Coronary disease & ACSDiagnostic or prognostic study
Sex-Consistent Performance of an AI-Enabled ECG for Acute Myocardial Infarction
- prospective external validation study
- multicenter
- 18 centers in South Korea
- emergency department cohort
- prespecified risk thresholds
- sex-stratified analyses
- prespecified subgroup analyses
Authors' conclusion
In a prospective, multicenter emergency department cohort, AI-ECG demonstrated sex-consistent diagnostic performance and preserved rule-out safety for AMI. Further validation and implementation studies are warranted. (ROMIAE [Rule-Out Acute Myocardial Infarction Using Artificial Intelligence Electrocardiogram Analysis] Trial; NCT05435391).
Study context
- Population
- Adults with suspected acute myocardial infarction (AMI) presenting to emergency departmentspatients, 3,186 were women · women 3,186
- Participants
- 8,493 adults
- Comparison
- AI-ECG analysis of initial ECGs for AMI, sex-stratified
- womenn = 3,186
Performance
As reported in the abstract
women
0.875
area under the receiver-operating characteristic curve · 95% CI 0.853–0.896
men
0.871
area under the receiver-operating characteristic curve · 95% CI 0.858–0.883
Further findings
| Outcome | women | men |
|---|---|---|
| Rule-out sensitivity at the prespecified low-risk cutoff | sensitivity 98.8% (95% CI 97.0–99.5) | sensitivity 99.8% (95% CI 99.4–100.0) |
| Negative predictive value at the prespecified low-risk cutoff | negative predictive value 99.2% (95% CI 97.9–99.7) | negative predictive value 99.1% (95% CI 96.7–99.7) |
Missed AMI rate at the prespecified low-risk cutoff
- Missed AMI rates in both sexes
- <1%
Performance across ST-segment elevation and non-ST-segment elevation myocardial infarction
- Performance remained stable across ST-segment elevation and non-ST-segment elevation myocardial infarction, without degradation in women
Original publication
Summarised from the published abstract; every number is checked against it