Key result
Machine learning models demonstrated comparable discrimination to the MAGGIC risk score and NT-proBNP for predicting 1-year (AUC 0.742) and 3-year (AUC 0.732) mortality in ischemic heart failure.
Why the study?
Machine learning models have not been developed specifically for ischemic HF patients, and whether their predictive performance exceeds the MAGGIC risk score and NT-proBNP is unknown.
Do machine learning models improve the prediction of 1-year and 3-year all-cause mortality compared to the MAGGIC risk score and NT-proBNP in ischemic heart failure patients?
Observational
Do machine learning models improve the prediction of 1-year and 3-year all-cause mortality compared to the MAGGIC risk score and NT-proBNP in ischemic heart failure patients?
Effect estimate: AUC 0.742 (95% CI 0.697-0.787)
Machine learning models provide good discrimination and calibration for predicting 1-year and 3-year mortality in ischemic heart failure, performing comparably to established risk scores like MAGGIC and NT-proBNP.
ML risk models for ischemic HF mortality warrant prospective validation before use; leaves open superiority over MAGGIC or NT-proBNP.
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.
No takes yet. Share an insight, caveat, or question.
Cai et al. (2022) conducted an observational in Ischemic heart failure. Machine learning models (Random forest, Support vector machine) vs. MAGGIC risk score and NT-proBNP was evaluated on 1-year all-cause mortality prediction (AUC 0.742, 95% CI 0.697-0.787). Machine learning models demonstrated comparable discrimination to the MAGGIC risk score and NT-proBNP for predicting 1-year (AUC 0.742) and 3-year (AUC 0.732) mortality in ischemic heart failure.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: