Arrhythmias & electrophysiology
An artificial intelligence–based model for prediction of atrial fibrillation from single-lead sinus rhythm electrocardiograms facilitating screening
Authors' conclusion
An artificial intelligence-enabled network has the ability to predict AF from a sinus rhythm single-lead ECG. Performance improves with a wider age distribution.
Study context
- Population
- Patients aged ≥65 years in atrial fibrillation (AF) screening studies; prediction of paroxysmal AF from normal sinus rhythm single-lead ECG
- Participants
- 14,831 patients478,963 single-lead ECGs
- Comparison
- SAFER vs STROKESTOP I vs STROKESTOP II
- Outcome
- Accuracy (AUC) of artificial intelligence (AI)-based network to predict paroxysmal AF from a single timepoint sinus rhythm single-lead ECG
Methodological detailsconvolutional neural network, data from 3 AF screening studies
- Convolutional neural network
- Data from 3 AF screening studies
Performance
As reported in the abstract
Paroxysmal AF prediction (AUC)
| Test or model | AUC |
|---|---|
| SAFER | 0.80 (CI 0.78-0.83) |
| STROKESTOP I | 0.62 (CI 0.61-0.64) |
| STROKESTOP II | 0.62 (CI 0.58-0.65) |
AUC
SAFER0.80 (CI 0.78-0.83)
STROKESTOP I0.62 (CI 0.61-0.64)
STROKESTOP II0.62 (CI 0.58-0.65)
Original publication
An artificial intelligence–based model for prediction of atrial fibrillation from single-lead sinus rhythm electrocardiograms facilitating screening. Europace. Published 7 March 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →