Deep neural networks can predict mortality from 12-lead electrocardiogram voltage data

TL;DR

This study demonstrates that deep neural networks can accurately predict one-year mortality from 12-lead ECG voltage data, providing prognostic information beyond traditional clinical interpretation.

Contribution

The paper introduces a deep learning model that predicts mortality from ECG data with high accuracy, even in cases deemed normal by physicians, highlighting its potential clinical utility.

Findings

AUC of 0.85 for mortality prediction across 1.7 million ECGs

High model performance (AUC=0.84) within normal ECGs

Deep learning captures prognostic information not visually apparent to cardiologists

Abstract

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.