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 .
Formal Matters
Applicant’s response, filed 01/15/2026, has been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Status of Claims
Claims 1-9 and 11-18 are currently pending and have been examined.
Claims 1, 4, 6 and 11-16 have been amended.
Claim 10 has been canceled.
Claim 18 is new.
Claims 1-9 and 11-18 have been rejected.
Information Disclosure Statement
The information disclosure statements (IDS) were submitted on 07/11/2024 and 10/29/2024. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 112(a)
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 18 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 18 discloses, “administering a first treatment plan to the patient if the output indicates the patient is a slow progressor; and administering a second treatment plan to the patient if the output indicates the patient is a fast progressor, wherein the first treatment plan is different than the second treatment plan.” While Page 1, para 4 of the Applicant’s specification discloses, “However, even within the population of later stage patients, CKD may progress at different speeds, and often, patients with slow progression who do not require specialist treatment but may be treated by a general practitioner, are not identified and are unnecessarily referred to a specialist, therefore putting a higher burden on the healthcare system,” and Page 11, para 2 of the Applicant’s specification discloses, “As we have explained throughout this application, one of the main purposes of the invention is to enable a determination of whether a given patient is a "slow progressor" or a "fast progressor" as regards CKD. By making this prediction at an early stage, it is possible to better shape a patient's treatment plan.” However, the specification does not provide support for, “administering a first treatment plan to the patient if the output indicates the patient is a slow progressor; and administering a second treatment plan to the patient if the output indicates the patient is a fast progressor, wherein the first treatment plan is different than the second treatment plan.”
Claim Rejections - 35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 4 and 12-16 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
In regards to claim 4, the limitation discloses “input data comprises (b) and/or (d)” where claim 1 (b) discloses eGFR0 and (d) discloses eGFRi. However, claim 4 only discloses “the or each the eGFR value eGFR0 is calculated from a corresponding creatinine level c0.” It is unclear if this is in regards to both (b) and/or (d) as now (b) and (d) do not disclose eGFR0. Further, claim 4 recites, “and wherein the or each the eGFR value eGFR0 is calculated from a corresponding creatinine level c0.“ The removal of the subscript 0 from eGFR in step (b) of claim 1 means there is lack of antecedent basis for eGFR0. Thus, the Examiner is interpreting the claim 4 limitation to read, “the or each of the eGFR values, the initial eGFR or eGFRi , are calculated from a corresponding creatinine level, c or ci” because claim 4 discloses the input data comprises specifically (b) and/or (d).
In regards to claim 12, claim 12 discloses that “the input data comprises… cj,R… or eGFRj,R” but only discloses that “wherein the output data comprises… the time of measurement of cj,R. “ The claim is indefinite as the output does not depend on the same two options for the input as disclosed by the claim, since the input could broadly be selected as just the eGFRj,R. Thus, the Examiner is interpreting the output limitation to read as, “wherein the output data comprises… the time of measurement of cj,R or eGFRj,R”
Dependent claims 13-16 are rejected as dependent on a rejected base claim.
Thus, claims 4 and 12-16 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph.
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 1-9 and 11-18 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claimed invention is directed to an abstract idea without significantly more. Claims 1-9 and 11-18 are directed to a system, method, or product which are one of the statutory categories of invention. (Step 1: YES).
Independent Claim 1 discloses a computer-implemented method of determining, at a prediction time tp, likelihood of kidney failure of a patient within an amount of time Δt, the computer-implemented method comprising: receiving input data, the input data comprising a recent creatinine level cR or recent estimated glomerular filtration (eGFR) value eGFRR, and one or more of the following: (a) an initial creatinine level c0 and either: a time t0 at which the initial creatinine level c0 was measured, or a time interval ΔT0 = tp - t0; (b) an initial eGFR and either: a time to at which the initial eGFR was determined, or a time interval ΔT0 = tp - t0; (c) for a plurality of past creatinine level measurements ci measured at a respective times ti, a statistical parameter derived from a linear regression of the plurality of past creatinine level measurements; and (d) for a plurality of past eGFR values eGFR determined at respective times ti, a statistical parameter derived from a linear regression of the plurality of past eGFR values; and applying a machine-learning model to the input data to generate an output indicating the likelihood of kidney failure within the given amount of time Δt; determining, based on the output of the machine-learning model, whether the patient is a fast progressor or a slow progressor; and generating a treatment plan recommendation in accordance with the determination of whether the patient is a fast progressor or a slow progressor.
Independent Claim 12 discloses a computer-implemented method of generating a machine-learning model configured to determine, at a prediction time tp, a likelihood of kidney failure of a patient within a given amount of time Δt, the computer-implemented method comprising: receiving training data, the training data comprising a plurality of data sets, representing a plurality of patients, each data set comprising input data and output data, wherein for the jth data set: the input data comprises a recent creatinine level cj,R or a recent eGFR eGFR j,R and: (a) a historical creatinine level c j,H, and the time t j,H at which it was obtained; (b) a historical eGFR eGFR j,H, and the time t j,H at which it was obtained; (c) for a plurality of past creatinine levels measured at respective times tij, a statistical parameter derived from a linear regression of the plurality of past creatinine level measurements; and (d) for a plurality of past eGFR values eGFR determined at respective times ti, a statistical parameter derived from a linear regression of the plurality of past eGFR values; wherein the output data comprises an indication of an interval Δt between the time t of kidney failure, and the time of measurement of c j,R; training the machine-learning model using the training data; applying the trained machine-learning model to the input data to generate an output indicating the likelihood of kidney failure within the given amount of time Δt, determining, based on the output of the machine-learning model, whether the patient is a fast progressor or a slow progressor; and generating a treatment plan recommendation in accordance with the determination of whether the patient is a fast progressor or a slow progressor.
The examiner is interpreting the above bolded limitations as additional elements as further discussed below. The remaining un-bolded limitations are merely directed to a mathematical concept, (specifically a statistical parameter derived from a linear regression), which is an abstract idea. (Step 2A- Prong 1: YES. The claims are abstract).
This judicial exception is not integrated into a practical application. Limitations that are not indicative of integration into a practical application include: (1) 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 uses a computer as a tool to perform an abstract idea (MPEP 2106.05.f), (2) Adding insignificant extra- solution activity to the judicial exception (MPEP 2106.05.g), (3) Generally linking the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05.h).
Claims 1 and 12 disclose the following additional elements:
A computer implemented method
A machine learning model
In particular, the computer implemented model and machine learning model are recited at a high-level of generality such that it amounts to no more than mere instructions to implement an abstract idea by adding the words ‘apply it’ (or an equivalent) with the judicial exception. Applicant’s specification Page 17 discloses “further aspects of the invention may provide a computer program comprising instructions, which when executed by a computer (or a processor thereof), cause the computer (or processor thereof) to execute the computer-implemented method of the first and/or second aspects of the invention.” And further that the computer could be the kidney failure likelihood determination system 100 where figure 1 discloses the system 100 to include an interface, processor, and memory with a machine learning model. Thus, disclosing a computer or processor operating as expected: executing computer programs comprising instructions to implement the abstract idea. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Accordingly, claim(s) 1 and 12 are directed to an abstract idea(s) without a practical application. (Step 2A-Prong 2: NO: the additional claimed elements are not integrated into a practical application).
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of the computer implemented method and the machine learning model amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept ("significantly more’). MPEP2106.05(I)(A) indicates that merely saying "apply it” or equivalent to the abstract idea cannot provide an inventive concept ("significantly more").
Accordingly, even in combination, these additional elements do not provide significantly more. As such the independent claims 1 and 12 are not patent eligible. (Step 2B: NO. The claims do not provide significantly more).
Dependent claim(s) 2-9, 11, and 13-18 are similarly rejected because they either further define/narrow the abstract idea and/or do not further limit the claim to a practical application or provide an inventive concept such that the claims are subject matter eligible even when considered individually or as an ordered combination.
Specifically, dependent claim 2 further narrows the abstract idea directed to a mathematical concept by disclosing the gradient boosted decision trees algorithm while also disclosing the additional element(s) of a neural network model, which is narrowing the machine learning model of independent claim 1.
Dependent claim 3 further narrows the abstract idea by disclosing specific details on the statistical parameter derived from a linear regression.
Dependent claim 18 further discloses the additional element of administering a first treatment plan to the patient if the output indicates the patient is a slow progressor; and administering a second treatment plan to the patient if the output indicates the patient is a fast progressor, wherein the first treatment plan is different than the second treatment plan.
In particular, the neural network is recited at a high-level of generality such that it amounts to no more than mere instructions to implement an abstract idea by adding the words ‘apply it’ (or an equivalent) with the judicial exception. Further, although “administering a first treatment plan to the patient if the output indicates the patient is a slow progressor; and administering a second treatment plan to the patient if the output indicates the patient is a fast progressor, wherein the first treatment plan is different than the second treatment plan,” indicates that a treatment is to be administered, it does not provide any information as to how the patient is to be treated, or what the treatment is, but instead covers any possible treatment that a doctor decides to administer to the patient. Thus, the claim fails to meaningfully limit the claim because it does not require the administration of any particular treatment, and is at best the equivalent of merely adding the words “apply it” to the judicial exception. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of the neural network (of claim 2) and the administering limitations (of claim 18) amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept ("significantly more’). MPEP2106.05(I)(A) indicates that merely saying "apply it” or equivalent to the abstract idea cannot provide an inventive concept ("significantly more").
