Key result
GUARDIAN-P Risk Score predicts HHF and CV death with ~80% AUC.
Why the study?
Diabetes mellitus contributes majorly to adverse outcomes in HFpEF, motivating the development and external validation of a machine learning-based model to predict hospitalization for heart failure and cardiovascular death.
Does a machine learning-based random survival forest model accurately predict the composite outcome of hospitalization for heart failure and cardiovascular death in adult patients with coexisting diabetes mellitus and HFpEF?
Cohort (n=2,179)
Yes
Does a machine learning-based random survival forest model accurately predict the composite outcome of hospitalization for heart failure and cardiovascular death in adult patients with coexisting diabetes mellitus and HFpEF?
Effect estimate: AUC 79.8%
A 9-variable machine learning-based random survival forest model (GUARDIAN-P) accurately predicts the risk of heart failure hospitalization and cardiovascular death in patients with concurrent diabetes and HFpEF.
Substantial event rate signals high risk in diabetic HFpEF; leaves open whether the RSF model improves prospective risk stratification.
Background Diabetes mellitus (DM) is a major contributor to adverse outcomes in patients with heart failure with preserved ejection fraction (HFpEF). We aim to develop and externally validate a machine learning–based model using a random survival forest (RSF) approach for predicting the composite outcome of hospitalization for heart failure (HHF) and cardiovascular (CV) death in patients with DM and HFpEF. Methods This retrospective cohort study included 1,450 adult patients with coexisting DM and HFpEF identified from the National Taiwan University Hospital–Integrated Medical Database. An initial RSF model was trained using 27 clinical variables, and the top 9 predictors were selected to construct a parsimonious final model. Predictive performance was evaluated using area under the receiver operating characteristic curve (AUC), and external validation was conducted in an independent cohort (n = 729) from MacKay Memorial Hospital. Results Over a mean follow-up of 3.6 ± 3.0 years, 327 patients (22.6%) experienced the composite outcome. The final RSF model achieved an AUC of 88.2% in the training cohort and 79.8% in the validation cohort. The nine selected predictors were age, N-terminal pro-brain natriuretic peptide, serum albumin, fasting glucose, estimated glomerular filtration rate, uric acid, left atrial diameter, peripheral artery disease, and left ventricular ejection fraction. Risk increased progressively with the number of risk factors present. Conclusions The RSF-based model incorporating nine routinely available variables accurately predicts HHF and CV death in patients with DM and HFpEF. This tool may support personalized risk assessment and guide clinical decision-making.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2026) conducted a cohort in Diabetes mellitus and heart failure with preserved ejection fraction (n=2,179). GUARDIAN-P Risk Score (random survival forest model) was evaluated on Composite outcome of hospitalization for heart failure (HHF) and cardiovascular (CV) death (AUC 79.8%). The GUARDIAN-P Risk Score, a random survival forest model using nine variables, accurately predicted heart failure hospitalization and cardiovascular death with an AUC of 79.8% in external validation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: