Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-20 are pending in the present application with claims 1 and 11 being independent.
Claim Rejections - 35 USC § 112
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 1-20 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.
Claim 1 recites obtaining "a plurality of patient records" for a patient and then executing the engine to generate the risk score using features extracted from "the patient record" which leads to confusion as to which of the plurality of patient records is being referred. It is recommended that Applicant amends claim 1 to recite executing the engine to generate the risk score using features extracted from "the plurality of patient records."
Claim 11 recites, inter alia:
"obtain a plurality of patient records for a patient containing patient health data, one or more health measurements, and a training label indicating the health status of the training patient for the training record;
execute the machine-learning architecture of the risk prediction engine to generate the risk score for the patient using a set of patient features extracted from the one or more health measurements of the training record." (Emphasis added)
It appears Applicant has inadvertently included language from the training dataset limitations which renders these limitations nonsensical. Reference is made to the corresponding "obtaining" and "executing" steps of independent claim 1 which do not reference the training patient and training record. It is recommended that Applicant removes "and a training label indicating the health status of the training patient for the training record" from the "obtain" step of claim 11 and amends "of the training record" in the "execute" step of claim 11 to read --of the patient record-- for clarity and the Examiner will assume this is so for purposes of examination.
The remaining claims are rejected based on their dependency from one of the above rejected claims.
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 1-20 are rejected under 35 U.S.C. §101 because the claimed invention is directed to an abstract idea without significantly more:
Subject Matter Eligibility Criteria - Step 1:
Claims 1-10 are directed to a method (i.e., a process) and claims 11-20 are directed to a system (i.e., a machine). Accordingly, claims 1-20 are all within at least one of the four statutory categories. 35 USC §101.
Subject Matter Eligibility Criteria - Alice/Mayo Test: Step 2A - Prong One:
Regarding Prong One of Step 2A of the Alice/Mayo test (which collectively includes the guidance in the January 7, 2019 Federal Register notice and the October 2019 and July 2024 updates issued by the USPTO as incorporated into the MPEP, as supported by relevant case law), the claim limitations are to be analyzed to determine whether, under their broadest reasonable interpretation, they “recite” a judicial exception or in other words whether a judicial exception is “set forth” or “described” in the claims. MPEP 2106.04(II)(A)(1). An “abstract idea” judicial exception is subject matter that falls within at least one of the following groupings: a) certain methods of organizing human activity, b) mental processes, and/or c) mathematical concepts. MPEP 2106.04(a).
Representative independent claim 1 includes limitations that recite at least one abstract idea. Specifically, independent claim 1 recites:
A method of using machine-learning for predicting risks of hypertensive disorders of pregnancy (HDP), the method comprising:
generating, by a computer, a training dataset comprising a plurality of training records containing training health data for a plurality of patients and a corresponding plurality of training labels indicating a health status, each training record includes an indication of a training patient, a timestamp, one or more training health measurements, and a training label indicating the health status of the training patient of the training record;
for each training record in a first training set of one or more training patients having a first endpoint, extracting, by the computer, a set of training features from the one or more training measurements of the training record according to the first endpoint;
for each training record in a second training set of one or more training patients having a second endpoint, extracting, by the computer, the set of training features from the one or more training measurements of the training record according to the second endpoint;
training, by the computer, a machine-learning architecture of a risk prediction engine to generate a risk score using the set of training features and the training labels of the first training set of training records according to the first endpoint, the set of training features and the training labels of the second set of training records according to the second endpoint;
obtaining, by the computer, a plurality of patient records for a patient containing patient health data and one or more health measurements;
executing, by the computer, the machine-learning architecture of the risk prediction engine to generate the risk score for the patient using a set of patient features extracted from the one or more health measurements of the patient record;
identifying, by the computer, the health status of the patient based upon comparing the risk score for the patient against a disorder prediction threshold; and
generating, by the computer, health report data of the patient for display at a user interface of one or more client devices, the health report data indicating the one or more health measurements and the health status of the patient.
