Predicting Mortality After Percutaneous Coronary Intervention in a Multiethnic Southeast Asian Population: Insights
Yih Miin Liew1, Yin Kia Chiam2, Pei Ling Ngo3
1Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, 50603, Malaysia. liewym@um.edu.my.
Insights
Machine learning models accurately predict mortality in acute coronary syndrome patients undergoing percutaneous coronary intervention. Key predictors include age, hemodynamic status, and renal function for improved patient outcomes.
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.
Abstract:
Ischemic heart disease remains a major contributor to mortality in Malaysia, with non-elective percutaneous coronary intervention (PCI) frequently performed in high-risk acute coronary syndrome (ACS) patients. Using nationwide registry data (2007-2020), we evaluated 29,521 patients and compared seven machine learning (ML) models for predicting in-hospital, 30-day, and 1-year mortality. Models were developed in a training cohort and externally validated using hospital-level (TEST1) and prospective temporal (TEST2) cohorts. After logistic recalibration, discrimination for in-hospital mortality ranged from 0.927 to 0.943 (TEST1) and 0.865-0.884 (TEST2). For 30-day mortality, ROC-AUC ranged from 0.902 to 0.923 (TEST1) and 0.753-0.838 (TEST2), and for 1-year mortality from 0.833 to 0.859 (TEST1) and 0.750-0.801 (TEST2). Calibration remained acceptable, and decision curve analysis demonstrated positive net benefit across clinically relevant thresholds. Cross-model stability analysis consistently identified age, haemodynamic status, and renal function as key predictors.
