Related Experiment Video
Updated: May 1, 2026

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
Derivation and validation of a prediction model for long-term mortality in patients with ST-segment elevation
Luis Ortega-Paz1, Claudio Laudani1,2, Salvatore Brugaletta3
1Division of Cardiolgy, University of Florida College of Medicine - Jacksonville, Jacksonville, Florida, USA.
Insights
A new PREDICT-STEMI score predicts long-term mortality in ST-elevation myocardial infarction (STEMI) patients after percutaneous coronary intervention (PCI). This simple tool aids in early risk stratification and clinical decision-making for STEMI patients.
Area of Science:
- Cardiology
- Clinical Prediction Models
- Public Health
Background:
- Limited models exist for predicting long-term mortality in ST-elevation myocardial infarction (STEMI) patients undergoing percutaneous coronary intervention (PCI).
- Developing a reliable predictive tool is crucial for risk stratification and clinical decision-making in this patient population.
Purpose of the Study:
- To derive and validate a predictive model for long-term mortality in patients with STEMI undergoing PCI.
- To develop a simple, accessible score for clinical use.
Main Methods:
- A total of 23,086 STEMI patients were included in the derivation cohort.
- Time-to-event regression analysis identified predictors of long-term mortality.
- The model was validated in two independent cohorts (n=1498 and n=1112).
Main Results:
- The PREDICT-STEMI score includes seven variables: age, diabetes, prior myocardial infarction, prior ischemic stroke/TIA, hemodynamic status, three-vessel disease, and mechanical circulatory support.
- The score demonstrated good predictive performance with a Concordance index of 0.81 in the derivation cohort and 0.81-0.84 in validation cohorts.
- A score of 60 was identified as the optimal cut-off, with higher scores indicating a sixfold increased risk of long-term mortality.
Conclusions:
- The PREDICT-STEMI score is a validated, simple tool for predicting long-term mortality in STEMI patients undergoing PCI.
- It facilitates early risk stratification, enabling informed clinical decision-making.
- This score can improve patient management and outcomes.
Background:
There are limited prediction models of long-term mortality for patients with ST-elevation myocardial infarction (STEMI) undergoing percutaneous coronary intervention (PCI). Against this background, we aimed to derive and validate a predictive model for long-term mortality in patients with STEMI undergoing PCI.
Methods:
A total of 23 086 patients from a STEMI network were included in the derivation cohort. Using time-to-event regression analysis, predictors of long-term mortality were identified and used to develop a score ranging from 0 to 206 points, with a score directly proportional to the probability of mortality. The predictive performance of this score was then validated in patients from the EXAMINATION-EXTEND study (n=1498) and Coronary Artery diSease Tracking registry (n=1112). An outcome-based cut-point optimisation analysis was performed to determine the best cut-off value in the derivation and validation cohorts.
Results:
The prediction model for long-term mortality in STEMI (PREDICT-STEMI) score comprised seven variables: age, diabetes mellitus, previous myocardial infarction, previous ischaemic stroke/transient ischaemic attack, haemodynamic status, three-vessel disease and mechanical circulatory support. The score showed a Concordance index for long-term mortality of 0.81 (95% CI 0.80 to 0.81) in the derivation and 0.81 (95% CI 0.78 to 0.84) and 0.84 (95% CI 0.81 to 0.87) in the validation cohorts, respectively. The optimal prediction model cut-off was 60 points; compared with those with a low score, patients with a high score had a sixfold increased risk of long-term mortality in both the derivation and validation cohorts.
Conclusions:
The PREDICT-STEMI score is a simple tool for predicting long-term mortality and facilitating early risk stratification and inform clinical decision-making.
Related Concept Videos
Acute Coronary Syndrome III: Diagnostic Studies
Acute Coronary Syndrome I: Introduction