Therefore, the dependent claims 2-9, 11, and 13-18 are also directed to an abstract idea.
Thus, Claims 1-9 and 11-18 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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.
Claim(s) 1-5, 9-11 and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Tangri (US PG Pub 2023/0054069 A1) in view of Chan (Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease - diabetologia), further in view of Subasi (A classification model to predict the rate of decline of kidney function).
Regarding Claim 1, Tangri discloses:
A computer-implemented method of determining, at a prediction time tp, likelihood of kidney failure of a patient within an amount of time Δt, the computer-implemented comprising: (Para 49 discloses the disclosed embodiments may facilitate various technical advantages over existing systems and methods associated with prediction of CKD progression, particularly in being able to predict chronic kidney disease progression for patients experiencing any stage of chronic kidney disease (CKD) (or patients with no CKD or unknown CKD status).
receiving input data, the input data comprising a recent creatinine level cR or recent estimated glomerular filtration (eGFR) value R, and (Para 94 discloses act 314 of flow diagram 310 includes generating a prediction of CKD progression for a new patient by applying an input dataset associated with the new patient to the machine learning model, the prediction of CKD progression for the new patient being based upon output of the machine learning model resulting from applying the input dataset associated with the new patient to the machine learning model, the input dataset comprising an age of the new patient, a sex of the new patient, and a second set of medical laboratory data indicating for the new patient one or more of: eGFR, urine ACR, urea, serum sodium, serum chloride, serum hemoglobin, serum potassium, glucose, serum albumin, ALKP, serum phosphate, serum bicarbonate, serum magnesium, serum calcium, AST, ALT, bilirubin, GGT, hematocrit, and platelet count. As used herein, “urine ACR” may comprise a direct urine ACR measurement, a derived or estimated urine ACR, and/or components of urine ACR such as urine albumin, urine creatinine, urine protein, and/or qualitative urine albumin (e.g., from dipstick). Para 175 discloses the primary outcome in the present example was a 40% decline in eGFR or kidney failure. The 40% decline in eGFR was determined as the first eGFR test in the laboratory data that was 40% or greater in decline from the baseline eGFR, requiring a second confirmatory test result between 90 days and 2 years after the first test [wherein both of these eGFR tests read on a recent eGFR, and wherein para 130 discloses eGFR is calculated from available serum creatinine tests, thus this reads on a recent creatinine level] unless the patient dies or experiences kidney failure within 90 days after the first test result revealing a 40% or greater decline.)
one or more of the following: (a) an initial creatinine level co and either: a time to at which the initial creatinine level c0 was measured, or a time interval ΔT0 = tp – t0; (b) 0 at which the initial eGFR was determined, or a time interval ΔT0 = tp – t0; (Para 96 discloses the prediction of CKD progression may indicate a risk of experiencing CKD progression within a particular amount of time from a time period associated with the input dataset for the new patient (e.g., an amount of time from an eGFR measurement associated with the new patient) [thus disclosing a time interval ΔT0]. Para 130 discloses eGFR was calculated from available serum creatinine tests using the CKD-EPI equation [thus an initial eGFR measurement reads on an initial creatinine level]. Para 175 discloses the primary outcome in the present example was a 40% decline in eGFR or kidney failure. The 40% decline in eGFR was determined as the first eGFR test in the laboratory data that was 40% or greater in decline from the baseline eGFR [wherein the baseline is the initial eGFR], requiring a second confirmatory test result between 90 days and 2 years after the first test unless the patient dies or experiences kidney failure within 90 days after the first test result revealing a 40% or greater decline.)
applying a machine-learning model to the input data to generate an output indicating the likelihood of kidney failure within the given amount of time Δt. (Para 78 discloses the training module 153 is configured to train a machine learning model 145 to generate a prediction of chronic kidney disease progression by applying a training dataset 141 comprising medical laboratory data 142 and patient information 143 in order to produce as output the CKD progression prediction data 144. Para 98 discloses act 316 of flow diagram 310 includes determining that the prediction of CKD progression indicates a predicted risk of the new patient experiencing CKD within a particular time period that satisfies one or more predicted risk threshold values... In one example, for a 2 year time period, a 2% or greater prediction of CKD progression (e.g., indicating a 2% likelihood that the new patient experiences CKD progression in the form of a 40% reduction in eGFR or kidney failure is 2%). Para 99 discloses the acts 318A, 318B, 318C, and/or 318D performed responsive to the prediction of CKD progression satisfying the one or more thresholds in accordance with act 316 may be selected based upon the particular time period associated with the prediction of CKD progression (e.g., 2 year or 5 year), the particular threshold(s) satisfied (e.g., whether the patient is classified as being at “intermediate” or “high” risk)…)
While Tangri discloses the above limitations and Tangri Para 175 discloses, “The primary outcome in the present example was a 40% decline in eGFR or kidney failure. The 40% decline in eGFR was determined as the first eGFR test in the laboratory data that was 40% or greater in decline from the baseline eGFR, requiring a second confirmatory test result between 90 days and 2 years after the first test unless the patient dies or experiences kidney failure within 90 days after the first test result revealing a 40% or greater decline,” it does not fully disclose the following limitation that Chan discloses:
(c) for a plurality of past creatinine level measurements ci measured at a respective times ti, a statistical parameter derived from a linear regression of the plurality of past creatinine level measurements; and (d) for a plurality of past eGFR values eGFR determined at respective times ti, a statistical parameter derived from a linear regression of the plurality of past eGFR values; and (Statistical analysis discloses the derivation set was then randomly split into secondary training and test sets for model optimisation with 70%-30% spitting and a tenfold cross validation for AUC. Wherein study sample discloses only individuals with a stored plasma specimen, a minimum follow-up time from enrolment of at least 21 months, at least three eGFR values after baseline (ESM Fig. 1) were included [and ESM Fig. 1 selection of cohorts with 1146 patients with eGFR values 30-59.9 or >= 60, data harmonization including demographics or laboratory values, outcome ascertainment including eGFR slope or kidney failure and further splitting this into randomized datasets consisting of a training dataset (60%) and a validation dataset (40%). Study sample discloses for eGFR, we defined the baseline period as 1 year before or up to 3 months after biobank enrolment… Only individuals with a stored plasma specimen, a minimum follow-up time from enrolment of at least 21 months, at least three eGFR values after baseline (ESM Fig. 1) [wherein even if the most recent eGFR value is not included, there would be at least two eGFR values after baseline and thus a plurality of past eGFRs with the baseline being the initial] were included. Ascertainment and definition of the kidney endpoint discloses we determined eGFR using the CKD-EPI creatinine equation [21] [thus disclosing a plurality of past creatinine levels measured at respective times ti with a statistical parameter because the eGFR is calculated from the creatinine equation].. We employed linear mixed models with an unstructured variance-covariance matrix and random intercept/slope for each individual to estimate the eGFR slope [22]. Discussion discloses utilising plasma samples of individuals with type 2 diabetes from two biobanks and linked EHR data, we developed and validated a risk score combining clinical data and three plasma biomarkers via a random forest algorithm to predict a composite kidney outcome, progressive decline in kidney function, consisting of RKFD, sustained 40% decline in eGFR, and kidney failure over 5 years [given amount of time Δt]. See further: Statistical analysis.)
determining, based on the output [of the machine-learning model], whether the patient is a fast progressor or a slow progressor; and (The primary composite outcome, progressive decline in kidney function, included the following: RKFD (wherein the introduction defines RKFD as rapid kidney function decline) defined as an eGFR slope decline of ≥5 ml min−1 [1.73 m]−2 per year [thus reading on a fast progressor]. The Discussion discloses utilising plasma samples of individuals with type 2 diabeters from two biobanks and linked EHR data, we developed and validated a risk score combining clinical data and three plasma biomarkers via a random forest algorithm to predict a composite kidney outcome, progressive decline in kidney function, consisting of RKFD, sustained 40% decline in eGFR, and kidney failure over 5 years.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the systems and methods for predicting kidney function decline as taught by Tangri with the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan in order to precisely identify patients who will experience rapid kidney function decline (RKFD) and to appropriately risk stratify and counsel patients on the progressive nature of DKD (Chan Introduction).
While the combination of Tangri and Chan discloses the above limitations and Tangri discloses an output of the machine-learning model (See Tangri Para 78 discloses the training module 153 is configured to train a machine learning model 145 to generate a prediction of chronic kidney disease progression... Para 98-99 discloses act 316 of flow diagram 310 includes determining that the prediction of CKD progression indicates a predicted risk of the new patient experiencing CKD within a particular time period that satisfies one or more predicted risk threshold values... In one example, for a 2 year time period, a 2% or greater prediction of CKD progression (e.g., indicating a 2% likelihood that the new patient experiences CKD progression in the form of a 40% reduction in eGFR or kidney failure is 2%)) and Chan discloses in the introduction, “The primary composite outcome, progressive decline in kidney function, included the following: RKFD (wherein the introduction defines RKFD as rapid kidney function decline) defined as an eGFR slope decline of ≥5 ml min−1 [1.73 m]−2 per year”, it does not fully disclose the treatment limitation that Subasi discloses:
generating a treatment plan recommendation in accordance with the determination of whether the patient is a fast progressor or a slow progressor (Discussion section paragraph 6 discloses we may also be able to avoid complications of therapy if we can identify a truly low risk group that can just be observed rather than treated (note for example that that BP control to a lower than usual goal (<130/80) in AASK took almost four BP drugs, each with its own side effect profile). If an LAD risk score is associated with less than a 10% risk of progression [slow progressor], patients in that category could likely be observed [treatment plan recommendation for a slow progressor] rather than immediately treated with aggressive therapy [treatment plan recommendation for a fast progressor] or could forego such therapy if side complications arise. While current therapies for CKD are relatively benign, it should be noted that recent clinical trials have been performed with other drugs that are likely to have much more aggressive side effect profiles. If such medications are effective at slowing CKD progression, robust predictors of disease progression would be very helpful evaluating the overall risk/benefit ratio of therapy, which may not be beneficial at low progression risk.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri and the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan with the classification model to predict the rate of decline of kidney function as taught by Subasi in order to avoid complications of therapy if a truly low risk group can be identified and only observed rather than treated with aggressive therapy (Subasi Discussion section paragraph 6).
Regarding Claim 2, this claim recites the limitations of Claim 1 and as to those limitations is rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, and Subasi discloses the following limitation that Tangri further discloses:
A computer-implemented method according to claim 1, wherein: the machine-learning model comprises a gradient-boosted decision trees algorithm or a neural network model. (Para 53 discloses As used herein, a machine learning model or module refers to any combination of software and/or hardware components that are operable to facilitate processing using machine learning models or other artificial intelligence-based structures/architectures. For example, one or more processors may comprise and/or utilize hardware components and/or computer-executable instructions operable to carry out function blocks and/or processing layers configured in the form of, by way of non-limiting example, random forest models, random survival forest models… single-layer neural networks, feed forward neural networks, radial basis function networks, deep feed-forward networks, recurrent neural networks, long-short term memory (LSTM) networks, gated recurrent units, autoencoder neural networks, variational autoencoders, denoising autoencoders, sparse autoencoders, Markov chains, Hopfield neural networks, Boltzmann machine networks, restricted Boltzmann machine networks, deep belief networks, deep convolutional networks (or convolutional neural networks), deconvolutional neural networks, deep convolutional inverse graphics networks, generative adversarial networks, liquid state machines, extreme learning machines, echo state networks, deep residual networks, Kohonen networks, support vector machines, neural Turing machines, and/or others.)
Regarding Claim 3, this claim recites the limitations of Claim 1 and as to those limitations is rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, and Subasi discloses the following limitation that Chan further discloses:
A computer-implemented method according to claim 1, wherein: the statistical parameter comprises one or more of: a slope with respect to time; an error calculated from a sum of residuals; an intercept; a number of points considered when constructing the linear regression; and a variance. (Ascertainment and definition of the kidney endpoint discloses we employed linear mixed models with an unstructured variance-covariance matrix and random intercept/slope for each individual to estimate the eGFR slope [22].)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the systems and methods for predicting kidney function decline as taught by Tangri with the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan in order to appropriately risk stratify and counsel patients on the progressive nature of DKD (Chan Introduction).
Regarding Claim 4, this claim recites the limitations of Claim 1 and as to those limitations is
rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, and Subasi discloses the following limitation that Tangri further discloses:
A computer-implemented method according to claim 1, wherein: the input data comprises (b); the or each the eGFR value eGFRo is calculated from a corresponding creatinine level co and (Para 96 discloses the prediction of CKD progression may indicate a risk of experiencing CKD progression within a particular amount of time from a time period associated with the input dataset for the new patient (e.g., an amount of time from an eGFR measurement associated with the new patient) [thus disclosing a time interval]. Para 130 discloses eGFR was calculated from available serum creatinine tests using the CKD-EPI equation.)
additional patient data comprising one or more of: age, sex, race, body size, blood urea nitrogen measurement, and serum albumin measurement. (Para 94 discloses the prediction of CKD progression for the new patient being based upon output of the machine learning model resulting from applying the input dataset associated with the new patient to the machine learning model, the input dataset comprising an age of the new patient, a sex of the new patient, and a second set of medical laboratory data indicating for the new patient one or more of: eGFR, urine ACR, urea, serum sodium, serum chloride, serum hemoglobin, serum potassium, glucose, serum albumin, ALKP, serum phosphate, serum bicarbonate, serum magnesium, serum calcium, AST, ALT, bilirubin, GGT, hematocrit, and platelet count. As used herein, “urine ACR” may comprise a direct urine ACR measurement, a derived or estimated urine ACR, and/or components of urine ACR such as urine albumin, urine creatinine, urine protein, and/or qualitative urine albumin (e.g., from dipstick).)
While Tangri discloses the above limitations and thus satisfies the limitations of claim 4, to strengthen the rejection of the claim, Chan further discloses:
the input data comprises (d); the or each the eGFR value eGFRo is calculated from a corresponding creatinine level co and (Ascertainment and definition of the kidney endpoint discloses we determined eGFR using the CKD-EPI creatinine equation [21].)
additional patient data comprising one or more of: age, sex, race, body size, blood urea nitrogen measurement, and serum albumin measurement. (Ascertainment of clinical variables discloses data on sex and race were obtained from the BioMe and PMBB biobanks or from EHR data. Clinical data were extracted for all EHR variables with concordant time stamps. Data harmonization discloses we harmonised data from BioMe and PMBB biobanks. Race/ethnicity was collapsed into four major, non-overlapping categories (White, Non-Hispanic Black, Hispanic, and other)… Only variables represented in >70% of participants throughout the combined dataset (except uACR and BP because of their established clinical importance) were included and used to train the KidneylntelX algorithm.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the systems and methods for predicting kidney function decline as taught by Tangri with the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan in order to appropriately risk stratify and counsel patients on the progressive nature of DKD (Chan Introduction).
Regarding Claim 5, this claim recites the limitations of Claim 1 and as to those limitations is
rejected for the same basis and reasons as disclosed above. It is noted that Chan further discloses, “(Ascertainment of clinical variables discloses data on sex and race were obtained from the BioMe and PMBB biobanks or from EHR data. Clinical data were extracted for all EHR variables with concordant time stamps,” as disclosed in claim 4.” Thus, the combination of Tangri, Chan, and Subasi discloses the following limitation that Tangri further discloses:
A computer-implemented method according to claim 1, wherein: the input data further comprises one or more of: age, albumin to creatinine ratio, serum albumin, serum cystatin-c, serum phosphate, serum bicarbonate, serum calcium, haemoglobin, glycated haemoglobin, blood urea nitrogen, number of acute kidney injury events, systolic blood pressure, diastolic blood pressure, resting heart rate, diabetes status, hypertension status, CKD diagnosis status; and patient's gender. (Para 83 discloses a new input data set 240 associated with a new patient 242 (e.g… a patient for whom a prediction of CKD progression is desired) is applied as input to the CKD progression prediction model 270 to generate a CKD progression prediction 280 for the new patient 242. The input data set 242 comprises a CKD stage 244, a sex 246, an age 248 and medical laboratory data 250 for the new patient. Para 94 discloses the prediction of CKD progression for the new patient being based upon output of the machine learning model resulting from applying the input dataset associated with the new patient to the machine learning model, the input dataset comprising an age of the new patient, a sex of the new patient, and a second set of medical laboratory data indicating for the new patient one or more of: eGFR, urine ACR [urine albumin-to-creatinine ratio], urea, serum sodium, serum chloride, serum hemoglobin [haemogloblin], serum potassium, glucose, serum albumin, ALKP, serum phosphate, serum bicarbonate, serum magnesium, serum calcium, AST, ALT, bilirubin, GGT, hematocrit, and platelet count. As used herein, “urine ACR” may comprise a direct urine ACR measurement, a derived or estimated urine ACR, and/or components of urine ACR such as urine albumin, urine creatinine, urine protein, and/or qualitative urine albumin (e.g., from dipstick).)
Regarding Claim 9, this claim recites the limitations of Claim 1 and as to those limitations is
rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, and Subasi discloses the following limitation that Tangri further discloses:
A computer-implemented method according to claim 1, wherein: the amount of time Δt is 1 to 10 years; or the input data further comprising the value of Δt, which is selectable by a user of the computer-implemented method. (Para 71 discloses a single machine learning model 145 (e.g., a single random survival forest model) is trained for generating CKD progression predictions associated with different time horizons. For instance, a time horizon or particular amount of time (e.g., 2 years, 5 years, or any amount of time or number of days) may be provided as input to the machine learning model 145 in combination with the sex, age, and medical laboratory data for a new patient to cause the machine learning model 145 to generate a prediction of CKD progression for the input time horizon or particular amount of time. Para 96 discloses the prediction of CKD progression may indicate a risk of experiencing CKD progression within a particular amount of time from a time period associated with the input dataset for the new patient (e.g., an amount of time from an eGFR measurement associated with the new patient) [thus disclosing a time interval]. Para 99 discloses the acts 318A, 318B, 318C, and/or 318D performed responsive to the prediction of CKD progression satisfying the one or more thresholds in accordance with act 316 may be selected based upon the particular time period associated with the prediction of CKD progression (e.g., 2 year or 5 year)… Para 130 discloses eGFR was calculated from available serum creatinine tests using the CKD-EPI equation.)
Regarding Claim 11, this claim recites the limitations of Claim 1 and as to those limitations is rejected for the same basis and reasons as disclosed above. While Chan inclusion criteria discloses, “patients were included if, by the KDIGO eGFR and uACR criteria, they were stage G3a-G3b with all grades of albuminuria (A1-A3) and stage G1-G2 with moderate to high albuminuria (uACR ≥30 mg/g [A2-A3]) [2] [thus discloses stages 1, 2, or 3 CKD],” the combination of Tangri, Chan, and Subasi further discloses the following limitation that Tangri discloses:
A computer-implemented method according claim 1, wherein: either: the patient has been diagnosed with Stage 1 or Stage 2 (Para 66 discloses the patient information 143 may additionally or alternatively comprise a stage of CKD of one or more patients. The stage of CKD may comprise stage G1, stage G2, stage G3, stage G4, or stage G5. The stage may, in some instances, also be selected from a plurality of sub-stages corresponding to each aforementioned stage (e.g., a substage of stage G1, etc.). Para 69 discloses as noted above, the machine learning model 145 may be utilized to generate such CKD progression prediction data 144 even for patients who are in early stages of CKD such as stage G1 or stage G2 or a substage thereof (e.g., for patients not in a CKD stage of G3 or later). Para 83 discloses a new input data set 240 associated with a new patient 242 (e.g… a patient for whom a prediction of CKD progression is desired) is applied as input to the CKD progression prediction model 270 to generate a CKD progression prediction 280 for the new patient 242. The input data set 242 comprises a CKD stage 244, a sex 246, an age 248 and medical laboratory data 250 for the new patient. Para 142 discloses to evaluate generalizability, the system evaluated the model in subpopulations of the testing cohort, including: (1) patients with diabetes; (2) patients without diabetes; (3) patients with CKD as defined by eGFR<60 ml/min/1.73 m2 or urine ACR>3 mg/mmol (including converted urine PCR tests); and (4) patients with CKD stages G1-G3 as defined by patients with eGFR 30-60 ml/min/1.73 m2 or eGFR>60 ml/min/1.73 m2 and urine ACR>3 mg/mmol (including converted urine PCR tests).
Regarding Claim 17, this claim recites the limitations of Claim 1 and as to those limitations is rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, and Subasi discloses the following limitation that Tangri further discloses:
A kidney failure likelihood determination system configured to determine, at a prediction time tp, a likelihood of kidney failure of a patient within an amount of time Δt, the system comprising a processor which is configured to perform the method of claim 1. (Para 55-57 disclose the computing system 110 of FIG. 1 includes one or more processor(s) (such as one or more hardware processor(s)) 112 and storage (i.e., hardware storage device(s) 140) storing computer-readable instructions 118… As shown in FIG. 1 , the storage (e.g., hardware storage device(s) 140) may include computer-readable instructions 118, which may be usable to facilitate training/configuring and/or executing (e.g., for CKD progression prediction generation) of one or more of the models and/or modules shown in FIG. 1 (e.g., machine learning model 145). Para 78 discloses the training module 153 is configured to train a machine learning model 145 to generate a prediction of chronic kidney disease progression by applying a training dataset 141 comprising medical laboratory data 142 and patient information 143 in order to produce as output the CKD progression prediction data 144. Para 98 discloses act 316 of flow diagram 310 includes determining that the prediction of CKD progression indicates a predicted risk of the new patient experiencing CKD within a particular time period that satisfies one or more predicted risk threshold values... In one example, for a 2 year time period, a 2% or greater prediction of CKD progression (e.g., indicating a 2% likelihood that the new patient experiences CKD progression in the form of a 40% reduction in eGFR or kidney failure is 2%) Para 99 discloses the acts 318A, 318B, 318C, and/or 318D performed responsive to the prediction of CKD progression satisfying the one or more thresholds in accordance with act 316 may be selected based upon the particular time period associated with the prediction of CKD progression (e.g., 2 year or 5 year), the particular threshold(s) satisfied (e.g., whether the patient is classified as being at “intermediate” or “high” risk)…)
Regarding Claim 18, this claim recites the limitations of Claim 1 and as to those limitations is
rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, and Subasi discloses the following limitation that Subasi further discloses:
(New) The computer-implemented method according to claim 1, further comprising: administering a first treatment plan to the patient if the output indicates the patient is a slow progressor; and administering a second treatment plan to the patient if the output indicates the patient is a fast progressor, wherein the first treatment plan is different than the second treatment plan. (Discussion section paragraph 6 discloses we may also be able to avoid complications of therapy if we can identify a truly low risk group that can just be observed rather than treated (note for example that that BP control to a lower than usual goal (<130/80) in AASK took almost four BP drugs, each with its own side effect profile). If an LAD risk score is associated with less than a 10% risk of progression [slow progressor], patients in that category could likely be observed [thus reading on administering treatment plan for a slow progressor] rather than immediately treated with aggressive therapy [thus reading on administering treatment plan for a fast progressor] or could forego such therapy if side complications arise. While current therapies for CKD are relatively benign, it should be noted that recent clinical trials have been performed with other drugs that are likely to have much more aggressive side effect profiles. If such medications are effective at slowing CKD progression, robust predictors of disease progression would be very helpful evaluating the overall risk/benefit ratio of therapy, which may not be beneficial at low progression risk.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri and the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan with the classification model to predict the rate of decline of kidney function as taught by Subasi in order to avoid complications of therapy if a truly low risk group can be identified and only observed rather than treated with aggressive therapy (Subasi Discussion section paragraph 6).
Claim(s) 6 and 12-16 are rejected under 35 U.S.C. 103 as being unpatentable over Tangri (US PG Pub 2023/0054069 A1) in view of Chan (Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease – diabetologia) further in view of Subasi (A classification model to predict the rate of decline of kidney function) and Dong (Machine learning model for early prediction of Acute Kidney Injury (AKI) in pediatric critical care - critical care).
Regarding Claim 6, this claim recites the limitations of Claim 1 and as to those limitations is
rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, and Subasi discloses the following limitation that Tangri further discloses:
A computer-implemented method according to claim 5, wherein: the input data comprises: and the patient’s age; and (Para 68 discloses the labs/measurement for the new patient may include components of one or more of a urine chemistry test (e.g., urine creatinine, urine albumin, urine ACR), a comprehensive metabolic panel (e.g., eGFR, glucose, calcium, sodium, albumin, potassium, bicarbonate, chloride, urea, phosphate/phosphorous, magnesium, liver enzymes), a complete blood cell count (e.g., hemoglobin, hematocrit, platelet count), a liver panel (e.g., ALT, AST, ALKP, GGT, bilirubin), and/or a uric acid test. Para 69 discloses the age, sex, and medical laboratory data for the new patient may be utilized as input to the (trained) machine learning model 145 to generate CKD progression prediction data 144 for the new patient.)
While the combination of Tangri, Chan, and Subasi discloses the above limitations that Tangri discloses and Tangri para 170 discloses, “eGFR was calculated from available serum creatinine tests” and Chan further discloses in ascertainment and definition of the kidney endpoint, “we determined eGFR using the CKD-EPI creatinine equation [21] We employed linear mixed models with an unstructured variance-covariance matrix and random intercept/slope for each individual to estimate the eGFR slope [22] [and thus discloses a slope dependent on a plurality creatinine levels, see Fig. 3], Dong further strengthens the combination by further disclosing the following limitations:
the recent creatinine level cR; and (Predictors discloses predictors were aggregated every six hours to generate AKI risk predictions. After model design and feature selection, the final model was trained on derivation and validation data spanning 48 to 24 h before AKI onset , and tested on holdout data 48 to 6 h before AKI onset… Fig. 1 discloses the top plot shows the patient’s measured serum creatinine values, with AKI onset time referenced as Time 0 [wherein the most recent creatinine measurement was between 12 and 24 hours before AKI onset time].
One or more of: … a plurality of past creatinine level measurements ci measured at a respective times ti, a slope s of the linear regression over time. (Predictors discloses for creatinine, an additional creatinine rate of change (CRoC) was determined by calculating the slope (mg/dL/hour) of a line least square fitted to the creatinine measurements within the previous 48 h [a plurality of past creatinine level measurements]. Fig. 1 discloses the top plot shows the patient’s measured serum creatinine values, with AKI onset time referenced as Time 0 [wherein the plurality of past creatinine levels was between 30 and 48 hours before AKI onset time]. Results discloses the final cohort demographics including the combined derivation, validation, and holdout cohorts of each hospital are shown in Table 1. The model uses 15 input predictors [including serum creatinine rate of change], plus age, as shown in Table 2.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri, the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan, and the classification model to predict the rate of decline of kidney function as taught by Subasi with the creatinine slope as taught by Dong in order to determine kidney function based on an easily attainable measurement from a patient such as creatinine especially given the fact that the analysis of Tangri and Chan is utilized on eGFR which is calculated on creatinine. It would have been obvious to use the analysis on creatinine alone as disclosed by Dong in order to utilize less steps in the analysis or to have multiple data for comparison.
Regarding Claim 12, Tangri discloses:
A computer-implemented method of generating a machine-learning model configured to determine, at a prediction time tp, a likelihood of kidney failure of a patient within a given amount of time Δt, the computer-implemented method comprising:
receiving training data, the training data comprising a plurality of data sets, representing a plurality of patients, each data set comprising input data and output data, wherein (Para 58-59 discloses the machine learning model 145 may be trained using a training dataset 141, which may comprise medical laboratory data (e.g., included in medical laboratory data 142) and/or other patient information (e.g., included in patient information 143) for a cohort of patients. Para 66 discloses the training dataset 141 may include additional information associated with the plurality of patients (or cohort of patients), such as patient outcome information (e.g., included in patient information 143). Such patient outcome information may include whether and/or when the patients experienced a decline in eGFR (e.g., a 40% or other decline), kidney failure (e.g., necessitating dialysis or kidney transplant), and/or other clinical outcomes associated with CKD.)
for the jth data set: the input data comprises a recent creatinine level cj,R or a recent eGFR eGFR j,R and: (Para 59 discloses the various labs/measurements associated with the various patients included in the training cohort may be collected (or have been collected) at one or more timepoints or during one or more time periods [thus discloses recent labs that may be collected]. Para 62 discloses at least some of the measurements represented in the training dataset 141 may comprise one or more measurements obtained in association with a urine chemistry test (e.g., urine creatinine, urine albumin, urine ACR), a comprehensive metabolic panel (e.g., eGFR, glucose, calcium, sodium, albumin, potassium, bicarbonate, chloride, urea, phosphate/phosphorous, magnesium, liver enzymes), a complete blood cell count (e.g., hemoglobin, hematocrit, platelet count), a liver panel (e.g., ALT, AST, ALKP, GGT, bilirubin), and/or a uric acid test.)
(a) a historical creatinine level c j,H, and the time t j,H at which it was obtained; (b) a historical eGFR eGFR j,H, and the time t j,H at which it was obtained; (Para 130 discloses the training data set included all adult (age 18+) individuals in the province with an available outpatient eGFR test between Apr. 1, 2006, and Dec. 31, 2016, with valid Manitoba Health registration for at least 1 year pre-index. For example, eGFR was calculated from available serum creatinine tests using the CKD-EPI equation… Para 134 discloses training datasets included age, sex, eGFR, and urine ACR as described above. Baseline eGFR was calculated as the average of all available eGFR results beginning with the first recorded eGFR during the study period and moving to the last available test in a 6-month window [historic eGFR values and the corresponding times and thus disclosing historical creatinine levels and the time at which it was obtained because para 130 the eGFR is calculated from available serum creatinine tests (see para 130)] and calculating the mean of tests during this period.)
wherein the output data comprises: an indication of an interval ΔtJ between the time tJ of kidney failure, and the time of measurement of c j,R or eGFRR; (Para 66 discloses such patient outcome information may include whether and/or when the patients experienced [thus reading on an interval of ΔtJ ] a decline in eGFR (e.g., a 40% or other decline), kidney failure (e.g., necessitating dialysis or kidney transplant), and/or other clinical outcomes associated with CKD. Para 131 discloses for evaluation of the outcome at 2 years, the training dataset included complete follow up in 61,353 individuals (42,947 in training and 18,406 in testing), and 35,736 individuals for evaluation of the outcome at 5 years (54,037 in training and 23,159 in testing).)
training the machine-learning model using the training data. (Para 67 discloses the training dataset 141 may be utilized to train the machine learning model 145 in various ways (e.g., utilizing supervised learning techniques, unsupervised learning techniques, combinations thereof, and/or others).)
applying the trained machine-learning model to the input data to generate an output indicating the likelihood of kidney failure within the given amount of time Δt (Para 78 discloses the training module 153 is configured to train a machine learning model 145 to generate a prediction of chronic kidney disease progression by applying a training dataset 141 comprising medical laboratory data 142 and patient information 143 in order to produce as output the CKD progression prediction data 144. Para 98 discloses act 316 of flow diagram 310 includes determining that the prediction of CKD progression indicates a predicted risk of the new patient experiencing CKD within a particular time period that satisfies one or more predicted risk threshold values... In one example, for a 2 year time period, a 2% or greater prediction of CKD progression (e.g., indicating a 2% likelihood that the new patient experiences CKD progression in the form of a 40% reduction in eGFR or kidney failure is 2%). Para 99 discloses the acts 318A, 318B, 318C, and/or 318D performed responsive to the prediction of CKD progression satisfying the one or more thresholds in accordance with act 316 may be selected based upon the particular time period associated with the prediction of CKD progression (e.g., 2 year or 5 year), the particular threshold(s) satisfied (e.g., whether the patient is classified as being at “intermediate” or “high” risk)…)
While Tangri discloses the above limitations, it does not fully disclose the following limitations that Chan discloses:
(c) for a plurality of past creatinine levels measured at respective times tij, a statistical parameter derived from a linear regression of the plurality of past creatinine level measurements; and (d) for a plurality of past eGFR values eGFR determined at respective times ti, a statistical parameter derived from a linear regression of the plurality of past eGFR values; (Statistical analysis discloses the derivation set was then randomly split into secondary training and test sets for model optimisation with 70%-30% spitting and a tenfold cross validation for AUC. Wherein study sample discloses only individuals with a stored plasma specimen, a minimum follow-up time from enrolment of at least 21 months, at least three eGFR values after baseline (ESM Fig. 1) were included [and ESM Fig. 1 selection of cohorts with 1146 patients with eGFR values 30-59.9 or >= 60, data harmonization including demographics or laboratory values, outcome ascertainment including eGFR slope or kidney failure and further splitting this into randomized datasets consisting of a training dataset (60%) and a validation dataset (40%). Study sample discloses for eGFR, we defined the baseline period as 1 year before or up to 3 months after biobank enrolment… Only individuals with a stored plasma specimen, a minimum follow-up time from enrolment of at least 21 months, at least three eGFR values after baseline (ESM Fig. 1) [wherein even if the most recent eGFR value is not included, there would be at least two eGFR values after baseline and thus a plurality of past eGFRs with the baseline being the initial] were included. Ascertainment and definition of the kidney endpoint discloses we determined eGFR using the CKD-EPI creatinine equation [21] [thus disclosing a plurality of past creatinine levels measured at respective times tij with a statistical parameter because the eGFR is calculated from the creatinine equation].. We employed linear mixed models with an unstructured variance-covariance matrix and random intercept/slope for each individual to estimate the eGFR slope [22]. Discussion discloses utilising plasma samples of individuals with type 2 diabetes from two biobanks and linked EHR data, we developed and validated a risk score combining clinical data and three plasma biomarkers via a random forest algorithm to predict a composite kidney outcome, progressive decline in kidney function, consisting of RKFD, sustained 40% decline in eGFR, and kidney failure over 5 years [given amount of time Δt]. See further: Statistical analysis.)
determining, based on the output [of the machine-learning model], whether the patient is a fast progressor or a slow progressor; and (The primary composite outcome, progressive decline in kidney function, included the following: RKFD (wherein the introduction defines RKFD as rapid kidney function decline) defined as an eGFR slope decline of ≥5 ml min−1 [1.73 m]−2 per year [thus reading on a fast progressor]. The Discussion discloses utilising plasma samples of individuals with type 2 diabeters from two biobanks and linked EHR data, we developed and validated a risk score combining clinical data and three plasma biomarkers via a random forest algorithm to predict a composite kidney outcome, progressive decline in kidney function, consisting of RKFD, sustained 40% decline in eGFR, and kidney failure over 5 years.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the systems and methods for predicting kidney function decline as taught by Tangri with the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan in order to precisely identify patients who will experience rapid kidney function decline (RKFD) and to appropriately risk stratify and counsel patients on the progressive nature of DKD (Chan Introduction).
While the combination of Tangri and Chan discloses the above limitations and Tangri discloses an output of the machine-learning model (See Tangri Para 78 discloses the training module 153 is configured to train a machine learning model 145 to generate a prediction of chronic kidney disease progression... Para 98-99 discloses act 316 of flow diagram 310 includes determining that the prediction of CKD progression indicates a predicted risk of the new patient experiencing CKD within a particular time period that satisfies one or more predicted risk threshold values... In one example, for a 2 year time period, a 2% or greater prediction of CKD progression (e.g., indicating a 2% likelihood that the new patient experiences CKD progression in the form of a 40% reduction in eGFR or kidney failure is 2%)) and Chan discloses in the introduction, “The primary composite outcome, progressive decline in kidney function, included the following: RKFD (wherein the introduction defines RKFD as rapid kidney function decline) defined as an eGFR slope decline of ≥5 ml min−1 [1.73 m]−2 per year”, it does not fully disclose the treatment limitation that Subasi discloses:
generating a treatment plan recommendation in accordance with the determination of whether the patient is a fast progressor or a slow progressor (Discussion section paragraph 6 discloses we may also be able to avoid complications of therapy if we can identify a truly low risk group that can just be observed rather than treated (note for example that that BP control to a lower than usual goal (<130/80) in AASK took almost four BP drugs, each with its own side effect profile). If an LAD risk score is associated with less than a 10% risk of progression [slow progressor], patients in that category could likely be observed [treatment plan recommendation for a slow progressor] rather than immediately treated with aggressive therapy [treatment plan recommendation for a fast progressor] or could forego such therapy if side complications arise. While current therapies for CKD are relatively benign, it should be noted that recent clinical trials have been performed with other drugs that are likely to have much more aggressive side effect profiles. If such medications are effective at slowing CKD progression, robust predictors of disease progression would be very helpful evaluating the overall risk/benefit ratio of therapy, which may not be beneficial at low progression risk.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri and the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan with the classification model to predict the rate of decline of kidney function as taught by Subasi in order to avoid complications of therapy if a truly low risk group can be identified and only observed rather than treated with aggressive therapy (Subasi Discussion section paragraph 6).
