Digital twinning of cardiac electrophysiology for congenital heart disease.

In 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.

Computational simulations of the 4D micro-circulatory network in zebrafish tail amputation and regeneration.

Wall shear stress (WSS) contributes to the mechanotransduction underlying microvascular development and regeneration. Using computational fluid dynamics, we elucidated the interplay between WSS and vascular remodelling in a zebrafish model of tail amputation and regeneration. The transgenic Tg (fli1:eGFP; Gata1:ds-red) zebrafish line was used to track the three-dimensional fluorescently labelled vascular endothelium for post-image segmentation and reconstruction of the fluid domain. Particle image velocimetry was used to validate the blood flow. Following amputation to the dorsal aorta and posterior cardinal vein (PCV), vasoconstriction developed in the dorsal longitudinal anastomotic vessel (DLAV) along with increased WSS in the proximal segmental vessels (SVs) from amputation. Angiogenesis ensued at the tips of the amputated DLAV and PCV where WSS was minimal. At 2 days post amputation (dpa), vasodilation occurred in a pair of SVs proximal to amputation, followed by increased blood flow and WSS; however, in the SVs distal to amputation, WSS normalized to the baseline. At 3 dpa, the blood flow increased in the arterial SV proximal to amputation and through anastomosis with DLAV formed a loop with PCV. Thus, our in silico modelling revealed the interplay between WSS and microvascular adaptation to changes in WSS and blood flow to restore microcirculation following tail amputation.