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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 07/24/2025 has been entered.
Response to Amendment
In the amendment filed 07/24/2025, the following has occurred: claims 1, 13, and 25 have been amended and claim 5 has been canceled. Now, claims 1-4, 6-13 and 25 are pending.
The previous rejections under 35 U.S.C. 112(b) are withdrawn based on the amendments to the claims. However, new rejections under 112(b) are set forth below.
The previous rejections under 35 U.S.C. 101 are withdrawn based on the amendments to the claims. Paragraphs 0037-0040 describe computational efficiency and accuracy from applying the neural network grow-and-prune process. The claims recite carrying out the grow-and-prune process by growing connections and/or neurons based on gradient information and pruning connections and/or neurons based on magnitude information. This achieves the computational improvements described in the specification and integrates the abstract idea into a practical application.
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 6-7 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 6-7 recite “The machine-learning based system of claim 5…” Claim 5 has been canceled, rendering the scope of these claims indefinite. For examination purposes, claims 6-7 will be treated as being dependent on claim 1.
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.
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.
Claim(s) 1, 4, 6-8, 10-11, 13, and 25 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wu, US Patent Application Publication No. 2023/0207120 in view of Itu, US Patent Application Publication No. 2019/0139641 and further in view of Dai et al., NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm.
As per claim 1, Wu teaches a machine-learning based system for identification and monitoring of a mental health disorder, comprising one or more processors configured to interact with a plurality of wearable medical sensors (WMSs), the one or more processors configured to: receive physiological data captured over time from the WMSs (see paragraph 0006; obtaining sensor data over a period of time of an agent monitoring device; paragraph 0042 describing wearable sensors of the monitoring devices); train at least one neural network based on raw physiological data augmented with additional data drawn from a probability distribution to generate at least one mental health disorder inference model (see paragraph 0007; training data includes sensor data and similar data of a plurality of different agents; paragraph 0044; recurrent neural network is trained as described above on a plurality of other agents similar to the agent being monitored; paragraphs 0056-0057; trained model being the mental health disorder inference model); and output a mental health disorder-based decision, at a patient level, by inputting the physiological data captured over time from the WMSs into the at least one mental health disorder inference model (see paragraph 0059; output of sensor data processed by model may be a mental condition of the agent (being a monitored patient, at a patient level); paragraph 0006; describes the sensor data is monitored over a period of time; paragraph 0058 additionally describes sensor data being continuously transmitted as it is collected over time).
Wu does not explicitly teach the training is based on raw physiological data augmented with synthetic data drawn from a same probability distribution as the raw physiological data.
Itu teaches training a neural network based on raw physiological data augmented with synthetic data drawn from a same probability distribution as the raw physiological data (see paragraph 0023; synthetic data in addition to patient-specific sample data may be used to train the network). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to generate synthetic data from raw data as described in Itu for training the model using the raw data of Wu with the motivation of handling a broad range of pathologies with sample data (see paragraph 0023 of Itu).
Wu and Itu does not explicitly teach the training is subjected to a grow-and-prune paradigm to generate at least one model.
Dai teaches training a neural network using a grow-and-prune paradigm, wherein the grow-and-prune paradigm comprises the at least one neural network growing at least one of connections and neurons based on gradient information and pruning away at least one of connections and neurons based on magnitude information (see pages 1487-1488, paragraph beginning “To address these problems…” describing the growing based on gradient information and pruning based on magnitude information).. It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to apply a grow-and-prune paradigm to train the neural network model of Wu as taught by Dai with the motivation of improving the architecture and processing of the neural network-based modeling of Wu and described in Dai.
As per claim 4, Wu, Itu, and Dai teaches the system of claim 1 as described above. Wu further teaches the one or more processors are further configured to synchronize and normalize the received physiological data from the WMSs (see paragraph 0062; normalizes data computed for each sensor to values on a common scale to compare values of different sensors).
As per claim 6, Wu, Itu, and Dai teaches the system of claim 1 as described above. As noted above, Wu does not explicitly teach the grow-and-prune paradigm. Dai further teaches growing at least one of connections and neurons based on gradient information comprises adding connection or neuron when its gradient magnitude is greater than a predefined percentile of gradient magnitudes based on a growth ratio (see page 1489, Gradient-Based Growth section describing this process). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to apply a grow-and-prune paradigm to train the neural network model of Wu for the reasons given above with respect to claim 1.
As per claim 7, Wu, Itu, and Dai teaches the system of claim 1 as described above. As noted above, Wu does not explicitly teach the grow-and-prune paradigm. Dai further teaches pruning away at least one of connections and neurons based on magnitude information comprises removing a connection or neuron when its magnitude is less than a predefined percentile of magnitudes based on a pruning ratio (see page 1489, Gradient-Based Growth section describing this process). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to apply a grow-and-prune paradigm to train the neural network model of Wu for the reasons given above with respect to claim 1.
As per claim 8, Wu, Itu, and Dai teaches the system of claim 1 as described above. Wu further teaches the modeling process is iterative (see paragraph 0007; model goes through a training and updating process). As noted above, while Wu does not explicitly teach the training is subjected to a grow-and-prune paradigm to generate at least one model, the broadest reasonable interpretation of “grow-and-prune paradigm, as recited in the claim, encompasses any paradigm for training a model. Nevertheless, Dai describes training a neural network using a grow-and-prune paradigm (see pages 1487-1488, paragraph beginning “To address these problems…” describing training a neural network using growing and pruning). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to apply a grow-and-prune paradigm for the reasons given above with respect to claim 1.
As per claim 10, Wu, Itu, and Dai teaches the system of claim 1 as described above. Wu further teaches the one or more processors are further configured to label the additional data using a machine learning model (see paragraph 0071; labeling all incoming, output, sensor, training data for use with learning model). As noted above, Wu does not explicitly teach training using synthetic data. Itu teaches generating synthetic data for training the neural network model (see paragraph 0023). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to apply synthetic data for training for the reasons given above with respect to claim 1.
As per claim 11, Wu, Itu, and Dai teaches the system of claim 1 as described above. Wu further teaches training the at least one neural network further comprises pre training the at least one neural network with the additional data (see paragraph 0007; training data includes sensor data and similar data of a plurality of different agents). As noted above, Wu does not explicitly teach training using synthetic data. Itu teaches generating synthetic data for training the neural network model (see paragraph 0023). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to apply synthetic data for training for the reasons given above with respect to claim 1.
Claims 13 and 25 recite substantially similar method and computer medium limitations as system claim 1 and are, as such, rejected for similar reasons as given above.
Claim(s) 2-3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wu, US Patent Application Publication No. 2023/0207120 in view of Itu, US Patent Application Publication No. 2019/0139641 and Dai et al., NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm and further in view of Karanam, US Patent Application Publication No. 2021/0158550 and further in view of Lisy, US Patent No. 9,579,060.
As per claim 2, Wu, Itu, and Dai teaches the system of claim 1 as described above. Wu further teaches the physiological data comprises three-way acceleration received from a smartwatch (see paragraph 0042; describes smart watch; paragraph 0052 describes sensor data as accelerometer; paragraph 0062 describes sensor data as heartrate in beats per minute).
Wu does not explicitly describe the physiological data comprising galvanic skin response, skin temperature, inter-beat interval. Lisy teaches collecting physiological data comprising galvanic skin response, skin temperature, inter-beat interval from a smartwatch (see column 3, lines 33-49; describing temperature, galvanic skin sensor; column 12, lines 10-12; smartwatch may serve as primary device for collecting the sensor data; column 28, lines 36-42; accelerometer; column 37; lines 1-5; beat-to-beat interval). Lisy also includes descriptions of using these measurements for mental health purposes (see column 25, lines 27-29; column 27, lines 3-9; column 37, lines 38-41). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date collect such data in association with the system of Wu, Itu, and Dai with the motivation of improving the convenience of monitoring a plurality of variables of a user (see column 1, lines 29-36 of Lisy). It is additionally noted that, in combining these features with those of Wu, Itu, and Dai, the recited “physiological data” only further definiens the initial receiving step of claim 1, but does not further limit the “raw data” in the training step” or the “physiological data captured over time” in the outputting step. Therefore, the combination only requires receiving additional data to the data received in Wu, Itu, and Dai.
As per claim 3, Wu, Itu, and Dai teaches the system of claim 1 as described above. Wu further teaches the physiological data comprises motion patterns, ambient temperature, gravity, acceleration, and angular velocity received from a smartphone (see paragraph 0050; describes user device as a mobile phone, mobile tablet; see paragraph 0052 describes sensor data as accelerometer; paragraph 0061; describes sensor data as temperature data).
Wu does not explicitly teach the physiological data comprises motion patterns, ambient temperature, gravity, and angular velocity. Lisy teaches collecting physiological data comprising motion patterns, ambient temperature, gravity, acceleration, and angular velocity received from a smartphone (see column 28, lines 1-6; motion, acceleration, velocity; column 29, lines 56-57; gravity, ambient temperature; column 30, lines 3-5). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date collect such data in association with the system of Wu, Itu, and Dai with the motivation of improving the convenience of monitoring a plurality of variables of a user (see column 1, lines 29-36 of Lisy). It is additionally noted that, in combining these features with those of Wu and Dai, the recited “physiological data” only further definiens the initial receiving step of claim 1, but does not further limit the “raw data” in the training step” or the “physiological data captured over time” in the outputting step. Therefore, the combination only requires receiving additional data to the data received in Wu, Itu, and Dai.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wu, US Patent Application Publication No. 2023/0207120 in view of Itu, US Patent Application Publication No. 2019/0139641 and Dai et al., NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm and further in view of Karanam, US Patent Application Publication No. 2021/0158550.
As per claim 9, Wu, Itu, and Dai teaches the system of claim 1 as described above. Wu does not explicitly teach generate the synthetic data using a Gaussian mixture model. Karanam teaches generate synthetic data using a Gaussian mixture model (see paragraph 0087; describes training a machine learning model by fitting a Gaussian mixture model to synthetic data). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to apply a Gaussian mixture model in the training with synthetic data in Wu and Itu with the motivation of ensuring that parameters follow a consistent distribution (see paragraph 0087 of Karanam).
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wu, US Patent Application Publication No. 2023/0207120 in view of Itu, US Patent Application Publication No. 2019/0139641 and Dai et al., NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm and further in view of Lee, US Patent Application Publication No. 2022/0338772.
As per claim 12, Wu, Itu, and Dai teaches the system of claim 1 as described above. Wu does not explicitly teach the mental health disorder comprises at least one of schizoaffective disorder, major depressive disorder, and bipolar disorder. Lee teaches applying a model to sensor data to output a mental health disorder comprising at least one of schizoaffective disorder, major depressive disorder, and bipolar disorder (see paragraphs 0020-0021; describes applying a model to brain sensor data to determine a mental disorder of major depressive disorder). It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to include determinations of common mental health conditions in the system of Wu, Itu, and Dai with the motivation of as these may be common conditions from user stress (see paragraph 0003), which is detectable in the system of Wu (see paragraph 0011; acquires physical activity, sleep activity, etc.).
Response to Arguments
Applicant’s arguments regarding the 101 rejections are moot in view of these rejections being withdrawn as explained above. Applicant’s arguments regarding Wu failing to teach the use of synthetic date is moot in view of the new grounds of rejection set forth above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Hassantabar et al., CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks, describes training a model with raw sensor data, from wearable sensors, augmented with synthetic data and applying the model with grow-and-prune to detect a physiological condition.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to C. Luke Gilligan whose telephone number is (571)272-6770. The examiner can normally be reached Monday through Friday 9:00 - 5:00.
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, Robert Morgan can be reached on 571-272-6773. 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.
C. Luke Gilligan
Primary Examiner
Art Unit 3683
/CHRISTOPHER L GILLIGAN/ Primary Examiner, Art Unit 3683