Related Experiment Video
Updated: Aug 31, 2025
Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
Machine learning model for predicting 1-year and 3-year all-cause mortality in ischemic heart failure patients
Anping Cai1, Rui Chen2, Chengcheng Pang3
1Department of Cardiology, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China.
Insights
Machine learning (ML) models show promise for predicting mortality in ischemic heart failure (HF) patients. These ML models perform comparably to existing risk scores, offering a potential new tool for clinical decision-making.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Ischemic heart failure (HF) prognosis prediction lacks specific machine learning (ML) models.
- The comparative performance of ML models against established metrics like the MAGGIC risk score and NT-proBNP for ischemic HF is unknown.
Purpose of the Study:
- To develop and evaluate ML models for predicting 1-year and 3-year all-cause mortality in ischemic HF patients.
- To compare the predictive performance of ML models against the MAGGIC risk score and NT-proBNP.
Main Methods:
- Utilized three ML algorithms with and without feature selection for model development.
- Performance was assessed using the area under the curve (AUC) via five-fold cross-validation.
- Model calibration was evaluated using the Brier score.
Main Results:
- Random forest with feature selection achieved the highest AUC (0.742) for 1-year mortality prediction.
- Support vector machine without feature selection yielded the highest AUC (0.732) for 3-year mortality prediction.
- ML models demonstrated comparable AUCs to the MAGGIC risk score and NT-proBNP for both 1-year and 3-year mortality predictions.
Conclusions:
- ML models exhibit good discrimination and calibration for predicting prognosis in ischemic HF.
- These ML models can serve as valuable decision-making tools for clinicians managing ischemic HF patients.
Objective:
Machine learning (ML) model has not been developed specifically for ischemic heart failure (HF) patients. Whether the performance of ML model is better than the MAGGIC risk score and NT-proBNP is unknown. The current study was to apply ML algorithm to build risk model for predicting 1-year and 3-year all-cause mortality in ischemic HF patient and to compare the performance of ML model with the MAGGIC risk score and NT-proBNP.
Method:
Three ML algorithms without and with feature selection were used for model exploration, and the performance was determined based on the area under the curve (AUC) in five-fold cross-validation. The best performing ML model was selected and compared with the MAGGIC risk score and NT-proBNP. The calibration of ML model was assessed by the Brier score.
Results:
Random forest with feature selection had the highest AUC (0.742 and 95% CI: 0.697-0.787) for predicting 1-year all-cause mortality, and support vector machine without feature selection had the highest AUC (0.732 and 95% CI: 0.694-0.707) for predicting 3-year all-cause mortality. When compared to the MAGGIC risk score and NT-proBNP, ML model had a comparable AUC for predicting 1-year (0.742 vs 0.714 vs 0.694) and 3-year all-cause mortality (0.732 vs 0.712 vs 0.682). Brier scores for predicting 1-year and 3-year all-cause mortality were 0.068 and 0.174, respectively.
Conclusion:
ML models predicted prognosis in ischemic HF with good discrimination and well calibration. These models may be used by clinicians as a decision-making tool to estimate the prognosis of ischemic HF patients.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
