US 11,694,804 B2Granted

Reduced power machine learning system for arrhythmia detection

AssigneeMedtronic, Inc.

InventorsNiranjan Chakravarthy, Siddharth Dani, Tarek D. Haddad, Donald R. Musgrove, Andrew Radtke, Rodolphe Katra, Lindsay A. Pedalty

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

Techniques are disclosed for using feature delineation to reduce the impact of machine learning cardiac arrhythmia detection on power consumption of medical devices. In one example, a medical device performs feature-based delineation of cardiac electrogram data sensed from a patient to obtain cardiac features indicative of an episode of arrhythmia in the patient. The medical device determines whether the cardiac features satisfy threshold criteria for application of a machine learning model for verifying the feature-based delineation of the cardiac electrogram data. In response to determining that the cardiac features satisfy the threshold criteria, the medical device applies the machine learning model to the sensed cardiac electrogram data to verify that the episode of arrhythmia has occurred or determine a classification of the episode of arrhythmia.

Claims22

Dependent claims

A method comprising:

sensing, by a medical device comprising processing circuitry and a storage medium, cardiac electrogram data of a patient;
determining that a portion of the cardiac electrogram data is indicative of an arrhythmia, wherein to determining that the portion of the cardiac electrogram data is indicative of the arrhythmia comprises performing, by the medical device, feature-based delineation of the sensed cardiac electrogram data to obtain cardiac features present in the cardiac electrogram data and indicative of an episode of arrhythmia in the patient;
in response to determining that the portion of the cardiac electrogram data is indicative of the arrhythmia, determining, by the medical device and based on the feature-based delineation, whether the cardiac features indicative of the episode of arrhythmia satisfy threshold criteria for application of a machine learning model for verifying that the episode of arrhythmia has occurred in the patient;
in response to determining that the cardiac features satisfy the threshold criteria for application of the machine learning model, applying, by the medical device, the machine learning model, trained using cardiac electrogram data for a plurality of patients, to the sensed cardiac electrogram data to verify, based on the machine learning model, that the episode of arrhythmia has occurred in the patient;
and
in response to verifying, by the machine learning model, that the episode of arrhythmia has occurred in the patient, transmitting, by the medical device to the external device, an indication that the episode of arrhythmia has occurred in the patient and one or more of the cardiac features that coincide with the episode of arrhythmia;
and
in response to determining that the cardiac features do not satisfy the threshold criteria for application of the machine learning model, transmitting the indication that the episode of the arrhythmia has occurred to the external device without using the machine learning model to verify the that the episode of the arrhythmia has occurred in the patient.

5 more elements

A medical device comprising:

a storage medium;
and
processing circuitry operably coupled to the storage medium, and configured to:
sense cardiac electrogram data of a patient;
determine that a portion of the cardiac electrogram data is indicative of an arrhythmia, wherein to determine that the portion of the cardiac electrogram data is indicative of the arrhythmia, the processing circuitry is configured to perform feature- based delineation of the sensed cardiac electrogram data to obtain cardiac features present in the cardiac electrogram data and indicative of an episode of arrhythmia in the patient;
in response to determining that the portion of the cardiac electrogram data is indicative of the arrhythmia, determine, based on the feature-based delineation, whether the cardiac features indicative of the episode of arrhythmia satisfy threshold criteria for application of a machine learning model for verifying that the episode of arrhythmia has occurred in the patient;
in response to determining that the cardiac features satisfy the threshold criteria for application of the machine learning model, apply the machine learning model, trained using cardiac electrogram data for a plurality of patients, to the sensed cardiac electrogram data to verify, based on the machine learning model, that the episode of arrhythmia has occurred in the patient;
and
in response to verifying, by the machine learning model, that the episode of arrhythmia has occurred in the patient, transmit, to the external device, an indication that the episode of arrhythmia has occurred in the patient and one or more of the cardiac features that coincide with the episode of arrhythmia;
and
in response to determining that the cardiac features do not satisfy the threshold criteria for application of the machine learning model, transmit the indication that the episode of the arrhythmia has occurred to the external device without using the machine learning model to verify the that the episode of the arrhythmia has occurred in the patient.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/851,603Filed 17 Apr 2020 · us provisional application
Priority: 6 May 2019
Published: US 2020/0357519 A112 Nov 2020
Granted: 4 Jul 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification27 codes

A61N 1/3621
Heart stimulators: for treating or preventing abnormally high heart rate
G16H 50/20
ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or…: for…
A61B 5/1116
Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb: determining posture transitions
A61B 5/1118
Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb: determining activity level