DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Claims
The office action is in response to the claims filed on July 7, 2025 for the application filed October 8, 2024 which claims priority to an application filed on May 19, 2022. Claims 16-32, 34-35 and 37 are currently pending and have been examined.
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 16-32, 34-35 and 37 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Eligibility Step 1:
Under step 1 of the 2019 Revised Patent Subject Matter Eligibility Guidance, claims 16-32 and 34 are directed towards a method (i.e. a process), which is a statutory category. Claims 35 and 37 are directed towards a non-transitory computer-readable medium (i.e. a manufacture), which is a statutory category. Since the claims are directed toward statutory categories, it must be determined if the claims are directed towards a judicial exception (i.e. a law of nature, a natural phenomenon, or an abstract idea). In the instant application, the claims are directed towards an abstract idea.
Eligibility Step 2A, Prong One:
Under step 2A, prong one of the 2019 Revised Patent Subject Matter Eligibility Guidance, independent claims 16, 34 and 35 are determined to be directed to an judicial exception because an abstract idea is recited in the claims which fall within the subject matter groupings of abstract ideas.
The abstract idea (identified in bold) recited in representative claim 16 is identified as:
A method comprising:
obtaining, by a computing system, an observation of demographic values of an individual, vital sign values of the individual, and blood test values of the individual;
applying, by the computing system, a machine learning model to the observation, wherein the machine learning model was trained with a training data set, wherein the training data set contained observations of corresponding demographic values, vital sign values, blood test values, and either urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values for a plurality of individuals, and wherein the machine learning model is configured to provide predictions of whether further observations are indicative of undiagnosed albuminuria or proteinuria; and
providing, by the computing system, a prediction of whether the individual exhibits undiagnosed albuminuria or proteinuria based on the observation.
The abstract idea (identified in bold) recited in claim 34 is identified as:
A method comprising:
obtaining, by a computing system, a quantile and an observation of demographic values of an individual, vital sign values of the individual, and blood test values of the individual;
applying, by the computing system, a quantile regression machine learning model to the observation, wherein the quantile regression machine learning model was trained with a training data set, wherein the training data set contained observations of corresponding demographic values, vital sign values, blood test values, and either urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values for a plurality of individuals, and wherein the quantile regression machine learning model is configured to provide predictions of UACR or UPR values at one or more quantiles for further observations; and
based on the observation and for the individual, providing, by the computing system, a prediction of a UACR or UPR value at the quantile.
The identified limitations of the abstract idea of claims 1, 34 and 35 fall within the subject matter grouping of certain methods of organizing human activity related and the sub grouping of managing personal behavior or relationships or interactions between people, (including social activities, teaching, and following rules or instructions), commercial or legal interactions (including agreements in the form of contracts, legal obligations, advertising, marketing or sales activities or behaviors, and business relations) or fundamental economic principles or practices (including hedging, insurance, mitigating risk). The identified abstract idea recites the human activity of providing predictions based on obtained observations, which is routinely performed by human such as physicians. Limiting the observed data to demographic values of an individual, vital sign values of the individual, and blood test values of the individual and the prediction to whether the individual exhibits undiagnosed albuminuria or proteinuria, as in claims 1 and 35, is a certain method of organizing the human activating of providing predictions based on obtained observed data. Similarly, limiting the a prediction to a UACR or UPR value at an obtained quantile, as in claims 34, is a certain method of organizing the human activating of providing predictions based on obtained observed data, such as providing quantile prediction.
Accordingly, claims 16, 34 and 35 recite an abstract idea under step 2A, prong one.
Eligibility Step 2A, Prong Two:
Under step 2A, prong two of the 2019 Revised Patent Subject Matter Eligibility Guidance, it must be determined whether the identified abstract ideas are integrated into a practical application. After evaluation, there is no indication that any additional elements or combination of elements integrate the abstract idea into a practical application, such as through: an additional element that reflects an improvement to the functioning of a computer, or an improvements to any other technology or technical field; an additional element that applies or uses a judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition; an additional element that implements the judicial exception with, or uses the judicial exception in connection with, a particular machine or manufacture that is integral to the claim; an additional element that effects a transformation or reduction of a particular article to a different state or thing; or an additional element that applies or uses the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. As shown below, the additional elements, other than the abstract idea per se, when considered both individually and as an ordered combination, amount to no more than a recitation of: generally linking the abstract idea to a particular technological environment or field of use; insignificant extra-solution activity to the judicial exception; and/or adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea as evidenced below.
The additional elements recited in representative claim 16 are identified in italics as:
A method comprising:
obtaining, by a computing system, an observation of demographic values of an individual, vital sign values of the individual, and blood test values of the individual;
applying, by the computing system, a machine learning model to the observation, wherein the machine learning model was trained with a training data set, wherein the training data set contained observations of corresponding demographic values, vital sign values, blood test values, and either urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values for a plurality of individuals, and wherein the machine learning model is configured to provide predictions of whether further observations are indicative of undiagnosed albuminuria or proteinuria; and
providing, by the computing system, a prediction of whether the individual exhibits undiagnosed albuminuria or proteinuria based on the observation.
The additional elements recited in claim 34 are identified in italics as:
A method comprising:
obtaining, by a computing system, a quantile and an observation of demographic values of an individual, vital sign values of the individual, and blood test values of the individual;
applying, by the computing system, a quantile regression machine learning model to the observation, wherein the quantile regression machine learning model was trained with a training data set, wherein the training data set contained observations of corresponding demographic values, vital sign values, blood test values, and either urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values for a plurality of individuals, and wherein the quantile regression machine learning model is configured to provide predictions of UACR or UPR values at one or more quantiles for further observations; and
based on the observation and for the individual, providing, by the computing system, a prediction of a UACR or UPR value at the quantile.
The additional limitations of “”by a/the computer system” and “non-transitory computer-readable medium” (claim 35) are determined to be mere instructions to apply an abstract idea under MPEP §2106.05(f). The computer system and non-transitory computer-readable medium are recited at a high level of generality and used in their ordinary capacity to implement the abstract idea .Therefore, these additional elements amount to no more than a recitation of the words "apply it" (or an equivalent) or no more than mere instructions to implement an abstract idea or other exception on a computer or no more than merely using a computer as a tool to perform an abstract idea. The limitations reciting “applying, by the computing system, a machine learning model to the observation, wherein the machine learning model was trained with a training data set, wherein the training data set contained observations of corresponding demographic values, vital sign values, blood test values, and either urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values for a plurality of individuals” and “applying, by the computing system, a quantile regression machine learning model to the observation, wherein the quantile regression machine learning model was trained with a training data set, wherein the training data set contained observations of corresponding demographic values, vital sign values, blood test values, and either urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values for a plurality of individuals” provide nothing more than mere instructions to implement an abstract idea on a generic computer. See MPEP 2106.05(f). The trained machine learning model and quantile regression machine learning model are used to generally apply the abstract idea without placing any limits on how the trained machine learning models function. Rather, these limitations only recite the outcome of “providing predictions of whether further observations are indicative of undiagnosed albuminuria or proteinuria” and “providing predictions of UACR or UPR values at one or more quantiles ” and do not include any details about how the “predictions” are accomplished. See MPEP 2106.05(f).
The additional limitations of “XXX” are determined to be no more than insignificant extra-solution activity to the judicial exception under MPEP §2106.05(g). Provide an explanation using the guidance in MPEP §2106.05(g).
The additional limitations of “applying… a quantile regressions machine learning model… to provide predictions at one or more quantiles” in claim 34 is also determined to be no more than generally linking the use of a judicial exception to a particular technological environment or field of use under MPEP §2106.05(h). Although the additional element limits the identified judicial exceptions “providing predictions of UACR or UPR values at one or more quantiles for further observations” this type of limitation merely confines the use of the abstract idea to a particular technological environment (quantile regression) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Accordingly, claims 1, 34 and 35 do not recite additional elements which integrate the abstract idea into a practical application.
Eligibility Step 2B:
Under step 2B of the 2019 Revised Patent Subject Matter Eligibility Guidance, it must be determined whether provide an inventive concept by determining if the claims include additional elements or a combination of elements that are sufficient to amount to significantly more than the judicial exception. After evaluation, there is no indication that an additional element or combination of elements are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional limitations amount to mere instructions to apply an abstract idea under MPEP §2106.05(f) and generally linking the use of a judicial exception to a particular technological environment or field of use under MPEP §2106.05(h), which cannot amount to significantly more than the judicial exception.
Furthermore, looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements amounts to an inventive concept.
Dependent Claims:
The dependent claims merely present additional abstract information in tandem with further details regarding the elements from the independent claims and are, therefore, directed to an abstract idea for similar reasons as given above. None of these limitations are deemed to integrate the claims into a practical application or to amount to significantly more than the abstract idea as detailed below.
Regarding claims 17-18, limiting the obtaining of observations to be from a client device in communication with the computing system over a network, and the providing the prediction to be include transmitting the prediction to the client device and displaying the prediction on a graphical user interface are determined to be additional elements that amount to mere instructions to apply an abstract idea under MPEP §2106.05(f).
Regarding claims 19-21, further limiting the observation to include specific data is considered part of the identified abstract idea.
Regarding claims 22, 27, 28, 29 and 37, further defining the training data set which was used to train the machine learning model is insignificant pre-solution activity under MPEP §2106.05(g) and well-understood, routine and conventional as evidenced by Klug, Obermeyer and Mortenza.
Regarding claims 23, limiting the machine learning model to be based on gradient boosting is also determined to be no more than generally linking the use of a judicial exception to a particular technological environment (gradient boosting) under MPEP §2106.05(h).
Regarding claims 24-26, further limiting the provided prediction to include specific predictions is considered part of the identified abstract idea
Regarding claims 30-31, recommending treatments and clinical trial enrollment based on the predictions is considered part of the identified abstract idea.
Regarding claim 32, the limiting the training data set to include UACR values mathematically derived from UPR values is insignificant pre-solution activity under MPEP §2106.05(g) and well-understood, routine and conventional as evidenced by Weaver.
Therefore, whether taken individually or as an ordered combination, 16-32, 34-35 and 37 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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 16-21, 23-26, 29, 32, 34-35 and 37 are rejected under 35 U.S.C. 103 as being unpatentable over Mortenza et al. (Inconsistency in albuminuria predictors in type 2 diabetes: a comparison between neural network and conditional logistic regression) in view of Xiao et al. (Comparison and development of machine learning tools in the prediction of chronic kidney disease progression) and Weaver et al. (Estimating Urine Albumin-to-Creatinine Ratio from Protein-to-Creatinine Ratio: Development of Equations using Same-Day Measurements).
Regarding claim 16, Morteza discloses a method comprising:
obtaining,Page 397, Abstract, The input variables were sex, duration of diabetes, systolic and diastolic blood pressure, glomerular filtration rate, high-density lipoprotein, low-density lipoprotein, triglyceride, high-density lipoprotein/triglyceride ratio, cholesterol, fasting blood sugar, and glycated hemoglobin. Age and BMI were included only in the neural network model. Also see pages 398-399, Methods and Blood Samples.);
applying,Page 399, Statistical Analysis, A total of 621 cases were analyzed using the neural network to predict normo-, micro-, and macro-albuminuria. To correct for potential detection errors using the neural network, we integrated data from 3 different types of “samples”: training, testing, and holdout samples. The training sample consists of data records used to train the neural network to populate the model. The testing sample is an independent set of data records used to track errors during training to prevent overtraining. Network training is generally more efficient if the testing sample is smaller than the training sample. The holdout sample is another independent set of data records used to assess the final neural network. Since the holdout cases were not used to build the model, the error of the holdout samples provides an “honest” estimate of the predictive capacity of the model. Therefore, the training sample must have the largest size, the testing sample is intermediate, and the holdout sample is the smallest. Patients were randomly classified into (1) training (388/621; 62.5%), (2) testing (168/621; 27.1%), and (3) holdout (65/621; 10.5%) groups. The neural network uses a learning algorithm to define the nonlinear mathematical transfer functions to modify the synaptic weights of a network’s processing units in an orderly fashion to obtain the desired outcome prediction (training data sets). Input variables were age, sex, time of onset of diabetes, systolic and diastolic blood pressure, eGFR, HDL-cholesterol, LDL, FBS, TG, HDL/TG ratio, HbA1c, and cholesterol. Normo, micro-, and macro-albuminuria were defined as urinary albumin excretion rate <30 mg/24 h, between 30 and 300 mg/24 h, and >300 mg/24 h, respectively.); and
providing,Page 397, Abstract, We have used 2 different statistical models to predict albuminuria in type 2 diabetes mellitus: a multilayer perception neural network and a conditional logistic regression. Neural network models were used to predict the level of albuminuria in patients with type 2 diabetes mellitus. Our neural network model complements the current risk factor models to improve the care of patients with diabetes. Page 399, Statistical Analysis, A total of 621 cases were analyzed using the neural network to predict normo-, micro-, and macro-albuminuria.).
Morteza does not appear to explicitly disclose that the method is done by a computer system; wherein the training data set contained observations of corresponding to urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR); or wherein the machine learning model is configured to provide predictions of whether further observations are indicative of undiagnosed albuminuria or proteinuria.
Xiao teaches that it was old and well known in the art of albuminuria and proteinuria diagnosis at the time of the filing to use a computer system to obtain observations, apply a machine learning model to provide predictions of whether further observations are indicative of undiagnosed albuminuria or proteinuria; and provide a prediction of whether the individual exhibits undiagnosed albuminuria or proteinuria based on the observation (Xiao, Page 1, Objective, To quickly predict the severity of CKD using more easily available demographic and blood biochemical features during follow-up, we developed and compared several predictive models using statistical, machine learning and neural network approaches. Page 1, Results, Blood-derived tests could be applied as non-urinary predictors during outpatient follow-up. Features in routine blood tests, including ALB, Scr, TG, LDL and EGFR levels, showed predictive ability for CKD severity. The developed online tool can facilitate the prediction of proteinuria progress during follow-up in clinical practice. Page 6, Results, 330 mild CKD patients (urinary protein ≤ 1 g/24 h) and 221 moderate/severe CKD patients (urinary protein ≥ 1 g/24 h). The following non-urine indicators of 13 outpatient blood biochemistry tests and 5 demographic features were used as predictive variables: CRP, ALB, TC, TG, BG, BUN, EGFR, Scr, SUA, SK, Sna, LDL, HDL, sex, age, height, weight, and BMI. Urine protein (g/24 h) was considered an outcome variable to judge the status of CKD patients. Page 8, Establishment of the website and Fig. 5, Web tool (CKD Prediction System) for clinical practice that can be widely used in the evaluation of proteinuria progress in nephrology and during follow-up examinations. After we input the features into the CKD Pre diction System, the tool will feed back the prediction of the patient’s current status with “mild” or “moderate/severe”) to facilitate the prediction of proteinuria progress during follow-up practice (Xiao, Page 11, Conclusion).
Weaver teaches that it was old and well known in the art of albuminuria and proteinuria diagnosis at the time of the filing that urine values for diagnosing albuminuria can be urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values (Weaver, Pages 591-592, The albumin-to-creatinine ratio (ACR) is recommended by guidelines6,7 as the preferred test for quantifying albuminuria/proteinuria for several reasons. Assays for measurement of albuminuria are typically susceptible to less analytical imprecision than total protein, particularly at lower levels of proteinuria. Further, albumin is the predominant urinary protein in the majority of kidney diseases, and it is possible to accurately measure urine albumin at levels in the physiologic range.8 Finally, ACR is more sensitive than protein-to-creatinine ratio (PCR) in detecting the onset of diabetic nephropathy. Despite these benefits of ACR, in many instances, particularly when using secondary data for research, PCR but not ACR is available. To capitalize on the prognostic power of albuminuria from existing data sets, it would be useful to estimate ACR from PCR as accurately as possible. Also see Page 593, Table I).
Therefore, it would have been obvious to one of ordinary skill in the art albuminuria and proteinuria diagnosis at the time of the filing to modify the method of Morteza such that the method is done by a computer system; such that the training data set contained observations of corresponding to urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR); and such that the machine learning model is configured to provide predictions of whether further observations are indicative of undiagnosed albuminuria or proteinuria, as taught by Xiao and Weaver, in order to facilitate the prediction of proteinuria progress during follow-up practice, to follow guideline recommendations and to capitalize on the prognostic power of albuminuria from existing data sets.
Regarding claim 17, Mortenza does not appear to explicitly disclose but Xiao further teaches that it was old and well known in the art of albuminuria and proteinuria diagnosis at the time of the filing, wherein providing the prediction comprises displaying the prediction on a graphical user interface (Xiao, Page 8, Establishment of the website and Page 10, Fig. 5).
Therefore, it would have been obvious to one of ordinary skill in the art albuminuria and proteinuria diagnosis at the time of the filing to modify the method of Morteza such that providing the prediction comprises displaying the prediction on a graphical user interface, as taught by Xiao, in order to facilitate the prediction of proteinuria progress during follow-up practice.
Regarding claim 18, Mortenza does not appear to explicitly disclose but Xiao further teaches that it was old and well known in the art of albuminuria and proteinuria diagnosis at the time of the filing wherein obtaining the observation comprises receiving the observation from a client device in communication with the computing system over a network, and wherein providing the prediction comprises transmitting the prediction to the client device (Xiao, Page 8, Establishment of the website, Clinicians can visit the system website (http://www.ckdprediction.com) and use the desired clinical model by entering the 13 clinical bio chemical indicators and 5 demographic features from follow-up CKD patients. Also see Page 10, Fig. 5.).
Therefore, it would have been obvious to one of ordinary skill in the art albuminuria and proteinuria diagnosis at the time of the filing to modify the method of Morteza such that obtaining the observation comprises receiving the observation from a client device in communication with the computing system over a network, and wherein providing the prediction comprises transmitting the prediction to the client device, as taught by Xiao, in order to facilitate the prediction of proteinuria progress during follow-up practice.
Regarding claim 19, Mortenza further discloses wherein the demographic values include ages, genders, or ethnicities of the plurality of individuals (Page 397, Abstract, The input variables were sex, duration of diabetes, systolic and diastolic blood pressure, glomerular filtration rate, high-density lipoprotein, low-density lipoprotein, triglyceride, high-density lipoprotein/triglyceride ratio, cholesterol, fasting blood sugar, and glycated hemoglobin. Age and BMI were included only in the neural network model.).
Regarding claim 20, Mortenza further discloses wherein the vital sign values include body mass indices, blood pressure readings, or heart rates of the plurality of individuals (Page 397, Abstract, The input variables were sex, duration of diabetes, systolic and diastolic blood pressure, glomerular filtration rate, high-density lipoprotein, low-density lipoprotein, triglyceride, high-density lipoprotein/triglyceride ratio, cholesterol, fasting blood sugar, and glycated hemoglobin. Age and BMI were included only in the neural network model.).
Regarding claim 21, Mortenza further discloses wherein the blood test values include creatinine levels, glycated hemoglobin levels, triglycerides, blood albumin levels, or a white blood cell count of the plurality of individuals (Page 397, Abstract, The input variables were sex, duration of diabetes, systolic and diastolic blood pressure, glomerular filtration rate, high-density lipoprotein, low-density lipoprotein, triglyceride, high-density lipoprotein/triglyceride ratio, cholesterol, fasting blood sugar, and glycated hemoglobin. Age and BMI were included only in the neural network model.).
Regarding claim 23, Mortenza does not appear to explicitly disclose, but Xiao teaches that it was old and well known in the art of albuminuria and proteinuria diagnosis at the time of the filing wherein the machine learning model is based on gradient boosting (Xiao, Page 1, Abstract, Nine predictive models were established and compared, including logistic regression, Elastic Net, lasso regression, ridge regression, support vector machine, random forest, XGBoost, neural network and k-nearest neighbor. The AU-ROC, sensitivity (recall), specificity, accuracy, log-loss and precision of each of the models were evaluated. XGBoost showed the highest specificity.).
Therefore, it would have been obvious to one of ordinary skill in the art albuminuria and proteinuria diagnosis at the time of the filing to modify the method of Morteza such that he machine learning model is based on gradient boosting, as taught by Xiao, in order to provide a model with higher specificity.
Regarding claim 24, Mortenza further discloses wherein the prediction of whether the individual exhibiting the observation has undiagnosed albuminuria comprises predicting whether the individual has microalbuminuria (Page 399, Statistical Analysis, A total of 621 cases were analyzed using the neural network to predict normo, micro-, and macro-albuminuria.).
Regarding claim 25, Mortenza further discloses wherein the prediction of whether the individual exhibiting the observation has undiagnosed albuminuria comprises predicting whether the individual has macroalbuminuria (Page 399, Statistical Analysis, A total of 621 cases were analyzed using the neural network to predict normo, micro-, and macro-albuminuria.).
Regarding claim 26, Mortenza as modified by Weaver further discloses wherein the prediction of whether the individual exhibiting the observation has undiagnosed albuminuria or proteinuria comprises predicting a UACR value or a UPR value for the individual (Page 397, Abstract, Neural network models were used to predict the level of albuminuria in patients. Page 398, Methods, Normo, micro-, and macro-albuminuria were defined as urinary albumin excretion rate <30 mg/24 h, between 30 and 300 mg/24 h, and >300 mg/24 h, respectively. As modified by Weaver in claim 16, UACR and UPR values can be used instead of urinary albumin excretion rate values.).
Regarding claim 29, Mortenza as modified by Weaver further discloses wherein between 5% and 25% of the observations have UACR values that are indicative of albuminuria or UPR values indicative of proteinuria (Page 399, Results, The study included 654 females and 450 males with a mean age of 56 years. The occurrence of albuminuria was as follows: 69.5% had less than 30 mg/24 h, 15.7% were between 30 and 300 mg/24 h, and 9.8% had more than 300 mg/24 h. As modified by Weaver in claim 16, UACR and UPR values can be used instead of urinary albumin excretion rate values to indicate the occurrence of albuminuria and proteinuria.)..
Regarding claim 32, Mortenza does not appear to explicitly disclose, but Weaver teaches that it was old and well known in the art of albuminuria and proteinuria diagnosis at the time of the filing wherein the UACR values were derived mathematically from UPR values (Weaver, Page 591, Abstract, For situations in which PCR only is available, having a method to estimate ACR from PCR as accurately as possible would be useful. We developed equations to estimate the median ACR from a PCR.).
Therefore, it would have been obvious to one of ordinary skill in the art albuminuria and proteinuria diagnosis at the time of the filing to modify the method of Morteza such that the UACR values were derived mathematically from UPR values, as taught by Weaver, in order to estimate ACR for situations in which only PCR is available.
Regarding claim 34, Mortenza discloses a method comprising:
obtaining, by a computing system,Page 397, Abstract, The input variables were sex, duration of diabetes, systolic and diastolic blood pressure, glomerular filtration rate, high-density lipoprotein, low-density lipoprotein, triglyceride, high-density lipoprotein/triglyceride ratio, cholesterol, fasting blood sugar, and glycated hemoglobin. Age and BMI were included only in the neural network model. Also see pages 398-399, Methods and Blood Samples.);
applying, by the computing system, a quantile regression machine learning model to the observation, wherein the quantile regression machine learning model was trained with a training data set, wherein the training data set contained observations of corresponding demographic values, vital sign values, blood test values, and either urine albumin-Page 399, Statistical Analysis, A total of 621 cases were analyzed using the neural network to predict normo-, micro-, and macro-albuminuria. To correct for potential detection errors using the neural network, we integrated data from 3 different types of “samples”: training, testing, and holdout samples. The training sample consists of data records used to train the neural network to populate the model. The testing sample is an independent set of data records used to track errors during training to prevent overtraining. Network training is generally more efficient if the testing sample is smaller than the training sample. The holdout sample is another independent set of data records used to assess the final neural network. Since the holdout cases were not used to build the model, the error of the holdout samples provides an “honest” estimate of the predictive capacity of the model. Therefore, the training sample must have the largest size, the testing sample is intermediate, and the holdout sample is the smallest. Patients were randomly classified into (1) training (388/621; 62.5%), (2) testing (168/621; 27.1%), and (3) holdout (65/621; 10.5%) groups. The neural network uses a learning algorithm to define the nonlinear mathematical transfer functions to modify the synaptic weights of a network’s processing units in an orderly fashion to obtain the desired outcome prediction (training data sets). Input variables were age, sex, time of onset of diabetes, systolic and diastolic blood pressure, eGFR, HDL-cholesterol, LDL, FBS, TG, HDL/TG ratio, HbA1c, and cholesterol. Normo, micro-, and macro-albuminuria were defined as urinary albumin excretion rate <30 mg/24 h, between 30 and 300 mg/24 h, and >300 mg/24 h, respectively.); and
based on the observation and for the individual, providing, by the computing system, a prediction of a Page 397, Abstract, We have used 2 different statistical models to predict albuminuria in type 2 diabetes mellitus: a multilayer perception neural network and a conditional logistic regression. Neural network models were used to predict the level of albuminuria in patients with type 2 diabetes mellitus. Our neural network model complements the current risk factor models to improve the care of patients with diabetes. Page 398, Methods, Normo, micro-, and macro-albuminuria were defined as urinary albumin excretion rate <30 mg/24 h, between 30 and 300 mg/24 h, and >300 mg/24 h, respectively. Page 399, Statistical Analysis, A total of 621 cases were analyzed using the neural network to predict normo-, micro-, and macro-albuminuria.).
Morteza further discloses combining the important variables obtained from neural networks with those extracted from the conditional logistic regression to obtain more accurate predictions (Page 397), but does not appear to explicitly disclose that the method is done by a computer system; obtaining a quantile; that the machine learning model is a quantile regression model; wherein the training data set contained observations of corresponding to urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values ; wherein the quantile regression machine learning model is configured to provide predictions of UACR or UPR values at one or more quantiles for further observations; or providing a prediction of a UACR or UPR value at the quantile.
Xiao teaches that it was old and well known in the art of albuminuria and proteinuria diagnosis at the time of the filing to use a computer system to obtain observations, apply a regression machine learning model to provide predictions of whether further observations are indicative of undiagnosed albuminuria or proteinuria; and provide a prediction of whether the individual exhibits undiagnosed albuminuria or proteinuria based on the observation (Xiao, Page 1, Objective, To quickly predict the severity of CKD using more easily available demographic and blood biochemical features during follow-up, we developed and compared several predictive models using statistical, machine learning and neural network approaches. Page 1 Methods, ine predictive models were established and compared, including logistic regression, Elastic Net, lasso regression, ridge regression, support vector machine, random forest, XGBoost, neural network and k-nearest neighbor. Page 1, Results, Blood-derived tests could be applied as non-urinary predictors during outpatient follow-up. Features in routine blood tests, including ALB, Scr, TG, LDL and EGFR levels, showed predictive ability for CKD severity. The developed online tool can facilitate the prediction of proteinuria progress during follow-up in clinical practice. Page 6, Results, 330 mild CKD patients (urinary protein ≤ 1 g/24 h) and 221 moderate/severe CKD patients (urinary protein ≥ 1 g/24 h). The following non-urine indicators of 13 outpatient blood biochemistry tests and 5 demographic features were used as predictive variables: CRP, ALB, TC, TG, BG, BUN, EGFR, Scr, SUA, SK, Sna, LDL, HDL, sex, age, height, weight, and BMI. Urine protein (g/24 h) was considered an outcome variable to judge the status of CKD patients. Page 8, Establishment of the website and Fig. 5, Web tool (CKD Prediction System) for clinical practice that can be widely used in the evaluation of proteinuria progress in nephrology and during follow-up examinations. After we input the features into the CKD Pre diction System, the tool will feed back the prediction of the patient’s current status with “mild” or “moderate/severe”. Page 11, We are also establishing a Lasso based predicted proteinuria range, which provides doctors and patients with more intuitive predictions) to facilitate the prediction of proteinuria progress during follow-up practice (Xiao, Page 11, Conclusion).
Weaver teaches that it was old and well known in the art of albuminuria and proteinuria diagnosis at the time of the filing that urine values for diagnosing albuminuria can be urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values (Weaver, Pages 591-592, The albumin-to-creatinine ratio (ACR) is recommended by guidelines6,7 as the preferred test for quantifying albuminuria/proteinuria for several reasons. Assays for measurement of albuminuria are typically susceptible to less analytical imprecision than total protein, particularly at lower levels of proteinuria. Further, albumin is the predominant urinary protein in the majority of kidney diseases, and it is possible to accurately measure urine albumin at levels in the physiologic range.8 Finally, ACR is more sensitive than protein-to-creatinine ratio (PCR) in detecting the onset of diabetic nephropathy. Despite these benefits of ACR, in many instances, particularly when using secondary data for research, PCR but not ACR is available. To capitalize on the prognostic power of albuminuria from existing data sets, it would be useful to estimate ACR from PCR as accurately as possible. Also see Page 593, Table I) and to obtain a quantile and use quantile regression machine learning to provide a predicted a prediction of a UACR or UPR value at the quantile (Weaver, Page 591, Methods, After log-transforming ACR and PCR, we used cubic splines and quantile regression to estimate the median ACR from a PCR, allowing for modification by specified covariates. On the basis of the cubic splines, we created models using linear splines to develop equations to estimate ACR from PCR. Page 592, Model Development: Primary Approach, Through this process we created models for median log(ACR) with no covariates, specified covariates, and all covariates. In addition, to better describe the prediction interval for estimated log(ACR), we fit quantile regression models for the 25th and 75th percentiles. Page 600, We recommend estimating 25th and 75th percentiles of ACR in addition to the median, to estimate an approximate range of ACR.); .
Therefore, it would have been obvious to one of ordinary skill in the art albuminuria and proteinuria diagnosis at the time of the filing to modify the method of Morteza such that the method is done by a computer system; to obtain a quantile; such that the machine learning model includes a quantile regression model; such that the training data set contained observations of corresponding to urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values; such that the quantile regression machine learning model is configured to provide predictions of UACR or UPR values at one or more quantiles for further observations; and such that the providing includes a prediction of a UACR or UPR value at the quantile, as taught by Xiao and Weaver, in order to facilitate the prediction of proteinuria progress during follow-up practice, provide doctors and patients with more intuitive predictions, to follow guideline recommendations and to capitalize on the prognostic power of albuminuria from existing data sets.
Regarding claims 35 and 37: all limitations as recited have been analyzed and rejected with respect to claims 16 and 29. Claims 35 and 37 pertain to a A non-transitory computer-readable medium, corresponding to the method perfomed by the computer system of claims 35 and 37. Claims 35 and 37 do not teach or define any new limitations beyond claims 16 and 29; therefore claims 35 and 37 are rejected under the same rationale.
Claims 22 is rejected under 35 U.S.C. 103 as being unpatentable over Mortenza et al. (Inconsistency in albuminuria predictors in type 2 diabetes: a comparison between neural network and conditional logistic regression) in view of Xiao et al. (Comparison and development of machine learning tools in the prediction of chronic kidney disease progression) and Weaver et al. (Estimating Urine Albumin-to-Creatinine Ratio from Protein-to-Creatinine Ratio: Development of Equations using Same-Day Measurements) and Klug et al. (A Gradient Boosting Machine Learning Model for Predicting Early Mortality in the Emergency Department Triage: Devising a Nine-Point Triage Score).
Regarding claim 22, Mortenza does not appear to explicitly disclose, but Xiao and Klug teach that it was old and well known in the art of clinical prediction at the time of the filing wherein values within the training data set are 20%-50% populated (Klug, Page 225, Table 5 shows that machine learning models, such as XGBoost, can by trained on cohorts (observation) data with >50% having missing values. Xiao, Page 1, Abstract, XGBoost showed the highest specificity in the prediction of proteinuria from available demographic and blood biochemical features).
Therefore, it would have been obvios to one of ordinary skill in the art of clinical prediction at the time of the filing to modify the training data set of Mortenza, to accommodate values within the training data set being 20%-50% populated, as taught by Klug and Xiao, in order to handle sparse data and provide a model with high specificity.
Claims 27-28 rejected under 35 U.S.C. 103 as being unpatentable over Mortenza et al. (Inconsistency in albuminuria predictors in type 2 diabetes: a comparison between neural network and conditional logistic regression) in view of Xiao et al. (Comparison and development of machine learning tools in the prediction of chronic kidney disease progression) and Weaver et al. (Estimating Urine Albumin-to-Creatinine Ratio from Protein-to-Creatinine Ratio: Development of Equations using Same-Day Measurements) and Obermeyer et al. (Predicting the Future — Big Data, Machine Learning, and Clinical Medicine).
Regarding claim 27, Mortenza does not appear to explicitly disclose, but Obermeyer teaches that it was old and well known in the art of clinical machine learning at the time of the filing wherein the training data set includes at least 100,000 observations gathered from medical claim records or electronic health records (Oberbeyer, Page 2, Machine learning algorithms are highly “data hungry,” often requiring millions of observations to reach acceptable performance levels.2 In addition, biases in data collection can substantially affect both performance and generalizability. Lactate might be a good predictor of risk of death, for example, but only a small, nonrepresentative sample of patients has their lactate level checked. Private companies spend enormous resources to amass high-quality, unbiased data to feed their algorithms, and existing data in electronic health records (EHRs) or claims databases need careful curation and processing before they are usable.).
Therefore, it would have been obvious to one of ordinary skill in the art of clinical machine learning at the time of the filing to modify the training data set of Mortenza to include at least 100,000 observations gathered from medical claim records or electronic health records, as taught by Obermeyer, in order to improve performance and generalizability.
Regarding claim 28, Mortenza does not appear to explicitly disclose, but Obermeyer teaches that it was old and well known in the art of clinical machine learning at the time of the filing wherein the training data set includes at least 1,000,000 observations gathered from medical claim records or electronic health records (Oberbeyer, Page 2, Machine learning algorithms are highly “data hungry,” often requiring millions of observations to reach acceptable performance levels.2 In addition, biases in data collection can substantially affect both performance and generalizability. Lactate might be a good predictor of risk of death, for example, but only a small, nonrepresentative sample of patients has their lactate level checked. Private companies spend enormous resources to amass high-quality, unbiased data to feed their algorithms, and existing data in electronic health records (EHRs) or claims databases need careful curation and processing before they are usable.).
Therefore, it would have been obvious to one of ordinary skill in the art of clinical machine learning at the time of the filing to modify the training data set of Mortenza to include at least 1,000,000 observations gathered from medical claim records or electronic health records, as taught by Obermeyer, in order to improve performance and generalizability.
Claims 30-31 rejected under 35 U.S.C. 103 as being unpatentable over Mortenza et al. (Inconsistency in albuminuria predictors in type 2 diabetes: a comparison between neural network and conditional logistic regression) in view of Xiao et al. (Comparison and development of machine learning tools in the prediction of chronic kidney disease progression) and Weaver et al. (Estimating Urine Albumin-to-Creatinine Ratio from Protein-to-Creatinine Ratio: Development of Equations using Same-Day Measurements) and Kiritzky et al. (Identification and Management of Albuminuria in the Primary Care Setting).
Regarding claim 30, Mortenza does not appear to explicitly disclose, but Kiritzky teaches that it was old and well known in the art of albuminuria management at the time of the filing that based on the prediction indicating that the individual exhibits undiagnosed albuminuria or proteinuria, recommending that the individual be treated for albuminuria or proteinuria (Kiritzky, Page 445, Fig, 5 shows recommending treatment after establishing a patient has albuminuria.) to provide salutary outcomes in reference to reduction in albuminuria, improved renal function, and decreased end-stage renal disease and it is even associated with reductions in CV events (Kiritzky, Page 438).
Therefore, it would have been obvious to one of ordinary skill in the art of albuminuria management at the time of the filing to modify the method of Mortenza to include based on the prediction indicating that the individual exhibits undiagnosed albuminuria or proteinuria, recommending that the individual be treated for albuminuria or proteinuria, as taught by Kiritzky, in order to provide salutary outcomes in reference to reduction in albuminuria, improved renal function, and decreased end-stage renal disease and it is even associated with reductions in CV events.
Regarding claim 31, Mortenza does not appear to explicitly disclose, but Kiritzky teaches that it was old and well known in the art of albuminuria management at the time of the filing that based on the prediction indicating that the individual exhibits undiagnosed albuminuria or proteinuria, recommending that the individual be enrolled in a clinical trial related to albuminuria or proteinuria (Kiritzky, Page 445, Fig. 5 and TREATMENT ALGORITHM FOR MANAGING ALBUMINURIA, show and discuss recommending treatment after establishing a patient has albuminuria and that patients with diabetes and elevated UAE may be enrolled in clinical trials to test treatments.) to provide salutary outcomes in reference to reduction in albuminuria, improved renal function, and decreased end-stage renal disease and it is even associated with reductions in CV events (Kiritzky, Page 438).
Therefore, it would have been obvious to one of ordinary skill in the art of albuminuria management at the time of the filing to modify the method of Mortenza to include based on the prediction indicating that the individual exhibits undiagnosed albuminuria or proteinuria, recommending that the individual be enrolled in a clinical trial related to albuminuria or proteinuria, as taught by Kiritzky, in order to provide salutary outcomes in reference to reduction in albuminuria, improved renal function, and decreased end-stage renal disease and it is even associated with reductions in CV events.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Khitan et al. (Machine learning approach to predicting albuminuria in persons with type 2 diabetes: An analysis of the LOOK AHEAD Cohort) discusses using machine learning methods to assess the risk of albuminuria in persons with diabetes using body composition and other determinants of metabolic health.
Lin et al. (Development of a Risk Model for Predicting Microalbuminuria in the Chinese Population Using Machine Learning Algorithms) discusses using machine learning algorithms to establish an effective risk score which uses SBP, DBP, FBG, TG, gender, age, and smoking in the screening process for Microalbuminuria.
Villa-Zapata et al. (Predictive modeling using a nationally representative database to identify patients at risk of developing microalbuminuria) discusses developing a patient data-driven predictive model and a risk-score assessment to improve the identification microalbuminuria.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Devin C. Hein whose telephone number is (303)297-4305. The examiner can normally be reached 9:00 AM - 5:00 PM M-F MDT.
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, Jason B. Dunham can be reached at (571) 272-8109. 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.
/DEVIN C HEIN/Examiner, Art Unit 3686