Key result
A gradient boosting machine model accurately predicted incident heart failure risk in patients with hypertension, achieving an overall accuracy of 0.731 and an AUC of 0.763 (95% CI 0.676-0.840).
Why the study?
Patients with hypertension are particularly susceptible to developing heart failure, making timely identification and predictive assessment of HF risk clinically important.
Does a GBM-based machine learning model accurately predict incident heart failure in patients with hypertension?
Observational (n=324)
Does a GBM-based machine learning model accurately predict incident heart failure in patients with hypertension?
Effect estimate: AUC 0.763 (95% CI 0.676-0.840)
A gradient boosting machine learning model can predict incident heart failure in hypertensive patients with moderate accuracy and good interpretability.
Should not yet change HF risk stratification in hypertension; leaves open the need for external validation of ML models.
Background: Heart failure (HF) is a heterogeneous syndrome affecting over 60 million individuals globally. Patients with hypertension are particularly susceptible to developing HF. Therefore, timely identification and predictive assessment of HF risk have significant clinical implications in this population. Thus, this study aimed to develop a new interpretable machine learning (ML) model for HF prediction. Methods: Using data from the Systolic Blood Pressure Intervention Trial (SPRINT), a random under-sampling technique was applied to address class imbalance in the target variable, achieving a 1:1 ratio between positive and negative samples. By randomly matching 162 individuals without HF events to those with events, a balanced dataset comprising 324 participants was constructed. The test set comprised 40% of the total dataset to ensure a robust evaluation of model performance. Seven ML algorithms, including support vector machine (SVM), adaptive boosting (Adaboost), naïve Bayes (NB), logistic regression (LR), gradient boosting machine (GBM), random forest (RF), and multilayer perceptron (MLP), were employed to construct the predictive models. Model performance was evaluated using the area under the curve (AUC), decision curve analysis (DCA), calibration curves, and other metrics. The SHapley Additive exPlanations (SHAP) approach was employed to rank feature significance and provide interpretability for the final model. Results: Over a median follow-up of 3.88years, 162 patients (1.8%) developed incident HF. Among the seven ML models, GBM demonstrated the best performance. A total of 14 features were retained after the least absolute shrinkage and selection operator (LASSO) selection. The final model exhibited robust predictive capability for identifying HF risk, with an overall accuracy of 0.731, a precision of 0.770, and an AUC (95% confidence interval (CI)) of 0.763 (0.676-0.840). Conclusion: The GBM-based explainable prediction model demonstrated robust performance in predicting HF risk among patients with hypertension.
No takes yet. Share an insight, caveat, or question.
Han et al. (2026) conducted an observational in Hypertension (n=324). Gradient boosting machine (GBM) model vs. Other machine learning models was evaluated on Incident heart failure prediction (AUC 0.763, 95% CI 0.676-0.840). A gradient boosting machine model accurately predicted incident heart failure risk in patients with hypertension, achieving an overall accuracy of 0.731 and an AUC of 0.763 (95% CI 0.676-0.840).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: