Deep Learning for Cardiologist-level Myocardial Infarction Detection in Electrocardiograms

TL;DR

This paper develops a neural network model that achieves cardiologist-level accuracy in detecting myocardial infarction from ECG data, using minimal data and no manual feature extraction, with a focus on the importance of specific ECG leads.

Contribution

The study introduces a domain-inspired neural network for myocardial infarction detection, highlighting the critical ECG leads and adapting earthquake detection models for medical diagnosis.

Findings

Achieved 99.43% accuracy on record-wise split

Achieved 97.83% accuracy on patient-wise split

Identified v6, vz, and ii leads as most critical

Abstract

Myocardial infarction is the leading cause of death worldwide. In this paper, we design domain-inspired neural network models to detect myocardial infarction. First, we study the contribution of various leads. This systematic analysis, first of its kind in the literature, indicates that out of 15 ECG leads, data from the v6, vz, and ii leads are critical to correctly identify myocardial infarction. Second, we use this finding and adapt the ConvNetQuake neural network model--originally designed to identify earthquakes--to attain state-of-the-art classification results for myocardial infarction, achieving $99.43\%$ classification accuracy on a record-wise split, and $97.83\%$ classification accuracy on a patient-wise split. These two results represent cardiologist-level performance level for myocardial infarction detection after feeding only 10 seconds of raw ECG data into our model. Third, we show that our multi-ECG-channel neural network achieves cardiologist-level performance without the need of any kind of manual feature extraction or data pre-processing.