While the combination of Tangri, Chan, and Subasi discloses the above limitations that Tangri discloses and Tangri para 170 discloses, “eGFR was calculated from available serum creatinine tests” and Chan further discloses in ascertainment and definition of the kidney endpoint, “we determined eGFR using the CKD-EPI creatinine equation [21] We employed linear mixed models with an unstructured variance-covariance matrix and random intercept/slope for each individual to estimate the eGFR slope [22] [and thus discloses a statistical parameter dependent on a plurality creatinine levels, see Fig. 3], Dong further strengthens the combination by further disclosing the following limitations:
the recent creatinine level cR; and (Predictors discloses predictors were aggregated every six hours to generate AKI risk predictions. After model design and feature selection, the final model was trained on derivation and validation data spanning 48 to 24 h before AKI onset , and tested on holdout data 48 to 6 h before AKI onset… Fig. 1 discloses the top plot shows the patient’s measured serum creatinine values, with AKI onset time referenced as Time 0 [wherein the most recent creatinine measurement was between 12 and 24 hours before AKI onset time].
(c) for a plurality of past creatinine levels measured at respective times tij, a statistical parameter derived from a linear regression of the plurality of past creatinine level measurements; (Predictors discloses for creatinine, an additional creatinine rate of change (CRoC) was determined by calculating the slope (mg/dL/hour) of a line least square fitted to the creatinine measurements within the previous 48 h [a plurality of past creatinine level measurements]. Fig. 1 discloses the top plot shows the patient’s measured serum creatinine values, with AKI onset time referenced as Time 0 [wherein the plurality of past creatinine levels was between 30 and 48 hours before AKI onset time]. Results discloses the final cohort demographics including the combined derivation, validation, and holdout cohorts of each hospital are shown in Table 1. The model uses 15 input predictors [including serum creatinine rate of change], plus age, as shown in Table 2.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri, the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan, and the classification model to predict the rate of decline of kidney function as taught by Subasi with the creatinine slope as taught by Dong in order to determine kidney function based on an easily attainable measurement from a patient such as creatinine especially given the fact that the analysis of Tangri and Chan is utilized on eGFR which is calculated on creatinine. It would have been obvious to use the analysis on creatinine alone as disclosed by Dong in order to utilize less steps in the analysis or to have multiple data for comparison.
Regarding Claim 13, this claim recites the limitations of Claim 12 and as to those limitations is rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, Subasi, and Dong discloses the following limitation that Tangri further discloses:
A computer-implemented method according to claim 12, wherein: the plurality of data sets may include one or more clusters of data sets, wherein each cluster comprises a plurality of input data items and a respective plurality of corresponding output data items, the input data items and output data items in each cluster corresponding to data obtained at different times or over different timescales for the same patient. (Paras 58-59 disclose the first set of medical laboratory data may include various labs/measurements associated with specific patients, such as, by way of non-limiting example, estimated glomerular filtration rate (eGFR), urine albumin-to-creatinine ratio (ACR), urea, serum sodium, serum chloride, serum hemoglobin, serum potassium, glucose, serum albumin, alkaline phosphatase, serum phosphate, serum bicarbonate, serum magnesium, serum calcium, aspartate aminotransferase (AST), alanine transaminase (ALT), bilirubin, gamma-glutamyl transferase (GGT), hematocrit, platelet count, and/or others… The various labs/measurements associated with the various patients included in the training cohort may be collected (or have been collected) at one or more timepoints or during one or more time periods (e.g., resulting from samples or measurements obtained from each particular patient over the course of one or more patient-practitioner interactions over time [and thus discloses data from different time points for each patient], such as over the course of multiple sequential clinical appointments to obtain a series of samples or measurements over the course of a time period (e.g., a week, a month, etc.)).)]
Regarding Claim 14, this claim recites the limitations of Claim 13 and as to those limitations is
rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, Subasi, and Dong discloses the following limitation that Tangri further discloses:
A computer-implemented method according to claim 13, wherein: the patients for whom there is an associated cluster of data sets include patients diagnosed with end-stage renal disorder (ESRD). (Para 2 discloses for instance, in 2009, the treatment of the end stage of CKD, e.g., kidney failure or end-stage renal disease (ESRD) [wherein end stage renal disease is also known as kidney failure] required the expenditure of 40 billion dollars in the United States alone. Although only a few patients with CKD develop kidney failure, much of the excessive morbidity and costs associated with CKD are driven by individuals who progress to more advanced stages of CKD before reaching organ failure requiring dialysis. Para 66 discloses the training dataset 141 may include additional information associated with the plurality of patients (or cohort of patients), such as patient outcome information (e.g., included in patient information 143). Such patient outcome information may include whether and/or when the patients experienced a decline in eGFR (e.g., a 40% or other decline), kidney failure (e.g., necessitating dialysis or kidney transplant) [ESRD], and/or other clinical outcomes associated with CKD. The patient information 143 may additionally or alternatively comprise a stage of CKD of one or more patients. The stage of CKD may comprise stage G1, stage G2, stage G3, stage G4, or stage G5 [wherein stage G5 of CKD is ESRD].)
Regarding Claim 15, this claim recites the limitations of Claim 12 and as to those limitations is
rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, Subasi, and Dong discloses the following limitation that Tangri further discloses:
A computer-implemented method according to claim 12, wherein:
PNG
media_image1.png
3
3
media_image1.png
Greyscale
the training data comprises a further plurality of pairs of data, wherein for the kth further pair: the input data comprises a recent creatinine level ck,R and (Para 58-59 discloses the machine learning model 145 may be trained using a training dataset 141, which may comprise medical laboratory data (e.g., included in medical laboratory data 142) and/or other patient information (e.g., included in patient information 143) for a cohort of patients… the various labs/measurements associated with the various patients included in the training cohort may be collected (or have been collected) at one or more timepoints or during one or more time periods [thus discloses recent labs that may be collected]. Para 62 discloses at least some of the measurements represented in the training dataset 141 may comprise one or more measurements obtained in association with a urine chemistry test (e.g., urine creatinine, urine albumin, urine ACR), a comprehensive metabolic panel (e.g., eGFR, glucose, calcium, sodium, albumin, potassium, bicarbonate, chloride, urea, phosphate/phosphorous, magnesium, liver enzymes), a complete blood cell count (e.g., hemoglobin, hematocrit, platelet count), a liver panel (e.g., ALT, AST, ALKP, GGT, bilirubin), and/or a uric acid test. Para 130 discloses eGFR was calculated from available serum creatinine tests using the CKD-EPI equation.)
one or more of: (e) a historical creatinine level ck,H and the time tk, H at which it was obtained; (f) a historical eGFR eGFRk,H and the time tk, H at which it was obtained; (Para 130 discloses the training data set included all adult (age 18+) individuals in the province with an available outpatient eGFR test between Apr. 1, 2006, and Dec. 31, 2016, with valid Manitoba Health registration for at least 1 year pre-index. For example, eGFR was calculated from available serum creatinine tests using the CKD-EPI equation… Para 134 discloses training datasets included age, sex, eGFR, and urine ACR as described above. Baseline eGFR was calculated as the average of all available eGFR results beginning with the first recorded eGFR during the study period and moving to the last available test in a 6-month window [historic eGFR values wherein the last available test in a 6 month window would be the eGFRk,H and the corresponding times and thus disclosing historical creatinine levels matching the time of the historic eGFR and the time at which it was obtained because para 130 discloses the eGFR is calculated from available serum creatinine tests] and calculating the mean of tests during this period.)
the output data comprises an indication that kidney failure has not occurred within an interval of Atk since the time of measurement of ck, R. (Para 66 discloses such patient outcome information may include whether and/or when the patients experienced a decline in eGFR (e.g., a 40% or other decline), kidney failure (e.g., necessitating dialysis or kidney transplant), and/or other clinical outcomes associated with CKD.)
While Tangri discloses the above limitations, it does not fully disclose the following limitations that Chan further discloses:
(g) for a plurality of past creatinine levels ci measured at respective times tki, a statistical parameter determined from a linear regression of the plurality of past creatinine level measurements; and (h) for a plurality of past eGFR values eGFRi determined at respective times tki, a statistical parameter derived from a linear regression of the plurality of past eGFR values; (Statistical analysis discloses the derivation set was then randomly split into secondary training and test sets for model optimisation with 70%-30% spitting and a tenfold cross validation for AUC. Wherein study sample discloses only individuals with a stored plasma specimen, a minimum follow-up time from enrolment of at least 21 months, at least three eGFR values after baseline (ESM Fig. 1) were included [and ESM Fig. 1 selection of cohorts with 1146 patients with eGFR values 30-59.9 or >= 60, data harmonization including demographics or laboratory values, outcome ascertainment including eGFR slope or kidney failure and further splitting this into randomized datasets consisting of a training dataset (60%) and a validation dataset (40%). Study sample discloses for eGFR, we defined the baseline period as 1 year before or up to 3 months after biobank enrolment… Only individuals with a stored plasma specimen, a minimum follow-up time from enrolment of at least 21 months, at least three eGFR values after baseline (ESM Fig. 1) [wherein even if the most recent eGFR value is not included, there would be at least two eGFR values after baseline and thus a plurality of past eGFRs with the baseline being the initial] were included. Ascertainment and definition of the kidney endpoint discloses we determined eGFR using the CKD-EPI creatinine equation [21] [thus disclosing a plurality of past creatinine levels measured at respective times tij with a statistical parameter because the eGFR is calculated from the creatinine equation].. We employed linear mixed models with an unstructured variance-covariance matrix and random intercept/slope for each individual to estimate the eGFR slope [22]. Discussion discloses utilising plasma samples of individuals with type 2 diabetes from two biobanks and linked EHR data, we developed and validated a risk score combining clinical data and three plasma biomarkers via a random forest algorithm to predict a composite kidney outcome, progressive decline in kidney function, consisting of RKFD, sustained 40% decline in eGFR, and kidney failure over 5 years [given amount of time Δt]. See further: Statistical analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri and the classification model to predict the rate of decline of kidney function as taught by Subasi with the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan in order to appropriately risk stratify and counsel patients on the progressive nature of DKD (Chan Introduction).
