Abstract
AbstractIn recent years, blending mechanistic knowledge with machine learning has had a major impact in digital healthcare. In this work, we introduce a computational pipeline to build certified digital replicas of cardiac electrophysiology in pediatric patients with congenital heart disease. We construct the patient-specific geometry by means of semi-automatic segmentation and meshing tools. We generate a dataset of electrophysiology simulations covering cell-to-organ level model parameters and utilizing rigorous mathematical models based on differential equations. We previously proposed Branched Latent Neural Maps (BLNMs) as an accurate and efficient means to recapitulate complex physical processes in a neural network. Here, we employ BLNMs to encode the parametrized temporal dynamics of in silico 12-lead electrocardiograms (ECGs). BLNMs act as a geometry-specific surrogate model of cardiac function for fast and robust parameter estimation to match clinical ECGs in pediatric patients. Identifiability and trustworthiness of calibrated model parameters are assessed by sensitivity analysis and uncertainty quantification.
Publisher
Cold Spring Harbor Laboratory
Reference70 articles.
1. “A matrix–free high–order solver for the numerical solution of cardiac electrophysiology;In: Journal of Computational Physics,2023
2. “Arrhythmia risk stratification of patients after myocardial infarction using personalized heart models;In: Nature Communications,2016
3. F. Bagge Carlson . “Hyperopt.jl: Hyperparameter optimization in Julia”. In: (2018).
4. D. C. Bartos , E. Grandi , and C. M. Ripplinger . “Ion Channels in the Heart”. In: Comprehensive Physiology. 2015, pp. 1423–1464.
5. M. Betancourt and M. Girolami . “A Conceptual Introduction to Hamiltonian Monte Carlo”. In: arXiv:1701.02434 (2017).