# Peak strain dispersion as a nonlinear mediator in HFpEF: Unraveling subtype-specific pathways via SHAP-augmented ensemble modeling

## TL;DR

This study identifies two distinct subtypes of heart failure with preserved ejection fraction (HFpEF) and shows that peak strain dispersion (PSD) plays a key role in mediating heart function differently in each group.

## Contribution

The study introduces a novel approach using SHAP-augmented machine learning to uncover subtype-specific pathways of PSD in HFpEF.

## Key findings

- Two distinct HFpEF subtypes were identified with different clinical and echocardiographic profiles.
- PSD was found to mediate effects on heart function differently in each subtype, with younger patients showing stronger cardiorenal interactions.
- Machine learning models demonstrated that PSD and its interactions are important predictors of myocardial work outcomes.

## Abstract

Heart failure with preserved ejection fraction (HFpEF) represents a heterogeneous syndrome with diverse pathophysiological mechanisms and limited therapeutic options. Peak strain dispersion (PSD) has emerged as a potential mediator in HFpEF pathophysiology. This study aimed to identify distinct HFpEF subtypes and investigate PSD’s subtype-specific mediating pathways.

This prospective single-center study included 150 HFpEF patients recruited from December 2023 to December 2024. Unsupervised K-means clustering was performed on the entire cohort to identify patient subtypes. For detailed analysis, rigorous data quality control was performed by removing cases with missing values in any of the 25 baseline features or outcome variables. Consequently, 84 patients with complete data were retained for analysis. Comprehensive clinical and echocardiographic data were collected, including PSD measured by speckle-tracking echocardiography and myocardial work parameters (global work waste and global work efficiency). Unsupervised K-means clustering was performed to identify distinct patient subtypes using eight key variables. Machine learning models with feature engineering (incorporating five clinically meaningful interaction terms: PSD_LVEF, age_HTN, eGFR_BNP, RWT_E/e’, and GLS_LVMI) were developed to predict myocardial work parameters and assess feature importance using SHAP (SHapley Additive exPlanations) analysis. Nonlinear mediation analysis was conducted within each subtype to evaluate the mediating pathways through which clinical factors influence myocardial work outcomes.

Two distinct HFpEF subtypes were identified: Cluster 0 characterized by younger age (58.6 ± 13.2 years), severe renal dysfunction (eGFR 12.8[8.9-19.9] mL/min/1.73m²), higher PSD (56.0[48.0-64.5] ms), and lower global work efficiency; and Cluster 1 characterized by older age (71.2 ± 9.7 years), preserved renal function (eGFR 104.0[78.5-126.0] mL/min/1.73m²), lower PSD (41.0[35.0-49.0] ms), and higher GWE. Machine learning models achieved moderate to good predictive performance (R² = 0.58-0.61 for GWE and GWW). SHAP analysis revealed that PSD was the most important predictor, with the PSD×LVEF interaction term showing prominent importance in GWE prediction. Nonlinear mediation analysis demonstrated striking subtype-specific differences in mediation patterns.In Cluster 0, eGFR showed a trend toward mediating its effects on GWW through PSD (indirect effect = 0.313), reflecting complex cardiorenal interactions in younger patients with severe renal disease. In contrast, Cluster 1 demonstrated significant mediation effects: BNP’s effect on GWW was significantly mediated through PSD (indirect effect = -0.4877, P < 0.05), and BNP’s effect on GWE was entirely mediated through PSD (indirect effect = 0.5389, P < 0.05).

This study identified two distinct HFpEF subtypes with fundamentally different pathophysiological mechanisms. Cluster 0 shows prominent PSD-mediated effects through cardiorenal interactions, while Cluster 1 demonstrates weaker PSD mediation, suggesting age-related mechanisms operate through pathways less dependent on myocardial mechanical dyssynchrony. These findings support HFpEF heterogeneity and highlight PSD as a valuable biomarker for subtype-specific risk stratification and therapeutic targeting.

We studied a challenging type of heart failure called heart failure with preserved ejection fraction, where the heart appears to pump normally but patients still experience symptoms like shortness of breath and fatigue. This condition affects millions of people worldwide, yet doctors struggle to treat it effectively because patients with the same diagnosis can have different underlying problems. We examined 150 patients and used computer analysis to identify groups. The first group consisted of younger patients with severe kidney disease and heart muscle coordination problems, driven by kidney-heart interactions. The second group included older patients with relatively healthy kidneys, suggesting different age-related mechanisms.Using intelligence techniques, we discovered that a measurement called peak strain dispersion—which reflects how well different parts of the heart muscle work together—plays a crucial role as a messenger between other health problems and heart function. Importantly, this measurement worked differently in each patient group, with younger patients showing strong coordination effects and older patients showing weaker effects. Our findings help explain why this type of heart failure is so difficult to treat and suggest that doctors should consider grouping patients differently when choosing treatments. This personalized approach could lead to better outcomes for patients suffering from this complex condition.