While the combination of Tangri, Chan, and Subasi discloses the above limitations that Tangri discloses and Tangri para 170 discloses, “eGFR was calculated from available serum creatinine tests” and Chan further discloses in ascertainment and definition of the kidney endpoint, “we determined eGFR using the CKD-EPI creatinine equation [21] We employed linear mixed models with an unstructured variance-covariance matrix and random intercept/slope for each individual to estimate the eGFR slope [22] [and thus discloses a statistical parameter dependent on a plurality creatinine levels, see Fig. 3], Dong further strengthens the combination by further disclosing the following limitations:
the recent creatinine level cR; and (Predictors discloses predictors were aggregated every six hours to generate AKI risk predictions. After model design and feature selection, the final model was trained on derivation and validation data spanning 48 to 24 h before AKI onset , and tested on holdout data 48 to 6 h before AKI onset… Fig. 1 discloses the top plot shows the patient’s measured serum creatinine values, with AKI onset time referenced as Time 0 [wherein the most recent creatinine measurement was between 12 and 24 hours before AKI onset time].
(c) for a plurality of past creatinine levels measured at respective times tij, a statistical parameter derived from a linear regression of the plurality of past creatinine level measurements; (Predictors discloses for creatinine, an additional creatinine rate of change (CRoC) was determined by calculating the slope (mg/dL/hour) of a line least square fitted to the creatinine measurements within the previous 48 h [a plurality of past creatinine level measurements]. Fig. 1 discloses the top plot shows the patient’s measured serum creatinine values, with AKI onset time referenced as Time 0 [wherein the plurality of past creatinine levels was between 30 and 48 hours before AKI onset time]. Results discloses the final cohort demographics including the combined derivation, validation, and holdout cohorts of each hospital are shown in Table 1. The model uses 15 input predictors [including serum creatinine rate of change], plus age, as shown in Table 2.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri, the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan, and the classification model to predict the rate of decline of kidney function as taught by Subasi with the creatinine slope as taught by Dong in order to determine kidney function based on an easily attainable measurement from a patient such as creatinine especially given the fact that the analysis of Tangri and Chan is utilized on eGFR which is calculated on creatinine. It would have been obvious to use the analysis on creatinine alone as disclosed by Dong in order to utilize less steps in the analysis or to have multiple data for comparison.
Regarding claim 16, the claim is directed to the computer-implemented method implementing the same limitations of computer-implemented method of claim 1 (and thus is similarly rejected) and further reciting wherein the machine-learning model is generated using the computer-implemented method of claim 12 (and thus is similarly rejected).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Tangri (US PG Pub 2023/0054069 A1) in view of Chan (Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease - diabetologia) and further in view of Subasi (A classification model to predict the rate of decline of kidney function), Dong (Machine learning model for early prediction of Acute Kidney Injury (AKI) in pediatric critical care - critical care) and Li (Potential role of the renal arterial resistance index in the differential diagnosis of diabetic kidney disease).
Regarding Claim 7, this claim recites the limitations of Claim 1 and as to those limitations is rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, and Subasi discloses the following limitations that Tangri further discloses:
A computer-implemented method according to claim 5, wherein: the input data comprises: albumin-to-creatinine ratio; serum albumin; haemoglobin; CKD diagnosis status; Patient’s gender; and (Para 83 discloses a new input data set 240 associated with a new patient 242 (e.g… a patient for whom a prediction of CKD progression is desired) is applied as input to the CKD progression prediction model 270 to generate a CKD progression prediction 280 for the new patient 242. The input data set 242 comprises a CKD stage 244, a sex 246, an age 248 and medical laboratory data 250 for the new patient. Para 94 discloses the prediction of CKD progression for the new patient being based upon output of the machine learning model resulting from applying the input dataset associated with the new patient to the machine learning model, the input dataset comprising an age of the new patient, a sex of the new patient, and a second set of medical laboratory data indicating for the new patient one or more of: eGFR, urine ACR [urine albumin-to-creatinine ratio], urea, serum sodium, serum chloride, serum hemoglobin [haemogloblin], serum potassium, glucose, serum albumin, ALKP, serum phosphate, serum bicarbonate, serum magnesium, serum calcium, AST, ALT, bilirubin, GGT, hematocrit, and platelet count. As used herein, “urine ACR” may comprise a direct urine ACR measurement, a derived or estimated urine ACR, and/or components of urine ACR such as urine albumin, urine creatinine, urine protein, and/or qualitative urine albumin (e.g., from dipstick).)
While Tangri discloses the above limitations, the combination of Tangri, Chan and Subasi discloses the following limitation that Chan further discloses:
systolic blood pressure; (Prediction of the composite kidney endpoint (progressive decline in kidney function) discloses the most significant data features contributing to performance of the KidneylnteLX model included the three plasma biomarkers (TNFRl, TNFR2 and KIM1, as discrete values and ratios), eGFR, uACR, and systolic BP (Fig. 1 ).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri and the classification model to predict the rate of decline of kidney function as taught by Subasi with the systolic blood pressure of the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan in order to determine the affect kidney disease has on a variety of variables to further strengthen the prediction of kidney disease.
While the combination of Tangri, Chan, and Subasi discloses the above limitations that Tangri discloses and Tangri para 170 discloses, “eGFR was calculated from available serum creatinine tests” and Chan further discloses in ascertainment and definition of the kidney endpoint, “we determined eGFR using the CKD-EPI creatinine equation [21] We employed linear mixed models with an unstructured variance-covariance matrix and random intercept/slope for each individual to estimate the eGFR slope [22] [and thus discloses a slope dependent on a plurality creatinine levels, see Fig. 3], Dong further strengthens the combination by further disclosing the following limitations:
the recent creatinine level cR; and (Predictors discloses predictors were aggregated every six hours to generate AKI risk predictions. After model design and feature selection, the final model was trained on derivation and validation data spanning 48 to 24 h before AKI onset , and tested on holdout data 48 to 6 h before AKI onset… Fig. 1 discloses the top plot shows the patient’s measured serum creatinine values, with AKI onset time referenced as Time 0 [wherein the most recent creatinine measurement was between 12 and 24 hours before AKI onset time].
One or more of: … a plurality of past creatinine level measurements ci measured at a respective times ti, a slope s of the linear regression over time. (Predictors discloses for creatinine, an additional creatinine rate of change (CRoC) was determined by calculating the slope (mg/dL/hour) of a line least square fitted to the creatinine measurements within the previous 48 h [a plurality of past creatinine level measurements]. Fig. 1 discloses the top plot shows the patient’s measured serum creatinine values, with AKI onset time referenced as Time 0 [wherein the plurality of past creatinine levels was between 30 and 48 hours before AKI onset time]. Results discloses the final cohort demographics including the combined derivation, validation, and holdout cohorts of each hospital are shown in Table 1. The model uses 15 input predictors [including serum creatinine rate of change], plus age, as shown in Table 2.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri, the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan, and the classification model to predict the rate of decline of kidney function as taught by Subasi with the creatinine slope as taught by Dong in order to determine kidney function based on an easily attainable measurement from a patient such as creatinine especially given the fact that the analysis of Tangri and Chan is utilized on eGFR which is calculated on creatinine. It would have been obvious to use the analysis on creatinine alone as disclosed by Dong in order to utilize less steps in the analysis or to have multiple data for comparison.
While Chan Table 1 discloses a baseline Hba1c it does not fully disclose the following limitation that Li discloses:
glycated haemoglobin; (The clinical characteristics and renal pathological features of the included patients discloses a total of 469 patients were divided into two groups based on kidney biopsy results, with 332 patients in the DKD group and 137 patients in the NDKD group. The general clinical information of the two groups was shown in Table 1. Compared with the NDKD group, patients in the DKD group had longer diabetes duration, higher incidence of DR, and higher levels of systolic blood pressure, fasting blood glucose, HbA1c [glycated hemoglobin], serum creatine, blood urea nitrogen and RI value, while lower levels of BMI, hemoglobin, triglyceride and eGFR.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri, the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan, the classification model to predict the rate of decline of kidney function as taught by Subasi and the creatinine slope as taught by Dong with the Hba1c as taught by Li in order to determine the affect kidney disease has on a variety of variables to further strengthen the prediction of kidney disease.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Tangri (US PG Pub 2023/0054069 A1) in view of Chan (Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease - diabetologia) further in view of Subasi (A classification model to predict the rate of decline of kidney function) and Li (Potential role of the renal arterial resistance index in the differential diagnosis of diabetic kidney disease).
