Key result
Machine learning predicts acute heart failure in-hospital mortality comparably to the GWTG-HF score.
Why the study?
The performance of the widely used GWTG-HF risk score for in-hospital mortality in AHF may vary across populations, and prospective validation data from Southeast Asia were scarce.
Do explainable machine-learning models improve the prediction of all-cause in-hospital mortality compared to the GWTG-HF risk score in patients hospitalized with acute heart failure in Vietnam?
Cohort (n=572)
No
Do explainable machine-learning models improve the prediction of all-cause in-hospital mortality compared to the GWTG-HF risk score in patients hospitalized with acute heart failure in Vietnam?
In a prospective Vietnamese cohort of patients with acute heart failure, explainable machine learning led by random forest achieved good discrimination for in-hospital mortality (AUC 0.846) but did not significantly outperform the traditional GWTG-HF risk score (AUC 0.817) and required probability recalibration.
Answers are grounded in this paper and cite their sources.
ML models matched GWTG-HF discrimination without outperforming it; leaves open whether explainable ML improves acute HF risk stratification.
Background Accurate risk stratification is essential in acute heart failure (AHF), which carries substantial in-hospital mortality. The Get With The Guidelines–Heart Failure (GWTG-HF) score is widely used, but its performance may vary across populations, and prospective data from Southeast Asia are scarce. We developed and internally validated explainable machine-learning (ML) models for in-hospital mortality in a Vietnamese AHF cohort and compared them with the GWTG-HF score. Methods We prospectively enrolled 572 consecutive patients admitted with AHF (October 2024–June 2025). Missing data were imputed with a random forest–based algorithm, and class imbalance handled with SMOTE within training folds. Six algorithms (logistic regression, elastic net, random forest, XGBoost, LightGBM, CatBoost) were trained with stratified cross-validation, with optimism correction, and evaluated on an independent 25% test set. We assessed discrimination (ROC-AUC, PR-AUC), calibration (calibration slope/intercept, Brier and scaled Brier scores), classification, and clinical utility (decision-curve analysis); thresholds were derived from training data only. Pairwise AUC comparisons used the DeLong test, and interpretation used SHAP. Reporting followed TRIPOD + AI. Results Fifty-three patients (9.3%) died in hospital. Random forest had the highest discrimination (AUC 0.846, 95% CI 0.757–0.922), followed by the GWTG-HF score (0.817), logistic regression (0.795), elastic net (0.794), CatBoost (0.786), XGBoost (0.763), and LightGBM (0.694). No ML model significantly outperformed the GWTG-HF score (all DeLong p > 0.05), a comparison limited by only 13 test-set events. Although CatBoost had the numerically lowest Brier score (0.085), scaled Brier scores were low for all models and calibration intercepts were uniformly negative, indicating over-estimation of risk from aggressive imbalance correction; predicted probabilities therefore require recalibration. SHAP identified respiratory failure, NT-proBNP, high-sensitivity troponin I (risk-increasing) and an ADHF phenotype and left ventricular dilation (associated with lower predicted risk) as the most influential features. Conclusions Explainable ML, led by random forest, achieved good discrimination but did not significantly outperform the GWTG-HF score, most plausibly reflecting limited statistical power rather than true equivalence. With miscalibrated probabilities requiring recalibration, explainable ML is best viewed as a complementary risk-ranking tool; external, multicenter, and temporal validation are required before clinical use.
No takes yet. Share an insight, caveat, or question.
Hoang et al. (2026) conducted a cohort in Acute heart failure (n=572). Explainable machine learning models (Random Forest) vs. GWTG-HF risk score was evaluated on All-cause in-hospital mortality prediction (ROC-AUC) (AUC 0.846, 95% CI 0.757-0.922, p=0.713). Random forest machine learning achieved an AUC of 0.846 for predicting in-hospital mortality in acute heart failure, comparable to the GWTG-HF score.
Synapse has enriched 10 related papers. Consider them for comparative context: