使用心房颤动或扑动心电图预测左心室射血分数降低：一项机器学习研究。
Prediction of reduced left ventricular ejection fraction using atrial fibrillation or flutter electrocardiograms: A machine-learning study.
作者信息
Kwon Soonil, Chung SooMin, Lee So-Ryoung, Kim Kwangsoo, Kim Junmo, Baek Dahyeon, Yang Hyun-Lim, Choi Eue-Keun, Oh Seil
机构信息
Division of Cardiology, Department of Internal Medicine, SMG-SNU Boramae Medical Center, Seoul, Republic of Korea.
Interdisciplinary Program in Bioengineering, Seoul National University, Seoul, Republic of Korea.
出版信息
Digit Health. 2025 Jan 17;11:20552076241311460. doi: 10.1177/20552076241311460. eCollection 2025 Jan-Dec.
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, = 0.04) and AUPRC (0.547 vs. 0.508, < 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.
目的
虽然评估心房颤动（AF）或心房扑动（AFL）患者的左心室射血分数（LVEF）对于恰当的医疗管理至关重要，但利用AF/AFL心电图（ECG）预测LVEF降低（<50%）缺乏证据。本研究旨在探讨深度学习方法，以根据AF/AFL心电图及易于获取的临床信息预测LVEF降低（<50%）。
方法
将有AF/AFL的12导联心电图及超声心动图检查的患者分为LVEF<50%和≥50%两组。研究了一种针对本研究定制的基于卷积神经网络的模型（AFibEFNet）及其他深度学习模型。收集心电图信号、心电图特征及临床特征（人口统计学信息、合并症、血细胞计数及血液检测结果）用于训练。使用不同的招募时间段构建一个留出检验数据集。采用五折交叉验证和校准图评估性能。
结果
共分析了15683例患者（平均年龄70.0±11.7岁；男性占61.2%），其中82.2%的患者LVEF≥50%，17.8%的患者LVEF<50%。在学习模型中，AFibEFNet在受试者工作特征曲线下面积（AUROC）、精确召回率曲线下面积（AUPRC）及F1评分方面优于其他模型。仅使用心电图信号时，AFibEFNet模型预测LVEF降低的AUROC为0.798（95%置信区间[CI]，0.767 - 0.829），AUPRC为0.508（95%CI，0.434 - 0.564）。对于AFibEFNet模型，使用心电图和临床特征进行额外训练可显著提高AUROC（0.816对0.798，P = 0.04）和AUPRC（0.547对0.508，P<0.001）。AFibEFNet模型主要关注心电图信号中的R波、QRS波起始和结束以及T波。
结论
在AF/AFL患者中，机器学习可通过AF/AFL的12导联心电图预测LVEF降低。
Zotero 插件