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 .
Examiner Note
This 2nd Non-Final Rejection supersedes the previous Non-Final Rejection dated August 10, 2026, which did not include SPE signature for re-opening prosecution after appeal. SPE signature is provided below.
Prosecution Re-Opened
In view of the Appeal Brief filed on September 25, 2025, PROSECUTION IS HEREBY REOPENED. New ground(s) of rejection are set forth in the Non-Final Rejection dated August 10, 2026.
To avoid abandonment of the application, appellant must exercise one of the following two options:
(1) file a reply under 37 CFR 1.111 (if this Office action is non-final) or a reply under 37 CFR 1.113 (if this Office action is final); or,
(2) initiate a new appeal by filing a notice of appeal under 37 CFR 41.31 followed by an appeal brief under 37 CFR 41.37. The previously paid notice of appeal fee and appeal brief fee can be applied to the new appeal. If, however, the appeal fees set forth in 37 CFR 41.20 have been increased since they were previously paid, then appellant must pay the difference between the increased fees and the amount previously paid.
A Supervisory Patent Examiner (SPE) has approved of reopening prosecution by signing below:
/TAMARA T KYLE/ Supervisory Patent Examiner, Art Unit 2144
Allowable Subject Matter
Claims 1-9, 11-19, 21, and 22 are pending.
Claims 2-4 and 12-14 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, 5, 8, 9, 11, 15, 18, 19, 21, and 22 are rejected under 35 U.S.C. 103 as being unpatentable over Shakur et al. (US Pub. 20190059763) in view of Chen et al. (US Pat. 10729351).
Referring to claim 1, Shakur discloses A computer-implemented method for classifying individual heartbeats using patient electrocardiogram (ECG) data [pars. 33, 104, and 110-114; each heartbeat in an ECG signal is identified as being normal or anomalous)], which comprises unstructured waveform data and structured time interval data [fig. 6; the ECG signal is processed into waveform data (e.g., for P-wave detection) and interval data (e.g., for R-R detection)], the method comprising:
providing the unstructured waveform data to a first neural network in a first path of a machine learning architecture [fig. 6; pars. 24-33, 40-42, 62, 63, and 106-108; the waveform data is segmented into individual heartbeats, which are fed into an autoencoder (i.e., a first neural network) for feature extraction, and the extracted features are provided to a neural network classifier (i.e., a second neural network)];
generating a first set of output values by using the first neural network to analyze the unstructured waveform data [fig. 6; pars. 24-33, 40-42, 44-52, 62, 63, and 106-108; the neural network classifier analyzes the waveform data / extracted features and outputs a classification score used to determine the presence or absence of a P-wave, atrial fibrillation (AF), inverted T-waves, deep Q-waves, and or deep S-waves];
providing the structured time interval data to a second [module] n a second path of the machine learning architecture [fig. 6; pars. 34-36, 60, and 105; the interval data is provided to an irregular rhythm detector];
generating a second set of output values by using the second [module] to analyze the structured time interval data [fig. 6; pars. 34-36, 60, and 105; the irregular rhythm detector detects irregular rhythms and flags them (e.g., outputs an irregular R-R interval flag)]; and
generating a classification for each of the individual heartbeats based on the first set of output values and the second set of output values [pars. 31-33 and 109-111; output from the neural network classifier is combined with the output from the irregular rhythm detector for diagnosis of cardiac arrhythmia (e.g., AF) at beat-level resolution], …wherein the classification is selected from one of the following: a normal beat or a ventricular beat [pars. 22, 33, 41, 109-113; the individual heartbeats are identified as being normal or anomalous (e.g., non-AF or AF)].
Shakur does not appear to explicitly disclose a second neural network; and wherein the first neural network comprises a different type of neural network than the second neural network.
However, Chen discloses a second neural network; and wherein the first neural network comprises a different type of neural network than the second neural network [fig. 18, elements 1830-1840; col. 13, lines 11-18; col. 16, lines 46-67; col. 21, lines 30-39; an ECG signal comprising waveform data and timing information is processed using AI algorithms comprising two different types of neural networks (e.g., deep learning algorithm 1832 and neural network algorithm 1831)].
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 heartbeat identification taught by Shakur so that the waveform data and the interval data are processed using two different types of neural networks as taught by Chen, with a reasonable expectation of success. The motivation for doing so would have been to quickly and accurately diagnose heart problems in an intelligent manner [Chen, col. 7, lines 20-25 and col. 21, lines 45-59].
Referring to claim 5, Chen discloses The computer-implemented method of claim 1, wherein the first neural network comprises a convolutional neural network [fig. 18, elements 1830-1840; col. 13, lines 11-18; col. 16, lines 46-67; col. 21, lines 30-39; the two different types of neural networks may include a CNN].
Referring to claim 8, Shakur discloses The computer implemented method of claim 1, wherein the first neural network does not process the structured time interval data, wherein the second neural network does not process the unstructured waveform data [fig. 6; pars. 24-36, 40-42, 44-52, 60-63, and 105-108; note the separate waveform processing by the classifier neural network and the interval processing by the irregular rhythm detector].
Referring to claim 9, Shakur discloses The computer-implemented method of claim 1, wherein the structured time interval data comprises R-R interval data [fig. 6; pars. 34-36, 60, and 105; note the R-R interval detection].
Referring to claim 11, see at least the rejection for claim 1. Shakur further discloses A system for classifying individual heartbeats using patient electrocardiogram (ECG) data, which comprises unstructured waveform data and structured time interval data, the system comprising: one or more servers, each including one or more processors and computer- readable memory, wherein instructions are stored on the memory and cause the one or more servers to perform an operation comprising the claimed steps [fig. 3; pars. 94 and 95; server 316 and/or ECG device 305].
Referring to claim 15, see the rejection for claim 5.
Referring to claim 18, see the rejection for claim 8.
Referring to claim 19, see the rejection for claim 9.
Referring to claim 21, Chen discloses The system of claim 11, wherein the classification is further selected from a supra-ventricular beat [col. 23, lines 34-39; the AI algorithms are used to detect heart failure (HF), atrium fibrillation (AF), atrial conductor block, premature atrial contraction (PAC), premature ventricular condition (PVC), atrial tachycardia, and ventricular tachycardia)].
Referring to claim 22, see the rejection for claim 21.
Claims 6, 7, 16, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Shakur and Chen in view of Aliamiri et al. (US Pub. 20190133468).
Referring to claim 6, Shakur and Chen do not appear to explicitly disclose The computer-implemented method of claim 5, wherein the second neural network comprises a fully-connected neural network.
However, Aliamiri discloses The computer-implemented method of claim 5, wherein the second neural network comprises a fully-connected neural network [par. 58; to effectively extract both local structures of waveforms and their temporal progression as features for predictive atrial fibrillation (AFib), a hybrid model of CNN and RNN (which uses fully connected layers) is used].
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 heartbeat identification taught by the combination of Shakur and Chen so that the two different types of neural networks include a CNN and an RNN as taught by Aliamiri, with a reasonable expectation of success. The motivation for doing so would have been to effectively extract both local structures of waveforms and their temporal progression as features [Aliamiri, par. 58].
Referring to claim 7, Aliamiri discloses The computer-implemented method of claim 6, wherein the second path does not comprise a convolution layer [par. 58; note that an RNN does not use convolution].
Referring to claim 16, see the rejection for claim 6.
Referring to claim 17, see the rejection for claim 7.
Conclusion
The following prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Braun et al. (US Pub. 20180336466) discloses concatenating the outputs of a CNN and an FCNN.
Li et al. (US Pub. 20200312459) discloses combining multiple neural networks with a fully connected layer at the end.
Vrudhula et al. (US Pub. 20190150794) discloses concatenating the outputs of parallel neural networks.
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