Related Experiment Video
Updated: Jun 19, 2026
An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Development and validation of an interpretable machine learning model for predicting 5-year major adverse
Zhongxing Jiang1, Haofeng Zhou2,3, Yindu Liu4
1Department of Cardiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, 106 Zhongshan Second Road, Yuexiu District, Guangzhou, Guangdong Province, China.
Insights
Machine learning models can predict 5-year major adverse cardiovascular events (MACE) in hospitalized coronary artery disease (CAD) patients. The random survival forest model shows promise for personalized risk stratification and secondary prevention strategies.
Area of Science:
- Cardiology
- Machine Learning
- Predictive Analytics
Background:
- Coronary artery disease (CAD) is a leading cause of cardiovascular mortality globally.
- Accurate prognosis for CAD patients is crucial for effective clinical management.
- This study focuses on developing interpretable machine learning (ML) models for predicting 5-year MACE in hospitalized CAD patients.
Purpose of the Study:
- To develop and validate interpretable ML models for predicting 5-year MACE in hospitalized CAD patients.
- To identify key predictors of MACE using LASSO regression.
- To assess the clinical utility and interpretability of ML models for risk stratification.
Main Methods:
- A prospective cohort of 705 CAD patients was used, divided into training and validation sets.
- Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed for predictor selection.
- Four survival-based ML models were developed and evaluated using discrimination, calibration, and decision curve analysis, with SHAP analysis for interpretability.
Main Results:
- The study included 705 hospitalized CAD patients; 31.3% experienced MACE within 5 years.
- Eleven key predictors were identified, including LVEF, NT-proBNP, nitrate use, CAD duration, depressive symptoms, and age.
- The Random Survival Forest (RSF) model demonstrated strong performance (C-index 0.804 training, 0.710 validation) and clinical utility, with LVEF, age, and diseased vessels being most impactful.
Conclusions:
- The RSF model shows favorable discrimination, calibration, and clinical utility for predicting 5-year MACE in hospitalized CAD patients.
- Interpretable ML models, like RSF, can aid in individualized risk stratification for CAD patients.
- These ML approaches may enhance secondary prevention strategies for improved patient outcomes.
Background:
Coronary artery disease (CAD) remains a major contributor to global cardiovascular mortality and accurate prognosis is critical for guiding clinical decision-making. This study aimed to develop and validate interpretable machine learning (ML) models for predicting 5-year major adverse cardiovascular events (MACE) in hospitalized CAD patients.
Methods:
A prospective cohort of 705 CAD patients was included and randomly divided into training (n = 494) and validation (n = 211) sets. Key predictors were selected using least absolute shrinkage and selection operator (LASSO) regression. Four survival-based models were developed, and model performance was assessed using discrimination, calibration, and decision curve analysis. Shapley Additive Explanations (SHAP) analysis was applied to enhance model interpretability.
Results:
A total of 705 hospitalized CAD patients were included (mean age 63.2 years; 72.5% men), of whom 221 (31.3%) developed MACEs during the 5-year follow-up. LASSO regression revealed 11 key predictors, including left ventricular ejection fraction (LVEF), N-terminal pro-B-type natriuretic peptide (NT-proBNP) level, nitrate use, CAD duration, depressive symptoms, and age. Among the four models, the random survival forest (RSF) model showed favourable discrimination performance, with C-index of 0.804 (95% CI: 0.770-0.837) in the training cohort and 0.710 (95% CI: 0.650-0.768) in the validation cohort. The RSF model also showed acceptable calibration, achieving the lowest Brier score in the validation cohort. Decision curve analysis (DCA) demonstrated that the RSF model provided potential clinical benefit over the treat-all and treat-none strategies across a wide range of risk thresholds. SHAP analysis revealed that the LVEF, age, and number of diseased vessels were the most important predictors of 5-year MACEs.
Conclusions:
The RSF model demonstrated relatively favourable discrimination, calibration, and clinical utility for predicting 5-year MACEs in hospitalized CAD patients. These findings suggest that ML-based approaches may assist in individualized risk stratification and guide secondary prevention strategies.