In this work, a scalable hybrid model is proposed for the purpose of screening and continuous monitoring of atrial fibrillation (AF) using electrocardiogram (ECG) signals collected from wearable ECG devices. The time series of RR intervals (with units in seconds) extracted from the ECG signal is fed into a recurrent neural network (RNN), and the bandpass filtered and scaled signal itself is fed into a convolutional neural network (CNN). At the post-processing stage, these two predictions are merged. An additional logistic regression model using statistical features of “pseudo” PR interval sequence is applied to aid making the final prediction. The proposed model is trained and validated on several datasets from PhysioNet and achieves a precision of 98.28% and a specificity of 99.82% on a dataset collected from several PhysioNet databases. This hybrid model has already been deployed through a WeChat applet, providing services those using wearable ECG devices, thus helping the screening and continuous out-of-hospital monitoring of the disease of AF.

中文翻译：

---

用于心房颤动检测的可扩展混合模型

在这项工作中，提出了一种可扩展的混合模型，用于使用从可穿戴心电图设备收集的心电图 (ECG) 信号筛查和连续监测心房颤动 (AF)。从 ECG 信号中提取的 RR 间隔时间序列（以秒为单位）被输入循环神经网络（RNN），带通滤波和缩放的信号本身被输入卷积神经网络（CNN）。在后处理阶段，这两个预测被合并。应用使用“伪”PR 区间序列的统计特征的附加逻辑回归模型来帮助进行最终预测。所提出的模型在来自 PhysioNet 的多个数据集上进行了训练和验证，在从多个 PhysioNet 数据库收集的数据集上实现了 98.28% 的精度和 99.82% 的特异性。