Mortality score in chronic coronary syndrome: prediction model from the ISCHEMIA trial
An erratum to this article was published (Eur J Prev Cardiol, 5 Aug 2026 ↗)
Authors' conclusion
The ISCHEMIA-PREDICT score provides a practical tool to stratify cardiovascular and all-cause mortality among CCS patients, enabling risk-guided clinical decision-making.
Study context
- Population
- Patients with chronic coronary syndromes (CCS)validation registry n = 23,303
- Participants
- 5,179 patients
- Outcome
- Model discrimination for CV and all-cause death
- Follow-up
- Median 3.2 years
Methodological detailsmachine learning analysis of the ISCHEMIA randomised controlled trial, external validation in multicentre registry
- Machine learning analysis of the ISCHEMIA randomised controlled trial
- External validation in multicentre registry
Performance
As reported in the abstract
Model discrimination (ISCHEMIA-PREDICT: eGFR, exercise-induced ST depression, exercise duration, SBP, multivessel CAD, invasive vs conservative strategy)
AUC, CV mortality
0.94
95% CI 0.92–0.96
AUC, all-cause mortality (0.91-0.96)
0.94
Further findings
| Outcome | Highest quartile | Lowest quartile | HR (CI) | |
|---|---|---|---|---|
| CV mortality, highestvs lowest quartileDifference 6.0% | 7.10 % | 1.10% | 6.65 (3.15–14.03) | |
| 0.050.21520Hazard ratio (log scale) |
All-cause mortality discrimination, external registry validation · median follow-up 7.4 years
- AUC (0.81-0.84)
- 0.82
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Mortality score in chronic coronary syndrome: prediction model from the ISCHEMIA trial. Eur J Prev Cardiol. Published 11 March 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →