Abnormal Rhythm Detection from a Single-lead ECG via a Recurrent Neural Network
No Thumbnail Available
Author
Van Zaen, Jérôme
Bonnier, Guillaume
Parak, Jakub
Salonen, Mikko
Proust, Yara-Maria
Marques, Luisa
Lemkaddem, Alia
Pellaton, Cyril
Lemay, Mathieu
DOI
10.22489/CinC.2023.127
Abstract
Cardiac arrhythmias affect millions of individuals worldwide and can lead to severe complications such as stroke or heart failure. They can be difficult to diagnose with ambulatory electrocardiogram monitors due to their transient nature. We propose a system for long-term arrhythmia monitoring that takes single-lead electrocardiogram and tri-axis acceleration signals as inputs. It is composed of a beat detector to extract interbeat intervals and a classifier to detect arrhythmias. This system is evaluated on two datasets including 42 patients and achieves an accuracy of 0.988 for the abnormal class, 0.967 for the normal class, and 0.979 for the tachycardia class.
Publication Reference
CinC 2023, Atlanta (USA), pp. 1-4
Year
2023-11-26