Deep Learning Prediction of Left Atrial Structure and Function from 12-lead Electrocardiograms
Brody, J. A.; Yogeswaran, V.; Wiggins, K. L.; Sitlani, C. M.; Bis, J. C.; Chen, L. Y.; Heckbert, S. R.; Lima, J. A. C.; Longstreth, W. T.; Soliman, E. Z.; Tison, G. H.; Ye, T.; Psaty, B. M.; Shojaie, A.; Floyd, J. S.
Show abstract
Abnormal cardiac atrial structure and function (atrial cardiopathy)1 typically precedes atrial fibrillation (AF) and predicts other cardiovascular complications, yet detection is limited by the cost and limited accessibility of high-quality cardiac imaging. We trained a deep learning model (ECG-AI) using 12-lead electrocardiograms paired with 21,749 cardiac magnetic resonance scans to predict left atrial structure and function. ECG-AI measures of atrial cardiopathy were strongly associated with new-onset AF, heart failure, and ischemic stroke after adjustment for clinical risk factors and biomarkers in two external cohorts, outperforming imaging measures and clinical risk factors. The risk of cardioembolic stroke, the hallmark complication of AF, was 66% greater per SD left atrial volume. In a screening population, ECG-AI predicted subclinical AF from 14-day cardiac monitoring better than a clinical risk prediction tool. Our ECG-AI is an inexpensive, accessible tool that identifies individuals at high-risk for AF and related complications.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Leveraging a genetic proxy to investigate the effects of lifelong cardiac sodium channel blockade 96%
- Genetically Predicted IL-18 Inhibition and Risk of Cardiovascular Events: A Mendelian Randomization Study 96%
- Arrhythmia variant associations and reclassifications in the eMERGE-III sequencing study 94%
Similar papers in this journal
- Clinical and genetic associations of asymmetric apical and septal left ventricular hypertrophy 96%
- Development and Multinational Validation of an Ensemble Deep Learning Algorithm for Detecting and Predicting Structural Heart Disease Using Noisy Single-lead Electrocardiograms 96%
- Simple Models Versus Deep Learning in Detecting Low Ejection Fraction From The Electrocardiogram 95%
Similar papers in this journal
- Biomarker panels for improved risk prediction and enhanced biological insights in patients with atrial fibrillation 96%
- Deep Learning of Left Atrial Structure and Function Provides Link to Atrial Fibrillation Risk 96%
- Genome-wide association analysis and Mendelian randomization proteomics identify novel protein biomarkers and drug targets for primary prevention of heart failure 94%
Similar papers in this journal
- Vascular Endothelial Barrier Protection Prevents Atrial Fibrillation by Preserving Cardiac Nanostructure 95%
- Adrenergic Hypersensitivity Drives Ventricular Arrhythmias Following Loss of Plexin-Mediated Cardiac Innervation 95%
- Evidence of Superior and Inferior Sinoatrial Nodes in the Mammalian Heart 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.