HyPer-EP: Meta-Learning Hybrid Personalized Models for Cardiac Electrophysiology

TL;DR

This paper introduces a hybrid modeling framework combining physics-based models and neural networks, enhanced by meta-learning, to improve personalized cardiac electrophysiology models with better interpretability and efficiency.

Contribution

It proposes a novel hybrid modeling approach with meta-learning for separate identification of physics-based and neural components in personalized cardiac models.

Findings

Feasibility demonstrated with synthetic experiments.

Hybrid models outperform purely physics-based or neural models.

Meta-learning enables effective separation of model components.

Abstract

Personalized virtual heart models have demonstrated increasing potential for clinical use, although the estimation of their parameters given patient-specific data remain a challenge. Traditional physics-based modeling approaches are computationally costly and often neglect the inherent structural errors in these models due to model simplifications and assumptions. Modern deep learning approaches, on the other hand, rely heavily on data supervision and lacks interpretability. In this paper, we present a novel hybrid modeling framework to describe a personalized cardiac digital twin as a combination of a physics-based known expression augmented by neural network modeling of its unknown gap to reality. We then present a novel meta-learning framework to enable the separate identification of both the physics-based and neural components in the hybrid model. We demonstrate the feasibility and generality of this hybrid modeling framework with two examples of instantiations and their proof-of-concept in synthetic experiments.