Predicting Intramyocardial Hemorrhage Before Reperfusion in STEMI Patients With Intrinsically Explainable Artificial Intelligence
Authors' conclusion
Explainable artificial intelligence enabled rapid integration of clinical parameters from cardiac catheterization procedures to accurately predict IMH in STEMI before revascularization. The proposed approach could guide clinical decisions in real-time. This could inform future strategies aimed at reducing the incidence of IMH.
Study context
- Population
- STEMI patients undergoing emergency coronary angiographySTEMI patients enrolled between June 2023 and December 2024 · model development 252 · validation 36
- Participants
- 288 patientsEvents: 142/288
- Predictors
- 3-variable model: presence of coronary collaterals, degree of coronary artery occlusion, and sum ST-score (Superposable Neural Network informing a point-based scoring model)
- Predicted outcome
- Intramyocardial hemorrhage (IMH), identified by cardiac magnetic resonance imaging 48 to 72 hours post-percutaneous coronary intervention
Model performance
As reported in the abstract
before reperfusion
Accuracy
84.9%
Sensitivity
82.3%
Specificity
87.3%
Further findings
Intramyocardial hemorrhage (IMH), validation cohort
- Accuracy
- 83.3%
- Sensitivity
- 81.3%
- Specificity
- 85%
Coronary collaterals and total occlusion
- Coronary collaterals present
- 144/288
- Total occlusion
- 131/288
Sum ST-score
- Sum ST-score substantially higher in IMH-positive than IMH-negative patients
Original publication
Predicting Intramyocardial Hemorrhage Before Reperfusion in STEMI Patients With Intrinsically Explainable Artificial Intelligence. JACC Adv. Published 11 June 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →