Arrhythmias & electrophysiology
Single-lead electrocardiogram Artificial Intelligence model with risk factors detects atrial fibrillation during sinus rhythm
Authors' conclusion
An AI model using a single-lead SR ECG and six risk factors can identify patients with concurrent AF with similar accuracy as a 12-lead ECG-AI model.
Study context
- Population
- Atrial fibrillation (AF) patients in sinus rhythm (SR) around the time of diagnosis and age- and sex-matched controls13,479 AF + 53,916 control electrocardiogram (ECGs)
- Comparison
- Single-lead ECG AI model with or without risk factors vs 12-lead ECG AI model
- Outcome
- Detection of AF from SR ECG (AUC)
Methodological detailsretrospective, age- and sex-matched controls
- Retrospective
- Age- and sex-matched controls
Performance
As reported in the abstract
AF detection
| Test or model | AUC |
|---|---|
| Single-lead model | 0.74 |
| Single-lead model + 6 risk factors | 0.76 |
AUC
Single-lead model0.74
Single-lead model + 6 risk factors0.76
Further findings
Model bias by age and sex
- Results stable for both sexes, over ages 40 to 90 years
Risk factors needed
- 6 of 17 clinical variables sufficient for optimal accuracy
Original publication
Single-lead electrocardiogram Artificial Intelligence model with risk factors detects atrial fibrillation during sinus rhythm. Europace. Published 11 December 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →