Machine Learning Identification of Pro-arrhythmic Structures in Cardiac Fibrosis.

Radek Halfar,Kevin Burrage,Brodie A J Lawson,Rodrigo Weber Dos Santos

doi:10.3389/fphys.2021.709485

Abstract

Cardiac fibrosis and other scarring of the heart, arising from conditions ranging from myocardial infarction to ageing, promotes dangerous arrhythmias by blocking the healthy propagation of cardiac excitation. Owing to the complexity of the dynamics of electrical signalling in the heart, however, the connection between different arrangements of blockage and various arrhythmic consequences remains poorly understood. Where a mechanism defies traditional understanding, machine learning can be invaluable for enabling accurate prediction of quantities of interest (measures of arrhythmic risk) in terms of predictor variables (such as the arrangement or pattern of obstructive scarring). In this study, we simulate the propagation of the action potential (AP) in tissue affected by fibrotic changes and hence detect sites that initiate re-entrant activation patterns. By separately considering multiple different stimulus regimes, we directly observe and quantify the sensitivity of re-entry formation to activation sequence in the fibrotic region. Then, by extracting the fibrotic structures around locations that both do and do not initiate re-entries, we use neural networks to determine to what extent re-entry initiation is predictable, and over what spatial scale conduction heterogeneities appear to act to produce this effect. We find that structural information within about 0.5 mm of a given point is sufficient to predict structures that initiate re-entry with more than 90% accuracy.

Highlights

According to the WHO, in 2016, 17.9 million people worldwide died of cardiovascular diseases (31% of all deaths)
To explore how much information regarding re-entry risk is contained in the patterning of fibrosis, we considered the ability of neural networks (NN) to successfully classify different structures as discriminative about excitation transfer or not
We have used high-throughput simulation to approach an exhaustive exploration of the issue of re-entry initiation in fibrosis-afflicted tissue, a key precursor to arrhythmia (Hansen et al, 2015; Sachetto Oliveira et al, 2018a)

Summary

Introduction

According to the WHO, in 2016, 17.9 million people worldwide died of cardiovascular diseases (31% of all deaths). The function and dysfunction of the heart have been extensively studied, the sheer complexity of the spatiotemporal dynamics underlying its electrical signalling process leaves much still poorly understood. This is true when complicating factors are present, such as cardiac fibrosis. Fibroblasts deposit extracellular matrix proteins that can separate myocytes, resulting in tortuous paths of activation that increase the risk of signalling malfunctions. This risk depends critically on the extent and arrangement of afflicted tissue, but this dependency is intricate and very difficult to quantify.

Methods

Results

Conclusion