Arrhythmias & electrophysiologyDiagnostic or prognostic study
AI-ECG Detection of Structural Heart Disease in the Community Setting
- Diagnostic accuracy study
- external validation
- community-based
- propensity matching
Authors' conclusion
In a community-dwelling population with lower disease prevalence and milder phenotypes, AI-ECG performance was attenuated relative to hospital-based cohorts, driven by differences in disease spectrum.
Study context
- Population
- Community-dwelling individuals aged 65 to 85 years undergoing in-home ECG and transthoracic echocardiography2,402 analysed
- Participants
- 3,000 individuals
- Comparison
- AI-ECG performance in community vs hospital-based cohorts
- PREVUE-VALVEn = 2,402
- Outcome
- Detection of structural heart disease (SHD) by AI-ECG: AUC and predictive value
Performance
As reported in the abstract
SHD detection (AUC)
| Test or model | AUC | Structural heart disease (SHD) prevalence |
|---|---|---|
| PREVUE-VALVE | 71% (95% CI: 66%-76%) | 8% |
| Hospital-based | 83% (95% CI: 82%-83%) | 43% |
Further findings
| Outcome | Abnormal ECG | Impaired health status |
|---|---|---|
| SHD detection (AUC), PREVUE-VALVE subgroups | ||
| AUC | 79% (95% CI: 75%-83%) | 76% (95% CI: 70%-82%) |
Original publication
AI-ECG Detection of Structural Heart Disease in the Community Setting. J Am Coll Cardiol. Published 18 August 2026. doi:10.1016/j.jacc.2026.06.013
Summarised from the published abstract; every number is checked against it