ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation

TL;DR

This paper introduces an ECG World Model that simulates cardiac responses to interventions, integrating physiological priors for realistic predictions and uncertainty estimation to enhance clinical decision support.

Contribution

It presents a novel framework combining ODE priors with latent diffusion to generate physiologically plausible ECG trajectories under interventions.

Findings

Improved risk calibration in ECG predictions.

Enhanced alignment with expert treatment preferences.

Effective simulation of drug-response scenarios.

Abstract

Electrocardiogram (ECG)-based models have achieved strong performance in diagnostic tasks, yet they remain limited in modeling how cardiac dynamics evolve under external interventions. In particular, existing approaches focus primarily on static prediction and lack mechanisms to capture ECG variations under different pharmacological conditions. In this work, we propose an ECG World Model for action-conditioned predictive simulation of cardiac electrophysiology. Moving beyond disjoint pipelines, our framework features a principled integration of physiological ordinary differential equation (ODE) priors into latent diffusion dynamics via energy regularization. This structural constraint enables the synthesis of physiologically plausible post-intervention ECG trajectories while effectively mitigating generative hallucinations. Building on this simulation process, we introduce an uncertainty-aware evaluation strategy that leverages the stochasticity of diffusion sampling to characterize both the expected clinical risk and its variability, allowing a more reliable comparative assessment of candidate interventions. We evaluate our method across diverse settings, including controlled drug-response scenarios and real-world clinical records. Beyond standard waveform metrics, experimental results demonstrate improved risk calibration and strong alignment with expert-informed treatment preferences. These results establish our approach as a robust foundation for safe and intervention-aware clinical decision support.