Distinguishing sinus rhythm from atrial fibrillation on single-lead ECGs using a deep neural network
Session title: Machine Learning Approaches to ECG Interpretation: State of the Art
Topic: Electrocardiogram (ECG) and Arrhythmia Analysis
Session type: Advances in Science
Available from:

View abstract

M Oudkerk Pool1 , BD De Vos2 , JM Wolterink2 , S Blok3 , MJ Schuuring4 , H Bleijendaal1 , DAJ Dohmen5 , II Tulevski3 , GA Somsen3 , BJM Mulder1 , Y Pinto1 , BJ Bouma1 , I Isgum2 , MM Winter1 , 1Amsterdam UMC - Location Academic Medical Center - Amsterdam - Netherlands (The) , 2Amsterdam UMC, University of Amsterdam, Biomedical Engineering - Amsterdam - Netherlands (The) , 3Cardiology centre Netherlands - Amsterdam - Netherlands (The) , 4Haga Teaching Hospital, Cardiology - Den Haag - Netherlands (The) , 5Luscii - Amsterdam - Netherlands (The) ,


Citation: N/A

Background: The growing availability of mobile phones increases the popularity of portable telemonitoring devices. An atrial fibrillation diagnosis can be reached with a recording of 30s on such telemonitoring devices. However, current commercially available automatic algorithms still require approval by experts. 

Purpose: In this research we aimed to build an artificial intelligence (AI) algorithm to improve automatic distinction of atrial fibrillation (AF) from sinus rhythm (SR), to ultimately save time, costs, and to facilitate telemonitoring programs.

Methods: We developed a deep convolutional neural network (CNN), based on a residual neural network (ResNet), tailored to single-lead ECG analysis. The CNN was trained using publicly available single-lead ECGs from the 2017 PhysioNet/ Computing in Cardiology Challenge. This dataset consists of 60% SR, 9% AF, 30% alternative rhythm, and 1% noise ECGs. The 8528 available ECGs were divided into a training (90%) and validation set (10%) for model development and hyperparameter optimization. 

Results: The trained CNN was applied to an independent set containing single-lead ECGs of 600 patients equally divided into two groups: SR and AF. Both groups comprised of 300 unique ECGs (SR; 60% male, 63±11 years, AF; 38% male, 56±14 years). In distinguishing between AF and SR, the method achieved an accuracy of 0.92, an F1-score of 0.91, and area under the ROC-curve of 0.98.

Conclusion: The results demonstrate that distinguishing SR and AF by a fully automatic AI algorithm is feasible. This approach has the potential to reduce cost by minimizing expert supervision, especially when extending the algorithm to other heart rhythms, like premature atrial/ventricular contractions and atrial flutter.