DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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.
Continued Examination Under 37 CFR 1.114
2. 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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 21 April 2025 has been entered.
Information Disclosure Statement
3. The Information Disclosure Statement submitted on 21 April 2025 has been considered by the Examiner.
Status of Claims
4. Claims 1-6 and 12-17 are pending, of which claims 1, 3, 6, 12, 14, and 17 have been amended; claims 12-17 have been withdrawn; claims 7-11 and 18-22 have been canceled; and claims 1-6 are under consideration for patentability.
Response to Arguments
5. Applicant’s arguments dated 19 December 2024, referred to herein as “the Arguments”, have been fully considered but they are not persuasive in view of the new grounds of rejection necessitated by Applicant’s amendments to the claims.
The Examiner has addressed the amended limitations within the updated text below.
Applicant argued that Sullivan and Gopalakrishnan do not explicitly teach the amended limitation of claim 1 that recites wherein the second GPU is configured to apply the ECG signal of the patient and population data to update the machine learning algorithm, wherein the population data comprises data of ECG signals from a plurality of other patients (page 8 of the Arguments). The Examiner respectfully disagrees, as Gopalakrishnan teaches a computer which may process a patient’s raw heart rate signals (e.g., ECG data) through a computer application, such as an Application Program Interface (API) ([0050, 0055-0056]). Specifically, the API provides access to machine learning operations for ranking, clustering, classifying, and predicting from the R-R interval and/or the patient’s raw heart rate signals (e.g., ECG data) ([0050, 0055-0056]). Furthermore, the machine learning operations or algorithms may also learn or make predictions from raw heart rate signals (e.g., ECG data) of a population of users ([0056]). Therefore, the Examiner respectfully maintains that Gopalakrishnan suggests wherein the second GPU is configured to apply the ECG signal of the patient and population data to update the machine learning algorithm, wherein the population data comprises data of ECG signals from a plurality of other patients.
Applicant argued that Sullivan and Gopalakrishnan do not explicitly teach the amended limitation of claim 3 that recites the implantable cardioverter defibrillator configured to store and execute a tachyarrhythmia detection algorithm, wherein the computing system is configured to configure the tachyarrhythmia detection algorithm for the patient based on ECG signals classified by the machine learning algorithm. The Examiner respectfully disagrees, as Sullivan teaches an implantable cardioverter defibrillator comprising an arrhythmia detection algorithm for a cardiac event or arrhythmia (e.g., tachycardia) ([0041, 0063-0064]). Specifically, the arrhythmia detection algorithm is configured to determine if the patient is having a cardiac event or arrhythmia (e.g., tachycardia) based on the ECG signals that are classified by the machine learning algorithm ([0041, 0064]). Thus, Examiner respectfully submits that Sullivan suggests the implantable cardioverter defibrillator being configured to store and execute a tachyarrhythmia detection algorithm, wherein the computing system is configured to configure the tachyarrhythmia detection algorithm for the patient based on ECG signals classified by the machine learning algorithm.
Claim Rejections - 35 USC § 103
6. The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
7. Claims 1-3 and 6 are rejected under 35 U.S.C. 103 as being unpatentable over Sullivan et al. (US 2016/0000349 A1) in view of Gopalakrishnan et al. (US 2015/0265164 A1).
Regarding claim 1, Sullivan teaches a system for cardiac defibrillation ([abstract, 0022]), the system comprising:
an apparatus configured to deliver defibrillation therapy, wherein the apparatus is configured to be worn by a patient (the wearable defibrillator 1 [0042]), wherein the apparatus comprises:
processing circuitry comprising a first graphics processing unit (GPU) (the processor or controller unit 3 comprises the microcontroller 15 that is coupled to graphical display 13 [0047-0048, FIG. 2]);
sensing electrodes configured to sense an electrocardiogram signal of the patient (ECG electrodes 5a, 5b, 5c, and 5d [0043]);
defibrillation electrodes (the therapy pads 7 [0043, 0045, 0055]);
therapy delivery circuitry configured to deliver defibrillation therapy to the patient via the defibrillation electrodes (the microcontroller 15 includes a power circuit 17 that has sufficient capacity to administer one or more shocks to the therapy pads 7 [0047, FIG. 2]); and
a memory (the memory module 33 [0056]) configured to store the ECG signal ([0056]) and a machine learning algorithm (the machine learning algorithm is stored in the memory module 33 [0063]);
wherein the first GPU is configured to apply the machine learning algorithm to the ECG signal, and the processing circuitry is configured to determine whether to control delivery of the defibrillation therapy based on a result of the application of the machine learning algorithm to the signal (the microcontroller 15 is configured to detect abnormal heart rhythms based on information received from the ECG electrodes 5a-5d and administer a therapeutic shock to the patient via the pads 7 if an abnormal heart rhythm is detected (e.g., VT/VF condition) [0053, 0055]. Specifically, the machine learning algorithm may assist in determining whether the abnormal heart rhythm is a VT/VF condition or if it is caused by noise [0061]).
Sullivan does not explicitly teach a computing system communicatively coupled to the apparatus, the computing system comprising a second GPU, and
wherein the second GPU is configured to apply the ECG signal of the patient and population data to update the machine learning algorithm, wherein the population data comprises data of ECG signals from a plurality of other patients.
The prior art by Gopalakrishnan is analogous to Sullivan, as they both teach a system for detecting an arrhythmia by applying a machine learning algorithm ([0050, 0055-0056]).
Gopalakrishnan teaches a computing system communicatively coupled to the apparatus (the computing device may communicate with a wearable device (e.g., patch) comprising ECG sensors [0050, 0055-0056]), the computing system comprising a second GPU (the computing device may be a computer or tablet which inherently includes a graphics processing unit [0050, 0054]), and
wherein the second GPU is configured to apply the ECG signal of the patient and population data to update the machine learning algorithm, wherein the population data comprises data of ECG signals from a plurality of other patients (the computer may process a patient’s raw heart rate signals (e.g., ECG data) through a computer application, such as an Application Program Interface (API) [0050, 0055-0056]. Specifically, the API provides access to machine learning operations for ranking, clustering, classifying, and predicting from the R-R interval and/or the patient’s raw heart rate signals (e.g., ECG data) [0050, 0055-0056]. Furthermore, the machine learning operations or algorithms may also learn or make predictions from raw heart rate signals (e.g., ECG data) of a population of users [0056]).
Therefore, it would have been obvious to a person having ordinary skill in the art at the time the application was effectively filed to modify Sullivan’s apparatus to be coupled to a computing system that applies the ECG signal of the patient and population data to update the machine learning algorithm, as taught by Gopalakrishnan. The advantage of such modification will allow the algorithm learn from the patient’s data and a population of other patient’s data to improve the prediction or detection of an arrhythmia (see paragraphs [0050, 0055-0056] by Gopalakrishnan).
Regarding claim 2, Sullivan in view of Gopalakrishnan suggests the system of claim 1. Gopalakrishnan teaches wherein the plurality of other patients comprises a subset of the other patients having one or more characteristics that match respective characteristics of the patient (a plurality of heart health scores may be generated by a plurality of users to generate a set of population data [0093]. This population data may be used to train the machine learning algorithms to detect and predict the patient’s arrhythmic condition [0093]).
Therefore, it would have been obvious to a person having ordinary skill in the art at the time the application was effectively filed to modify the apparatus suggested by Sullivan in view of Gopalakrishnan to match the characteristics of the patient’s data with the characteristics of the other patient’s data, as further taught by Gopalakrishnan. The advantage of such modification will allow for comparing the patient’s data to a population of other patient’s data to improve the prediction or detection of an arrhythmia (see paragraphs [0050, 0055-0056, 0093] by Gopalakrishnan).
Regarding claim 3, Sullivan teaches an implantable cardioverter defibrillator (ICD) ([0027, 0041]) is configured to store and execute a tachyarrhythmia detection algorithm (the implantable cardioverter defibrillator comprises an arrhythmia detection algorithm for a cardiac event or arrhythmia (e.g., tachycardia) [0041, 0063-0064]), wherein the computing system is configured to configure the tachyarrhythmia detection algorithm for the patient based on ECG signals classified by the machine learning algorithm (the arrhythmia detection algorithm is configured to determine if the patient is having a cardiac event or arrhythmia (e.g., tachycardia) based on the ECG signals that are classified by the machine learning algorithm ([0041, 0064]).
Regarding claim 6, Sullivan in view of Gopalakrishnan suggests the system of claim 1. Sullivan teaches wherein the processing circuitry of the apparatus is configured to control the therapy delivery circuitry to deliver the defibrillation therapy based on a result of the application of the machine learning algorithm to the data and the ECG signal (the machine learning algorithm may assist the microcontroller 15 in determining whether the abnormal heart rhythm is a VT/VF condition or if it is caused by noise [0053, 0055, 0061]. If the abnormal heart rhythm is a VT/VF condition, the activation module 37 may initiate treatment by a sending a signal to deliver a therapeutic shock via the therapy pads 7 [0098-0099]. As stated previously in claim 1, the power circuit 17 provides sufficient power to administer the shock to the therapy pads 7 [0047]).
8. Claims 4-5 are rejected under 35 U.S.C. 103 as being unpatentable over Sullivan et al. in view of Gopalakrishnan et al., further in view of Hoffman et al. (US 2016/0250490 A1).
Regarding claim 4, Sullivan in view of Gopalakrishnan suggests the system of claim 1. Sullivan and Gopalakrishnan do not explicitly teach wherein the second GPU comprises at least one of a greater number of parallel cores or a greater clock speed than the first GPU.
The prior art by Hoffman is analogous to Sullivan, as they both teach a cardiac defibrillator ([0046, 0051]).
Hoffman teaches wherein the second GPU comprises at least one of a greater number of parallel cores or (the processing units may include single core processors and/or multi-core processors with multi-thread execution capability. The Examiner respectfully submits that multi-core processor with multi-thread execution capability would inherently have a greater number of parallel cores than a single core processor ([0309])
Thus, it would have been obvious to a person having ordinary skill in the art at the time the application was effectively filed to modify the second GPU suggested by Sullivan in view of Gopalakrishnan to comprise a greater number of parallel cores than the first GPU, as taught by Hoffman. The advantage of such modification will enhance the performance of the computing device (see paragraph [0309] by Hoffman).
Regarding claim 5, Sullivan in view of Gopalakrishnan and Hoffman suggests the system of claim 4. Sullivan, Gopalakrishnan, and Hoffman do not explicitly teach wherein the second GPU executes a more computationally complex version of the machine learning algorithm than the first GPU.
However, as stated previously in claim 4, Hoffman teaches the second GPU having greater parallel cores than the first GPU (the multi-core processor with multi-thread execution capability would inherently have a greater number of parallel cores than a single core processor ([0309]). Furthermore, the first and second GPUs are configured to execute machine learning algorithms (the processing units are configured to execute machine learning algorithms [0308-0309]) Thus, a person having ordinary skill in the art would have found it obvious to utilize the second GPU (e.g., multi-core processor with multi-thread) to execute a more computationally complex version of the machine learning algorithm than the first GPU. This modification is beneficial, as the second GPU (e.g., multi-core processor with multi-thread) of the computing device will have a sufficient number of parallel cores to receive, process, and learn from larger sets of data consisting of the ECG measurements (see paragraphs [0114, 0116, 0308-0309] by Hoffman).
Statement on Communication via Internet
9. Communications via Internet email are at the discretion of the applicant. All Internet communications between USPTO employees and applicants must be made using USPTO tools.
Without a written authorization by applicant in place, the USPTO will not respond via Internet email to any Internet correspondence which contains information subject to the confidentiality requirement as set forth in 35 U.S.C. 122. A paper copy of such correspondence and response will be placed in the appropriate patent application. Except for correspondence that only sets up an interview time, all correspondence between the Office and the applicant including applicant's representative must be placed in the appropriate patent application. If an email contains any information beyond scheduling an interview such as an interview agenda or authorization, it must be placed in the application.
For those applications where applicant wishes to communicate with the examiner via Internet communications, e.g., email or video conferencing tools, the following is a sample authorization form which may be used by applicant:
"Recognizing that Internet communications are not secure, I hereby authorize the USPTO to communicate with the undersigned and practitioners in accordance with 37 CFR 1.33 and 37 CFR 1.34 concerning any subject matter of this application by video conferencing, instant messaging, or electronic mail. I understand that a copy of these communications will be made of record in the application file."
Please refer to MPEP 502.03 for guidance on Communications via Internet.
Conclusion
10. Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSHUA BRENDON SOLOMON whose telephone number is (571)270-7208. The examiner can normally be reached on 7:30am -4:30pm.
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, Niketa Patel can be reached on (571)272-4156. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JOSHUA BRENDON SOLOMON/Examiner, Art Unit 3792
Prosecution Insights