The Examiner submits that the foregoing underlined limitations relating to predicting risks of HDP recite “mental processes” because they are observations/evaluations/judgments/analyses that can, at the currently claimed high level of generality, be practically performed in the human mind (e.g., with pen and paper). As an example a person could readily review EMRs, medical literature, etc. and develop/generate a set of training records that indicate a training patient, a timestamp (e.g., a time/time period during pregnancy), health measurements (e.g., SBP, DBP, BP variability, etc.), and a training label (e.g., gestational hypertension, early onset preeclampsia, etc.). The medical professional could then extract/glean certain training features from the training dataset corresponding to first and second endpoints (e.g., certain time periods during pregnancy) to generate first and second training sets, compare the features in the training sets to corresponding features of a current patient extracted from the current patient's health measurements to generate a risk score for the current patient (e.g., based on how close the features of the current patient are to those of the training sets), compare the risk score of the current patient to a threshold to determine a health status of the current patient (e.g., high risk of developing early onset PE), and generate (e.g., with pen and paper) a health report indicating the health status and the health measurements of the current patient. These recitations, under their broadest reasonable interpretation, are similar to how the concepts of collecting information, analyzing it, and displaying certain results of the collection and analysis in the claims were characterized to be "mental processes" in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQe2d 1739 (Fed. Cir. 2016)). MPEP 2106.04(a)(2)(III).
Claims "directed to collection of information, comprehending the meaning of that collected information, and indication of the results, all on a generic computer network operating in its normal, expected manner," fail step one of the Alice framework. In re Killian, 45 F.4th 1373, 1380 (Fed. Cir. 2022). Claims directed to "collecting, analyzing, manipulating, and displaying data" are abstract. Univ. of Fla. Research Found., Inc. v. General Elec. Co., 916 F.3d 1363, 1368 (Fed. Cir. 2019). Claims directed to organizing, storing, and transmitting information determined to be directed to an abstract idea. Cyberfone Sys., L.L.C. v. CNN Interactive Grp., Inc., 558 F. App’x 988, 992 (Fed. Cir. 2014).
Accordingly, the claim recites at least one abstract idea.
Furthermore, dependent claims 2-10 and 12-20 further define the at least one abstract idea (and thus fail to make the abstract idea any less abstract) as set forth below:
-Claims 2 and 12 call for selecting from the plurality of records of the training dataset the first training set of the training records having the first endpoint and the second training set of the training records having the second endpoint, the timestamp of each training record in the first training set satisfying the first endpoint, and the timestamp of each training record in the second training set satisfying the second endpoint. These limitations just further define the "mental processes" abstract idea discussed above.
-Claims 3 and 13 recite how each training record in the plurality of training records in the training dataset includes a source device indicator for a type of source device, including at least one of a clinician device or an edge device, and wherein the set of training features and the set of patient features includes the source device indicator for the type of source device. These limitations just further define the "mental processes" abstract idea discussed above.
-Claims 4 and 14 further call for identifying in the training dataset a bias training record for the training patient, the health status of the bias training record indicating a disorder status for the training patient, and the timestamp of the bias training record fails to satisfy a status update threshold from the timestamp of a prior training record for the patient indicating an initial instance of the disorder status; and omitting each bias training record from the training dataset. These limitations just further define the "mental processes" abstract idea discussed above.
-Claims 5 and 15 recite how each training patient includes at least two training records having at least two training measurements. These limitations just further define the "mental processes" abstract idea discussed above.
-Claims 6 and 16 call for updating, for a next training record for the training patient, at least a portion of the set of training features for the training patient according to the one or more training measurements of the next training record. These limitations just further define the "mental processes" abstract idea discussed above.
-Claims 7 and 17 call for extracting, for a next patient record for the patient, a set of updated features for the patient using the one or more measurements of the next patient record; and generating an updated health report of the patient for display at the user interface of the one or more client devices. These limitations just further define the "mental processes" abstract idea discussed above.
-Claims 8 and 18 recite how the set of patient features for the patient and the set of training features for the training patient include at least one of: maximum blood pressure, minimum blood pressure, mean blood pressure, median blood pressure, blood pressure variability, blood pressure average real variability, blood pressure coefficient of variation, proportion of measures exceeding range, or a measurement slope. These limitations just further define the "mental processes" abstract idea discussed above.
-Claims 9 and 19 recite the one or more measurements include at least one of: a systolic blood pressure, an interpregnancy interval, a prior diagnosis, a pre- pregnancy body mass index, a diastolic measurement, or a systolic measurement. These limitations just further define the "mental processes" abstract idea discussed above.
-Claims 10 and 20 call for identifying one or more intervention actions corresponding to the set of one or more features extracted for the patient in response to determining that the risk score for the patient satisfies the disorder prediction threshold. These limitations just further define the "mental processes" abstract idea discussed above.
Subject Matter Eligibility Criteria - Alice/Mayo Test: Step 2A - Prong Two:
Regarding Prong Two of Step 2A of the Alice/Mayo test, it must be determined whether the claim as a whole integrates the abstract idea into a practical application. As noted at MPEP §2106.04(II)(A)(2), it must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements such as merely using a computer to implement an abstract idea, adding insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.” MPEP §2106.05(I)(A).
In the present case, the additional limitations beyond the above-noted at least one abstract idea recited in the claim are as follows (where the bolded portions are the “additional limitations” while the underlined portions continue to represent the at least one “abstract idea”):
A method of using machine-learning for predicting risks of hypertensive disorders of pregnancy (HDP), the method comprising:
generating, by a computer, a training dataset comprising a plurality of training records containing training health data for a plurality of patients and a corresponding plurality of training labels indicating a health status, each training record includes an indication of a training patient, a timestamp, one or more training health measurements, and a training label indicating the health status of the training patient of the training record;
for each training record in a first training set of one or more training patients having a first endpoint, extracting, by the computer, a set of training features from the one or more training measurements of the training record according to the first endpoint;
for each training record in a second training set of one or more training patients having a second endpoint, extracting, by the computer, the set of training features from the one or more training measurements of the training record according to the second endpoint;
training, by the computer, a machine-learning architecture of a risk prediction engine to generate a risk score using the set of training features and the training labels of the first training set of training records according to the first endpoint, the set of training features and the training labels of the second set of training records according to the second endpoint;
obtaining, by the computer, a plurality of patient records for a patient containing patient health data and one or more health measurements;
executing, by the computer, the machine-learning architecture of the risk prediction engine to generate the risk score for the patient using a set of patient features extracted from the one or more health measurements of the patient record;
identifying, by the computer, the health status of the patient based upon comparing the risk score for the patient against a disorder prediction threshold; and
generating, by the computer, health report data of the patient for display at a user interface of one or more client devices, the health report data indicating the one or more health measurements and the health status of the patient.
For the following reasons, the Examiner submits that the above-identified additional limitations, when considered as a whole with the limitations reciting the at least one abstract idea, do not integrate the above-noted at least one abstract idea into a practical application.
Regarding the additional limitations of the computer (and the processor in independent claim 11), the Examiner submits that these limitations amount to merely using a computer or other machinery as tools performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f)).
Regarding the additional limitations of the training the ML architecture of the risk prediction engine to generate the risk score using the set of training features and the training labels of the first and second training sets and executing the machine-learning architecture of the risk prediction engine, the Examiner submits that these limitations amount to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)). Claims that do no more than apply established methods of machine learning to a new data environment are not patent eligible. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), pp. 10, 14. An abstract idea does not become nonabstract by limiting the invention to a particular field of use or technological environment. Id.
Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id.
Thus, taken alone, the additional elements do not integrate the at least one abstract idea into a practical application. Furthermore, looking at the additional limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. MPEP §2106.05(I)(A) and §2106.04(II)(A)(2).
For these reasons, representative independent claim 1 and analogous independent claim 11 do not recite additional elements that integrate the judicial exception into a practical application. Accordingly, representative independent claim 1 and analogous independent claim 11 are directed to at least one abstract idea.
The remaining dependent claim limitations not addressed above fail to integrate the abstract idea into a practical application as set forth below:
-Claims 6 and 16 call for re-training the machine-learning architecture of the risk prediction engine to generate the risk score using the set of training features as updated and the training label of the next training record. These limitations amount to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)). Again, requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id.
When the above additional limitations are considered as a whole along with the limitations directed to the at least one abstract idea, the at least one abstract idea is not integrated into a practical application. Therefore, the claims are directed to at least one abstract idea.
Subject Matter Eligibility Criteria - Alice/Mayo Test: Step 2B:
Regarding Step 2B of the Alice/Mayo test, representative independent claim 1 does not include additional elements (considered both individually and as an ordered combination) that are sufficient to amount to significantly more than the judicial exception for reasons the same as those discussed above with respect to determining that the claim does not integrate the abstract idea into a practical application.
Regarding the additional limitations of the computer (and the processor in independent claim 11), the Examiner submits that these limitations amount to merely using a computer or other machinery as tools performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f)).
