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. FUNDING None.

中文翻译：

---

一种具有人工智能功能的ECG算法，用于在窦性心律期间识别房颤患者：对结果预测的回顾性分析。

背景技术房颤通常是无症状的，因此未被发现，但与中风，心力衰竭和死亡有关。现有的筛选方法需要长时间的监测，并且受到成本和低产率的限制。我们旨在开发一种快速，廉价，即时的医疗手段，通过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具有人工智能（AI）功能的心电图仪（ECG），以使用标准的10秒，12导联心电图来检测正常窦性心律期间心房颤动的心电图特征。我们纳入了1993年12月31日之间在Mayo Clinic ECG实验室仰卧位获得的，至少具有18个数字，正常窦性心律，标准10秒，12导联心电图的18岁或18岁以上的所有患者，和2017年7月21日，由经过培训的人员在心脏病专家的监督下验证了节奏标签。我们将心电图或心房扑动节律至少为一种的心电图患者归为房颤阳性。我们以7：1：2的比例将ECG分配给了训练，内部验证和测试数据集。我们为内部验证数据集计算了接收者操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以及两侧为95％CI的准确性，敏感性，特异性和F1得分来评估测试数据集上的模型性能。结果我们纳入180 922名患者和649 931例正常窦性心律心电图进行分析：从训练数据集中的126 526名患者中记录了454 789例心电图，内部验证数据集中来自18 116位患者的64 340个ECG，测试数据集中来自36 280位患者的130 802个ECG。测试数据集中有3051名患者（8·4％）在该模型测试的正常窦性心律ECG之前已确认房颤。单个具有AI功能的心电图可确定房颤的AUC为0·87（95％CI 0·86-0·88），敏感性为79·0％（77·5-80·4），特异性为79·5 ％（79·0-79·9），F1得分39·2％（38·1-40·3）和总体准确度为79·4％（79·0-79·9）。包括在每个患者关注窗口的第一个月（即研究开始日期或首次记录的房颤ECG之前的31天）内获得的所有ECG，AUC均提高至0·90（0·90-0·91），得分为82·3％（80·9-83·6），特异性为83·4％（83·0-83·8），F1得分为45·4％（44·2-46·5），整体准确度达到83·3％（83·0-83·7）。解释在正常窦性心律下获得的AI功能心电图可以在房颤患者的护理时进行识别。资金无。