Gao Qunxia, Shang Lijuan, Wu Kai
Department of Electronic, Software Engineering Institute of Guangzhou, Guangzhou 510990, P.R.China.
Department of software engineering, Neusoft Institute Guangdong, Foshan, Guangdong 528225, P.R.China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2021 Aug 25;38(4):678-685. doi: 10.7507/1001-5515.202012025.
Sleep apnea (SA) detection method based on traditional machine learning needs a lot of efforts in feature engineering and classifier design. We constructed a one-dimensional convolutional neural network (CNN) model, which consists in four convolution layers, four pooling layers, two full connection layers and one classification layer. The automatic feature extraction and classification were realized by the structure of the proposed CNN model. The model was verified by the whole night single-channel sleep electrocardiogram (ECG) signals of 70 subjects from the Apnea-ECG dataset. Our results showed that the accuracy of per-segment SA detection was ranged from 80.1% to 88.0%, using the input signals of single-channel ECG signal, RR interval (RRI) sequence, R peak sequence and RRI sequence + R peak sequence respectively. These results indicated that the proposed CNN model was effective and can automatically extract and classify features from the original single-channel ECG signal or its derived signal RRI and R peak sequence. When the input signals were RRI sequence + R peak sequence, the CNN model achieved the best performance. The accuracy, sensitivity and specificity of per-segment SA detection were 88.0%, 85.1% and 89.9%, respectively. And the accuracy of per-recording SA diagnosis was 100%. These findings indicated that the proposed method can effectively improve the accuracy and robustness of SA detection and outperform the methods reported in recent years. The proposed CNN model can be applied to portable screening diagnosis equipment for SA with remote server.
基于传统机器学习的睡眠呼吸暂停（SA）检测方法在特征工程和分类器设计方面需要付出很多努力。我们构建了一个一维卷积神经网络（CNN）模型，它由四个卷积层、四个池化层、两个全连接层和一个分类层组成。通过所提出的CNN模型结构实现了自动特征提取和分类。该模型通过来自Apnea-ECG数据集中70名受试者的整夜单通道睡眠心电图（ECG）信号进行了验证。我们的结果表明，分别使用单通道ECG信号、RR间期（RRI）序列、R波峰序列和RRI序列 + R波峰序列作为输入信号时，逐段SA检测的准确率在80.1%至88.0%之间。这些结果表明，所提出的CNN模型是有效的，并且可以从原始单通道ECG信号或其派生信号RRI和R波峰序列中自动提取特征并进行分类。当输入信号为RRI序列 + R波峰序列时，CNN模型表现最佳。逐段SA检测的准确率、灵敏度和特异性分别为88.0%、85.1%和89.9%。并且每次记录的SA诊断准确率为100%。这些发现表明，所提出的方法可以有效提高SA检测的准确性和鲁棒性，并且优于近年来报道的方法。所提出的CNN模型可应用于带有远程服务器的SA便携式筛查诊断设备。
