Augmenting expert detection of early coronary artery occlusion from 12 lead electrocardiograms using deep learning

TL;DR

This paper presents a deep learning model that improves early detection of coronary artery occlusion from ECGs, balancing sensitivity and specificity better than current criteria and expert analysis.

Contribution

It introduces a novel deep learning approach that enhances expert detection of early coronary occlusion from ECGs, outperforming existing methods.

Findings

Deep learning model achieves higher sensitivity and specificity than STE criteria.

Model outperforms existing computerized analyzers and expert cardiologists.

Improves early diagnosis, potentially saving lives.

Abstract

Early diagnosis of acute coronary artery occlusion based on electrocardiogram (ECG) findings is essential for prompt delivery of primary percutaneous coronary intervention. Current ST elevation (STE) criteria are specific but insensitive. Consequently, it is likely that many patients are missing out on potentially life-saving treatment. Experts combining non-specific ECG changes with STE detect ischaemia with higher sensitivity, but at the cost of specificity. We show that a deep learning model can detect ischaemia caused by acute coronary artery occlusion with a better balance of sensitivity and specificity than STE criteria, existing computerised analysers or expert cardiologists.