OR), DL-based approaches may enable cost-effective genetic screening (e.g., to a general population or a high-risk population such as individuals with family history and/or symptoms of CD) in the extremes of DL prediction)
As per claim 8,
The combined teaching of McGovern and Seres teaches the limitations of claim 1.
McGovern further teaches wherein selecting the at least one risk factor associated with developing the at least one disorder includes identifying at least one risk factor in a first year of the target prediction period associated with a diagnosis of the at least one disorder by the end of the target prediction period:
(Paragraphs [0003]-[0011], [0049]-[0053], [0084]-[0091] and [0222]-[0227] of McGovern. The teaching describes that inflammatory disease or condition may comprise a likelihood, risk, or susceptibility of having an inflammatory disease in the future (e.g., within about 1 hour- about 10 years, or more than about 10 years. Prediction model of CD risk was constructed using DeepLearning algorithms using genetic data from the IIBDGC cohort - best performance of risk prediction of complex human diseases using genetic data - DL predicted risk score is also strongly associated with disease clinical phenotypes of CD including disease location, severity and need for surgery.)
As per claim 9,
The combined teaching of McGovern and Seres teaches the limitations of claim 1.
McGovern further teaches wherein the at least one risk factor corresponds to at least one Clinical Classifications Software Refined (CCSR) category:
(Paragraphs [0072]-[0075] of McGovern. The teaching describes that a sample may be taken from a subject at risk of developing an inflammatory disease or disorder due to factors such as familial history, age, hypertension or pre-hypertension, 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)
As per claim 10,
The combined teaching of McGovern and Seres teaches the limitations of claim 1.
McGovern further teaches wherein the at least one disorder is breast cancer:
(Paragraph [0089] of McGovern. The teaching describes that the system can detect disorders including Breast Cancer, Breast Cancer in Men - HER2-Positive Breast Cancer)
As per claim 11,
The combined teaching of McGovern and Seres teaches the limitations of claim 1.
McGovern further teaches wherein the trained ML model is configured to receive input data corresponding to a user and provide a risk prediction indicating the user's risk of being diagnosed with the at least one disorder by the end of the target prediction period:
(Paragraphs [0003]-[0011] and [0116]-[0122] of McGovern. The teaching describes DeepLeaming algorithm may be used to apply a machine learning classifier to a plurality of inflammatory disease-associated genomic loci that are associated with individuals with known conditions (e.g., an inflammatory disease or disorder, such as an IBD) and individuals not having the condition (e.g., healthy individuals, or individuals who do not have an inflammatory disease or disorder, such as an IBD), in order to classify a subject as having the condition (e.g., positive test outcome) or not having the condition (e.g., negative test outcome))
As per claim 12,
The combined teaching of McGovern and Seres teaches the limitations of claim 11.
McGovern further teaches wherein the risk prediction includes a risk score:
(Paragraphs [0003]-[0011], [0049]-[0053], [0084]-[0091] and [0222]-[0227] of McGovern. The teaching describes that inflammatory disease or condition may comprise a likelihood, risk, or susceptibility of having an inflammatory disease in the future (e.g., within about 1 hour- about 10 years, or more than about 10 years. Prediction model of CD risk was constructed using DeepLearning algorithms using genetic data from the IIBDGC cohort - best performance of risk prediction of complex human diseases using genetic data - DL predicted risk score is also strongly associated with disease clinical phenotypes of CD including disease location, severity and need for surgery.)
As per claim 13,
Claim 13 is substantially similar to claim 1. Accordingly, claim 13 is rejected for the same reasons as claim 1.
As per claim 15,
Claim 15 is substantially similar to claim 4. Accordingly, claim 15 is rejected for the same reasons as claim 4.
As per claim 16,
Claim 16 is substantially similar to claim 5. Accordingly, claim 16 is rejected for the same reasons as claim 5.
As per claim 17,
Claim 17 is substantially similar to claim 6. Accordingly, claim 17 is rejected for the same reasons as claim 6.
As per claim 18,
Claim 18 is substantially similar to claim 8. Accordingly, claim 18 is rejected for the same reasons as claim 8.
As per claim 19,
Claim 19 is substantially similar to claim 9. Accordingly, claim 19 is rejected for the same reasons as claim 9.
As per claim 20,
Claim 20 is substantially similar to claim 10. Accordingly, claim 20 is rejected for the same reasons as claim 10.
As per claim 21,
Claim 21 is substantially similar to claim 11. Accordingly, claim 21 is rejected for the same reasons as claim 11.
As per claim 22,
Claim 22 is substantially similar to claim 12. Accordingly, claim 22 is rejected for the same reasons as claim 12.
Response to Arguments
Applicant's arguments filed October 20, 2025 have been fully considered.
Applicant’s arguments pertaining to the rejections made under 35 U.S.C. 102 are ultimately persuasive. McGovern did not disclose all of the limitations of claims 1 and 13. However, in the specific arguments, the Applicant argued that some limitations were not taught by McGovern, for which the Examiner was able to show that McGovern does teach. Please see the updated rejection above. Regardless, the primary argument still holds that McGovern was deficient in disclosing the limitations of claims 1 and 13. Accordingly, these rejections are removed and rejections made under 35 U.S.C. 103 have taken their place for the reasons indicated above.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 CHAD A NEWTON whose telephone number is (313)446-6604. The examiner can normally be reached M-F 8:00AM-4:00PM (EST).
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.
/CHAD A NEWTON/Primary Examiner, Art Unit 3681