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 .
Response to Amendment and Arguments
Applicant’s amendment filed on July 2, 2026 has been entered and made of record. Claims 1-19 are pending and are being examined in this application.
In light of Applicant’s amendments to the claims, the 112(b) rejection is withdrawn.
Applicant’s arguments with respect to the 103 rejections have been considered, but are moot in view of the new ground(s) of rejection provided below.
Allowable Subject Matter
Claims 8-10, 18, and 19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-7, 11-17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Chang et al. (US Pub. 20210232914) in view of Crespin et al. (US Pub. 20210386354) and further in view of Nemani et al. (US Pub. 20240221936).
Referring to claim 1, Chang discloses A prediction model training method, being adapted for use in an electronic apparatus [par. 18; a heart rhythm classification model is implemented by a computer device], wherein the prediction model training method comprises the following steps:
training a first model according to a plurality of first electrocardiograms [abstract; par. 16; a neural network model is trained using ECG datasets], wherein the first model comprises a feature extraction layer… [abstract; pars. 16 and 21; the neural network model is trained to extract features for classification];
extracting, by the feature extraction layer of the first model, first feature information corresponding to a plurality of second electrocardiograms according to the plurality of second electrocardiograms, wherein each of the plurality of second electrocardiograms is corresponding to at least one of the first feature information [abstract; pars. 16 and 21; the neural network model extracts the features to classify a heart rhythm measured from a person (e.g., 12-lead ECG data)].
Chang does not appear to explicitly disclose that the first model comprises a fifth submodel; the fifth submodel is configured to generate a possibility; and training a second model according to the first feature information, gender information corresponding to the plurality of second electrocardiograms, and age information corresponding to the plurality of second electrocardiograms.
However, Crespin discloses that the first model comprises a fifth submodel [pars. 114-120; note the chain of machine learning algorithms; each of the machine learning algorithms of the chain is trained as a classifier chain, so that the output of each algorithm is part of the inputs of all the subsequent algorithms]; and the fifth submodel is configured to generate a possibility [pars. 114-120; the machine learning algorithms (e.g., XGBoost algorithms) output a score vector comprising a ‘1’ or ‘0’ for each type of abnormal heart rhythm; note that, in XGBoost, the ‘1’ or ‘0’ is a transformed probability score].
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 classification taught by Chang so that the neural network model includes a chain of machine learning algorithms forming a classifier chain as taught by Crespin, with a reasonable expectation of success. The motivation for doing so would have been to reduce the number of false positives in an efficient manner [Crespin, par. 17].
Chang and Crespin do not appear to explicitly training a second model according to the first feature information, gender information corresponding to the plurality of second electrocardiograms, and age information corresponding to the plurality of second electrocardiograms.
However, Nemani discloses training a second model according to the first feature information, gender information corresponding to the plurality of second electrocardiograms, and age information corresponding to the plurality of second electrocardiograms [pars. 31, 33, 36, 71, 72, 119, and 120; an existing neural network model processes an ECG waveform (i.e., received ECG features) to predict an abnormal heart rhythm; the neural network model may be enriched with additional multimodal data features (e.g., patient age and sex) by enabling the addition of a multimodal model; the multimodal model is trained using the received ECG features and additional EHR features].
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 classification taught by the combination of Chang and Crespin so that the heart rhythm classification model includes a multimodal model for processing EHR features in addition to ECG features as taught by Nemani, with a reasonable expectation of success. The motivation for doing so would have been to realize improvements in predictive power [Nemani, par. 31].
Referring to claim 2, Crespin and Nemani disclose The prediction model training method of claim 1, further comprising: receiving a patient electrocardiogram, patient gender information, and patient age information corresponding to a patient; extracting patient feature information corresponding to the patient electrocardiogram based on the feature extraction layer; and inputting the patient feature information, the patient gender information, and the patient age information into the second model to generate a prediction result [Nemani: pars. 31, 33, 36, 71, 72, 119, and 120; the multimodal model is trained on the EHR features (e.g., patient age and sex) to predict the abnormal heart rhythm]; wherein the prediction result is configured to indicate whether the patient corresponding to the patient electrocardiogram has a symptom of left ventricular hypertrophy [Crespin: par. 72; abnormal heart rhythms include left ventricular hypertrophy].
Referring to claim 3, Chang and Crespin disclose The prediction model training method of claim 1, wherein the step of training the first model further comprises: obtaining a plurality of first electrocardiogram segments from each of the plurality of first electrocardiograms, wherein each of the plurality of first electrocardiogram segments corresponds to a time interval in the plurality of first electrocardiograms; and training the first model according to the plurality of first electrocardiogram segments corresponding to the plurality of first electrocardiograms [Chang: abstract; pars. 16 and 21; note the training of the neural network model to extract features for classification / Crespin: pars. 86-89, 97, 98, 103, 106-109, and 113; note the ECG segments and sub-segments; R waves are identified in each segment, and the position of the peaks of the R waves is used for calculating at least one feature of the segment; the feature may be a rhythm feature, where rhythm features are statistics calculated based on time periods between two waves (e.g., time periods between each R peak)].
Referring to claim 4, Chang and Crespin disclose The prediction model training method of claim 3, wherein the step of extracting the first feature information corresponding to the plurality of second electrocardiograms further comprises: obtaining a plurality of second electrocardiogram segments from each of the plurality of second electrocardiograms, wherein each of the plurality of second electrocardiogram segments corresponds to the time interval in the plurality of second electrocardiograms; and extracting the first feature information corresponding to the plurality of second electrocardiograms based on the plurality of second electrocardiogram segments [Chang: abstract; pars. 16 and 21; note the training of the neural network model to extract features for classification / Crespin: 86-89, 97, 98, 103, 106-109, and 113; note the ECG segments, subsegments, and rhythm features; also note each of the machine learning algorithms of the chain corresponding to a type of abnormal heart rhythm (i.e., a subset of the plurality of annotated episodes)].
Referring to claim 5, Crespin discloses The prediction model training method of claim 4, wherein each of the plurality of first electrocardiogram segments comprises the time interval corresponding to a peak, and each of the plurality of second electrocardiogram segments comprises the time interval corresponding to the peak [pars. 86-89, 97, 98, 103, 106-109, and 113; note the ECG segments, subsegments, and rhythm features; also note each of the machine learning algorithms of the chain corresponding to a type of abnormal heart rhythm (i.e., a subset of the plurality of annotated episodes)].
Referring to claim 6, Crespin discloses The prediction model training method of claim 1, wherein the first model comprises a first submodel, a second submodel, a third submodel, a fourth submodel, and the fifth submodel, and the step of training the first model further comprises: training the first model based on a first composition order; wherein the first composition order corresponds to the fourth submodel, the first submodel, the second submodel, the third submodel, the second submodel, the third submodel, the second submodel, the third submodel, the second submodel, and the fifth submodel [pars. 114-120; note the chain of machine learning algorithms; each of the machine learning algorithms of the chain is trained as a classifier chain, so that the output of each algorithm is part of the inputs of all the subsequent algorithms (i.e., the training is performed in a specific order)].
Referring to claim 7, Crespin discloses The prediction model training method of claim 1, wherein the second model comprises the fifth submodel, a sixth submodel, and a seventh submodel, and the step of training the second model further comprises: generating second feature information according to the first feature information and the sixth submodel; generating a gender vector according to the gender information; generating an age vector according to the age information; and training the second model based on the second feature information, the gender vector, the age vector, and a second composition order, wherein the second composition order corresponds to the seventh submodel, the seventh submodel, and the fifth submodel [pars. 114-120; note the chain of machine learning algorithms, the training of which is performed in a specific order)].
Referring to claim 11, see at least the rejection for claim 1. Chang and Nemani further disclose A prediction model training device, comprising: a storage, configured to store a first model and a second model; and a processor, coupled to the storage, wherein the processor is configured to perform the claimed steps [Chang: par. 18; note the computer device implementing the heart rhythm classification model and storing the neural network model / Nemani: figs. 1A and 1B; par. 31; computing device 104 comprises processor 144 and memory 160, and trained models 136, which would include the additional multimodal model].
Referring to claim 12, see the rejection for claim 2.
Referring to claim 13, see the rejection for claim 3.
Referring to claim 14, see the rejection for claim 4.
Referring to claim 15, see the rejection for claim 5.
Referring to claim 16, see the rejection for claim 6.
Referring to claim 17, see the rejection for claim 7.
Referring to claim 20, see at least the rejection for claims 1 and 2. Chang and Nemani further disclose A prediction model training device, comprising: a storage, configured to store a first model and a second model; and a processor, coupled to the storage, wherein the processor is configured to perform the claimed steps [Chang: par. 18; note the computer device implementing the heart rhythm classification model and storing the neural network model / Nemani: figs. 1A and 1B; par. 31; computing device 104 comprises processor 144 and memory 160, and trained models 136, which would include the additional multimodal model].
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.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GRACE PARK whose telephone number is (571)270-7727. The examiner can normally be reached M-F 8AM-5PM.
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, TAMARA KYLE can be reached at (571)272-4241. 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.
/Grace Park/Primary Examiner, Art Unit 2144
Prosecution Insights