The electrocardiogram (ECG) is a widely-used medical test, typically consisting of 12 voltage versus time traces collected from surface recordings over the heart. Here we hypothesize that a deep neural network can predict an important future clinical event (one-year all-cause mortality) from ECG voltage-time traces. We show good performance for predicting one-year mortality with an average AUC of 0.85 from a model cross-validated on 1,775,926 12-lead resting ECGs, that were collected over a 34-year period in a large regional health system. Even within the large subset of ECGs interpreted as 'normal' by a physician (n=297,548), the model performance to predict one-year mortality remained high (AUC=0.84), and Cox Proportional Hazard model revealed a hazard ratio of 6.6 (p<0.005) for the two predicted groups (dead vs alive one year after ECG) over a 30-year follow-up period. A blinded survey of three cardiologists suggested that the patterns captured by the model were generally not visually apparent to cardiologists even after being shown 240 paired examples of labeled true positives (dead) and true negatives (alive). In summary, deep learning can add significant prognostic information to the interpretation of 12-lead resting ECGs, even in cases that are interpreted as 'normal' by physicians.
@article{arxiv.1904.07032,
title = {Deep neural networks can predict mortality from 12-lead electrocardiogram voltage data},
author = {Sushravya Raghunath and Alvaro E. Ulloa Cerna and Linyuan Jing and David P. vanMaanen and Joshua Stough and Dustin N. Hartzel and Joseph B. Leader and H. Lester Kirchner and Christopher W. Good and Aalpen A. Patel and Brian P. Delisle and Amro Alsaid and Dominik Beer and Christopher M. Haggerty and Brandon K. Fornwalt},
journal= {arXiv preprint arXiv:1904.07032},
year = {2020}
}
Comments
An updated version of this paper is now published with Nature Medicine (2020)