Physiology-Informed Digital Twin-AI Framework Predicts Pacing Therapy Response in HFpEF

Authors:
Preprint
Publisher website
Google Scholar
Abstract
Background and Aims: Heart failure with preserved ejection fraction (HFpEF) exhibits profound phenotypic heterogeneity, which likely contributes to variable therapeutic response. We developed a physiology-informed digital twin–AI framework to predict individual hemodynamic and myocardial energetic responses to accelerated atrial pacing and tested whether simulated physiologic response corresponds to responders in the myPACE randomized clinical trial. Methods: Patient-specific digital twins were constructed for 146 HFpEF patients and used to train a variational autoencoder that generated a virtual HFpEF population (n = 25,000). The model simulated pacing-induced changes in left atrial pressure (LAP), systolic blood pressure (SBP), cardiac output (CO), and cardiac efficiency (CE; derived from myocardial oxygen-demand estimates). These simulations served as labels to train classifiers based on clinical variables available in myPACE, allowing us to examine associations with clinical end points and test a hypothesized relationship between CE and treatment response. Results: Simulations revealed heterogeneous physiological responses, with 95.6% of virtual patients showing reduced LAP, 47.0% an SBP reduction greater than 8.5 mmHg, 93.8% increased CO, and 36.1% improved CE. Classifiers reproduced these patterns with high fidelity. In the myPACE trial, patients classified as having CE improvement or a larger SBP reduction experienced significantly greater 1-month improvements in quality-of-life scores and larger NT-proBNP reductions. Conclusions: A physiology-informed digital twin–AI framework can predict hemodynamic and energetic responses corresponding to clinical benefit in HFpEF patients receiving accelerated atrial pacing. CE improvement functioned as a mechanistic indicator, while SBP reduction served as an accessible clinical correlate, offering mechanistically grounded guidance for patient-specific pacing and motivating prospective validation. Graphical

This publication has 60 references indexed in Scilit: