An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction
An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction
复制标题
DOI：
10.1016/s0140-6736(19)31721-0
复制
发表时间：
2019-09-07
期刊：
影响因子：
168.9
通讯作者：
Friedman, Paul A.
中科院分区：
文献类型：
--
作者：
Attia, Zachi, I;Noseworthy, Peter A.;Friedman, Paul A.
背景：心房颤动通常无症状，因此未被发现，但与卒中、心力衰竭和死亡相关。现有的筛选方法需要长时间的监测，并受到成本和低产量的限制。我们的目标是开发一种快速，廉价，即时的方法，使用机器学习来识别房颤患者。方法我们使用卷积神经网络开发了一种人工智能（AI）心电图仪（ECG），以使用标准10秒12导联ECG检测正常窦性心律期间存在的房颤心电图特征。我们纳入了1993年12月31日至2017年7月21日期间在马约诊所ECG实验室以仰卧位采集的至少一次数字、正常窦性心律、标准10秒、12导联ECG的所有18岁或以上患者，心律标签由经过培训的人员在心脏病专家监督下进行验证。我们将至少有一次ECG显示房颤或房扑节律的患者归类为房颤阳性。我们以7：1：2的比例将ECG分配给训练、内部验证和测试数据集。我们计算了内部验证数据集的受试者工作特征曲线的曲线下面积（AUC），以选择概率阈值，并将其应用于测试数据集。我们通过计算AUC和准确度、灵敏度、特异性和F1评分以及双侧95% CI，评估了测试数据集上的模型性能。结果我们纳入了180 922例患者的649 931例正常窦性心律ECG进行分析：在训练数据集中记录了126 526例患者的454 789例ECG，在内部验证数据集中记录了18 116例患者的64 340例ECG，在测试数据集中记录了36 280例患者的130 802例ECG。测试数据集中3051例（8.4%）患者在模型测试的正常窦性心律ECG之前已验证房颤。单次AI启用ECG识别房颤的AUC为0.87（95% CI 0.86-0.88），灵敏度为79.0%（77.5-80.4），特异性为79.5%（79.0-79.9），F1评分为39.2%（38.1-40.3），总体准确度为79.4%（79.0-79.9）。包括每例患者关注时间窗第一个月内采集的所有ECG（即，研究开始日期或首次记录房颤ECG前31天）将AUC增加至0.90（0.90-0.91），敏感性82.3%（80.9-83.6），特异性83.4%（83.0-83.8），F1评分45.4%（44.2-46.5），总准确性83.3%（83.0-83.7）。解释在正常窦性心律期间采集的AI启用ECG允许在护理点识别房颤患者。版权所有（c）2019 Elsevier Ltd.保留所有权利。
Background Atrial fibrillation is frequently asymptomatic and thus underdetected but is associated with stroke, heart failure, and death. Existing screening methods require prolonged monitoring and are limited by cost and low yield. We aimed to develop a rapid, inexpensive, point-of-care means of identifying patients with atrial fibrillation using machine learning. Methods We developed an artificial intelligence (AI)-enabled electrocardiograph (ECG) using a convolutional neural network to detect the electrocardiographic signature of atrial fibrillation present during normal sinus rhythm using standard 10-second, 12-lead ECGs. We included all patients aged 18 years or older with at least one digital, normal sinus rhythm, standard 10-second, 12-lead ECG acquired in the supine position at the Mayo Clinic ECG laboratory between Dec 31, 1993, and July 21, 2017, with rhythm labels validated by trained personnel under cardiologist supervision. We classified patients with at least one ECG with a rhythm of atrial fibrillation or atrial flutter as positive for atrial fibrillation. We allocated ECGs to the training, internal validation, and testing datasets in a 7: 1: 2 ratio. We calculated the area under the curve (AUC) of the receiver operatoring characteristic curve for the internal validation dataset to select a probability threshold, which we applied to the testing dataset. We evaluated model performance on the testing dataset by calculating the AUC and the accuracy, sensitivity, specificity, and F1 score with two-sided 95% CIs. Findings We included 180 922 patients with 649 931 normal sinus rhythm ECGs for analysis: 454 789 ECGs recorded from 126 526 patients in the training dataset, 64 340 ECGs from 18 116 patients in the internal validation dataset, and 130 802 ECGs from 36 280 patients in the testing dataset. 3051 (8.4%) patients in the testing dataset had verified atrial fibrillation before the normal sinus rhythm ECG tested by the model. A single AI-enabled ECG identified atrial fibrillation with an AUC of 0.87 (95% CI 0.86-0.88), sensitivity of 79.0% (77.5-80.4), specificity of 79.5% (79.0-79.9), F1 score of 39.2% (38.1-40.3), and overall accuracy of 79.4% (79.0-79.9). Including all ECGs acquired during the first month of each patient's window of interest (ie, the study start date or 31 days before the first recorded atrial fibrillation ECG) increased the AUC to 0.90 (0.90-0.91), sensitivity to 82.3% (80.9-83.6), specificity to 83.4% (83.0-83.8), F1 score to 45.4% (44.2-46.5), and overall accuracy to 83.3% (83.0-83.7). Interpretation An AI-enabled ECG acquired during normal sinus rhythm permits identification at point of care of individuals with atrial fibrillation. Copyright (c) 2019 Elsevier Ltd. All rights reserved.