Deep neural network-estimated electrocardiographic age as a mortality predictor

TLDR

The electrocardiogram is the most widely used test for evaluating cardiovascular disease. The study proposes that the age predicted by AI from a raw ECG—termed ECG‑age—serves as a marker of cardiovascular health. A deep neural network was trained on 12‑lead ECGs from 1,558,415 patients in the CODE study to predict chronological age. Patients whose AI‑predicted ECG‑age exceeds their chronological age by more than 8 years had a 79 % higher mortality risk (HR 1.79), whereas those with a gap of more than 8 years below age had a 22 % lower risk (HR 0.78), findings replicated in external cohorts and holding even for normal ECGs, demonstrating that ECG‑age provides significant prognostic information.

Abstract

Abstract The electrocardiogram (ECG) is the most commonly used exam for the evaluation of cardiovascular diseases. Here we propose that the age predicted by artificial intelligence (AI) from the raw ECG (ECG-age) can be a measure of cardiovascular health. A deep neural network is trained to predict a patient’s age from the 12-lead ECG in the CODE study cohort ( n = 1,558,415 patients). On a 15% hold-out split, patients with ECG-age more than 8 years greater than the chronological age have a higher mortality rate (hazard ratio (HR) 1.79, p < 0.001), whereas those with ECG-age more than 8 years smaller, have a lower mortality rate (HR 0.78, p < 0.001). Similar results are obtained in the external cohorts ELSA-Brasil ( n = 14,236) and SaMi-Trop ( n = 1,631). Moreover, even for apparent normal ECGs, the predicted ECG-age gap from the chronological age remains a statistically significant risk predictor. These results show that the AI-enabled analysis of the ECG can add prognostic information.