Patient-Specific Myocardial Infarction Risk Thresholds From AI-Enabled Coronary Plaque Analysis
An erratum to this article was published (Circ Cardiovasc Imaging, Jul 2026 ↗)
Performance · MI by total plaque volume percentileResult — go to the resultHazard ratio 2.65 95% CI 1.47–4.78Authors' conclusion
Per-patient age- and sex-specific distributions for deep learning-based coronary plaque volumes are strongly predictive of myocardial infarction, with the highest risk seen in patients with coronary plaque volumes in the ≥75th percentile.
Study context
- Population
- Patients undergoing coronary CT angiography; reference distributions from patients with stable CAD (5 cohorts)external sample n=1847
- Participants
- 2,803 patients
- Comparison
- ≥75th vs <50th percentile of age- and sex-specific total plaque volume
- Outcome
- MI
Methodological detailsinternational, deep learning-based plaque quantification, external validation
- International
- Deep learning-based plaque quantification
- External validation
Performance
MI by total plaque volume percentile
Hazard ratio
2.65
95% CI 1.47–4.78
P = 0.001
≥75th percentilevs <50th percentile
HR 2.65 (95% CI 1.47–4.78); P = 0.001
As reported in the abstract
Further findings
MI, multivariable-adjusted (clinical characteristics, CAC, stenosis, plaque volume)
- Adjusted HRs for ≥75th percentile of total plaque volume
- 2.38 to 2.50
- Similar relationships for most plaque volumes
Plaque volume distribution
- Plaque volumes increased with age and were higher in male patients
- Reference distributions from 956 patients
Original publication
Patient-Specific Myocardial Infarction Risk Thresholds From AI-Enabled Coronary Plaque Analysis. Circ Cardiovasc Imaging. Published 30 September 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →