CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations

2026-06-05

AI Summary

Personalized virtual heart simulation faces significant challenges due to high computational costs and catastrophic forgetting, hindering its ability to continuously learn from new data in dynamic clinical settings. This work proposes a novel continual meta-learning framework that, for the first time, incorporates a mechanism capable of distinguishing between known and unknown dynamical sources in cardiac electrophysiological simulations. By integrating a memory-buffer-based continual Bayesian Gaussian mixture model, ensemble conditional neural surrogates, and amortized inference, the framework enables accurate identification of temporal data origins and inference of their underlying relationships, allowing efficient model updates without full retraining. Experimental results on synthetic cardiac data demonstrate that the proposed method substantially outperforms existing baselines, achieving superior performance in prediction accuracy, computational scalability, and resistance to catastrophic forgetting.

Abstract

Personalized virtual heart simulations face challenges in model personalization and computational cost. While neural surrogates offer state-of-the-art solutions, they typically address either efficient personalization or training generalizable models. Recent work reframes this by learning the process of personalizing a surrogate using limited subject-specific context data, through few-shot generative modeling with set-conditioned surrogates and meta-learned amortized inference. These methods, however, assume a static and diverse training distribution with known task identifiers. When new data becomes available, they require costly retraining with all prior data to avoid catastrophic forgetting - a phenomena where the model forgets earlier tasks when trained on new ones. This is a major limitation in clinical settings where often unlabeled data arrives sequentially and full retraining is infeasible. This paper presents a new continual meta-learning framework to achieve personalized neural surrogates able to not only continually integrate information but also identify whether incoming data stems from a known or unknown dynamics source. By leveraging a continual Bayesian Gaussian Mixture Model over a memory buffer, our framework can infer the identifiers and relationships of data over time - required for effective meta-learning. Empirical results on synthetic cardiac data demonstrate superior simulation forecasting, computational scalability, and resilience to catastrophic forgetting compared to existing baselines.

Problem

• continual learning
• catastrophic forgetting
• neural surrogates
• personalized simulation
• cardiac electrophysiology

Innovation

• continual meta-learning
• neural surrogates
• catastrophic forgetting
• Bayesian Gaussian Mixture Model
• personalized cardiac simulation