Coronary disease & ACSCohort study
AI-Enhanced Electrocardiogram for Detection of Occlusive Myocardial Infarction in High-Risk Non–ST-Segment Elevation Acute Coronary Syndrome
- Retrospective analysis of consecutive adults undergoing emergent invasive coronary angiography (ICA), evaluating an AI-ECG model validated against ICA findings
- retrospectively analyzed
- investigational AI-ECG model (Queen of Hearts, Powerful Medical)
Authors' conclusion
In high-risk NSTE-ACS, AI-ECG improved rule in accuracy for OMI, potentially enhancing early identification of patients requiring urgent ICA. However, rule out performance from initial ECG alone was limited, supporting the need for serial ECGs and clinical judgment.
Study context
- Population
- Consecutive adults undergoing emergent ICA under the institutional level 2 protocol for suspected high-risk NSTE-ACS (2022–2024); patients with ST-elevation myocardial infarction excludedOcclusive myocardial infarction (OMI) present in 129 (58%)
- Participants
- 224 adults
- Exposure
- AI-ECG model for detecting OMI using invasive coronary angiography (ICA) as the reference
Main finding
As reported in the abstract
AI-ECG classification of OMI · initial ECG
OMI patients identified as OMI by AI-ECG
75 (58%)
Patients classified as OMI overall
96 patients (43%)
Observational data: associations, not effects.
Further findings
| Outcome | AI-ECG | ICA | P value |
|---|---|---|---|
| Rule in performance · initial ECG | |||
| specificity | 78% (95% CI: 68%-86%) | Not reported in the abstract | |
| positive predictive value | 78% (95% CI: 69%-86%) | Not reported in the abstract | |
| Rule out performance · initial ECG | |||
| sensitivity | 58% (95% CI: 49%-66%) | Not reported in the abstract | |
| negative predictive value | 57% (95% CI: 48%-66%) | Not reported in the abstract | |
| False positives, AI-augmented triage vs standard of care | P < 0.001 |
- False positives, AI-augmented triage vs standard of care: standard of care 42%
- False positives, AI-augmented triage vs standard of care: AI-augmented triage approach 22%
- False positives, AI-augmented triage vs standard of care: false positives reduced from 42% to 22% with AI-augmented triage
False negatives with serial ECGs
- Serial ECGs reduced false negatives
- from 42% to 34%
Original publication
AI-Enhanced Electrocardiogram for Detection of Occlusive Myocardial Infarction in High-Risk Non–ST-Segment Elevation Acute Coronary Syndrome. JACC Adv. Published 25 March 2026. doi:10.1016/j.jacadv.2026.102663
Summarised from the published abstract; every number is checked against it