Reduced power machine learning system for arrhythmia detection

US11694804B2 · kind B2 · utility

Assignee

• Medtronic, Inc. · US

Inventors

• Niranjan Chakravarthy · Eden Prairie, US
• Siddharth Dani · Minneapolis, US
• Tarek D. Haddad · Minneapolis, US
• Donald R. Musgrove · Minneapolis, US
• Andrew Radtke · Minneapolis, US
• Rodolphe Katra · Blaine, US
• Lindsay A. Pedalty · Minneapolis, US

Key dates

• Filing date: Apr 17, 2020
• Grant date: Jul 4, 2023
• Expiry date: Apr 26, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G16H15/00
• WIPO field: Medical technology
• WIPO sector: Instruments

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.