Heart failure with preserved ejection fraction (HFpEF) in hypertrophic cardiomyopathy (HCM) has been identified as a major independent predictor of adverse outcomes in a new large-scale machine learning-powered study, highlighting an under-recognized high-risk patient subgroup.
HCM is a genetic heart disease characterized by abnormal thickening of the myocardium and has long been associated with a variable clinical course. Some patients remain stable, while others experience progressive heart failure, arrhythmias, and sudden cardiac death.
HFpEF in HCM is increasingly recognized as a common but poorly understood phenotype, prompting efforts to refine risk stratification.
HFpEF in HCM suggests increased risk
In this multicenter retrospective cohort study of 2,802 HCM patients, nearly half (47.8%) were found to have HFpEF. Even after propensity score matching to balance baseline characteristics, HFpEF in HCM remained strongly associated with worse event-free survival (hazard ratio) [HR]: 2.612; 95% confidence interval [CI]: 2.188–3.118; p<0.001).
Further stratification using H₂FPEF score revealed a clear gradient in risk. Patients classified as high risk had significantly poorer outcomes (HR: 2.925; 95% CI: 2.210-3.701; p<0.001), reinforcing the heterogeneity within this population.
Machine learning enhances risk prediction
To improve individual predictions, researchers developed four machine learning models.
Among these, the random forest model achieved the highest prediction accuracy (area under the curve: 0.856). Importantly, model interpretability analysis identified HFpEF status and B-type natriuretic peptide (BNP) levels as the most influential predictors of adverse outcomes.
A nonlinear relationship between BNP and risk was also observed, with higher biomarker concentrations accelerating event rates. This finding suggests that traditional linear risk models may underestimate the risk of patients with significantly elevated BNP levels.
Implications for precision cardiology
These findings position HFpEF in HCM as a common and clinically important phenotype that requires close attention in daily practice. This study provides a more nuanced framework for risk stratification by integrating clinical scoring systems, biomarker analysis, and machine learning.
Because this analysis was retrospective and conducted across tertiary centers, the authors noted that external validation is needed before widespread clinical adoption.
Nevertheless, this result highlights the potential of data-driven approaches to improve prognostic assessment and guide individualized management strategies in HCM.
As precision cardiology continues to evolve, identifying high-risk subgroups such as HFpEF in HCM may be key to improving long-term outcomes.
reference
Zhang W et al. Machine learning-based risk stratification identifies heart failure with preserved ejection fraction as an independent predictor of adverse outcome in hypertrophic cardiomyopathy. Sci Rep. 2026;DOI:10.1038/s41598-026-46573-z.
Featured image: Dai Yim by Adobe Stock
