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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 07/16/2025 has been entered.
Claims Pending
Applicant’s cancellation of claims 8 and 18, in the response filed 07/16/2025 is acknowledged.
Claims 1-7, 9-17, and 19-20 are the current claims hereby under examination.
Claim Rejections - 35 USC § 112
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.
Claims 1-7, 9-17, and 19-20 are 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.
Claims 1 and 11 recite the limitations “predict, using a prediction machine-learning model, a physiological indicator as a function of the time series input and the plurality of features” (Claim 1) and “predicting, using the at least a processor, a physiological indicator as a function of the time series input and the plurality of features, wherein predicting the physiological indicator utilizing a prediction machine-learning model comprising an active learning algorithm” (Claim 11), where the applicant’s specification lacks sufficient detail as to the structure of the “prediction machine-learning model” that accomplishes the corresponding functions of predicting a physiological indicator. The specification does state “A "machine-learning model," as used in this disclosure, is a data structure representing and/or instantiating a mathematical and/or algorithmic representation of a relationship between inputs and outputs, as generated using any machine-learning process…” “…nodes in adjacent layers of the neural network to produce the desired values at the output nodes.” (Par. 54 of applicant’s spec), “The machine-learning model may be performed using, without limitation, linear machine-learning models such as without limitation logistic regression....” (Par. 23 of applicant’s spec.), and “training a supervised machine-learning process may include, without limitation, iteratively updating coefficients, biases, weights based on an error…” (Par. 56 of applicant’s spec.). However, simply reciting an example of a type of algorithm, use of mathematical relationships, and a general structure of the algorithm does not provide sufficient detail in regards to the actual functionality and internal structure for the claimed “prediction machine learning model” or how the physiological indicator is predicted. For example, the applicant has not provided sufficient detail as to the actual weights utilized within the model itself. As such, the claim is rejected.
Claims 1 and 11 recite the limitation “calibrating, using the at least a processor, an uncertainty estimate associated with the prediction machine-learning model” and “determining, using the prediction machine-learning model, the physiological indicator and the calibrated uncertainty estimate as a function of the time series input and the plurality of features”, which lacks sufficient detail within the specification in regards to the structure of the “prediction machine-learning model” itself. The specification does indicate “As used in the current disclosure, an “uncertainty machine-learning model” is a machine-learning model that is configured to generate uncertainty metric 140…” “…The machine-learning model may be performed using, without limitation, linear machine-learning models such as without limitation logistic regression and/or naive Bayes machine-learning models, nearest neighbor machine-learning models such as k-nearest neighbors machine-learning models, support vector machines, least squares support vector machines, fisher's linear discriminant, quadratic machine-learning models, decision trees, boosted trees, random forest machine-learning model, and the like” (Par. 41 of applicant’s spec.), however, simply providing example types of algorithms and machine learning models does not amount to sufficient structure as the applicant does not indicate the exact weights, biases, or layers used for the model itself. Additionally, the applicant states “some embodiments, shown in FIG. 7, the model 703 can be updated or fine tuned when an unknown, new, unlabeled data set 705 is added (760). The trained model 03 is run on the new data set 705 to calculate the estimated continuous value and uncertainty for each sample.” (Par. 83 of applicant’s spec.), “Calibration may refer to the process of fine-tuning or adjusting the model's predictions to align more closely with the actual probabilities…” “… may be used to adjust or scale the data within each bin. The scaling factor can be unique to each bin and is typically determined based on some specific criteria or algorithm” (Par. 37 of applicant’s spec.), the generation of an uncertainty estimate (Par. 85-86 of applicant’s spec), “In some embodiments, the above optimization problems can be solved using a deep neural network and back-propagation algorithm.” (Par. 93 of applicant’s spec.), “The systems and methods disclosed herein can also include post-training hyperfine uncertainty calibration. In some embodiments, once the deep neural network…” (Par. 94 of applicant’s spec.). However, simply reciting an example of a type of algorithm, use of mathematical relationships, and a general structure of the algorithm does not provide sufficient detail in regards to the actual functionality and structure for the claimed “prediction machine learning model” or how the indicator and estimate are determined. For example, the applicant has not provided sufficient detail as to the actual weights or biases used for the model itself. As such, the claim is rejected.
Claims 2-7 and 9-10 are dependent on claim 1, and as such are also rejected.
Claims 12-17 and 19-20 are dependent on claim 11, and as such are also rejected.
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 1-7, 9-17, and 19-20 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.
Claims 1 and 11 recite “calibrating, using the at least a processor, an uncertainty estimate associated with the prediction machine-learning model” (Claims 1 and 11), “determining, using the prediction machine-learning model, the physiological indicator and the calibrated uncertainty estimate as a function of the time series input and the plurality of features” (Claims 1 and 11), “predict, using a prediction machine-learning model, a physiological indicator as a function of the time series input and the plurality of features” (Claim 1), and “predicting, using the at least a processor, a physiological indicator as a function of the time series input and the plurality of features, wherein predicting the physiological indicator utilizing a prediction machine-learning model comprising an active learning algorithm” (Claim 11), which fails to effectively define the metes and bounds of the claim as it is unclear as to the structure of the “prediction machine-learning model” that performs the indicated functions. The applicant does state “A "machine-learning model," as used in this disclosure, is a data structure representing and/or instantiating a mathematical and/or algorithmic representation of a relationship between inputs and outputs, as generated using any machine-learning process…” “…nodes in adjacent layers of the neural network to produce the desired values at the output nodes.” (Par. 54 of applicant’s spec), “The machine-learning model may be performed using, without limitation, linear machine-learning models such as without limitation logistic regression....” (Par. 23 of applicant’s spec.), “…The machine-learning model may be performed using, without limitation, linear machine-learning models such as without limitation logistic regression and/or naive Bayes machine-learning models, nearest neighbor machine-learning models such as k-nearest neighbors machine-learning models, support vector machines, least squares support vector machines, fisher's linear discriminant, quadratic machine-learning models, decision trees, boosted trees, random forest machine-learning model, and the like” (Par. 41 of applicant’s spec.), and “training a supervised machine-learning process may include, without limitation, iteratively updating coefficients, biases, weights based on an error…” (Par. 56 of applicant’s spec.), where it is unclear as to the actual structure of the model itself. For example, it is unclear as to the exact weights and biases used for the model. As such, the claim is indefinite as the applicant has failed to effectively define the metes and bounds of the claim. For examination purposes, the “prediction machine-learning model” will be interpreted as a generic algorithm.
Claims 2-7 and 9-10 are dependent on claim 1, and as such are also rejected.
Claims 12-17 and 19-20 are dependent on claim 11, and as such are also rejected.
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 1-7, 9-17, and 19-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed towards a judicial exception without significantly more. These claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception or that are sufficient to amount to significantly more than the judicial exception.
Step 1 of the subject matter eligibility test
Claims 1 and 11 are directed to an apparatus and method respectively, which describe one of the four statutory categories of patentable subject matter.
Step 2A of the subject matter eligibility test
Prong 1: Claims 1 and 11 recites the abstract idea of a mental process as follows: “detect an electrocardiogram signal” (Claim 1), “detecting…” “…an electrocardiogram signal” (Claim 11)”, “receive…” “… a time series input comprising the electrocardiogram signal”(Claim 1), “receiving …” “…a time series input comprising the electrocardiogram signal” (Claim 11), “extract…” “…a plurality of features from the time series input, wherein the plurality of features characterize the electrocardiogram signal”, “predict…” “… a physiological indicator as a function of the time series input and the plurality of features” (Claim 1), “predicting…” “…a physiological indicator as a function of the time series input and the plurality of features” (Claim 11), “utilizing a prediction machine learning model comprising an active learning algorithm” (Claim 11), “receiving…” “… prediction training data comprising a plurality of time series inputs correlated to examples of physiological indicators as outputs, wherein the examples of physiological indicators comprise continuous value labels” (Claim 1), “receiving prediction training data, wherein the prediction training data comprises a plurality of time series data and electrocardiogram signal inputs correlated to a plurality of examples of physiological indicators as outputs, wherein the examples of physiological indicators comprise continuous value labels” (Claim 11),“fitting…” “…the prediction training data with a kernel density estimate to model a distribution of the continuous value labels” (Claim 1), “fitting the plurality of prediction training data with a kernel density estimate” (Claim 11), “calibrating…” “… an uncertainty estimate associated with the prediction machine-learning model”, “assigning…” “… each time series input from a validation dataset to a bin based on an estimated continuous value output”, “calculating…” “… a bin-wise scaling factor for each bin based on differences between estimated values and actual values”, “adjusting…” “…an uncertainty output of the prediction machine-learning model as a function of a global scaling factor and the bin-wise scaling factor for the corresponding bin”, “generating…” “…a calibrated uncertainty estimate”, and “determining…” “… the physiological indicator and the calibrated uncertainty estimate as a function of the time series input and the plurality of features”.
The detecting an electrocardiogram signal, receiving a time series input comprising the electrocardiogram signal, extracting a plurality of features from the time series input, wherein the plurality of features characterize the electrocardiogram signal, predict a physiological indicator as a function of the time series input and the plurality of features, utilizing a prediction machine learning model comprising an active learning algorithm, receiving prediction training data comprising a plurality of time series inputs correlated to examples of physiological indicators as outputs, wherein the examples of physiological indicators comprise continuous value labels, receiving prediction training data wherein the prediction training data comprises a plurality of time series data and electrocardiogram signal inputs correlated to a plurality of examples of physiological indicators as outputs, wherein the examples of physiological indicators comprise continuous value labels, fitting the prediction training data with a kernel density estimate to model a distribution of the continuous value labels, fitting the plurality of prediction training data with a kernel density estimate, calibrating an uncertainty estimate associated with the prediction machine-learning model, assigning each time series input from a validation dataset to a bin based on an estimated continuous value output, calculating a bin-wise scaling factor for each bin based on differences between estimated values and actual values, adjusting an uncertainty output of the prediction machine-learning model as a function of a global scaling factor and the bin-wise scaling factor for the corresponding bin, generating a calibrated uncertainty estimate, and determining the physiological indicator and the calibrated uncertainty estimate as a function of the time series input and the plurality of features can practically performed by the human mind, with the aid of a pen and paper, but for performance on a generic processor, in a computer environment, or merely using the computer as a tool to perform the steps.
A person of ordinary skill in the art could reasonably mentally detect an ECG signal based on having a piece of paper with ECG data. A person of ordinary skill in the art could reasonably receive a piece of paper with time series data, time series data comprising an electrocardiogram signal, prediction training data, and time series data correlated to physiological indicators. A person of ordinary skill in the art could reasonably extract a plurality of features from a time series input that relate to an electrocardiogram signal based on having a piece of paper with time series data comprising an electrocardiogram signal. A person of ordinary skill in the art could reasonably make a prediction of a physiological indicator based on having a piece of paper with time series data on it. A person of ordinary skill in the art could reasonably utilize a prediction machine learning model with an active machine learning algorithm using a generic computer. A person of ordinary skill in the art could reasonable fit data with a kernel density estimate based on having training data with a generic computer. A person of ordinary skill in the art could reasonably calibrate an uncertainty estimate associated with a prediction machine learning model with a generic computer. A person of ordinary skill in the art could reasonably assign time series inputs to a bin based on estimated output based on having a piece of paper with time series data and validated data with a generic computer. A person of ordinary skill in the art could reasonably calculate a bin-wise scaling factor based on having a piece of paper with estimated and actual values using a generic computer. A person of ordinary skill in the art could reasonably adjust an output of a machine learning model by adjusting an input with a generic computer. A person of ordinary skill in the art could reasonably generate a calibrated uncertainty estimate based on having a validation dataset with a generic computer. A person of ordinary skill in the art could reasonably mentally determine a physiological indicator and uncertainty estimate based on having time series data and validated data. A person of ordinary skill in the art could reasonably generate an uncertainty metric based on being handed a piece of paper with a physiological indicator using a machine learning model on a generic computer. There is currently nothing to suggest an undue level of complexity in the receiving or detecting steps. Therefore, a person would be able to practically be able to perform the utilizing, extracting, predicting, fitting, calibrating, assigning, calculating, adjusting, generating, and determining steps mentally or with the aid of pen and paper.
Prong Two: Claims 1 and 11 do not recite additional elements that integrate the mental process into a practical application. Therefore, the claims are “directed to” the mental process. The additional elements merely:
Recite the words “apply it” or an equivalent with the judicial exception, or include instructions to implement the abstract idea on a computer, or merely use the computer as a tool to perform the abstract idea (e.g., a processor and memory, electrocardiogram sensor).
For claims 1 and 11. The additional elements merely serve to gather data to be used by the abstract idea. The processor and memory are merely used as a pre-solution step of necessary data gathering to be used by the abstract idea. There is no practical application because the abstract idea is not applied, relied on, or used in a meaningful way. The processing that is performed remains in the abstract realm, i.e. the gathered data is not used for a treatment or meaningful purpose. Additionally, there is no overall improvement to existing technology present. The mental process merely functions on generic computer elements that do not change the functionality of the mobile device itself. Therefore, the additional elements, alone or in combination, do not integrate the abstract idea into a practical application.
Step 2B of the subject matter eligibility test for Claims 1 and 11
Per the Berkheimer requirement, the additional elements are well-understood, routine, and conventional. For example,
a memory and processor as disclosed by Itu (US Pub. No. 20210064936) hereinafter Itu (“Systems, apparatuses, and methods described herein may be implemented using digital circuitry, or using one or more computers using well-known computer processors, memory units, storage devices, computer software, and other components. Typically, a computer includes a processor for executing instructions and one or more memories for storing instructions and data.”) (Par. 67) and Mihalef (US Pub. No. 20200323454) hereinafter Mihalef (“well-known computer processors, memory units, storage devices, computer software, and other components. Typically, a computer includes a processor for executing instructions and one or more memories for storing instructions and data”) (Par. 37),
electrocardiogram sensors as disclosed by Pijl (US Pub. No. 20160113591) hereinafter Pijl (“heart rate sensors are known in the art and known sensors include an electrocardiogram (ECG) sensor”) (Par. 45) and Doron (US Pub. No. 20080077440) hereinafter Doron “electrical sensors such as ECG and EEG, pulse oximeters, bio-impedance sensor, body fluid assay devices, DNA chips, glucose meters, optical and infrared sensors, acoustic and audio sensors, chemical sensors, and many other medical sensors known in the art” (Par. 31)
are all well-understood, routine, and conventional.
Claims 2-10 and 12-20 do not include additional elements, alone or in combination that are sufficient to amount to significantly more than the judicial exception (i.e., an inventive concept) as all of the elements are directed to the further describing of the abstract idea, pre-solution activities, and computer implementation.
The dependent claims merely further define the abstract idea and are, therefore, directed to an abstract idea for similar reasons: they merely further describe the abstract idea:
receiving a plurality electrocardiogram signals (Claims 2 and 12)
retraining the prediction machine learning model (Claims 3 and 13)(Examiners note: a person of ordinary skill in the art could reasonably train a machine learning model more than one time using a generic computer),
determine the uncertainty estimate for each value of the set of novel time-series inputs using the prediction machine-learning model (Claims 3 and 13),
choose a subset of novel time-series inputs (Claims 3 and 13)(Examiners note: a person of ordinary skill in the art could reasonably mentally choose an input),
labeling the subset of novel time-series inputs (Claims 4 and 14),
retraining the prediction machine learning model (Claims 4 and 14),
labeling the subset of novel time-series inputs using active learning (Claims 5 and 15),
a measurement of a left ventricular ejection fraction (LVEF) (Claims 6 and 16),
a measurement of a level of potassium in blood of a user (Claims 7 and 17).
generate diagnostic data as a function of an acceptance of a physiological parameter. (Claims 9 and 19),
selecting a bandwidth of the kernel density estimate (Claims 10 and 20).
Further describe the pre-solution activity (or structure used for such activity):
Electrocardiogram sensors (Claims 2 and 12),
Per the Berkheimer requirement, the additional elements are well-understood, routine, and conventional. For example,
electrocardiogram sensors as disclosed by Pijl and Doron above
are all well-understood, routine, and conventional.
Taken alone or in combination, the additional elements do not integrate the judicial exception into a practical application at least because the abstract idea is not applied, relied on, or used in a meaningful way. The additional elements do not add anything significantly more than the abstract idea. The collective functions of the additional elements merely provide computer/electronic implementation and processing, data gathering, and no additional elements beyond those of the abstract idea. There is no indication that the combination of elements improves the functioning of a computational device, output device, processor, or improves technology other than the technical field of the claimed invention, etc. Therefore, the claims are rejected as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103 - Withdrawn
Applicant’s amendments, filed 07/16/2025, have been fully considered, and the previous rejection withdrawn.
The claims are generally directed towards an apparatus for predicting a physiological indicator that comprises an electrocardiogram sensor and processor connected to a memory. The physiological indicator is predicted through the use and iterative training of machine learning algorithms stored in the memory.
The closest prior art of record includes Clifford (US Pub. No. 20190313960) hereinafter Clifford, Qiu (US Pat. No. 11836578) hereinafter Qiu, Büttner (US Pub. No. 20220067588) hereinafter Florian, Itu (US Pub. No. 20210064936) hereinafter Itu, Hong (US Pub. No. 20200089653) hereinafter Hong, Sedai (US Pub. No. 20210216825) hereinafter Sedai, Galloway (US Pub. No. 20180233227) hereinafter Galloway, and Bhattacharya (US Pub. No. 20210342641) hereinafter Bhattacharya
Clifford discloses an apparatus for predicting a physiological indicator (Abstract), wherein the apparatus comprises:
a sensor configured to detect an electrocardiogram signal (Par. 63, “ECG, magnetocardiography, photoplethysmography, and/or devices comprising one or more sensors of cardiac function such as accelerometers, pressure sensors, oxymeters, flow sensors, and impendence sensors.”) (Par. 120, “Individual 1010 wears or is in communication with heart activity monitor 1500 such that measured heart activity receiving unit 1515 receives a heart signal from individual 1010.”) (Par. 124, “the heart activity monitor 1500 may include an analog to digital converter, an electrode, a transducer, a microprocessor, and/or a system on a chip (SoC). The transducer may receive a heart signal from an individual 1010.”);
at least a processor (Par. 128 (Processor – 910 of computing device 900)); and
a memory communicatively connected to the at least a processor (Par. 128, 129 135 (memory communicatively connected to a processor)), wherein the memory containing instructions configuring the at least a processor to:
receive, using the at least a processor (Par. 128,135 (processing unit 1100 executed by computing device 900, which has processor 910)), a time series input comprising the electrocardiogram signal (Par. 100, “The measured heart activity processing unit (1100) receives information from measured heart activity 1535 from an individual”) (Par. 135 (processing unit 1100 executed by computing device 900, which has processor 910)) (Par. 63, 65, 66 (heart activity data)) (Par. 120, “Individual 1010 wears or is in communication with heart activity monitor 1500 such that measured heart activity receiving unit 1515 receives a heart signal from individual 1010.”)(Par. 124, “the heart activity monitor 1500 may include an analog to digital converter, an electrode, a transducer, a microprocessor, and/or a system on a chip (SoC). The transducer may receive a heart signal from an individual 1010.”);
extract, using the at least a processor (Par. 128,135 (processing unit 1100 executed by computing device 900, which has processor 910)), a plurality of features from the time series input (Par. 102, “Feature determining unit (1120) determines or extracts features from the information from the measured heart activity 1535 from the individual (1010). The features may include or be based on at least one quiescent segment…” “…The feature determining unit (1120) may determine a feature vector including one or more features. The feature determining unit (1120) may provide features or feature vectors to the memory device/bus (1125).”) (Par. 63, 65, 66 (heart activity data)), wherein the plurality of features characterize the electrocardiogram signal (Par. 102, “Feature determining unit (1120) determines or extracts features from the information from the measured heart activity 1535 from the individual (1010). The features may include or be based on at least one quiescent segment…” “…The feature determining unit (1120) may determine a feature vector including one or more features. The feature determining unit (1120) may provide features or feature vectors to the memory device/bus (1125).”) (Par. 103, “The features may be determined using a computing device. A feature vector may comprise a data structure with at least one value determined by the computing device based the information from measured heart activity 1535 from an individual 1010. Each feature vector may be associated with a label.”);
predict, using a prediction machine-learning model (Par. 106, “A model (e.g. machine learning model) may be a kernel or learned classifier, and determining…” “…solution may lead to the technical effect of reporting a PTSD status based on features determined from information from measured heart activity 1535 from an individual 1010.”)(Fig. 19 (classifier)), a physiological indicator as a function of the time series input and the plurality of features (Par. 100, (prediction of PTSD)) (Par. 65-66), wherein predicting the physiological indicator comprises:
receiving, using the at least a processor (Par. 128, 135 (processor implementation)), prediction training data (Fig. 19, step 1930 (the trained classifier)) comprising a plurality of time series inputs correlated to examples of physiological indicators as outputs (Fig. 19, step 1930 (trained classifier)) (Par. 209, “Fourth, features are extracted (750) from the RR interval data…” “…trained (770) on the features and labels. The classifier may be trained using a computing device. Optionally, seventh, the classifier's performance is assessed (780) on test sets.”) (Par. 127, “wherein the classifier is trained using quiescent segments of RR interval information, wherein measured heart activity is received from a plurality of test subjects”) (Par. 100, “The measured heart activity processing unit (1100) receives information from measured heart activity 1535 from an individual”), wherein the examples of physiological indicators comprise continuous value labels (Par. 65-66)(Fig. 19, step 1930) (Par. 209, “Fourth, features are extracted (750) from the RR interval data…” “…trained (770) on the features and labels. The classifier may be trained using a computing device. Optionally, seventh, the classifier's performance is assessed (780) on test sets.”);
determining the physiological indicator as a function of the time series input using the trained prediction machine-learning model (Fig. 19, step 1910, 1930-1940).
Clifford further teaches the use of a kernel density estimate of features (Par. 167 (estimated kernel density)).
Qiu teaches fitting data with a kernel density estimate (Col. 6, lines 43-67).
Florian teaches calibrating, using the at least a processor (Par. 162 (computer implementation)), an uncertainty estimate associated with the prediction machine-learning model (Fig. 3, S1,S2,S3)(Par. 159) by:
assigning, using the at least a processor (Par. 162 (computer implementation)), each time series input from a validation dataset to a bin based on an estimated continuous value output (Fig. 3, S2) (Par. 144, step T9);
calculating, using the at least a processor (Par. 162 (computer implementation)), a scaling factor (Fig. 3, S2, T11a, T12) (Par. 130, T11a, T12);
generating, using the at least a processor (Par. 162 (computer implementation)), a calibrated uncertainty estimate (S3, U6-U7)(Par. 132).
These prior art references do not reasonably disclose, teach, or suggest calculating, using the at least a processor, a bin-wise scaling factor for each bin based on differences between estimated values and actual values; adjusting, using the at least a processor, an uncertainty output of the prediction machine-learning model as a function of a global scaling factor and the bin-wise scaling factor for the corresponding bin; determining, using the prediction machine-learning model, the physiological indicator and the calibrated uncertainty estimate as a function of the time series input and the plurality of features.
Response to Arguments
Applicant's arguments, filed 07/16/2025, regarding the previous 112(a) rejection have been fully considered but are deemed as not persuasive.
The applicant’s arguments, that the amendments to the claims have overcome the 112 rejection, have been fully considered and deemed as not persuasive. As the limitations were not previously addressed, the limitations have been addressed in the 112 rejection as indicated above.
Applicant's arguments, filed 07/16/2025, regarding the previous 101 rejection have been fully considered, but are deemed as not persuasive.
The applicant’s arguments, that the amendments to the claims have overcome the 101 rejection, have been fully considered and deemed as not persuasive. As the limitations were not previously addressed, the limitations have been addressed in the 101 rejection as indicated above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ARI SINGH KANE PADDA whose telephone number is (571)272-7228. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 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, Jason Sims can be reached at (571) 272-7540. 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.
/ARI SINGH KANE PADDA/ Examiner, Art Unit 3791
/JASON M SIMS/ Supervisory Patent Examiner, Art Unit 3791