Clinical usability of deep learning-based saliency maps for occlusion myocardial infarction identification from the prehospital 12-Lead electrocardiogram.

INTRODUCTION: Deep learning (DL) models offer improved performance in electrocardiogram (ECG)-based classification over rule-based methods. However, for widespread adoption by clinicians, explainability methods, like saliency maps, are essential. METHODS: On a subset of 100 ECGs from patients with chest pain, we generated saliency maps using a previously validated convolutional neural network for occlusion myocardial infarction (OMI) classification. Three clinicians reviewed ECG-saliency map dyads, first assessing the likelihood of OMI from standard ECGs and then evaluating clinical relevance and helpfulness of the saliency maps, as well as their confidence in the model's predictions. Questions were answered on a Likert scale ranging from +3 (most useful/relevant) to -3 (least useful/relevant). RESULTS: The adjudicated accuracy of the three clinicians matched the DL model when considering area under the receiver operating characteristics curve (AUC) and F1 score (AUC 0.855 vs. 0.872, F1 score = 0.789 vs. 0.747). On average, clinicians found saliency maps slightly clinically relevant (0.96 ± 0.92) and slightly helpful (0.66 ± 0.98) in identifying or ruling out OMI but had higher confidence in the model's predictions (1.71 ± 0.56). Clinicians noted that leads I and aVL were often emphasized, even when obvious ST changes were present in other leads. CONCLUSION: In this clinical usability study, clinicians deemed saliency maps somewhat helpful in enhancing explainability of DL-based ECG models. The spatial convolutional layers across the 12 leads in these models appear to contribute to the discrepancy between ECG segments considered most relevant by clinicians and segments that drove DL model predictions.

Microheterogeneity-induced conduction slowing and wavefront collisions govern macroscopic conduction behavior: A computational and experimental study.

The incidence of cardiac arrhythmias is known to be associated with tissue heterogeneities including fibrosis. However, the impact of microscopic structural heterogeneities on conduction in excitable tissues remains poorly understood. In this study, we investigated how acellular microheterogeneities affect macroscopic conduction under conditions of normal and reduced excitability by utilizing a novel platform of paired in vitro and in silico studies to examine the mechanisms of conduction. Regular patterns of nonconductive micro-obstacles were created in confluent monolayers of the previously described engineered-excitable Ex293 cell line. Increasing the relative ratio of obstacle size to intra-obstacle strand width resulted in significant conduction slowing up to 23.6% and a significant increase in wavefront curvature anisotropy, a measure of spatial variation in wavefront shape. Changes in bulk electrical conductivity and in path tortuosity were insufficient to explain these observed macroscopic changes. Rather, microscale behaviors including local conduction slowing due to microscale branching, and conduction acceleration due to wavefront merging were shown to contribute to macroscopic phenomena. Conditions of reduced excitability led to further conduction slowing and a reversal of wavefront curvature anisotropy due to spatially non-uniform effects on microscopic slowing and acceleration. This unique experimental and computation platform provided critical mechanistic insights in the impact of microscopic heterogeneities on macroscopic conduction, pertinent to settings of fibrotic heart disease.

Modeling an Excitable Biosynthetic Tissue with Inherent Variability for Paired Computational-Experimental Studies.

To understand how excitable tissues give rise to arrhythmias, it is crucially necessary to understand the electrical dynamics of cells in the context of their environment. Multicellular monolayer cultures have proven useful for investigating arrhythmias and other conduction anomalies, and because of their relatively simple structure, these constructs lend themselves to paired computational studies that often help elucidate mechanisms of the observed behavior. However, tissue cultures of cardiomyocyte monolayers currently require the use of neonatal cells with ionic properties that change rapidly during development and have thus been poorly characterized and modeled to date. Recently, Kirkton and Bursac demonstrated the ability to create biosynthetic excitable tissues from genetically engineered and immortalized HEK293 cells with well-characterized electrical properties and the ability to propagate action potentials. In this study, we developed and validated a computational model of these excitable HEK293 cells (called "Ex293" cells) using existing electrophysiological data and a genetic search algorithm. In order to reproduce not only the mean but also the variability of experimental observations, we examined what sources of variation were required in the computational model. Random cell-to-cell and inter-monolayer variation in both ionic conductances and tissue conductivity was necessary to explain the experimentally observed variability in action potential shape and macroscopic conduction, and the spatial organization of cell-to-cell conductance variation was found to not impact macroscopic behavior; the resulting model accurately reproduces both normal and drug-modified conduction behavior. The development of a computational Ex293 cell and tissue model provides a novel framework to perform paired computational-experimental studies to study normal and abnormal conduction in multidimensional excitable tissue, and the methodology of modeling variation can be applied to models of any excitable cell.

Modeling dynamics in diseased cardiac tissue: Impact of model choice.

Cardiac arrhythmias have been traditionally simulated using continuous models that assume tissue homogeneity and use a relatively large spatial discretization. However, it is believed that the tissue fibrosis and collagen deposition, which occur on a micron-level, are critical factors in arrhythmogenesis in diseased tissues. Consequently, it remains unclear how well continuous models, which use averaged electrical properties, are able to accurately capture complex conduction behaviors such as re-entry in fibrotic tissues. The objective of this study was to compare re-entrant behavior in discrete microstructural models of fibrosis and in two types of equivalent continuous models, a homogenous continuous model and a hybrid continuous model with distinct heterogeneities. In the discrete model, increasing levels of tissue fibrosis lead to a substantial increase in the re-entrant cycle length which is inadequately reflected in the homogenous continuous models. These cycle length increases appear to be primarily due to increases in the tip path length and to altered restitution behavior, and suggest that it is critical to consider the discrete effects of fibrosis on conduction when studying arrhythmogenesis in fibrotic myocardium. Hybrid models are able to accurately capture some aspects of re-entry and, if carefully tuned, may provide a framework for simulating conduction in diseased tissues with both accuracy and efficiency.