Key result
AFibEFNet deep-learning model predicts reduced LVEF with an AUROC of ~0.82.
Why the study?
Evaluating LVEF in AF or AFL is crucial for management, but evidence is lacking for predicting reduced LVEF (<50%) using AF/AFL ECGs.
Does a deep-learning model using 12-lead ECGs and clinical features accurately predict reduced LVEF in patients with atrial fibrillation or flutter?
Cohort (n=15,683)
No
Does a deep-learning model using 12-lead ECGs and clinical features accurately predict reduced LVEF in patients with atrial fibrillation or flutter?
Absolute Event Rate: 0.816% vs 0.798%
p-value: p=0.04
A customized deep-learning model (AFibEFNet) can accurately predict reduced LVEF (<50%) using 12-lead ECGs and clinical features in patients with atrial fibrillation or flutter, potentially aiding in the early detection of left ventricular dysfunction.
Objective Although the evaluation of left ventricular ejection fraction (LVEF) in patients with atrial fibrillation (AF) or atrial flutter (AFL) is crucial for appropriate medical management, the prediction of reduced LVEF (<50%) with AF/AFL electrocardiograms (ECGs) lacks evidence. This study aimed to investigate deep-learning approaches to predict reduced LVEF (<50%) in patients with AF/AFL ECGs and easily obtainable clinical information. Methods Patients with 12-lead ECGs of AF/AFL and echocardiography were divided into those with LVEF <50% and ≥50%. A convolutional neural networks-based model customized to the study (AFibEFNet) and other deep-learning models were investigated. Electrocardiogram signals, ECG features, and clinical features (demographic information, comorbidities, blood cell counts, and blood test results) were collected for training. A hold-out test dataset was constructed using a different recruitment period. Five-fold cross-validation and calibration plots were used to evaluate performance. Results A total of 15,683 patients were analyzed (mean age, 70.0 ± 11.7 years; 61.2% men), with 82.2% having LVEF ≥50% and 17.8% having LVEF < 50%. Among the learning models, the AFibEFNet outperformed other models regarding area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and F1-score. Using ECG signals alone, the AFibEFNet model predicted reduced LVEF with AUROC of 0.798 (95% confidence interval [CI], 0.767–0.829) and AUPRC of 0.508 (95% CI, 0.434–0.564). For the AFibEFNet model, additional training with ECG and clinical features significantly improved AUROC (0.816 vs. 0.798, p = 0.04) and AUPRC (0.547 vs. 0.508, p < 0.001). The AFibEFNet model primarily focused on the R-wave, QRS onset and offset, and T-wave in ECG signals. Conclusions Among the patients with AF/AFL, machine learning may predict reduced LVEF with 12-lead ECGs of AF/AFL.
No takes yet. Share an insight, caveat, or question.
Kwon et al. (2025) conducted a cohort in Atrial fibrillation or atrial flutter (n=15,683). AFibEFNet deep-learning model (ECG signals, ECG features, and clinical features) vs. AFibEFNet model with ECG signals alone was evaluated on Prediction of reduced LVEF (<50%) measured by AUROC (95% CI 0.787-0.845, p=0.04). The AFibEFNet deep-learning model trained with ECG signals, ECG features, and clinical features predicted reduced left ventricular ejection fraction with an AUROC of 0.816.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: