Detecting and interpreting myocardial infarction using fully convolutional neural networks

TL;DR

This paper presents a convolutional neural network-based algorithm for detecting myocardial infarction directly from ECG data, achieving high accuracy and interpretability comparable to human cardiologists.

Contribution

The study introduces a fully convolutional neural network ensemble that operates without preprocessing and provides insights into decision criteria, outperforming existing methods.

Findings

Achieves 93.3% sensitivity and 89.7% specificity in detection

Outperforms state-of-the-art approaches

Provides channel-specific interpretability of decisions

Abstract

Objective: We aim to provide an algorithm for the detection of myocardial infarction that operates directly on ECG data without any preprocessing and to investigate its decision criteria. Approach: We train an ensemble of fully convolutional neural networks on the PTB ECG dataset and apply state-of-the-art attribution methods. Main results: Our classifier reaches 93.3% sensitivity and 89.7% specificity evaluated using 10-fold cross-validation with sampling based on patients. The presented method outperforms state-of-the-art approaches and reaches the performance level of human cardiologists for detection of myocardial infarction. We are able to discriminate channel-specific regions that contribute most significantly to the neural network's decision. Interestingly, the network's decision is influenced by signs also recognized by human cardiologists as indicative of myocardial infarction. Significance: Our results demonstrate the high prospects of algorithmic ECG analysis for future clinical applications considering both its quantitative performance as well as the possibility of assessing decision criteria on a per-example basis, which enhances the comprehensibility of the approach.