Regarding Claim 8, this claim recites the limitations of Claim 1 and as to those limitations is
rejected for the same basis and reasons as disclosed above. The combination of Tangri, Chan, and Subasi does not fully disclose the following limitation that Li discloses:
A computer-implemented method according to claim 6, wherein: the input data further comprises blood urea nitrogen. (The clinical characteristics and renal pathological features of the included patients discloses a total of 469 patients were divided into two groups based on kidney biopsy results, with 332 patients in the DKD group and 137 patients in the NDKD group. The general clinical information of the two groups was shown in Table 1. Compared with the NDKD group, patients in the DKD group had longer diabetes duration, higher incidence of DR, and higher levels of systolic blood pressure, fasting blood glucose, HbA1c, serum creatine, blood urea nitrogen and RI value, while lower levels of BMI, hemoglobin, triglyceride and eGFR.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of the systems and methods for predicting kidney function decline as taught by Tangri, the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan, the classification model to predict the rate of decline of kidney function as taught by Subasi and the creatinine slope as taught by Dong with the blood urea nitrogen as taught by Li in order to determine the affect kidney disease has on a variety of variables to further strengthen the prediction of kidney disease.
Response to Arguments
Applicant’s arguments filed 01/15/2026 with respect to 35 U.S.C. § 112(b) and 112(d) have been fully considered.
The amendments of claim 16 are persuasive and as such the previous 112(b) and 112(d) rejections of claim 16 have been withdrawn.
However, the amendments of claims 4 and 12 do not resolve the previous 112(b) rejections and as such the amendments are not persuasive. In regards to claim 4, the limitation discloses “input data comprises (b) and/or (d)” where claim 1 (b) discloses eGFR0 and (d) discloses eGFRi. However, claim 4 only discloses “the or each the eGFR value eGFR0 is calculated from a corresponding creatinine level c0.” It is unclear if this is in regards to both (b) and/or (d) as now (b) and (d) do not disclose eGFR0. Further, claim 4 recites, “and wherein the or each the eGFR value eGFR0 is calculated from a corresponding creatinine level c0.“ The removal of the subscript 0 from eGFR in (b) means there is lack of antecedent basis for eGFR0 , thus resulting in a new rejection under 112(b) on top of the previous 112(b) rejection. Thus, the Examiner is interpreting the claim 4 limitation to read, “the or each of the eGFR values, the initial eGFR or eGFRi , are calculated from a corresponding creatinine level, c or ci” because claim 4 discloses the input data comprises specifically (b) and/or (d).
In regards to claim 12, claim 12 discloses that “the input data comprises… cj,R… or eGFRj,R” but only discloses that “wherein the output data comprises… the time of measurement of cj,R. “ The claim is indefinite as the output does not depend on the same two options for the input as disclosed by the claim, since the input could broadly be selected as just the eGFRj,R. Thus, the Examiner is interpreting the output limitation to read as, “wherein the output data comprises… the time of measurement of cj,R or eGFRj,R”
Applicant’s arguments filed 01/15/2026 with respect to 35 U.S.C. § 101 have been fully considered, but are not persuasive.
The Applicant argues that the claims recite at least one step that should be considered a “corrective action” namely the treatment plan recommendation that is determined based on the output of the machine-learning model. MPEP 2106.04(d)(2) indicates that a practical application may be present where the abstract idea effects a particular treatment or provides particular prophylaxis for a disease or medical condition. Applicant’s claimed invention does not provide for a particular treatment or prophylaxis because no treatment or prophylaxis is recited in the claim. A recommendation to treat a patient is not actually administering a particular treatment to the patient. Because a particular treatment or prophylaxis is not present in the claims, a practical application is not present and this argument is not persuasive.
Further, the Applicant argues that the claims include at least one step that cannot reasonably be performed in the human mind. The Examiner submits that the abstract idea was not characterized as being directed to a mental process. The claimed invention was characterized as being directed to a mathematical concept, which is an abstract idea (see Non-Final Office Action dated 09/29/2025 at Pg. 6). As such, this argument cannot be persuasive.
Finally, the Applicant argues that claim 18 should qualify as a “particular treatment or prophylaxis” as discussed in MPEP 2106.04(d)(2). The Examiner respectfully disagrees. MPEP 2106.04(d)(2) indicates that a practical application may be present where the abstract idea effects a particular treatment or provides particular prophylaxis for a disease or medical condition. A particular treatment/prophylaxis is present where: (a) there is a particular (i.e., named/described) treatment /prophylaxis that occurs when the claim is implemented; (b) the treatment/prophylaxis has more than a nominal connection/correlation to the abstract idea; and (c) the administration is more than extra-solution activity or a field of use.
Applicant’s claimed invention does not provide for a particular treatment or prophylaxis because no treatment/prophylaxis is recited in the claim. Broadly claiming “administering a first treatment plan…” and “administering a second treatment plan…” does not disclose a particular treatment or prophylaxis. Because a particular treatment or prophylaxis is not present in the claims, a practical application is not present.
Applicant’s arguments filed 01/15/2026 with respect to 35 U.S.C. § 103 have been fully considered, but are not persuasive.
Applicant argues that Tangri only predicts CKD (and quotes “40% decline”) and not the same prediction of likelihood of Kidney Failure that the patent application claims. The Examiner respectfully disagrees. Tangri para 49 discloses, “Furthermore, predictions generated in accordance with the present disclosure may be based on a composite outcome of either 40% decline in eGFR and/or kidney failure (e.g., as opposed to solely kidney failure). Predictions generated in accordance with at least some embodiments of the present disclosure may provide a risk score for a patient experiencing either outcome.” Thus, Tangri reads on predictions based on a composite outcome of kidney failure. Thus, this argument is not persuasive.
The Applicant argues that neither Tengri nor Chan teach using a patient’s historical slope (determined from linear regression), from a plurality of measurements and states that the EGFR slope of the cited references is used to define the output or “endpoint” during training of the model and is not used as an input. Further, the Applicant argues that Chan uses entirely different sets of input features to predict future health risks. The Examiner respectfully disagrees. The “Ascertainment and definition of the kidney endpoint” section discloses we employed linear mixed models with an unstructured variance-covariance matrix and random intercept/slope for each individual to estimate the eGFR slope [22]. The primary composite outcome, progressive decline in kidney function, included the following: RKFD defined as an eGFR slope decline of ≥5 ml min−1 [1.73 m]−2 per year [2], a sustained (confirmed at least 3 months later) decline in eGFR of ≥40% [23] from baseline, or ‘kidney failure’ defined by sustained eGFR <15 ml min−1 [1.73 m]−2 confirmed at least 30 days later, or receipt of long-term maintenance dialysis or receipt of a kidney transplant [2].” Thus disclosing that the eGFR slope of <15 ml min−1 [1.73 m]−2 is used to determine kidney failure. As previously presented, Tangri reads on the limitation of “applying a machine learning model to the input data to generate an output indicating the likelihood of kidney failure within the given amount of time Δt” and it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the systems and methods for predicting kidney function decline as taught by Tangri with the derivation and validation of a machine learning risk score… to predict progression of diabetic kidney disease as taught by Chan in order to appropriately risk stratify and counsel patients on the progressive nature of DKD (Chan Introduction).
Further, to further prosecution, the Examiner notes that, as claim 1 is currently written, steps a-d are not included as input data. As the claim recites, “receiving input data, the input data comprising a recent creatinine level cr or recent estimated glomerular filtration (eGFR) value eGFRR , and one or more of the following: a-d.” Thus, claim 1 only claims receiving one or more of a-d and does not narrow it as input data. Further, claim 3, which narrows the statistical parameter to one or more of a plurality of options including slope with respect to time, intercept, and a variance, does not narrow the input data. It is not until dependent claim 4 that the input data comprises (b) and / or (d) wherein the use of “and/or” further does not require that step (d) is utilized as input as step (b) could be chosen. Claim 4 is also dependent on claim 1 and thus the statistical parameter of (d) is not narrowed in regards to claim 4 as it is not dependent on claim 3. In conclusion, at no point in the claims of the instant application is step (d) strictly required to be used as input.
Finally, the Applicant argues that another distinguishing feature between Chan and the present claims of the instant application is the output target. The Examiner respectfully disagrees. As the Applicant notes, Chan provides a composite outcome of eGFR decline of eGFR decline of ≥5 ml/min per year, ≥40% sustained decline, or kidney failure within 5 years and the present invention discloses according to claim 1 discloses a method providing a prediction of likelihood of kidney failure of a patient within an amount of time Δt. Thus, the broadest reasonable interpretation of the composite outcome includes kidney failure within 5 years which reads on the limitations of claim 1 and this argument is not persuasive.
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 SARA J MORICE DE VARGAS whose telephone number is (703)756-4608. The examiner can normally be reached M-F 8:30-5:30 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Peter H. Choi can be reached at (469)295-9171. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SARA JESSICA MORICE DE VARGAS/Examiner, Art Unit 3681
/PETER H CHOI/Supervisory Patent Examiner, Art Unit 3681
Prosecution Insights