ArNet-ECG: Deep Learning for the Detection of Atrial Fibrillation from the Raw Electrocardiogram

Noam Ben-Moshe, Shany Biton, Joachim A. Behar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Introduction: Atrial fibrillation (AF) is the most prevalent heart arrhythmia. AF manifests on the electrocar-diogram (ECG) though irregular beat-to-beat time interval variation, the absence of P-wave and the presence of fibrillatory waves (f-wave). We hypothesize that a deep learning (DL) approach trained on the raw ECG will enable robust detection of AF events and the estimation of the AF burden (AFB). We further hypothesize that the performance reached leveraging the raw ECG will be superior to previously developed methods using the beat-to-beat interval variation time series. Consequently, we develop a new DL algorithm, denoted ArNet-ECG, to robustly detect AF events and estimate the AFB from the raw ECG and bench-mark this algorithms against previous work. Methods: A dataset including 2,247 adult patients and totaling over 53,753 hours of continuous ECG from the University of Virginia (UVAF) was used. Results: ArNet-ECG obtained an F1 of 0.96 and ArNet2 obtained an F1 0.94. Discussion and conclusion: ArNet-ECG outperformed ArNet2 thus demonstrating that using the raw ECG provides added performance over the beat-to-beat interval time series. The main reason found for explaining the higher performance of ArNet-ECG was its high performance on atrial flutter examples versus poor performance on these recordings for ArNet2.

Original languageEnglish
Title of host publication2022 Computing in Cardiology, CinC 2022
ISBN (Electronic)9798350300970
StatePublished - 2022
Event2022 Computing in Cardiology, CinC 2022 - Tampere, Finland
Duration: 4 Sep 20227 Sep 2022

Publication series

NameComputing in Cardiology


Conference2022 Computing in Cardiology, CinC 2022

All Science Journal Classification (ASJC) codes

  • Cardiology and Cardiovascular Medicine
  • General Computer Science


Dive into the research topics of 'ArNet-ECG: Deep Learning for the Detection of Atrial Fibrillation from the Raw Electrocardiogram'. Together they form a unique fingerprint.

Cite this