IP Library › Granted Patent US 12,507,939
Granted Patent B2
US 12,507,939 · App. 18/331,756 · Granted Dec 30, 2025

Arrhythmia detection with feature delineation and machine learning

Inventors: Niranjan Chakravarthy (Singapore, SG); Siddharth Dani (Minneapolis, MN); Tarek D. Haddad (Minneapolis, MN); Donald R. Musgrove (Minneapolis, MN); Andrew Radtke (Minneapolis, MN); Eduardo N. Warman (Maple Grove, MN); Rodolphe Katra (Blaine, MN); Lindsay A. Pedalty (Minneapolis, MN)
Assignee: Medtronic, Inc.
A61B5/349A61B5/316G16H10/60A61B2560/0214
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,507,939
App. No.
18/331,756
Granted
Dec 30, 2025
Kind
B2
Abstract

Techniques are disclosed for using both feature delineation and machine learning to detect cardiac arrhythmia. A computing device receives cardiac electrogram data of a patient sensed by a medical device. The computing device obtains, via feature-based delineation of the cardiac electrogram data, a first classification of arrhythmia in the patient. The computing device applies a machine learning model to the received cardiac electrogram data to obtain a second classification of arrhythmia in the patient. As one example, the computing device uses the first and second classifications to determine whether an episode of arrhythmia has occurred in the patient. As another example, the computing device uses the second classification to verify the first classification of arrhythmia in the patient. The computing device outputs a report indicating that the episode of arrhythmia has occurred and one or more cardiac features that coincide with the episode of arrhythmia.

Claims (85)

1 . A system comprising processing circuitry and a storage medium, wherein the processing circuitry is configured to:

determine a first classification of arrhythmia of sensed electrocardiogram (ECG) data of a patient;

identify first cardiac features present in the sensed ECG data that coincide with the first classification of arrhythmia in the patient;

determine that one or more episodes of arrhythmia of the first classification have previously occurred in the patient;

in response to a determination that the one or more episodes of arrhythmia of the first classification have previously occurred in the patient, apply a machine learning model, trained using ECG data for a plurality of patients, to at least one of the sensed ECG data and the first cardiac features present in the ECG data to determine that an episode of arrhythmia of the first classification has occurred in the patient; and

in response to a determination that that the episode of arrhythmia of the first classification has occurred in the patient, generate data comprising an indication that the episode of arrhythmia of the first classification has occurred in the patient and one or more of the first cardiac features that coincide with the episode of arrhythmia of the first classification.

2 . The system of claim 1 , wherein to apply the machine learning model to at least one of the sensed ECG data and the first cardiac features present in the ECG data to determine that an episode of arrhythmia of the first classification has occurred in the patient, the processing circuitry is configured to:

apply the machine learning model to at least one of the sensed ECG data and the first cardiac features present in the ECG data to determine that the first cardiac features are similar to cardiac features that coincide with the one or more episodes of arrhythmia of the first classification that have previously occurred in the patient; and

in response to a determination that the first cardiac features are similar to the cardiac features that coincide with the one or more episodes of arrhythmia of the first classification that have previously occurred in the patient, determine that an episode of arrhythmia of the first classification has occurred in the patient.

3 . The system of claim 1 , wherein the processing circuitry is further configured to:

determine a second classification of arrhythmia of the sensed ECG data;

identify second cardiac features present in the sensed ECG data that coincide with the second classification of arrhythmia in the patient;

determine that one or more episodes of arrhythmia of the second classification have not previously occurred in the patient; and

in response to a determination that the one or more episodes of arrhythmia of the second classification have not previously occurred in the patient:

receive an indication that the second cardiac features demonstrate an episode of arrhythmia of the second classification in the patient; and

store the indication that the second cardiac features demonstrate the episode of arrhythmia of the second classification in the patient and the second cardiac features.

4 . The system of claim 3 , wherein the processing circuitry is further configured to:

determine a third classification of arrhythmia of the sensed ECG data;

identify third cardiac features present in the sensed ECG data that coincide with the third classification of arrhythmia in the patient;

determine that one or more episodes of arrhythmia of the third classification have previously occurred in the patient;

in response to a determination that the one or more episodes of arrhythmia of the third classification have previously occurred in the patient, apply a machine learning model, trained using ECG data for a plurality of patients, to at least one of the sensed ECG data and the third cardiac features present in the ECG data to determine that an episode of arrhythmia of the second classification has occurred in the patient; and

in response to a determination that that the episode of arrhythmia of the second classification has occurred in the patient, generate data comprising a second indication that the episode of arrhythmia of the third classification has occurred in the patient and one or more of the third cardiac features that coincide with the episode of arrhythmia of the third classification.

5 . The system of claim 4 , wherein to apply the machine learning model to at least one of the sensed ECG data and the third cardiac features present in the ECG data to determine that an episode of arrhythmia of the second classification has occurred in the patient, the processing circuitry is configured to:

apply the machine learning model, trained using ECG data for a plurality of patients, to at least one of the sensed ECG data and the third cardiac features present in the ECG data to determine that the third cardiac features are similar to the second cardiac features that coincide with the one or more episodes of arrhythmia of the second classification that have previously occurred in the patient; and

in response to a determination that the third cardiac features are similar to the second cardiac features that coincide with the one or more episodes of arrhythmia of the second classification that have previously occurred in the patient, determine that an episode of arrhythmia of the second classification has occurred in the patient.

6 . The system of claim 2 , wherein to apply the machine learning model to at least one of the sensed ECG data and the first cardiac features present in the ECG data to determine that the first cardiac features are similar to cardiac features that coincide with the one or more episodes of arrhythmia of the first classification that have previously occurred in the patient, the processing circuitry is configured to:

apply the machine learning model to the first cardiac features to generate a preliminary determination that the first cardiac features are similar to the cardiac features that coincide with the one or more episodes of arrhythmia of the first classification that have previously occurred in the patient and an estimate of certainty in the preliminary determination; and

in response to a determination that the estimate of certainty in the preliminary determination is greater than a predetermined threshold, determine that the first cardiac features are similar to the cardiac features that coincide with the one or more episodes of arrhythmia of the first classification that have previously occurred in the patient.

7 . The system of claim 1 , wherein to apply the machine learning model to at least one of the sensed ECG data and the first cardiac features present in the ECG data to determine that an episode of arrhythmia of the first classification has occurred in the patient, the processing circuitry is configured to:

apply the machine learning model to determine that the first cardiac features are indicative of an episode of at least one of bradycardia, tachycardia, atrial fibrillation, ventricular fibrillation, or AV Block that has previously occurred in the patient.

8 . The system of claim 1 , wherein the first cardiac features present in the ECG data comprise one or more of a mean heartrate of the patient, a minimum heartrate of the patient, a maximum heartrate of the patient, a PR interval of a heart of the patient, a variability of heartrate of the patient, one or more amplitudes of one or more features of ECG data, or an interval between the or more features of the ECG data.

9 . The system of claim 1 , wherein the machine learning model trained using ECG data for the plurality of patients comprises a machine learning model trained using a plurality of ECG waveforms, each ECG waveform labeled with one or more episodes of arrhythmia of one or more types in a patient of the plurality of patients.

10 . The system of claim 1 , wherein the processing circuitry is further configured to:

in response to generation of data comprising an indication that the episode of arrhythmia of the first classification has occurred in the patient and one or more of the first cardiac features that coincide with the episode of arrhythmia of the first classification:

receive an adjustment on how to identify first cardiac features present in the sensed ECG data; and

identify, in accordance with the adjustment, second cardiac features present in the sensed ECG data.

11 . The system of claim 1 , wherein to generate data comprising an indication that the episode of arrhythmia of the first classification has occurred in the patient and one or more of the first cardiac features that coincide with the episode of arrhythmia of the first classification, the processing circuitry is configured to:

identify a subsection of the ECG of the patient, wherein the subsection comprises ECG data for a first time period prior to the episode of arrhythmia, a second time period during the episode of arrhythmia, and a third time period after the episode of arrhythmia, and wherein a length of time of the ECG of the patient is greater than the first, second, and third time periods;

identify one or more of the first cardiac features that coincide with the first, second, and third time periods; and

include, in the data, the subsection of the ECG and the one or more of the first cardiac features that coincide with the first, second, and third time periods.

12 . The system of claim 1 , wherein the processing circuitry is further configured to:

process the sensed ECG data to generate an intermediate representation of the sensed ECG data; and

to apply the machine learning model, apply a machine learning model, trained using intermediate representations of ECG data for a plurality of patients, to at least one of the intermediate representation of the sensed ECG data and the first cardiac features present in the sensed ECG data to determine, based on the machine learning model, that an episode of arrhythmia of the first classification has occurred in the patient.

13 . The system of claim 12 , wherein to process the sensed ECG data to generate an intermediate representation of the sensed ECG data, the processing circuitry is configured to:

apply a filter to the sensed ECG data; and

perform signal decomposition on the sensed ECG data.

14 . The system of claim 13 , wherein to perform signal decomposition on the sensed ECG data, the processing circuitry is configured to:

perform wavelet decomposition on the sensed ECG data.

15 . A system comprising:

an insertable cardiac monitor (ICM) configured to:

sense electrocardiogram (ECG) data of a patient;

determine a first classification of arrhythmia of the sensed ECG data; and

identify first cardiac features present in the sensed ECG data that coincide with the first classification of arrhythmia in the patient; and

a computing device configured to:

determine that one or more episodes of arrhythmia of the first classification have previously occurred in the patient;

in response to a determination that the one or more episodes of arrhythmia of the first classification have previously occurred in the patient, apply a machine learning model, trained using ECG data for a plurality of patients, to at least one of the sensed ECG data and the first cardiac features present in the ECG data to determine that an episode of arrhythmia of the first classification has occurred in the patient; and

in response to a determination that that the episode of arrhythmia of the first classification has occurred in the patient, generate data comprising an indication that the episode of arrhythmia of the first classification has occurred in the patient and one or more of the first cardiac features that coincide with the episode of arrhythmia of the first classification.

16 . The system of claim 15 , wherein to apply the machine learning model to at least one of the sensed ECG data and the first cardiac features present in the ECG data to determine that an episode of arrhythmia of the first classification has occurred in the patient, the computing device is configured to:

apply the machine learning model to at least one of the sensed ECG data and the first cardiac features present in the ECG data to determine that the first cardiac features are similar to cardiac features that coincide with the one or more episodes of arrhythmia of the first classification that have previously occurred in the patient; and

in response to a determination that the first cardiac features are similar to the cardiac features that coincide with the one or more episodes of arrhythmia of the first classification that have previously occurred in the patient, determine that an episode of arrhythmia of the first classification has occurred in the patient.

17 . The system of claim 15 , wherein the ICM is further configured to:

determine a second classification of arrhythmia of the sensed ECG data; and

identify second cardiac features present in the sensed ECG data that coincide with the second classification of arrhythmia in the patient, and

wherein the computer device is further configured to:

determine that one or more episodes of arrhythmia of the second classification have not previously occurred in the patient; and

in response to a determination that the one or more episodes of arrhythmia of the second classification have not previously occurred in the patient:

receive an indication that the second cardiac features demonstrate an episode of arrhythmia of the second classification in the patient; and

store the indication that the second cardiac features demonstrate the episode of arrhythmia of the second classification in the patient and the second cardiac features.

18 . The system of claim 17 , wherein the ICM is further configured to:

determine a third classification of arrhythmia of the sensed ECG data; and

identify third cardiac features present in the sensed ECG data that coincide with the third classification of arrhythmia in the patient, and

wherein the computer device is further configured to:

determine that one or more episodes of arrhythmia of the third classification have previously occurred in the patient;

in response to a determination that the one or more episodes of arrhythmia of the third classification have previously occurred in the patient, apply a machine learning model, trained using ECG data for a plurality of patients, to at least one of the sensed ECG data and the third cardiac features present in the ECG data to determine that an episode of arrhythmia of the second classification has occurred in the patient; and

in response to a determination that that the episode of arrhythmia of the second classification has occurred in the patient, generate data comprising a second indication that the episode of arrhythmia of the third classification has occurred in the patient and one or more of the third cardiac features that coincide with the episode of arrhythmia of the third classification.

19 . The system of claim 15 , wherein to apply the machine learning model to at least one of the sensed ECG data and the first cardiac features present in the ECG data to determine that an episode of arrhythmia of the first classification has occurred in the patient, the computing device is configured to:

apply the machine learning model to the first cardiac features to generate a preliminary determination that the first cardiac features are similar to the cardiac features that coincide with the one or more episodes of arrhythmia of the first classification that have previously occurred in the patient and an estimate of certainty in the preliminary determination; and

in response to a determination that the estimate of certainty in the preliminary determination is greater than a predetermined threshold, determine that the first cardiac features are similar to the cardiac features that coincide with the one or more episodes of arrhythmia of the first classification that have previously occurred in the patient.

20 . The system of claim 15 , wherein to apply the machine learning model to the sensed ECG data and the first cardiac features present in the ECG data to determine that an episode of arrhythmia of the first classification has occurred in the patient, the computing device is configured to:

apply the machine learning model to determine that the first cardiac features are indicative of an episode of at least one of bradycardia, tachycardia, atrial fibrillation, ventricular fibrillation, or AV Block that has previously occurred in the patient.

21 . The system of claim 15 , wherein the first cardiac features present in the ECG data are one or more of a mean heartrate of the patient, a minimum heartrate of the patient, a maximum heartrate of the patient, a PR interval of a heart of the patient, a variability of heartrate of the patient, one or more amplitudes of one or more features of ECG data, or an interval between the or more features of the ECG data.

22 . The system of claim 15 , wherein the machine learning model trained using ECG data for the plurality of patients comprises a machine learning model trained using a plurality of ECG waveforms, each ECG waveform labeled with one or more episodes of arrhythmia of one or more types in a patient of the plurality of patients.

23 . The system of claim 15 , wherein the ICM further comprises:

a housing configured for subcutaneous implantation within a patient; and

a plurality of electrodes on the housing, wherein the ICM is configured to sense the ECG data via the plurality of electrodes.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 8, 2023
From: CHAKRAVARTHY, NIRANJAN; DANI, SIDDHARTH; HADDAD, TAREK D.; MUSGROVE, DONALD R.; RADTKE, ANDREW; WARMAN, EDUARDO N.; KATRA, RODOLPHE; PEDALTY, LINDSAY A.
To: MEDTRONIC, INC.
Reel/Frame 063899/0878 →
Continuity (4)
Continuation 17373480 · Jul 12, 2021
Continuation 16850699 · Apr 16, 2020
Provisional Application 62843738 · May 6, 2019
Related Publication 20230320648A1 · Oct 12, 2023
References Cited (174)
US 4458691A · Netravali · 1984 [cited by applicant]
US 6212428B1 · Hsu et al. · 2001 [cited by applicant]
US 6308094B1 · Shusterman et al. · 2001 [cited by applicant]
US 6594523B1 · Levine · 2003 [cited by applicant]
US 8103346B2 · Mass et al. · 2012 [cited by applicant]
US 8521281B2 · Patel et al. · 2013 [cited by applicant]
US 9149637B2 · Warren et al. · 2015 [cited by applicant]
US 9183351B2 · Shusterman · 2015 [cited by applicant]
US 9483529B1 · Pasoi et al. · 2016 [cited by applicant]
US 9585590B2 · McNair · 2017 [cited by applicant]
US 9743890B2 · Lord et al. · 2017 [cited by applicant]
US 9775559B2 · Zhang et al. · 2017 [cited by applicant]
US 10265028B2 · Moturu · 2019 [cited by examiner]
US 10368746B2 · Huelskamp et al. · 2019 [cited by applicant]
US 10463269B2 · Boleyn et al. · 2019 [cited by applicant]
US 10744334B2 · Perschbacher et al. · 2020 [cited by applicant]
US 10888282B2 · Ong et al. · 2021 [cited by applicant]
US 11311230B2 · Sullivan et al. · 2022 [cited by applicant]
US 11355244B2 · Haddad et al. · 2022 [cited by applicant]
US 11443852B2 · Chakravarthy et al. · 2022 [cited by applicant]
US 11723577B2 · Pedalty et al. · 2023 [cited by applicant]
US 20020016550A1 · Sweeney et al. · 2002 [cited by applicant]
US 20020123768A1 · Gilkerson et al. · 2002 [cited by applicant]
US 20060247709A1 · Gottesman et al. · 2006 [cited by applicant]
US 20070156187A1 · Ricci et al. · 2007 [cited by applicant]
US 20090177453A1 · Kouchi et al. · 2009 [cited by applicant]
US 20090259269A1 · Brown · 2009 [cited by applicant]
US 20100179444A1 · O'Brien et al. · 2010 [cited by applicant]
US 20100217141A1 · Ostrow · 2010 [cited by applicant]
US 20100268103A1 · McNamara et al. · 2010 [cited by applicant]
US 20100280841A1 · Dong et al. · 2010 [cited by applicant]
US 20100312130A1 · Zhang et al. · 2010 [cited by applicant]
US 20100312131A1 · Naware et al. · 2010 [cited by applicant]
US 20110270109A1 · Zhang et al. · 2011 [cited by applicant]
US 20120004563A1 · Kim et al. · 2012 [cited by applicant]
US 20120209126A1 · Amos et al. · 2012 [cited by applicant]
US 20130218038A1 · Zhang · 2013 [cited by applicant]
US 20130231947A1 · Shusterman · 2013 [cited by applicant]
US 20130274524A1 · Dakka et al. · 2013 [cited by applicant]
US 20130274624A1 · Mahanjan et al. · 2013 [cited by applicant]
US 20140142448A1 · Bae et al. · 2014 [cited by applicant]
US 20140257063A1 · Ong et al. · 2014 [cited by applicant]
US 20140378856A1 · Koike et al. · 2014 [cited by applicant]
US 20150065894A1 · Airaksinen et al. · 2015 [cited by applicant]
US 20150164349A1 · Gopalakrishnan et al. · 2015 [cited by applicant]
US 20150216435A1 · Bokan et al. · 2015 [cited by applicant]
US 20150265217A1 · Penders et al. · 2015 [cited by applicant]
US 20160008615A1 · Stahmann et al. · 2016 [cited by applicant]
US 20160022164A1 · Brockway et al. · 2016 [cited by applicant]
US 20160022166A1 · Stadler · 2016 [cited by applicant]
US 20160135706A1 · Sullivan et al. · 2016 [cited by applicant]
US 20160192853A1 · Bardy et al. · 2016 [cited by applicant]
US 20160220137A1 · Mahajan et al. · 2016 [cited by applicant]
US 20160232280A1 · Apte et al. · 2016 [cited by applicant]
US 20170095673A1 · Ludwig et al. · 2017 [cited by applicant]
US 20170105683A1 · Xue · 2017 [cited by applicant]
US 20170156592A1 · Fu · 2017 [cited by applicant]
US 20170196458A1 · Ternes et al. · 2017 [cited by applicant]
US 20170265765A1 · Baumann et al. · 2017 [cited by applicant]
US 20170290550A1 · Perschbacher et al. · 2017 [cited by applicant]
US 20170347894A1 · Bhushan et al. · 2017 [cited by applicant]
US 20170354365A1 · Zhou · 2017 [cited by applicant]
US 20180008976A1 · Luebbert et al. · 2018 [cited by applicant]
US 20180089763A1 · Okazaki · 2018 [cited by applicant]
US 20180146874A1 · Walker et al. · 2018 [cited by applicant]
US 20180146929A1 · Joo et al. · 2018 [cited by applicant]
US 20180206721A1 · Zhang · 2018 [cited by applicant]
US 20180233227A1 · Galloway et al. · 2018 [cited by applicant]
US 20180233233A1 · Sharma et al. · 2018 [cited by applicant]
US 20180272147A1 · Freeman et al. · 2018 [cited by applicant]
US 20180279891A1 · Miao et al. · 2018 [cited by applicant]
US 20180310892A1 · Perschbacher et al. · 2018 [cited by applicant]
US 20180350468A1 · Friedman et al. · 2018 [cited by applicant]
US 20190008461A1 · Gupta et al. · 2019 [cited by applicant]
US 20190029552A1 · Perschbacher et al. · 2019 [cited by applicant]
US 20190038148A1 · Valys et al. · 2019 [cited by applicant]
US 20190038149A1 · Gopalakrishnan et al. · 2019 [cited by applicant]
US 20190090769A1 · Boleyn et al. · 2019 [cited by applicant]
US 20190090774A1 · Yang et al. · 2019 [cited by applicant]
US 20190122097A1 · Shibahara et al. · 2019 [cited by applicant]
US 20190130554A1 · Rothberg et al. · 2019 [cited by applicant]
US 20190209022A1 · Sobol et al. · 2019 [cited by applicant]
US 20190216350A1 · Sullivan et al. · 2019 [cited by applicant]
US 20190231207A1 · Perschbacher et al. · 2019 [cited by applicant]
US 20190272920A1 · Teplitzky · 2019 [cited by applicant]
US 20190275335A1 · Volpe et al. · 2019 [cited by applicant]
US 20190328251A1 · Jin · 2019 [cited by applicant]
US 20190343415A1 · Saha et al. · 2019 [cited by applicant]
US 20190365342A1 · Ghaffarzadegan et al. · 2019 [cited by applicant]
US 20190378620A1 · Saren · 2019 [cited by applicant]
US 20200100693A1 · Velo · 2020 [cited by applicant]
US 20200108260A1 · Haddad et al. · 2020 [cited by applicant]
US 20200178825A1 · Weijia et al. · 2020 [cited by applicant]
US 20200288997A1 · Shute et al. · 2020 [cited by applicant]
US 20200352462A1 · Pedalty et al. · 2020 [cited by applicant]
US 20200352466A1 · Chakravarthy et al. · 2020 [cited by applicant]
US 20200352521A1 · Chakravarthy et al. · 2020 [cited by applicant]
US 20200353271A1 · Dani et al. · 2020 [cited by applicant]
US 20200357517A1 · Haddad et al. · 2020 [cited by applicant]
US 20200357518A1 · Musgrove et al. · 2020 [cited by applicant]
US 20200357519A1 · Chakravarthy et al. · 2020 [cited by applicant]
US 20210137384A1 · Robinson et al. · 2021 [cited by applicant]
US 20210169736A1 · Wijshoff et al. · 2021 [cited by applicant]
US 20210204858A1 · Attia et al. · 2021 [cited by applicant]
US 20210338134A1 · Chakravarthy et al. · 2021 [cited by applicant]
US 20210338138A1 · Pedalty et al. · 2021 [cited by applicant]
US 20210343416A1 · Chakravarthy et al. · 2021 [cited by applicant]
US 20210345865A1 · Spillinger et al. · 2021 [cited by applicant]
US 20210358631A1 · Haddad et al. · 2021 [cited by applicant]
US 20220023626A1 · Haddad et al. · 2022 [cited by applicant]
US 20230149726A1 · Dani et al. · 2023 [cited by applicant]
US 20230290512A1 · Chakravarthy et al. · 2023 [cited by applicant]
CN 106572807A · 2017 [cited by applicant]
CN 106573149A · 2017 [cited by applicant]
CN 106725428A · 2017 [cited by applicant]
CN 107408144A · 2017 [cited by applicant]
CN 107822622A · 2018 [cited by applicant]
CN 108030488A · 2018 [cited by applicant]
CN 108577823A · 2018 [cited by applicant]
CN 108883279A · 2018 [cited by applicant]
EP 1218060B1 · 2004 [cited by applicant]
EP 2427105A1 · 2012 [cited by applicant]
JP 2008293171A · 2007 [cited by applicant]
JP 2013524865A · 2013 [cited by applicant]
JP 2012532633A · 2013 [cited by applicant]
JP 2014100473A · 2014 [cited by applicant]
JP 2017042386A · 2017 [cited by applicant]
JP 2018503885A · 2018 [cited by applicant]
JP 2018538120A · 2018 [cited by applicant]
WO 0124876A1 · 2001 [cited by applicant]
WO 2010129447A1 · 2010 [cited by applicant]
WO 2011008550A1 · 2011 [cited by applicant]
WO 2013160538A1 · 2013 [cited by applicant]
WO 2015200527A1 · 2015 [cited by applicant]
WO 2017072250A1 · 2017 [cited by applicant]
WO 2017091736A1 · 2017 [cited by applicant]
WO 2018119316A1 · 2018 [cited by applicant]
WO 2018162901A1 · 2018 [cited by applicant]
WO 2019075035A1 · 2019 [cited by applicant]
WO 2020049267A1 · 2020 [cited by applicant]
Notice of Allowance from U.S. Appl. No. 18/320,522 dated Feb. 27, 2025, 7 pp. [cited by applicant]
Response to Final Office Action dated Dec. 4, 2024 from U.S. Appl. No. 18/320,522, filed Feb. 4, 2025, 10 pp. [cited by applicant]
“Classify ECG Signals Using Long Short-Term Memory Networks,” MATLAB, retrieved from https://www.mathworks.com/help/signal/examples/classify-ecg-signals-using-long-short-term-memory-networks.html, Nov. 2, 2018, 19 pp. [cited by applicant]
“Visualize Features of a Convolutional Neural Network,” MATLAB & Simulink, Mar. 15, 2018, 9 pp. [cited by applicant]
Andersen et al., “A Deep Learning Approach for Real-Time Detection of Atrial Fibrillation,” Expert Systems with Applications, vol. 114, Aug. 14, 2018, pp. 465-473. [cited by applicant]
Anonymous, “Receiver Operating Characteristic—Wikipedia,” Mar. 20, 2019, Retrieved from the Internet: URL:https://en.wikipedia.org/w/index.php?title=Receiver_operating_characteristic&old is=888671034#History, 12 pp. [cited by applicant]
Arrobo et al., “An Innovative Wireless Cardiac Rhythm Management (iCRM) System,” Computer Science, 2014 Wireless Telecommunications Symposium, Jun. 2014, 5 pp. [cited by applicant]
Bresnick, “Machine Learning Algorithm Outperforms Cardiologists Reading EKGs”, Health IT Analytics, Jul. 12, 2017, p. 5. [cited by applicant]
Chen et al., “Electrocardiogram Recognization Based on Variational AutoEncoder,” Machine Learning and Biometrics, IntechOpen, Aug. 29, 2018, pp. 71-90. [cited by applicant]
Fawaz et al., “Deep learning for time series classification: a review,” Irirmas, Universite Haute Alsace, Dec. 7, 2018, 53 pp. [cited by applicant]
Habibzadeh et al., “On Determining the Most Appropriate Test Cut-Off Value: the Case of Tests with Continuous Results,” Biochemia Medica, Oct. 15, 2016, pp. 297-307. [cited by applicant]
International Preliminary Report on Patentability from International Application No. PCT/US2020/028707, dated Nov. 18, 2021, 8 pp. [cited by applicant]
International Search Report and Written Opinion of International Application No. PCT/US2020/028707, mailed Aug. 10, 2020, 15 pp. [cited by applicant]
Isin et al., “Cardiac Arrhythmia Detection Using Deep Learning,” Procedia Computer Science vol. 120, 2017 (Applicant points out, in accordance with MPEP 609.04(a), that the year of publication, 2017, is sufficiently ear… [cited by applicant]
Kelwade et al., “Prediction of Cardiac Arrhythmia using Artificial Neural Network,” International Journal of Computer Applications (0975-8887), vol. 115-No. 20, Apr. 2015, 6 pp. [cited by applicant]
Lau et al., “Connecting the Dots: From Big Data to Healthy Heart,” Circulation, vol. 134, No. 5, Aug. 2, 2017, 5 pp. [cited by applicant]
Madani et al., “Fast and accurate view classification of echocardiograms using deep learning,” NPJ Digital Medicine, vol. 1, No. 6 Mar. 21, 2018, 8 pp. [cited by applicant]
Office Action from U.S. Appl. No. 16/850,699 dated Jul. 28, 2022, 22 pp. [cited by applicant]
Prosecution History from U.S. Appl. No. 16/851,603, dated Jul. 14, 2022 through Jun. 1, 2023, 64 pp. [cited by applicant]
Prosecution History from U.S. Appl. No. 17/373,480, dated Feb. 22, 2022 through May 25, 2023, 86 pp. [cited by applicant]
Prosecution History from U.S. Appl. No. 17/377,763, dated Oct. 13, 2021 through Aug. 5, 2022, 91 pp. [cited by applicant]
Schirrmeister et al., “Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG,” arXiv:170.05051v1, Mar. 16, 2017, 58 pp. [cited by applicant]
Schwab et al., “Beat by Beat: Classifying Cardiac Arrhythmias with Recurrent Neural Networks,” 2017 Computing in Cardiology (CinC), vol. 44, Oct. 24, 2017, 4 pp. [cited by applicant]
Swerdlow et al., “An Innovative Wireless Cardiac Rhythm Management (iCRM) System,” Advances in Arrhythmia and Electrophysiology, vol. 7, No. 6, Dec. 2014, pp. 1237-1261. [cited by applicant]
Swerdlow et al., “Troubleshooting Implanted Cardioverter Defibrillator Sensing Problems I,” Advances in Arrhythmia and Electrophysiology, vol. 7, No. 6, Dec. 2014, pp. 1237-1261. [cited by applicant]
Wartzek et al., “ECG on the Road: Robust and Unobtrusive Estimation of Heart Rate,” IEEE Transactions on Biomedical Engineering, vol. 58, No. 11, Nov. 2011, pp. 3112-3120. [cited by applicant]
Witten et al., “Data mining: Practical Machine Learning Tools and Techniques,” Third Edition, Morgan Kaufmann, Feb. 3, 2011, 665 pp. [cited by applicant]
U.S. Appl. No. 18/309,309, filed Apr. 28, 2023, naming inventors Haddad et al. [cited by applicant]
U.S. Appl. No. 18/479,228, filed Oct. 2, 2023, naming inventors Haddad et al. [cited by applicant]
U.S. Appl. No. 18/336,161, filed Jun. 16, 2023, naming inventors Pedalty et al. [cited by applicant]
Hao et al., “Application of implantable cardioverter-defibrillator in patients with tachyventricular fatal arhythmias”, vol. 26, No. 23, The Journal of Practical Medicine, Dec. 10, 2010, 4 pp., Translation provided for … [cited by applicant]
Final Office Action from U.S. Appl. No. 18/320,522 dated Dec. 4, 2024, 7 pp. [cited by applicant]
Office Action, and translation thereof, from counterpart Korean Application No. 10-2021-7038219 dated Oct. 15, 2024, 18 pp. [cited by applicant]
Second Office Action from counterpart Australian Application No. 2020269176 dated Jul. 22, 2025, 4 pp. [cited by applicant]