Regarding the additional limitations of the training the ML architecture of the risk prediction engine to generate the risk score using the set of training features and the training labels of the first and second training sets and executing the machine-learning architecture of the risk prediction engine, the Examiner submits that these limitations amount to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)). Claims that do no more than apply established methods of machine learning to a new data environment are not patent eligible. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), pp. 10, 14. An abstract idea does not become nonabstract by limiting the invention to a particular field of use or technological environment. Id.
Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id.
The dependent claims also do not include additional elements (considered both individually and as an ordered combination) that are sufficient to amount to significantly more than the judicial exception for reasons the same as those discussed above with respect to determining that the dependent claims do not integrate the at least one abstract idea into a practical application.
-Claims 6 and 16 call for re-training the machine-learning architecture of the risk prediction engine to generate the risk score using the set of training features as updated and the training label of the next training record. These limitations amount to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)). Again, Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id.
Therefore, claims 1-20 are ineligible under 35 USC §101.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 2, 5, 8, 9, 11, 12, 15, 18, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over NPL "Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data" to Li et al. ("Li") in view of U.S. Patent App. Pub. No. 2025/0259750 to Aherne et al. ("Aherne"):
Regarding claim 1, Li discloses a method of using machine-learning for predicting risks of hypertensive disorders of pregnancy (HDP) (the Abstract and Figure 1 on page 3 discloses/illustrates using ML techniques to predict risk of preeclampsia (a hypertensive disorder of pregnancy (HDP)), the method comprising:
generating, by a computer, a training dataset comprising a plurality of training records containing training health data for a plurality of patients and a corresponding plurality of training labels indicating a health status, each training record includes an indication of a training patient, a timestamp, one or more training health measurements, and a training label indicating the health status of the training patient of the training record (the middle of the left column and the right column on page 2 discuss digitally reconstructing pregnancy journeys (training dataset of training records) for a plurality of patients from EMR data, where each pregnancy journey necessarily includes some indication/identifier to distinguish its data from that of the other pregnancy journeys (indication of training patient), various clinical characteristics (training health measurements) at various time points during the journey (in order to separate clinical characteristics into the various time points, each pregnancy journey/training record would necessarily include one or more timestamps corresponding to the various characteristics/measurements/etc.), and an indication regarding whether the patient has PE (training label indicating health status); furthermore, because ML necessarily requires the use a computer, the training data is generated "by a computer");
for each training record in a first training set of one or more training patients having a first endpoint, extracting, by the computer, a set of training features from the one or more training measurements of the training record according to the first endpoint (the bottom of the right column on page 2 to the left column on page 3 and "Refining key features during the pregnancy journey starting on page 4 discloses selecting/extracting training features from the clinical characteristics for various timepoints during the antepartum, intrapartum, and postpartum periods; thus, the selected features for one of the timepoints (first endpoint) is a "first training set of one or more training patients");
for each training record in a second training set of one or more training patients having a second endpoint, extracting, by the computer, the set of training features from the one or more training measurements of the training record according to the second endpoint (the selected features for another of the time points (second endpoint) is a "second training set of one or more training patients");
training, by the computer, a machine-learning architecture of a risk prediction engine to generate a risk score using the set of training features and the training labels of the first training set of training records according to the first endpoint, the set of training features and the training labels of the second set of training records according to the second endpoint (the first full paragraph on the left column of page 13 discusses training ML models (ML-architecture of a risk prediction engine) using the training datasets (which include the training features/labels of the first/second training sets of training records according to the first/second endpoints as noted above) for each of the timepoints/time periods to predict PE risk (the bottom of the left column on page 2, Figure 1, "Discussion" on page 10, and the top of left column on page 13 disclose predicting PE risk); also, page 8-9 disclose generating relative PE risk);
obtaining, by the computer, a plurality of patient records for a patient containing patient health data and one or more health measurements (the bottom of the left column on page 2 discloses obtaining a patient's EMR (which necessarily includes patient health data and one or more health measurements);
executing, by the computer, the machine-learning architecture of the risk prediction engine to generate the risk score for the patient using a set of patient features extracted from the one or more health measurements of the patient record (the bottom of the left column on page 2 discloses running the model on relevant input features extracted from the patient's EMR to generate an indication of PE risk for the patient; where the ML model architecture would necessarily generate a numerical output (score) that corresponds to the indication of PE risk for the patient);
…; and
generating, by the computer, health report data of the patient for display at a user interface of one or more client devices, the health report data indicating …the health status of the patient (when the ML model architecture is applied "in clinical practice" per the bottom of the left column on page 2, the generated indication of PE risk ("health status") for the patient is necessarily displayed as "health report data" indicating the health status for display at a UI of some "client device").
However, Li might be silent regarding identifying, by the computer, the health status of the patient based upon comparing the risk score for the patient against a disorder prediction threshold; and the displayed health status also including the one or more health measurements.
Nevertheless, Aherne teaches that it was known in the healthcare informatics art to utilize an ML risk prediction model that processes input patient features to generate a risk score ([0098]-[0100]) indicative of a disease (e.g., ovarian cancer per [0032]), compare the risk score to one or more thresholds to classify the patient into one or more risk level groups ([0102]), and display the risk level groups (health status) and the feature set (health measurements) via a GUI to advantageously convey an easily perceivable level of patient health risk to a user (based on the risk level group into which the patient is classified) while also providing information (the feature set) relative to the determination of the risk level group thereby allowing medical professionals to determine corrective actions and the like.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have identified the health status of the patient based upon comparing the risk score for the patient against a disorder prediction threshold and displayed both the health status and the one or more health measurements in the method of Li as taught by Aherne to advantageously convey an easily perceivable level of patient health risk to a user while also providing information relative to the determination of the risk level group thereby allowing medical professionals to determine corrective actions and the like. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Regarding claim 2, the Li/Aherne combination discloses the method according to claim 1, further including selecting, by the computer, from the plurality of records of the training dataset the first training set of the training records having the first endpoint and the second training set of the training records having the second endpoint, the timestamp of each training record in the first training set satisfying the first endpoint, and the timestamp of each training record in the second training set satisfying the second endpoint (in order to select the training records for each of the 19 time points discussed on pages 2-3 of Li (which includes the recited "first training set" for the "first endpoint" and "second training set" for the "second endpoint"), the timestamps of the training records in the first training set would satisfy the first time point/endpoint and the timestamps of the training records in the second training set would satisfy the second time point/endpoint ).
Regarding claim 5, the Li/Aherne combination discloses the method according to claim 1, further including wherein each training patient includes at least two training records having at least two training measurements (pages 2-3 of Li discloses numerous features/characteristics for each of numerous patients at each of numerous time points such that each training patient includes at least two records (e.g., one for each timepoint) having at least two training measurements (features/characteristics)(e.g., see Table 1 on page 4)).
Regarding claim 8, the Li/Aherne combination discloses the method according to claim 1, further including wherein the set of patient features for the patient and the set of training features for the training patient include at least one of: maximum blood pressure, minimum blood pressure, mean blood pressure, median blood pressure, blood pressure variability, blood pressure average real variability, blood pressure coefficient of variation, proportion of measures exceeding range, or a measurement slope (Table 1 discloses median BP, bottom of right column on page 7 discloses median SBP).
Regarding claim 9, the Li/Aherne combination discloses the method according to claim 1, further including wherein the one or more measurements include at least one of: a systolic blood pressure, an interpregnancy interval, a prior diagnosis, a pre-pregnancy body mass index, a diastolic measurement, or a systolic measurement (top of right column on page 2 discloses diagnoses (which would be "prior" as they are already known), pages 4-5 and the top of right column on page 12 discloses SBP, DBP, height and weight (which allows for determination of BMI)).
Claims 11, 12, 15, 18, and 19 are rejected in view of the Li/Aherne combination as respectively discussed above in relation to claims 1, 2, 5, 8, and 9. In relation to a computer having at least one processor as recited in claim 11, the ML disclosed in Li necessarily requires the use of a computer which necessarily includes at least one processor.
Claims 3 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over NPL "Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data" to Li et al. ("Li") in view of U.S. Patent App. Pub. No. 2025/0259750 to Aherne et al. ("Aherne"), and further in view of U.S. Patent App. Pub. No. 2025/0049336 to Park et al. ("Park"):
Regarding claim 3, the Li/Aherne combination discloses the method according to claim 1, but appears to be silent regarding wherein each training record in the plurality of training records in the training dataset includes a source device indicator for a type of source device, including at least one of a clinician device or an edge device, and wherein the set of training features and the set of patient features includes the source device indicator for the type of source device.
Nevertheless, Park teaches ([0070], [0132], [0340], and claims 1-3) that it was known in the healthcare informatics art to train a heart rate information standardization model (ML model per [0129]) to generate standardized heart rate information of a user based on training heart rate information and corresponding type information indicating a type of wearable device used to generate the training heart rate information (source device indicator including an edge device), input heart rate information and wearable device type of a patient into the trained model (such that a set of patient features includes a source device indicator for a type of source device), determine standardized heart rate information of the patient, and generate disease monitoring information based on the heart rate information. This arrangement advantageously allows data from different types of devices to be used as training data (via standardizing the data) which increases the amount of available training data and thus predictions generated by the ML models ([0341]-[0343]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for each training record in the plurality of training records in the training dataset of the Li/Aherne combination to include a source device indicator for a type of source device, including an edge device, wherein the set of training features and the set of patient features includes the source device indicator for the type of source device, similar to as taught by Park to arrangement advantageously allows data from different types of devices to be used as training data (via standardizing the data) which increases the amount of available training data and thus predictions generated by the ML models. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Claim 13 is rejected in view of the Li/Aherne/Park combination as discussed above in relation to claim 3.
Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over NPL "Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data" to Li et al. ("Li") in view of U.S. Patent App. Pub. No. 2025/0259750 to Aherne et al. ("Aherne"), and further in view of U.S. Patent App. Pub. No. 2024/0206821 to Upadhyay et al. ("Upadhyay"):
Regarding claim 6, the Li/Aherne combination discloses the method according to claim 1, and discloses (first full paragraph on the left column of page 13 of Li) training ML models (ML-architecture of a risk prediction engine) using the training datasets (which include the training features/labels of the first/second training sets of training records according to the first/second endpoints as noted above) for each of the timepoints/time periods to predict PE risk (the bottom of the left column on page 2, Figure 1, "Discussion" on page 10, and the top of left column on page 13 disclose predicting PE risk)
However, the Li/Aherne combination might be silent regarding:
for a next training record for the training patient,
updating, by the computer, at least a portion of the set of training features for the training patient according to the one or more training measurements of the next training record; and
re-training, by the computer, the machine-learning architecture of the risk prediction engine to generate the risk score using the set of training features as updated and the training label of the next training record.
Nevertheless, Upadhyay teaches ([0032]-[0033], [0042], [0086]) that it was known in the healthcare informatics and machine learning art to train an ML model with features (set of training features) extracted from time-series physiological data (training measurements) and corresponding labels (training labels), analyze novel time-series data (next training records) to determine informative data points (features) for labeling (updating the set of training features according to training measurements of next training record), and retrain the ML model to generate a predicted physiological indicator using the updating features and training label of the next "training record" to advantageously provide the most valuable information for improving the model's performance.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have, for a next training record for the training patient in the method of the Li/Aherne combination, updated, by the computer, at least a portion of the set of training features for the training patient according to the one or more training measurements of the next training record; and re-trained, by the computer, the machine-learning architecture of the risk prediction engine to generate the risk score using the set of training features as updated and the training label of the next training record as taught by Upadhyay to advantageously provide the most valuable information for improving the model's performance. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Claim 16 is rejected in view of the Li/Aherne/Upadhyay combination as discussed above in relation to claim 6.
Claims 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over NPL "Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data" to Li et al. ("Li") in view of U.S. Patent App. Pub. No. 2025/0259750 to Aherne et al. ("Aherne"), and further in view of U.S. Patent App. Pub. No. 2023/0068453 to Boverman et al. ("Boverman"):
Regarding claim 7, the Li/Aherne combination discloses the method according to claim 1, but appears to be silent regarding
for a next patient record for the patient,
extracting, by the computer, a set of updated features for the patient using the one or more measurements of the next patient record; and
generating, by the computer, an updated health report of the patient for display at the user interface of the one or more client devices.
Nevertheless, Boverman teaches ([0048]) that it was known in the healthcare informatics and machine learning art to extract a plurality of features from new patient information (one or more measurements of next patient record) and generate using a risk model (ML per [0067]) an updated risk for a patient and generated an updated report for the patient ([0082]) which advantageously facilitate treatment decisions and improve survival outcomes, thereby leading to saved lives ([0083]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have, for a next patient record for the patient, extracted, by the computer, a set of updated features for the patient using the one or more measurements of the next patient record; and generated, by the computer, an updated health report of the patient for display at the user interface of the one or more client devices in the method of the Li/Aherne combination similar to as taught by Boverman to advantageously facilitate treatment decisions and improve survival outcomes, thereby leading to saved lives. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Claim 17 is rejected in view of the Li/Aherne/Boverman combination as discussed above in relation to claim 7.
Claims 10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over NPL "Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data" to Li et al. ("Li") in view of U.S. Patent App. Pub. No. 2025/0259750 to Aherne et al. ("Aherne"), and further in view of U.S. Patent App. Pub. No. 2023/0215579 to Ghosh et al. ("Ghosh"):
Regarding claim 10, the Li/Aherne combination discloses the method according to claim 1, but appears to be silent regarding in response to determining that the risk score for the patient satisfies the disorder prediction threshold, executing, by the computer, the machine-learning architecture of the risk prediction engine to identify one or more intervention actions corresponding to the set of one or more features extracted for the patient.
Nevertheless, Ghosh teaches ([0044]-[0064] and Figures 2-3) that it was known in the healthcare informatics art to utilize ML techniques to analyze medical history and dynamic clinical information (features) of a patient, determine a level of medical (e.g., AKI) risk based on the analyzed features, determine that the risk level exceeds a threshold, and generate an intervention based on the risk level exceeding the threshold (and the patient features because the features are used to generate the risk level) to advantageously improve real-time clinical deployment for decision making and improved patient outcomes ([0010]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have executed, by the computer, the machine-learning architecture of the risk prediction engine to identify one or more intervention actions corresponding to the set of one or more features extracted for the patient in response to determining that the risk score for the patient satisfies the disorder prediction threshold in the method of the Li/Aherne combination as taught by Ghosh to advantageously improve real-time clinical deployment for decision making and improved patient outcomes. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Claim 20 is rejected in view of the Li/Aherne/Ghosh combination as discussed above in relation to claim 10.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO-892.
US 2022/0189636 discloses systems, methods, and computer readable media that can diagnose a health condition based on patient time series data. For example, a method for diagnosing a health condition based on patient time series data includes identifying a training set of health records comprising a first set of patient time series data, training a neural network using the training set of health records, and executing the trained neural network model to diagnose a health condition based on a second set of patient time series data. In further examples, the first set of patient time series data and the second set of patient time series data can each comprise electrocardiogram data and the health condition can comprise pulmonary hypertension.
NPL "Early prediction of preeclampsia via machine learning" discloses use of statistical learning methods to analyze all available clinical and laboratory data that were obtained during routine prenatal visits in early pregnancy and to use them to develop a prediction model for preeclampsia. Two statistical learning algorithms were used to build a predictive model: (1) elastic net and (2) gradient boosting algorithm. Models for all preeclampsia and early-onset preeclampsia (<34 weeks gestation) were fitted with the use of patient data that were available at <16 weeks gestational age. The 67 variables that were considered in the models included maternal characteristics, medical history, routine prenatal laboratory results, and medication intake. Using the elastic net algorithm, a prediction model was developed that contained a subset of the most informative features from all variables. CONCLUSION: Statistical learning methods in a retrospective cohort study automatically identified a set of significant features for prediction and yielded high prediction performance for preeclampsia risk from routine early pregnancy information.
NPL "Early Identification of Maternal Cardiovascular Risk Through Sourcing and Preparing Electronic Health Record Data: Machine Learning Study" demonstrates that patient records extracted from the electronic health records (EHRs) of a large tertiary health care system can be made actionable for the goal of effectively using ML to identify maternal cardiovascular risk before evidence of diagnosis or intervention within the patient’s record. Maternal patient records were extracted from the EHRs of a large tertiary health care system and made into patient-specific, complete data sets through a systematic method. Data acquisition included the concatenation, anonymization, and normalization of health data across multiple EHRs in preparation for their use by a proprietary risk stratification algorithm designed to establish patient-specific baselines to identify and establish cardiovascular risk based on deviations from the patient’s baselines to inform early interventions. Conclusions: Upon acquiring data, including their concatenation, anonymization, and normalization across multiple EHRs, the use of an ML-based tool can provide early identification of cardiovascular risk in pregnant patients.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONATHON A. SZUMNY whose telephone number is (303) 297-4376. The examiner can normally be reached Monday-Friday 7-5.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jason Dunham, can be reached at 571-272-8109. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JONATHON A. SZUMNY/ Primary Examiner, Art Unit 3686
Prosecution Insights