Predicting Mortality After Percutaneous Coronary Intervention in a Multiethnic Southeast Asian Population: Insights...

Area of Science:

• Cardiology
• Medical Informatics
• Data Science

Background:

• Ischemic heart disease is a leading cause of death in Malaysia.
• Non-elective percutaneous coronary intervention (PCI) is common for high-risk acute coronary syndrome (ACS) patients.

Purpose of the Study:

• To evaluate and compare seven machine learning (ML) models for predicting mortality in ACS patients undergoing PCI.
• To assess model performance using nationwide registry data from 2007-2020.

Main Methods:

• Utilized nationwide registry data of 29,521 patients.
• Developed ML models in a training cohort and validated them externally on hospital-level (TEST1) and prospective temporal (TEST2) cohorts.
• Assessed model discrimination (ROC-AUC) and calibration for in-hospital, 30-day, and 1-year mortality.

Main Results:

• Models demonstrated strong discrimination for in-hospital mortality (ROC-AUC up to 0.943 in TEST1, 0.884 in TEST2).
• Discrimination for 30-day mortality ranged from 0.902-0.923 (TEST1) and 0.753-0.838 (TEST2).
• 1-year mortality prediction showed ROC-AUC from 0.833-0.859 (TEST1) and 0.750-0.801 (TEST2).
• Calibration was acceptable, and decision curve analysis confirmed clinical utility.
• Age, hemodynamic status, and renal function were consistently identified as key predictors across models.

Conclusions:

• Machine learning models show significant potential for predicting mortality in ACS patients undergoing PCI.
• These models can aid clinical decision-making and risk stratification.
• Age, hemodynamic status, and renal function are crucial factors for mortality prediction in this patient group.