A deep neural network using 12-lead ECG voltage-time traces predicted one-year all-cause mortality with an AUC of 0.85 and a hazard ratio of 4.4 between predicted risk groups.
Observational (n=397,840)
Yes
Does a deep neural network applied to 12-lead resting ECGs predict one-year all-cause mortality?
Deep learning applied to 12-lead resting ECGs can accurately predict one-year all-cause mortality, identifying prognostic patterns not visually apparent to cardiologists even in 'normal' ECGs.
Effect estimate: HR 4.4 (95% CI 4.0-4.5)
p-value: p=<0.005
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.
Raghunath et al. (Mon,) conducted a observational in All-cause mortality (n=397,840). Deep neural network (DNN) using 12-lead ECG voltage-time traces vs. XGBoost model using 39 clinically-derived ECG features was evaluated on 1-year all-cause mortality (HR 4.4, 95% CI 4.0-4.5, p=<0.005). A deep neural network using 12-lead ECG voltage-time traces predicted one-year all-cause mortality with an AUC of 0.85 and a hazard ratio of 4.4 between predicted risk groups.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: