Artificial intelligence applied to electrocardiogram to rule out acute myocardial infarction: the ROMIAE multicentre study
Authors' conclusion
In this multicentre prospective study, the AI-ECG demonstrated diagnostic accuracy and predictive power for AMI and 30 day MACE, which was similar to or better than that of traditional risk stratification methods and ED physicians.
Study context
- Population
- Adults presenting to the emergency department (ED) within 24 h of symptom onset concerning for acute myocardial infarction (AMI), Republic of Korea, March 2022 to October 20231,586 (18.6%) with AMI
- Participants
- 8,493 adults
- Exposure
- AI-ECG vs HEART score, GRACE 2.0 score, high-sensitivity troponin and Physician AMI score
- Outcome
- Diagnosis of AMI during index admission
- Follow-up
- Index admission
Methodological detailsmulticentre, 18 university-level teaching hospitals
- Multicentre
- 18 university-level teaching hospitals
Main finding
As reported in the abstract
AMI diagnosis
| Group | AUC |
|---|---|
| AI-ECG | 0.878 (95% CI, 0.868-0.888) |
| HEART score | 0.877 (95% CI, 0.869-0.886) |
AUC
AI-ECG0.878 (95% CI, 0.868-0.888)
HEART score0.877 (95% CI, 0.869-0.886)
Observational data: associations, not effects.
Secondary outcomes
| Outcome | AI-ECG | HEART score | Net reclassification improvement (95% CI) |
|---|---|---|---|
| 30-day MACE | |||
| AUC | 0.866 (95% CI, 0.856-0.877) | 0.858 (95% CI, 0.848-0.868) | |
| AMI discrimination with AI-ECG integrated vs HEART score alone | 19.6% (17.38–21.89) |
- AMI discrimination with AI-ECG integrated vs HEART score alone — C-index with AI-ECG integration
- 0.926 (95% CI, 0.919-0.933)
30-day major adverse cardiovascular event (MACE)
- AI-ECG performed comparably with HEART score
Original publication
Artificial intelligence applied to electrocardiogram to rule out acute myocardial infarction: the ROMIAE multicentre study. Eur Heart J. Published 24 February 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →