Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning

TL;DR

This paper introduces a Bayesian active learning approach to efficiently estimate the posterior distribution of cardiac electrophysiological model parameters, significantly reducing computational costs while maintaining high accuracy.

Contribution

The paper presents a novel Bayesian active learning method with a generative model and new acquisition functions for high-dimensional posterior estimation in cardiac models.

Findings

Improved accuracy in posterior approximation over traditional methods.

Reduced computational cost compared to standard MCMC sampling.

Effective in both synthetic and real-data experiments.

Abstract

Probabilistic estimation of cardiac electrophysiological model parameters serves an important step towards model personalization and uncertain quantification. The expensive computation associated with these model simulations, however, makes direct Markov Chain Monte Carlo (MCMC) sampling of the posterior probability density function (pdf) of model parameters computationally intensive. Approximated posterior pdfs resulting from replacing the simulation model with a computationally efficient surrogate, on the other hand, have seen limited accuracy. In this paper, we present a Bayesian active learning method to directly approximate the posterior pdf function of cardiac model parameters, in which we intelligently select training points to query the simulation model in order to learn the posterior pdf using a small number of samples. We integrate a generative model into Bayesian active learning to allow approximating posterior pdf of high-dimensional model parameters at the resolution of the cardiac mesh. We further introduce new acquisition functions to focus the selection of training points on better approximating the shape rather than the modes of the posterior pdf of interest. We evaluated the presented method in estimating tissue excitability in a 3D cardiac electrophysiological model in a range of synthetic and real-data experiments. We demonstrated its improved accuracy in approximating the posterior pdf compared to Bayesian active learning using regular acquisition functions, and substantially reduced computational cost in comparison to existing standard or accelerated MCMC sampling.