Key result
Echo-based ensemble machine learning outperforms MAGGIC score for predicting 3-year mortality with ~0.86 AUROC.
Why the study?
Current machine learning algorithms for HFrEF do not include comprehensive echocardiographic features or predict adverse kidney outcomes.
Does an Ensemble machine learning model improve the prediction of 3-year mortality, MACE, and MAKE in patients with HFrEF compared to traditional risk scores?
Cohort (n=1,732)
Yes
Does an Ensemble machine learning model improve the prediction of 3-year mortality, MACE, and MAKE in patients with HFrEF compared to traditional risk scores?
Answers are grounded in this paper and cite their sources.
Machine learning models incorporating comprehensive clinical and echocardiographic features significantly improve the risk prediction of mortality and major cardiorenal events in HFrEF patients compared to traditional scoring systems.
Background: Heart failure with reduced ejection fraction (HFrEF) links to adverse kidney and cardiovascular events. However, current machine learning (ML)-based algorithms do not include comprehensive echocardiographic features or predict adverse kidney outcomes. Methods: We built ML models to predict 3-year all-cause mortality, major adverse cardiovascular events (MACE), and major adverse kidney events (MAKE) in retrospective HFrEF cohorts. Models were developed from 1,486 patients at Taipei Veterans General Hospital during 2011-2018 and externally validated in 246 patients from the heart-failure-post-acute-care program at Taichung Veterans General Hospital during 2020-2023. Model performance was compared to the traditional Meta-Analysis Global Group in Chronic Heart Failure score (MAGGIC), Logistic Regression (LR), and Kidney-Failure-Risk-Equation (KFRE). Results: For mortality, Ensemble had the highest area under receiver-operating-characteristic curve (AUROC, 0.863; 95% confidence interval [CI], 0.814-0.913; p < 0.001), outperforming MAGGIC (AUROC, 0.741; 95% CI, 0.673-0.810) with net reclassification index (NRI) of 0.294 (95% CI, 0.147-0.440; p = 0.001). For MACE, Ensemble (AUROC, 0.816; 95% CI, 0.769-0.864; p < 0.001) surpassed LR (AUROC, 0.734; 95% CI, 0.677-0.791). For MAKE, Ensemble (AUROC, 0.858; 95% CI, 0.806-0.910; p < 0.001) exceeded KFRE (AUROC, 0.647; 95% CI, 0.560-0.735) with NRI of 0.267 (95% CI, 0.133-0.396; p < 0.001). External validation confirmed good Ensemble discrimination (AUROCs of 0.803, 0.808, and 0.859 for mortality, MACE, and MAKE, respectively). An online tool (https://vghhfrefai.com/) was created for application. Conclusion: Ensemble ML models with detailed clinical and echocardiographic features surpassed conventional risk scores, enabling early detection of major adverse cardiorenal events among HFrEF.
No takes yet. Share an insight, caveat, or question.
Lai et al. (2026) conducted a cohort in Heart failure with reduced ejection fraction (n=1,732). Ensemble machine learning model (incorporating clinical and echocardiographic features) vs. Traditional risk models (MAGGIC score, KFRE, Logistic Regression) was evaluated on Prediction of 3-year all-cause mortality (AUROC) (AUROC 0.863, 95% CI 0.814-0.913, p=<0.001). An ensemble machine learning model incorporating detailed echocardiographic features outperformed the traditional MAGGIC score in predicting 3-year all-cause mortality (AUROC 0.863 vs 0.741).
Synapse has enriched 10 related papers. Consider them for comparative context: