DETAILED ACTION
Acknowledgements
This office action is in response to the claims filed January 20, 2026.
Claims 1, 2, 4, 6, 8, 10, 12-15, 17, 19-20, 22-24, 26, 28-33, 35, 37, and 55 are pending.
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 .
Response to Amendment(s)
Claims 1, 2, 4, 6, 8, 10, 12-15, 17, 19-20, 22-24, 26, 28-33, 35, 37, and 55 are pending.
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, 2, 4, 6, 8, 10, 12-15, 17, 19-20, 22-24, 26, 28-33, 35, 37, and 55 are rejected to under 35 U.S.C 101 as not being directed to eligible subject matter based on the grounds set out in detail below:
Independent Claims 1, 19, 37, and 55:
Eligibility Step 1 (does the subject matter fall within a statutory category?):
Independent claim 1 falls within the statutory category of machine
Independent claim 19 and 55 fall within the statutory category of method.
Independent claim 37 falls within the statutory category of article of manufacture.
Eligibility Step 2A-1 (does the claim recite an abstract idea, law of nature, or natural phenomenon?): Independent claims 1, 19, 37, and 55 claimed invention is directed to an abstract idea without significantly more.
The claim elements which set forth the abstract idea in the independent claims 1, 19, 37, and 55 (claim 1 being representative) are:
predicting cardiovascular disease,
data of a plurality of cardiovascular risk factors to output a cardiovascular risk score, the plurality of cardiovascular risk factors subdivided into a first training data subset and a second training data subset,
wherein the first training data subset comprises a preselected subset of cardiovascular risk factors, and wherein the second training data subset comprises a remaining subset of cardiovascular risk factors
wherein the preselected subset of cardiovascular risk factors have a linear relationship,
and wherein the remaining subset of cardiovascular risk factors have a non- linear relationship,
and wherein the preselected subset of cardiovascular risk factors are used as training inputs,
and wherein the remaining subset of cardiovascular risk factors are used to generate a non-linear covariate that is used as a training input;
input user-specific cardiovascular data of a user wherein the user is a member of a geographic region, wherein the user-specific cardiovascular data of the user is data of the user corresponding to the preselected subset of cardiovascular risk factors and the remaining subset of cardiovascular risk factors,
and wherein the outputs a user-specific cardiovascular prediction of the user, the user-specific cardiovascular prediction comprising a cardiovascular risk score of the user;
and display, the user-specific cardiovascular prediction.
The abstract idea is “certain methods of organizing human activity” by following rules and instructions to determine a cardiovascular disease (see MPEP § 2106.04(a)(2))
Eligibility Step 2A-2 (does the claim recite additional elements that integrate the judicial exception into a practical application?): For Independent claims 1, 19, 37, and 55 judicial exception is not integrated into a practical application.
Independent claim 1 recites the additional elements below:
A machine learning (ML)-based system
Trained ML model stored on a computer memory
a set of computing instructions stored on the computer memory
a processor communicatively coupled to the computer memory
a graphical user interface (GUI) with a display
Examiner takes the applicable considerations stated in MPEP 2106.04 (d) and analyzes them below in light of the instant applications disclosure and claim elements as a whole.
The additional element, (c) and (d), are recited as executing the abstract idea as “apply-it” or an equivalent to analyze data
The additional element, (a) and (b), is recited as “apply-it” or an equivalent to analyze data
The additional element, (e), is recited as “apply-it” or an equivalent to output data
Independent claims 19 and 55 do not recite any additional elements not already recited in the independent claim 1
Independent claim 37 recites the additional elements not already recited in the independent claim 1 below:
A tangible, non-transitory computer-readable medium
Examiner takes the applicable considerations stated in MPEP 2106.04 (d) and analyzes them below in light of the instant applications disclosure and claim elements as a whole.
The additional element, (a), is recited as executing the abstract idea as “apply-it” or an equivalent to analyze data
Accordingly, independent claims 1, 19, 37, and 55 as a whole do not integrate the recited abstract idea into a practical application (MPEP 2106.05(f) and 2106.04(d)(1).
Eligibility Step 2B (Does the claim amount to significantly more?): The independent claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements as analyzed above in step 2A prong 2, are merely applying the abstract idea and therefore, do not amount to significantly more. The claims are patent ineligible.
Dependent Claims 2, 4, 6, 8, 10, 12-15, 17, 20, 22-24, 26, 28-33, and 35
Eligibility Step 1 (does the subject matter fall within a statutory category?):
Dependent claims 2, 4, 6, 8, 10, 12-15, 17 fall within a statutory category as a machine
Dependent claims 20, 22-24, 26, 28-33, and 35 fall within the statutory category of method.
Eligibility Step 2A-1 (does the claim recite an abstract idea, law of nature, or natural phenomenon?): Dependent claims 2, 4, 6, 8, 10, 12-15, 17, 20, 22-24, 26, 28-33, and 35 claimed invention is directed to an abstract idea without significantly more. The claims continue to limit the independent claims 1 and 19 abstract idea by (1) further limiting the types of mathematical analysis, (2) further limiting the cardiovascular risk factor data, and (3) further limiting the output of cardiovascular risk and planning. Therefore, the dependent claims inherit the same abstract idea of “certain methods of organizing human activity” by following rules and instructions to determine a cardiovascular disease (see MPEP § 2106.04(a)(2))
Eligibility Step 2A-2 (does the claim recite additional elements that integrate the judicial exception into a practical application?): For claims 2, 4, 6, 8, 10, 12-15, 17, 20, 22-24, 26, 28-33, and 35 this judicial exception is not integrated into a practical application.
The dependent claims recite no additional elements not already recited in the independent claims thus purely considered as further limiting the abstract idea.
Accordingly, dependent claims 2, 4, 6, 8, 10, 12-15, 17, 20, 22-24, 26, 28-33, and 35 as a whole do not integrate the recited abstract idea into a practical application (MPEP 2106.05(f) and 2106.04(d)(1).
Eligibility Step 2B (Does the claim amount to significantly more?): The dependent claims do not include additional elements that amount to significantly more for the same reasons given in Prong 2. The claims are patent ineligible.
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.
Claims 1, 2, 4, 6, 8, 10, 12-15, 17, 19-20, 22-24, 26, 28-33, 35, 37, and 55 are rejected under 35 U.S.C. 103 as being unpatentable over Weng et. al (hereinafter Weng) (WO2024226519A2) in view of LAI et. al (hereinafter LAI) (WO2024238728A2)
As per claim 1, Weng teaches:
A machine learning (ML)-based system for predicting cardiovascular disease, the ML-based system comprising: an ML model stored on a computer memory, the ML model trained with data of a plurality of cardiovascular risk factors to output a cardiovascular risk score, ([0003] discloses, “In a first aspect, a method for training a composite model to predict cardiovascular disease risk is provided that includes: (i) training a machine learning model of the composite model to output, based on an input photoplethysmographic waveform, a first set of features that are representative of the photoplethysmographic waveform; (ii) determining, based on the photoplethysmographic waveform, a heart rate; (iii) determining, based on the first set of features, a mapping of the composite model to project the first set of features to a second set of features, wherein the second set of features includes fewer features than the first set of features; (iv) determining a set of model coefficients of the composite model to predict, based on the second set of features, the heart rate, and a set of demographic information, a cardiovascular disease risk score; and (v) outputting an indication of the machine learning model, mapping, and set of model coefficients of the composite model.” And see [0006] discloses, “In another aspect, a non-transitory computer readable medium is provided having stored thereon program instructions executable by at least one processor to cause the at least one processor to perform any of the above methods.” And see [0007] discloses, “In another aspect a system is provided that includes: (i) at least one processor; and (ii) a non-transitory computer-readable medium, having stored therein instructions executable by the at least one processor to cause the system to perform any of the above methods” and see [0025] Thus, in one form of the disclosure, a “composite model” is proposed comprising a machine learning model for processing an input photoplethysmographic waveform (e.g. captured from a certain human subject) to generate a first set of features representative of the waveform, optionally a dimensionality-reduction process (e.g. as explained above based on a plurality of eigenvectors associated with the composite model, such as determined based on a PCA analysis) to generate a second set of features from the first set, and a further model defined by a set of model coefficients designed to process the second set of features (or, in the absence of the dimensionality reduction model, the first set of features), and typically further data such as (i) data derived from the input photoplethysmographic waveform (i.e. derived other than via a machine learning model) such as a heart rate for the subject and/or (ii) data (e.g. demographic data) characterizing the subject, to output a cardiovascular disease risk score.)”)
the plurality of cardiovascular risk factors subdivided into a first training data subset and a second training data subset prior to training the ML model, wherein the first training data subset comprises a preselected subset of cardiovascular risk factors, and wherein the second training data subset comprises a remaining subset of cardiovascular risk factors ([0025] discloses, “Thus, in one form of the disclosure, a “composite model” is proposed comprising a machine learning model for processing an input photoplethysmographic waveform (e.g. captured from a certain human subject) to generate a first set of features representative of the waveform, optionally a dimensionality-reduction process (e.g. as explained above based on a plurality of eigenvectors associated with the composite model, such as determined based on a PCA analysis) to generate a second set of features from the first set, and a further model defined by a set of model coefficients designed to process the second set of features (or, in the absence of the dimensionality reduction model, the first set of features), and typically further data such as (i) data derived from the input photoplethysmographic waveform (i.e. derived other than via a machine learning model) such as a heart rate for the subject and/or (ii) data (e.g. demographic data) characterizing the subject, to output a cardiovascular disease risk score.” And see [0056] discloses, “Figure 3 is a flowchart of an example computer-implemented method 300. The method 300 includes training a machine learning model of the composite model to output, based on an input photoplethysmographic waveform, a first set of features that are representative of the photoplethysmographic waveform (310). The method 300 additionally includes determining, based on the photoplethysmographic waveform, a heart rate (320). The method 300 additionally includes determining, based on the first set of features, a mapping of the composite model to project the first set of features to a second set of features, wherein the second set of features includes fewer features than the first set of features (330). The method 300 additionally includes determining a set of model coefficients of the composite model to predict, based on the second set of features, the heart rate, and a set of demographic information, a cardiovascular disease risk score (340). And see Fig. 2A and 2B)
a set of computing instructions stored on the computer memory and configured to access the ML model; a processor communicatively coupled to the computer memory, and the processor configured to access the set of computing instructions and the ML model, wherein the computing instructions, when executed by the processor, cause the processor to: (see [0006] discloses, “In another aspect, a non-transitory computer readable medium is provided having stored thereon program instructions executable by at least one processor to cause the at least one processor to perform any of the above methods.” And see [0007] discloses, “In another aspect a system is provided that includes: (i) at least one processor; and (ii) a non-transitory computer-readable medium, having stored therein instructions executable by the at least one processor to cause the system to perform any of the above methods”)
…[…]…input user-specific cardiovascular data of a user into the ML model, wherein the user is a member of a geographic region, wherein the user-specific cardiovascular data of the user as input into the ML model is data of the user corresponding to the preselected subset of cardiovascular risk factors and the remaining subset of cardiovascular risk factors, ([0065] discloses, “The DLS was developed and evaluated using data from the UKB dataset, filtered to focus on participants aged 40-74. UKB participants who had PPG waveforms recorded were stratified into three subsets: train (n=105,319), tune (n=46,868), and test (n=57,702) subsets based on geographic information on the site of data collection, i.e., latitude and longitude. This strategy comports with TRIPOD guidelines on external validation (specifically validation on a different geographic region) by allowing for non-random variation between data splits such as differences in data acquisition or environment.” And see [0066] discloses, “PPG waveforms from all visits for the participants were used in the training subset to train the PPG feature extractor in DLS. The low-dimensional numeric outputs (embeddings) computed by this model were used as additional input features to the Cox model. To develop the Cox model that generates DLS to predict MACE risk, additional clinical and demographic variables and inclusion/exclusion criteria were added. Participants with non-fatal myocardial infarction or stroke before their first visit, or that were missing any of the variables for the model (age, sex, and smoking status), were excluded. Those without body mass index (BMI) or systolic BP (SBP) were also excluded for a fair comparison against the other office- and lab-based risk prediction models. For each participant, only the measurements related to their first visit were included. All numerically measured variables were standard-scaled. Cox models were regularized using a ridge penalty. In the final cohort, 97,970, 43,539, and 54,856 participants were included to train, tune, and test the survival model, respectively (Figure 6). The descriptive statistics of this cohort are listed in Table 1.”)
and wherein the ML model outputs a user-specific cardiovascular prediction of the user, the user-specific cardiovascular prediction comprising a cardiovascular risk score of the user; ([0019] discloses, “The systems and methods described herein apply such PPG waveform data to a machine learning model (e.g., a ResNet18 model or other variety of deep learning model) to generate a set of output features that are representative of the PPG waveform. These features are then applied, in combination with a heart rate determined from the PPG waveform and demographic information (e.g., at least one of sex, age, and smoking status (whether the patient has ever been a smoker, and optionally all of these), and optionally BMI or other additional information), to a statistical model (e.g., a Cox proportional hazards model) to predict a score that is indicative of the likelihood that the patient will develop cardiovascular disease within a specified time period (e.g., ten years).” And see [0026] discloses, “Optionally, based on the cardiovascular disease risk score, corresponding information may be output (e.g. if the method is carried out by a computer which is a piece of user equipment, the information may be output to the user using a screen of that user equipment). For example, the information may be a warning if the risk score is above a threshold. The warning may be in the form of a message to consult a health specialist. Alternatively or additionally, based on the cardiovascular disease risk score, it may be determined whether to administer a drug and/or apply a treatment to the subject, and the method may include administering that drug and/or that treatment.”)
and display, by a graphical user interface (GUI), the user-specific cardiovascular prediction. ([0026] discloses, “Optionally, based on the cardiovascular disease risk score, corresponding information may be output (e.g. if the method is carried out by a computer which is a piece of user equipment, the information may be output to the user using a screen of that user equipment). For example, the information may be a warning if the risk score is above a threshold. The warning may be in the form of a message to consult a health specialist. Alternatively or additionally, based on the cardiovascular disease risk score, it may be determined whether to administer a drug and/or apply a treatment to the subject, and the method may include administering that drug and/or that treatment.” And see [0029] discloses, “Note that the systems and methods herein for the use of PPG waveforms and related demographic information to predict risk of cardiovascular disease can also be used to predict a risk score related to a variety of other progressive chronic diseases or disorders and/or medical events related thereto. For example, the systems and method escribed herein could be modified to predict a risk score relating to the likelihood of developing diabetes or hypertension within a specified time period. Additionally or alternatively, such systems and methods could be used to determine whether a patient is likely to be hospitalized, experience a cardiovascular event (e.g., heart attack, stroke), be prescribed a drug (e.g., a blood pressure drug, a heart disease drug, a diabetes drug), receive a treatment (e.g., an angioplasty, installation of a stent), or experience some other medical event or activity. Additionally or alternatively, the systems and methods herein may be used, in the case of the other progressive chronic diseases or disorders, to cause the display or a warning if a risk score is above a threshold, and/or determine a drug and/or a treatment to apply to a subject, and the method may include administering that drug and/or treatment.”)
However, Weng does not explicitly teach:
wherein the preselected subset of cardiovascular risk factors have a linear relationship with the ML model, and wherein the remaining subset of cardiovascular risk factors have a non- linear relationship with the ML model, and wherein the preselected subset of cardiovascular risk factors are used as training inputs to the ML model, and wherein the remaining subset of cardiovascular risk factors are used to generate a non-linear covariate that is used as a training input to the ML model;
However, LAI does teach:
wherein the preselected subset of cardiovascular risk factors have a linear relationship with the ML model, ([0039] discloses, “In the image (CMR) branch, the LGE-MRI image vector embeddings z are obtained by firstly creating n non-overlapping 3D image patches xi E R16x 16x4 from the original 3D image X E R96x96xzo, obtaining linear projections of the flattened image patches, appending a classification token zc1s (CLS-token), and adding positional embeddings:” and see [0040] discloses, “In Equation (1 ), E is a linear projection mapping each flattened image patch to Rd, with dimension d being a hyperparameter of the model, and p E RCn+i)xd is a learned positional embedding added to the embeddings to retain positional information. Learnable positional embeddings are employed in the ViT model here.”
and wherein the remaining subset of cardiovascular risk factors have a non- linear relationship with the ML model, ([0044] discloses, “In the EHR and CIR branches, processed EHR and CIR data are converted to vectors zEHR, zcrn fed into specific fully connected FNNs. The FNNs each include multiple linear transformation layers, with each layer also succeeded by a normalization layer, a non-linear activation function, and a drop-out layer. The latent vectors zEHR and icrn representing the EHR and CIR knowledge are extracted hereby.” And see [0050] discloses, “The CMR, EHR and CIR sub-networks were trained individually in a first step, and then the tri-channel reduction to practice was trained end-to-end with all the sub-networks and the multi-modality fusion module.”)
and wherein the preselected subset of cardiovascular risk factors are used as training inputs to the ML model, and wherein the remaining subset of cardiovascular risk factors are used to generate a non-linear covariate that is used as a training input to the ML model;([0021] discloses, “Various embodiments include a scalable multi-modality deep learning (DL) method for ventricular arrhythmia risk stratification, e.g., in HCM patients. The DL method can automatically analyze multiple modalities of input data, e.g., images, including raw late gadolinium enhancement cardiac magnetic resonance (LGE-MRI) images, and clinical covariates from electronic health records (EHR). According to some embodiments, the clinical covariates from EHR data may include cardiac imaging report (CIR) data. According to some embodiments, EHR data including CIRdata is passed to a single channel in a trained machine learning system; according to other embodiments, the CIR data is passed to a channel different from a channel that receives other EHR data. Various embodiments may use dedicated neural networks to extract features from raw LGE-MRI images (e.g., based on pixel intensity of the raw images) and EHR data, the latter of which may be split and passed to two or more channels, e.g., CIR data and other EHR data, fuse the multi-modality knowledge, and output a personalized risk score for VA.” And see
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Weng’s teachings of predicting cardiovascular disease risk as cited above with LAI’s teachings of linear and non-linear covariate math as previously cited, the motivation being Weng is concerned with the costly nature of determining cardiovascular risk with current methods (see e.g. [0002]) therefore it would be obvious to decrease cost and simply substitute the method of machine learning in LAI as it requires less computational cost (e.g. [0045]) while still coming to a risk of cardiovascular disease and would not render Weng inoperable.
As per claim 2, Weng further teaches:
The ML-based system of claim 1, wherein the ML model is a Cox proportional hazards model, ([0064] discloses, “The new CVD risk prediction score, DLS, was developed using age, sex, smoking status, and the results of analysis of PPG signals using deep learning models as described herein. A Cox proportional hazard model and data from the UKB were used to predict the ten-year risk of MACE among individuals free of CVD at baseline.”)wherein the computing instructions are further configured, when executed by the processor, to implement or apply a gradient boosting algorithm to the second training data subset of the remaining subset of cardiovascular risk factors to enhance the Cox proportional hazards model. ([0029] discloses, “Note that the systems and methods herein for the use of PPG waveforms and related demographic information to predict risk of cardiovascular disease can also be used to predict a risk score related to a variety of other progressive chronic diseases or disorders and/or medical events related thereto. For example, the systems and method escribed herein could be modified to predict a risk score relating to the likelihood of developing diabetes or hypertension within a specified time period. Additionally or alternatively, such systems and methods could be used to determine whether a patient is likely to be hospitalized, experience a cardiovascular event (e.g., heart attack, stroke), be prescribed a drug (e.g., a blood pressure drug, a heart disease drug, a diabetes drug), receive a treatment (e.g., an angioplasty, installation of a stent), or experience some other medical event or activity. Additionally or alternatively, the systems and methods herein may be used, in the case of the other progressive chronic diseases or disorders, to cause the display or a warning if a risk score is above a threshold, and/or determine a drug and/or a treatment to apply to a subject, and the method may include administering that drug and/or treatment. II. Example Machine Learning Models and Training Thereof [0030] A machine learning model as described herein may include, but is not limited to: an artificial neural network (e.g., Transformers, layered models wherein each layer includes two or more sub-layers one or more of which could include artificial neural networks, convolutional neural networks, a recurrent neural network, a Bayesian network, a hidden Markov model, a Markov decision process, a logistic regression function, a support vector machine, a suitable statistical machine learning algorithm, and/or a heuristic machine learning system), a support vector machine, a regression tree, an ensemble of regression trees (also referred to as a regression forest), a decision tree, an ensemble of decision trees (also referred to as a decision forest), or some other machine learning model architecture or combination of architectures.” And see [0031] discloses, “An artificial neural network (ANN) could be configured in a variety of ways. For example, the ANN could include two or more layers, could include units having linear, logarithmic, or otherwise-specified output functions, could include fully or otherwise- connected neurons, could include recurrent and/or feed-forward connections between neurons in different layers, could include filters or other elements to process input information and/or information passing between layers, or could be configured in some other way to facilitate the processing of input sequences, sets of embedding vectors representing input sequences, downstream vectors and/or set of vector determined by the operation of one or more layers or sublayers of a multi-layer model, and/or individual vectors (e.g., embedding vectors representing tokens of an input sequence, downstream vectors representing the processing of such embedding vectors by one or more layers or sublayers of a multi-layer model).” And see [0066] discloses, “PPG waveforms from all visits for the participants were used in the training subset to train the PPG feature extractor in DLS. The low-dimensional numeric outputs (embeddings) computed by this model were used as additional input features to the Cox model. To develop the Cox model that generates DLS to predict MACE risk, additional clinical and demographic variables and inclusion/exclusion criteria were added. Participants with non-fatal myocardial infarction or stroke before their first visit, or that were missing any of the variables for the model (age, sex, and smoking status), were excluded. Those without body mass index (BMI) or systolic BP (SBP) were also excluded for a fair comparison against the other office- and lab-based risk prediction models. For each participant, only the measurements related to their first visit were included. All numerically measured variables were standard-scaled. Cox models were regularized using a ridge penalty. In the final cohort, 97,970, 43,539, and 54,856 participants were included to train, tune, and test the survival model, respectively (Figure 6). The descriptive statistics of this cohort are listed in Table 1.” And see [0067] discloses, “Table 1: Cohort statistics for 10-year major adverse cardiovascular events (MACE) risk prediction at the first UK Biobank visit.” And see [0068] discloses, “First Stage model development: PPG Feature Extractor [0069] For DLS, a deep learning-based feature extractor was trained to learn PPG representations from raw PPG waveform signals, using a one-dimensional ResNet18 as the neural network architecture. The feature extractor was trained on the train subset, network weights were picked that maximized the Cox pseudolikelihood on the tune subset. These weights were used to compute PPG embeddings on the train, tune, and test subsets. The PPG embeddings were further processed by principal component analysis (PCA) to five PCA- derived DLS features that were used by the survival model.” / examiner notes that the embeddings used to further the datasets of the cox model can be produced from machine learning models such as e.g. ensemble of regression trees which is interpreted to be a boosting under BRI)
As per claim 4, Weng further teaches:
The ML-based system of claim 1, wherein each of the plurality of cardiovascular risk factors is specific to a population of the geographic region and wherein the geographic region defining the plurality of cardiovascular risk factors on which the ML model is trained comprises a plurality subregions or cohorts comprising individuals located within each respective subregion or cohort. ([0065] The DLS was developed and evaluated using data from the UKB dataset, filtered to focus on participants aged 40-74. UKB participants who had PPG waveforms recorded were stratified into three subsets: train (n=105,319), tune (n=46,868), and test (n=57,702) subsets based on geographic information on the site of data collection, i.e., latitude and longitude. This strategy comports with TRIPOD guidelines on external validation (specifically validation on a different geographic region) by allowing for non-random variation between data splits such as differences in data acquisition or environment.” / examiner interprets the TRIPOD guidelines on external validation based on different geographic region for datasets as a plurality of cohorts with individuals located within each cohort)
As per claim 6, Weng further teaches:
The ML-based system of claim 1, wherein the preselected subset of cardiovascular risk factors comprises risk factors selected from one or more risk categories defining indications of cardiovascular health, and wherein the one or more risk categories comprise demographic factors, family history of disease, healthcare utilization, clinical laboratory testing, medication history, disease history, and drug use. ([0024] discloses, Training data used to train the machine learning model (and/or to determine coefficients of the statistical model that receives the output of the machine learning model) could include stored sets of PPG waveforms and associated demographic data (e.g., at least one of age, sex, smoking status, BMI) along with data about whether the corresponding individuals were diagnosed with cardiovascular disease (e.g., a date of diagnosis and/or experienced a myocardial infarction, stroke, cardiovascular-related death, or other event relative to a date of measurement of the PPG waveform and other demographic data, a severity of the cardiovascular disease suffered by the patient) and/or experienced some other cardiovascular event (e.g., myocardial infarction, stroke, cardiovascular-related death) such that they are in a higher-risk group. The amount of such data needed to train the machine learning model could be reduced by augmenting the available data. This could include using a process to generate additional PPG waveforms from the existing PPG waveforms by simulating random (e.g., pseudorandom) variations in the ‘rate of playback’ of the existing PPG waveforms, or otherwise imposing random time-varying time-shifts to the existing PPG waveforms. This could include generating a random time-varying playback speed (e.g., pseudo-randomly generated normally- distributed playback speed) and then using that playback speed to generate a corresponding time-varying time-shift (e.g., via a running sum) to be applied to the PPG waveform in order to simulate “playing back” the PPG according to the time-varying playback speed. Such a data augmentation method (which may be referred to as “Brownian tape speed augmentation”) could be applied in a variety of applications to a variety of training data, e.g., to training data that represents band-limited time-series data or other data whose essential features will not be abolished by the application of random (e.g., pseudo-random) time-shifts thereto.” And see [0061] discloses, “Multiple risk scores, such as the WHO/ISH risk chart and Globorisk scores, have been developed to triage CVD risk based on demographics, past medical history, vital signs, and laboratory data.” And see [0026] discloses, “Optionally, based on the cardiovascular disease risk score, corresponding information may be output (e.g. if the method is carried out by a computer which is a piece of user equipment, the information may be output to the user using a screen of that user equipment). For example, the information may be a warning if the risk score is above a threshold. The warning may be in the form of a message to consult a health specialist. Alternatively or additionally, based on the cardiovascular disease risk score, it may be determined whether to administer a drug and/or apply a treatment to the subject, and the method may include administering that drug and/or that treatment. For example, if the risk score is above a certain threshold, the system may issue an instruction to administer to the subject a dose of a drug (e.g. a drug previously prescribed for the patient) and/or a treatment.”)
As per claim 8, Weng further teaches:
The ML-based system of claim 1, and wherein the preselected subset of cardiovascular risk factors comprises one or more of values related to: age, sex, family history of diabetes, accident and emergency visits per year, aspartate transaminase, alanine aminotransferase, low-density lipoprotein cholesterol, neutrophil, statins, myocardial infarction, angina, revascularization, atrial fibrillation, hypertension, and/or user history of diabetes. ([0019] discloses, “The systems and methods described herein apply such PPG waveform data to a machine learning model (e.g., a ResNet18 model or other variety of deep learning model) to generate a set of output features that are representative of the PPG waveform. These features are then applied, in combination with a heart rate determined from the PPG waveform and demographic information (e.g., at least one of sex, age, and smoking status (whether the patient has ever been a smoker, and optionally all of these), and optionally BMI or other additional information), to a statistical model (e.g., a 69proportional hazards model) to predict a score that is indicative of the likelihood that the patient will develop cardiovascular disease within a specified time period (e.g., ten years). The model-predicted output features are related to specific features of the PPG waveform morphology and are independent of heart rate.” And see [0020] discloses, “The features that are representative of the PPG waveform and that are applied to the statistical model could be directly output from the machine learning model, or could be the result of projecting the model output into a lower-dimensional set of features. For example, a set of principal component analysis (PCA) eigenvectors or some other dimensionality- reduction method (e.g., independent component analysis, PCA using a nonlinear kernel, a support vector machine, an isometric mapping, multidimensional scaling, linear discriminant analysis, factor analysis, singular value decomposition, non-negative matrix factorization) could be used to reduce the number p of “first” features output from the model (e.g., 512 or more features, e.g. independently varying features) to a smaller number l of “second” features (e.g., five features), where l is less than p. [0021] The eigenvectors may be selected based on a n x p matrix derived from the first features for PPG waveforms for a plurality of subjects, and denoted X, where the number of rows n is an integer and the number of columns p is an integer which is the number of first features. For example, n may be a number of human subjects (for whom a PPG waveform is available), each row may correspond to a different subject, and each value of each element of the matrix may be the output of the machine learning model for the corresponding feature when a PPG waveform captured by a measurement of the corresponding subject is input to the machine learning model.” And see [0022] discloses, “The calculation of the eigenvectors may be done by a standard method. For example, a number l of p-component orthogonal unit-length eigenvectors ^^^ ^ for may be successively selected such that each corresponding n-component vector ^^ ^ ^^^ has maximum variance. Once this is done, a dimensionality-reduction process may be applied to set of first features output by the machine learning model based on a PPG waveform for a specific process, by a linear projection based on the eigenvectors of the composite model, e.g. by obtaining the corresponding dot products of a p-component vector comprising the p first features respectively with each of the l eigenvectors, to give the l respective second features.” And see [0023] discloses, “The trained machine learning model could be trained in a variety of ways using a variety of training data. For example, the machine learning model could be trained to predict, from input PPG waveforms, human-interpretable features determined from the PPG waveforms (e.g., pulse wave reflection index, peak to peak time, pulse wave peak position, pulse wave notch position, pulse wave shoulder position, whether a dicrotic notch is present, and/or an arterial stiffness index; here the peaks may be in pressure or in any other parameter indicated by the PPG waveform which varies during the cardiac cycle, e.g. with a single peak in each cycle) or some other set of available information that is relevant to the condition(s) or event(s) to be predicted for the individuals from whom the PPG waveforms had been detected (e.g., sex, age, BMI, hypertension status, hba1c, total cholesterol, systolic blood pressure, previous experience of at least one previous major adverse cardiovascular event, and PPG dicrotic notch presence). This could include training the machine learning model in combination with an output model (which could itself be a machine learning model) such that the output of the machine learning model is applied as an input to the output model, which then generates predictions of the target features (e.g., human-interpretable features of the input PPG waveform, a set of physiological data like age, sex, BMI, etc.). Additionally or alternatively, the machine learning model could be trained in a self-supervised manner (e.g., as part of an encoder-decoder pair), semi-supervised manner, or fully supervised manner to generate feature vectors that represent useful latent features in the set of PPG waveforms used as training data.” And see [0024] discloses, “Training data used to train the machine learning model (and/or to determine coefficients of the statistical model that receives the output of the machine learning model) could include stored sets of PPG waveforms and associated demographic data (e.g., at least one of age, sex, smoking status, BMI) along with data about whether the corresponding individuals were diagnosed with cardiovascular disease (e.g., a date of diagnosis and/or experienced a myocardial infarction, stroke, cardiovascular-related death, or other event relative to a date of measurement of the PPG waveform and other demographic data, a severity of the cardiovascular disease suffered by the patient) and/or experienced some other cardiovascular event (e.g., myocardial infarction, stroke, cardiovascular-related death) such that they are in a higher-risk group. The amount of such data needed to train the machine learning model could be reduced by augmenting the available data.” Also see Figs. 6 and 7)
As per claim 12, Weng further teaches:
The ML-based system of claim 1, wherein a C-statistic for the ML model has a value of at least 0.69. ([0080] discloses, “DLS demonstrated non-inferiority to the office-based refit-WHO score. The ten-year MACE risk prediction performance of all methods was evaluated using the UKB test subset, which was held-out during the training process. The DLS yielded a C-statistic of 71.1% (95% CI [69.9, 72.4]).”)
As per claim 13, Weng further teaches:
The ML-based system of claim 1, wherein the user-specific cardiovascular prediction is a cardiovascular disease (CVD) risk prediction for the user in a 10-year timeframe. ([0087] discloses, “A deep learning PPG-based CVD risk score as described herein, DLS, was developed to predict ten-year MACE risk using age, sex, smoking status, heart rate and deep learning-derived PPG features.”)
As per claim 14, Weng further teaches:
The ML-based system of claim 1, wherein the ML model is further trained with data of one or more drug classes identified for reducing cardiovascular disease (CVD), and wherein the user-specific cardiovascular data of the user as input into the ML model further comprises a selection of one or more of the drug classes, and wherein the user-specific cardiovascular prediction of the user comprises a CVD risk prediction that predicts the user's cardiovascular after using the one or more of the drug classes as selected. ([0029] discloses, For example, the systems and method escribed herein could be modified to predict a risk score relating to the likelihood of developing diabetes or hypertension within a specified time period. Additionally or alternatively, such systems and methods could be used to determine whether a patient is likely to be hospitalized, experience a cardiovascular event (e.g., heart attack, stroke), be prescribed a drug (e.g., a blood pressure drug, a heart disease drug, a diabetes drug), receive a treatment (e.g., an angioplasty, installation of a stent), or experience some other medical event or activity. Additionally or alternatively, the systems and methods herein may be used, in the case of the other progressive chronic diseases or disorders, to cause the display or a warning if a risk score is above a threshold, and/or determine a drug and/or a treatment to apply to a subject, and the method may include administering that drug and/or treatment.”)
As per claim 15, Weng further teaches:
The ML-based system of claim 1, wherein the GUI is configured to receive the user-specific cardiovascular data of the user, and wherein the GUI is further configured to provide the user-specific cardiovascular data as input to the ML model, wherein the GUI provides graphical fields or selections for selecting one or more types of drug classes for selection or generation of a user-specific plan to address the user's cardiovascular health. ([0029] discloses, “Additionally or alternatively, the systems and methods herein may be used, in the case of the other progressive chronic diseases or disorders, to cause the display or a warning if a risk score is above a threshold, and/or determine a drug and/or a treatment to apply to a subject, and the method may include administering that drug and/or treatment.” And see [0026] discloses, “Optionally, based on the cardiovascular disease risk score, corresponding information may be output (e.g. if the method is carried out by a computer which is a piece of user equipment, the information may be output to the user using a screen of that user equipment). For example, the information may be a warning if the risk score is above a threshold. The warning may be in the form of a message to consult a health specialist. Alternatively or additionally, based on the cardiovascular disease risk score, it may be determined whether to administer a drug and/or apply a treatment to the subject, and the method may include administering that drug and/or that treatment. For example, if the risk score is above a certain threshold, the system may issue an instruction to administer to the subject a dose of a drug (e.g. a drug previously prescribed for the patient) and/or a treatment.”)
As per claim 17, Weng further teaches:
The ML-based system of claim 1, wherein the user- specific cardiovascular prediction comprises at least one of: a user-specific medical prescription predicted to reduce the user's cardiovascular disease (CVD) risk or causes generation of a user-specific activity predicted to reduce the user's cardiovascular disease (CVD) risk. ([0026] discloses, “Optionally, based on the cardiovascular disease risk score, corresponding information may be output (e.g. if the method is carried out by a computer which is a piece of user equipment, the information may be output to the user using a screen of that user equipment). For example, the information may be a warning if the risk score is above a threshold. The warning may be in the form of a message to consult a health specialist. Alternatively or additionally, based on the cardiovascular disease risk score, it may be determined whether to administer a drug and/or apply a treatment to the subject, and the method may include administering that drug and/or that treatment. For example, if the risk score is above a certain threshold, the system may issue an instruction to administer to the subject a dose of a drug (e.g. a drug previously prescribed for the patient) and/or a treatment.”)
As per claims 19, 20, 22, 23, 24, 26, 29, 30, 31, 32, 33, 35, and 55 they are method claims which repeats the same limitations of claim 1, 2, 4, 6, 8, 10, 12, 13, 14, 15, and 17 the corresponding system claims, as a series of process steps as opposed to a collection of elements. Since the collective teaching of Weng and LAI as well as motivations to combine disclose the structural elements that constitute the system of claims 1, 2, 4, 6, 8, 10, 12, 13, 14, 15, and 17, it is respectfully submitted that they perform the underlying process steps, as well. As such, the limitations of claim 19, 20, 22, 23, 24, 26, 29, 30, 31, 32, 33, 35, and 55 are rejected for the same reasons given above for claim 1, 2, 4, 6, 8, 10, 12, 13, 14, 15, and 17.
As per claim 37, it is an article of manufacture claim which repeats the same limitations of claim 19, the corresponding method claim, as a collection of executable instructions stored on machine readable media as opposed to a series of process steps. Since the teachings of Weng and LAI as well as motivations to combine disclose the underlying process steps that constitute the method of claim 19 it is respectfully submitted that they likewise disclose the executable instructions that perform the steps as well. As such, the limitations of claim 37 are rejected for the same reasons given above for claim 19.
Claims 10 and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Weng et. al (hereinafter Weng) (WO2024226519A2) in view of LAI et. al (hereinafter LAI) (WO2024238728A2) and in further view of Sharma et. al (hereinafter Sharma) (WO2024249688A2)
As per claim 10 and similarly claim 28, Weng further teaches the underlined portions:
The ML-based system of claim 1, wherein at least a portion of the preselected subset of cardiovascular risk factors comprises imputed data generated to replace missing values and wherein the remaining subset of cardiovascular risk factors are not imputed, ([0075] discloses, “All models were trained on the same train subset and tuned on the tune subset except for laboratory-based refit-WHO score, metadata + PPG morphology, and the Full models that were trained, tuned, and compared based on a subset of the testing data without missing values of the input features.”)
and wherein the ML model is further trained with data defining one or more threshold risks, where each threshold risk defines a magnitude of a clinical health benefit to a user of the geographic region. ([0078] discloses, “Additional evaluation metrics included the category-free net reclassification improvement (cfNRI), and after defining a specific risk threshold (model operating point), sensitivity, specificity, NRI, and adjusted hazard ratio (HRs). For NRI and cfNRI, the respective event and non-event components were also reported. Risk thresholds were selected in three ways: (1) matching the sensitivity of SBP-140 (described next), (2) matching the specificity of SBP-140, and (3) the 10% predicted risk threshold suggested by the Globorisk study. Elevated SBP above 140 mmHg (“SBP-140”) was used for threshold selection because it was used as a simple single-visit indicator of BP control in the healthcare program of some countries such as India.”)
However Weng and LAI do not teach:
The ML-based system of claim 1, wherein at least a portion of the preselected subset of cardiovascular risk factors comprises imputed data generated to replace missing values…[…]…
However, Sharma does teach:
The ML-based system of claim 1, wherein at least a portion of the preselected subset of cardiovascular risk factors comprises imputed data generated to replace missing values…[…]…(page 4 para. 2 and page 5 para. 1 discloses, “Additionally or alternatively, in some embodiments, missing data is imputed into the training dataset and/or feature dimensionality is reduced. The missing data may be imputed by any suitable method, such as, but not limited to, by Multivariate Imputation by Chained Equations (MICE; using predictive mean matching (pmm)), Random Forests, or a combination thereof. The feature dimensionality may be reduced by any suitable method, such as, but not limited to, principal component analysis (PCA). For example, in one embodiment, PCA is applied to all features and the top PCs are selected for each of the following 10 thresholds of the total variance: 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 95%, and 99%. In some embodiments, the training dataset includes one or more different feature groups, with each feature group representing a different subset of the features. The different subsets include any suitable grouping of features, such as, but not limited to, CUIs…[…]…”)
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Weng’s teachings of predicting cardiovascular disease risk as cited above and LAIs teachings as cited previously with Sharma’s teachings of utilizing MICE for missing values, the motivation being that Weng’s already discloses a dimensionality-reduction process may take place (e.g. [0022]) and for e.g. MICE is a dimensionality-reduction technique to address issues with missing or incomplete data, therefore it would be predictable to decrease the uncertainty and lead to increased validity of the ML predictions and would not render Weng inoperable.
Response to Arguments Regarding 35 U.S.C § 101 Rejections
Applicant’s arguments on pages 1-4 of remarks have been considered. Applicant argues the following: The Examiner has alleged that the claims are directed to "certain methods of organizing human activity" by following rules and instructions to determine cardiovascular disease. Applicant respectfully disagrees. The Federal Circuit has distinguished between claims that are "directed to" a judicial exception and those that are not, including claims that improve the functioning of a computer or other technology or technical field. Limitations the courts have found indicative that an additional element may have integrated the exception into a practical application include an improvement in the functioning of a computer, or an improvement to other technology or technical field.
Independent claims 1, 19, 37, and 55, as amended, recite specific technical features that integrate any alleged abstract idea into a practical application by providing a concrete technical solution for processing incomplete medical datasets with reduced memory requirements while maintaining predictive accuracy. The claims recite subdividing a plurality of cardiovascular risk factors into a first training subset and a second training data subset prior to training the ML model, where the first training subset comprises a preselected subset of cardiovascular risk factors and the second training subset comprises a remaining subset of cardiovascular risk factors. As described in the specification, the remaining subset of cardiovascular risk factors may comprise a dataset across hundreds of factors that comprise raw data, and such raw data includes missing or empty values. As-Filed Specification, paragraph [0027]. Despite the missing or empty values, the disclosed invention allows for training the ML model without requiring the raw data of the second subset to be updated with additional data or otherwise completed in order to train the ML model to have a high degree of predictive accuracy. As-Filed Specification, paragraph [0027]. Claims 1, 19, 37, and 55, as amended, recite "wherein the preselected subset of cardiovascular risk factors have a linear relationship with the ML model, and wherein the remaining subset of cardiovascular risk factors have a non-linear relationship with the ML model, wherein the preselected subset of cardiovascular risk factors are used as training inputs to the ML model, and wherein the remaining subset of cardiovascular risk factors are used to generate a non-linear covariate that is used as a training input to the ML model." This specific technical architecture is not merely organizing human activity but describes how different categories of risk factors are processed differently based on their relationship to the model.
This technical approach improves the functioning of the computer itself because the underlying computing device can operate with reduced memory storage-it need not store complete datasets across all of the risk factors in order to train or otherwise generate the ML model. As-Filed Specification, paragraph [0027]. This improves over the prior art at least because existing methodologies require extensive and complete datasets, requiring increased memory storage and processing power in order to successfully train a given model with any degree of accuracy. As-Filed Specification, paragraph [0027]. By contrast, the ML-based systems and methods recited in claims 1, 19, 37, and 55 can be trained on reduced or otherwise incomplete datasets, while still allowing for accurate predictions. This also increases the speed and efficiency of training the ML model, as the ML model can be trained and generated with less processing power or resources as compared to known ML training techniques that require larger datasets. As-Filed Specification, paragraph [0027].
The claims recite cardiovascular risk factors as a preselected subset. These preselected risk factors are identified as highly predictive covariates with respect to predicting cardiovascular disease and have a higher level of data completeness, event rate occurrence, or medical values or other conditions related to CVD. This is not an abstract concept but a specific technical selection that enables the reduced memory and processing requirements.
The application of a gradient boosting algorithm to the remaining subset of cardiovascular risk factors allows efficient handling of missing values without requiring significant preprocessing or data backfilling. As-Filed Specification, paragraph [0093]. Applying the gradient boosting algorithm to the data of the remaining subset of cardiovascular risk factors allows for generation of an additional covariate for use in the ML Model and to account for a nonlinear relationship between such remaining subset of cardiovascular risk factors and the preselected subset of cardiovascular risk factors. As-Filed Specification, paragraph [0094]. The remaining subset of cardiovascular risk factors are not imputed, and non-imputed data may comprise raw data. Use of raw data for the remaining subset of cardiovascular risk factors allows the invention to operate with reduced memory data storage requirements, while still allowing the ML model to be highly predictive. As-Filed Specification, paragraph [0098]. The technical improvement recited in claims 1, 19, 37, and 55 is analogous to improvements found patent-eligible under Step 2A Prong 2, where claims that improve computer functionality or other technology are integrated into a practical application. Here, the specific bifurcated training approach with linear and non-linear relationships, combined with the generation of a non-linear covariate from incomplete data, provides a concrete improvement in how computing systems process and train on medical datasets. The claims do not merely recite generic computer components implementing an abstract idea. Rather, claims 1, 19, 37, and 55 recite a specific technical architecture where the preselected cardiovascular risk factors have a linear relationship with the ML model, the remaining cardiovascular risk factors have a non- linear relationship with the ML model, and the remaining subset is used to generate a non-linear covariate that impacts risk score output. This specific technical configuration enables the reduced memory and processing requirements that constitute the technical improvement.
Accordingly, independent claims 1, 19, 37, and 55, as amended, integrate any alleged abstract idea into a practical application under Step 2A Prong 2 because they recite specific technical features that provide concrete improvements in computer functionality-namely, reduced memory storage requirements and increased processing efficiency when training ML models on incomplete medical datasets.
Dependent claims 2, 4, 6, 8, 10, 12-15, and 17 depend from independent claim 1 and are patent-eligible for at least the same reasons as claim 1. Dependent claims 20, 22-24, 26, 28-33, and 35 depend from independent claim 19 and are patent-eligible for at least the same reasons as claim 19.
Applicant respectfully requests withdrawal of the rejection under 35 U.S.C. § 101.
Examiner appreciates applicant’s arguments but respectfully does not find them persuasive. The MPEP states The Alice/Mayo two-part test is the only test that should be used to evaluate the eligibility of claims under examination. While the machine-or-transformation test is an important clue to eligibility, it should not be used as a separate test for eligibility. Instead it should be considered as part of the "integration" determination or "significantly more" determination articulated in the Alice/Mayo test. Bilski v. Kappos, 561 U.S. 593, 605, 95 USPQ2d 1001, 1007 (2010). See MPEP § 2106.04(d) for more information about evaluating whether a claim reciting a judicial exception is integrated into a practical application and MPEP § 2106.05(b) and MPEP § 2106.05(c) for more information about how the machine-or-transformation test fits into the Alice/Mayo two-part framework.
The enumerated groupings of abstract ideas are defined as:
1) Mathematical concepts – mathematical relationships, mathematical formulas or equations, mathematical calculations (see MPEP § 2106.04(a)(2), subsection I); (Mathematical Calculations - A claim that recites a mathematical calculation, when the claim is given its broadest reasonable interpretation in light of the specification, will be considered as falling within the "mathematical concepts" grouping. A mathematical calculation is a mathematical operation (such as multiplication) or an act of calculating using mathematical methods to determine a variable or number, e.g., performing an arithmetic operation such as exponentiation. There is no particular word or set of words that indicates a claim recites a mathematical calculation. That is, a claim does not have to recite the word "calculating" in order to be considered a mathematical calculation. For example, a step of "determining" a variable or number using mathematical methods or "performing" a mathematical operation may also be considered mathematical calculations when the broadest reasonable interpretation of the claim in light of the specification encompasses a mathematical calculation.)
2) Certain methods of organizing human activity – fundamental economic principles or practices (including hedging, insurance, mitigating risk); commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations); managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions) (see MPEP § 2106.04(a)(2), subsection II); and
3) Mental processes – concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III).
Examiners should determine whether a claim recites an abstract idea by (1) identifying the specific limitation(s) in the claim under examination that the examiner believes recites an abstract idea, and (2) determining whether the identified limitations(s) fall within at least one of the groupings of abstract ideas listed above. Furthermore, the MPEP state in 2106.04(d), “Examiners evaluate integration into a practical application by: (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception(s); and (2) evaluating those additional elements individually and in combination to determine whether they integrate the exception into a practical applications.”
The positively recited claim 1 (as representative) is directed to a judicial exception (i.e. certain methods of organizing human activity) as merely following rules or instructions to determine a cardiovascular risk prediction of a patient this is abstract in substance as a physician today with or without the aid of a computer environment can determine based on abstract algorithm or reasoning whether data indicates risk of cardiovascular disease by following rules and instructions. Being implemented by a computer environment and applying machine learning does not make the recited claim dispositive of being certain methods of organizing human activity. Furthermore, the claim is taken at its broadest reasonable interpretation based on claim construction and the specification is not read into the claims and it’s not would a human do it but could a human do it and it is not dispositive of being an abstract idea just because a computer is used. Examiner maintains the claims are certain methods of organizing human activity.
Further responding to applicants arguments, the judicial exception (abstract idea) cannot integrate itself into a practical application but identification of any additional elements recited in the claim can be evaluated to determine if the additional elements integrate the exception into a practical application. The claims additional elements are not recited as being an improvement to a technology field or a technology confined to the computer environment in which the claims recite. A technical problem must first be identified in instant application specification and reflected in the claims. Applicant states the claims recite and reflect providing a concrete technical solution for processing incomplete medical datasets with reduced memory requirements while maintaining predictive accuracy by improving the underlying computing device so it can operate with reduced memory storage as it need not store complete datasets across all of the risk factors in order to train or otherwise generate the ML model and further efficiently handling missing values without requiring significant preprocessing or data backfilling.
The additional elements are apply it level in light of the BRI of the claim construction and the claims do not recite technical improvements to the computer or machine learning whether alone or in combination with the abstract idea. The abstract idea of data configuration and management such as choosing subsets of data to train or not train the model with to predict a cardiovascular disease cannot bring forth the practical application as it is a part of the abstract idea. The trained machine learning model and machine learning system are recited at a very broad and high level in the claim and reflect the application a processor to use or apply the machine learning model to previously preselected data sets and then remaining data to bring forth the prediction. Examiner notes the technology of the memory of a computer, training process or the trained machine learning modelling itself for predictive accuracy as confined to the general computer environment in which the claim recites is not reflected in the claim as being improved, rather the claim recites management of what data is preselected and managed for this process which is improvement to the abstract idea and the abstract idea cannot bring forth the improvement or practical application. Examiner maintains the claims are directed to an abstract idea and do not integrate into a practical application. Therefore, they also do not amount to significantly more.
Examiner maintains the 35 U.S.C § 101 rejection
Response to Arguments Regarding 35 U.S.C § 102/103 Rejections
Applicant’s arguments on pages 4-8 of remarks have been considered. Applicant argues the 35 U.S.C § 102 rejection Applicant’s arguments with respect to the claims have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant argues claims 10 and 28 are rejected under 35 U.S.C. § 103 as being unpatentable over Weng in view of Sharma. Office Action, page 26. Applicant respectfully traverses this rejection.
Additionally, even assuming arguendo that Weng in view of Sharma could teach the features of the independent claims, the combination still fails to teach the specific limitation recited in claims 10 and 28 that "the ML model is further trained with data defining one or more threshold risks, where each threshold risk defines a magnitude of a clinical health benefit to a user of the geographic region."
The Examiner has alleged that Weng at paragraph [0078] teaches threshold risks.
However, Weng's paragraph [0078] discloses that "[a]dditional evaluation metrics included the category-free net reclassification improvement (cfNRI), and after defining a specific risk threshold (model operating point), sensitivity, specificity, NRI, and adjusted hazard ratio (HRs)." Weng et al., paragraph [0078]. Weng further discloses that "[r]isk thresholds were selected in three ways: (1) matching the sensitivity of SBP-140 (described next), (2) matching the specificity of SBP-140, and (3) the 10% predicted risk threshold suggested by the Globorisk study." Weng et al., paragraph [0078]. Applicant respectfully submits that Weng's risk thresholds are used for model evaluation purposes-specifically for calculating sensitivity, specificity, and net reclassification improvement metrics. These thresholds are operating points for evaluating model performance, not data used to train the ML model where each threshold risk defines a magnitude of a clinical health benefit.
In contrast, claims 10 and 28 recite that "the ML model is further trained with data defining one or more threshold risks, where each threshold risk defines a magnitude of a clinical health benefit to a user of the geographic region." The claimed threshold risks define magnitudes of clinical health benefits, such as the clinical value of treatment decisions. This is fundamentally different from Weng's use of risk thresholds as operating points for calculating evaluation metrics like sensitivity and specificity.
Applicant further submits that Sharma does not cure this deficiency. Sharma teaches that "missing data is imputed into the training dataset and/or feature dimensionality is reduced. The missing data may be imputed by any suitable method, such as, but not limited to, by Multivariate Imputation by Chained Equations (MICE; using predictive mean matching (pmm))." Sharma et al., page 13, Lines 10-14. Sharma's teachings relate to imputation of missing data values, not to training an ML model with data defining threshold risks where each threshold risk defines a magnitude of a clinical health benefit.
Accordingly, Applicant respectfully submits that the combination of Weng and Sharma fails to teach or suggest "the ML model is further trained with data defining one or more threshold risks, where each threshold risk defines a magnitude of a clinical health benefit to a user of the geographic region" as recited by claims 10 and 28, and the rejection under 35 U.S.C. § 103 should be withdrawn.
Examiner appreciates applicants arguments but does not find it persuasive. Claim 10 (as representative) recites “The ML-based system of claim 1, wherein at least a portion of the preselected subset of cardiovascular risk factors comprises imputed data generated to replace missing values and wherein the remaining subset of cardiovascular risk factors are not imputed, and wherein the ML model is further trained with data defining one or more threshold risks, where each threshold risk defines a magnitude of a clinical health benefit to a user of the geographic region.” And Wang clearly teaches the underlined portions of the claim in paragraph [0075]which discloses, “All models were trained on the same train subset and tuned on the tune subset except for laboratory-based refit-WHO score, metadata + PPG morphology, and the Full models that were trained, tuned, and compared based on a subset of the testing data without missing values of the input features.” And see [0078] discloses, “Additional evaluation metrics included the category-free net reclassification improvement (cfNRI), and after defining a specific risk threshold (model operating point), sensitivity, specificity, NRI, and adjusted hazard ratio (HRs). For NRI and cfNRI, the respective event and non-event components were also reported. Risk thresholds were selected in three ways: (1) matching the sensitivity of SBP-140 (described next), (2) matching the specificity of SBP-140, and (3) the 10% predicted risk threshold suggested by the Globorisk study. Elevated SBP above 140 mmHg (“SBP-140”) was used for threshold selection because it was used as a simple single-visit indicator of BP control in the healthcare program of some countries such as India.” Examiner notes Wang teaches one or more threshold risk determinations such as net benefits where the threshold selection is used as an indicator of BP control in a country such as India therefore defining a magnitude of benefit of an indicator based on geographic region for BP control based on net benefit improvement metrics which provide a clear classification picture of whether a patient will have a specific condition therefore under BRI this is considered understood by someone of ordinary skill in the art as a clinical health benefit metric based on geographic region when defining threshold risk in the broad manner in which it is claimed as there Is no specific clinic benefit metric claimed or what the magnitude in relation to threshold risk is.
Therefore, Examiner maintains the 35 USC 103 rejection.
Prior Art not cited but made of record
US20110105852- Morris et. al
Techniques for generating prediction of risks of medical outcomes and benefit scores for medical interventions, with imputation of missing patient data values, are disclosed. Apparatus or computer program products may be configured to receive a patient record for the patient from a database of a data storage unit, wherein one or more demographic data values or biometric data values in the patient record are missing or have null values; create and store a plurality of clone patient records in the database; impute a plurality of different Substitute demographic data values or biometric data values and substitute a different one of the plurality of substitute values into each one of the clone patient records; determine, create and store a first metric, based at least in part on the clone patient records, wherein the first metric comprises a current health related metric for the patient; determine, create and store one or more medical intervention metrics, each based at least in part on an associated medical intervention and the clone patient records, representing a predicted health related metric for the patient when the associated medical intervention is performed; transform the database by updating the patient record to include the first metric and the one or more medical intervention metrics.
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 Ashley Elizabeth Evans whose telephone number is (571) 270-0110. The examiner can normally be reached Monday – Friday 8:00 AM – 5:00 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Mamon Obeid can be reached on (571) 270-1813. The fax phone number for the organization where this application or proceeding is assigned 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. Should you have questions on access to the Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
/ASHLEY ELIZABETH EVANS/Examiner, Art Unit 3687
/MAMON OBEID/Supervisory Patent Examiner, Art Unit 3687
Prosecution Insights