Deep learning prediction of left atrial structure and function from 12-lead electrocardiograms.
JA, B., V, Y., KL, W., CM, S., JC, B., LY, C., SR, H., JAC, L., Jr, L.W., & BM, P. (2026). Deep learning prediction of left atrial structure and function from 12-lead electrocardiograms.. Nature communications. https://doi.org/10.1038/s41467-026-76155-6
JA B, V Y, KL W, CM S, JC B, LY C, et al. Deep learning prediction of left atrial structure and function from 12-lead electrocardiograms.. Nature communications. 2026; doi: 10.1038/s41467-026-76155-6
JA B, V Y, KL W, et al. Deep learning prediction of left atrial structure and function from 12-lead electrocardiograms.[J]. Nature communications. 2026. DOI: 10.1038/s41467-026-76155-6.
@article{ja2026,
author = {Brody JA and Yogeswaran V and Wiggins KL and Sitlani CM and Bis JC and Chen LY and Heckbert SR and Lima JAC and Longstreth WT Jr and Psaty BM},
title = {Deep learning prediction of left atrial structure and function from 12-lead electrocardiograms.},
journal = {Nature communications},
year = {2026},
doi = {10.1038/s41467-026-76155-6},
note = {PMID: 42669665},
}
TY - JOUR AU - Brody JA AU - Yogeswaran V AU - Wiggins KL AU - Sitlani CM AU - Bis JC AU - Chen LY AU - Heckbert SR AU - Lima JAC AU - Longstreth WT Jr AU - Psaty BM TI - Deep learning prediction of left atrial structure and function from 12-lead electrocardiograms. T2 - Nature communications PY - 2026 DO - 10.1038/s41467-026-76155-6 AN - PMID:42669665 ER -
Abnormal cardiac atrial structure and function, termed atrial cardiopathy, typically precedes atrial fibrillation and downstream cardiovascular complications, yet detection is limited by the cost and accessibility of high-quality cardiac imaging. Here we show that a deep learning model trained on 12-lead electrocardiograms paired with 21,749 cardiac magnetic resonance scans from the UK Biobank predicts left atrial structure and function. Model-derived measures of atrial cardiopathy are strongly associated with new-onset atrial fibrillation, heart failure, and ischemic stroke after adjustment for clinical risk factors and biomarkers in two external cohorts, with magnitudes comparable to or greater than those for direct imaging measures and clinical risk factors. The risk of cardioembolic stroke, the hallmark complication of atrial fibrillation, increases 66% per standard deviation of left atrial volume. In exploratory analyses, model measures predict cardiac monitor-detected atrial fibrillation more accurately than a clinical risk prediction tool and NT-proBNP levels. This model is an inexpensive, accessible tool that identifies individuals at high-risk for atrial fibrillation and related complications.