Why the study?
The authors evaluated whether age predicted by artificial intelligence from raw 12-lead ECGs (ECG-age) can serve as a measure of cardiovascular health and predict mortality.
Does deep neural network-estimated electrocardiographic age predict mortality in a large patient cohort?
Population
1,558,415 patients in the CODE cohort, plus ELSA-Brasil (n = 14,236) and SaMi-Trop (n = 1,631)
Comparison
ECG-age more than 8 years greater vs more than 8 years smaller than chronological age
Design
Cohort study with deep neural network training, internal hold-out split, and external cohort validation
Authors
Loading...
ECG-age >8 years above chronological age was associated with higher mortality; hypothesis-generating for AI-ECG as a health marker, pending prospective validation.
Does deep neural network-estimated electrocardiographic age predict mortality in a large patient cohort?
AI-estimated ECG-age gap from chronological age serves as a significant independent predictor of mortality, even in patients with apparently normal ECGs.
Lima et al. (2021) studied this question.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: