北京生物医学工程

基于多通道的睡眠呼吸暂停检测

Multichannel-based sleep apnea detection

作者：熊馨张亚茹吴迪冯建楠易三莉王春武刘瑞湘贺建峰

单位：昆明理工大学信息工程与自动化学院 (昆明650500)<br />韩山师范学院物理与电子工程学院 (广东潮州521000)<br />云南省第二人民医院临床心理科(昆明650021)<br />通信作者：贺建峰，教授。E-mail: 120112624@qq.com

关键词：睡眠呼吸暂停;心电信号;小波阈值; Relief算法;支持向量机

分类号：R318.04

出版年·卷·期（页码）：2023·42·2（152-157）

摘要：

目的为了提高检测性能和验证不同生理信号对睡眠呼吸暂停的检测结果。本文提出一种信号叠加和通道相加检测睡眠呼吸暂停的方法。方法首先对100例睡眠呼吸障碍患者的心电（electrocardiogram, ECG）和脑电（electroencephalogram, EEG）信号通过小波阈值方法进行预处理，其次进行通道相加和信号叠加，然后通过Relief特征选择算法对30个特征进行分析，最后采用支持向量机（support vector machine, SVM）构建睡眠呼吸暂停分类模型，并验证该模型的准确性。结果实验结果表明，通道相加和信号叠加时睡眠呼吸暂停检测的最高准确率分别为96.24%和96.18%。结论 ECG和EEG两种信号叠加和通道相加的方法均可提高睡眠呼吸暂停检测结果，且X2（ECG）和C3-A2（EEG）通道相加检测结果最好。

Objective In order to improve the detection performance and verify the detection results of different physiological signals on sleep apnea. This paper presents a method of signal superposition and channel addition to detect sleep apnea. Methods The electrocardiogram (ECG) and electroencephalogram (EEG) signals of 100 patients with sleep apnea were pretreated by wavelet threshold method, followed by channel addition and signal stacking. Then, the Relief feature selection algorithm was used to analyze the 30 features. Finally, support vector machine (SVM) was used to construct the classification model of sleep apnea, and the accuracy of the model was verified. Results The experimental results showed that the highest accuracy of the detection of sleep apnea was 96.24% and 96.18% when the channels were added and the signals were added, respectively. Conclusions ECG and EEG signal combination and channel addition can improve the detection results of sleep apnea, and the X2 (ECG) and C3-A2 (EEG) channel addition results are the best.

参考文献：

［1］Asghar Z, Asl BM. Automatic detection of obstructive sleep apnea using wavelet transform and entropy-based features from single-lead ECG signal [J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23 (3): 1011–1021.
［2］Song C, Liu K, Zhang X, et al. An obstructive sleep apnea detection approach using a discriminative hidden Markov model from ECG signals[J]. IEEE Transactions on Biomedical Engineering, 2016, 63(7): 1532-1542.
［3］Xie B, Minn H. Real-time sleep apnea detection by classifier combination[J]. IEEE Transactions on Information Technology in Biomedicine, 2012, 16 (3): 469–477.
［4］Sharan RV, Berkovsky S, Xiong H, et al. End-to-end sleep apnea detection using single-lead ECG Signal and 1-D residual neural networks[J]. Journal of Medical and Biological Engineering, 2021, 41: 758–766.
［5］Li K, Pan W, Li Y, et al. A method to detect sleep apnea based on deep neural network and hidden Markov model using single-lead ECG signal [J]. Neurocomputing, 2018, 294: 94-101.
［6］Sharma H, Sharma KK. An algorithm for sleep apnea detection from single-lead ECG using Hermite Basis functions [J]. Computers in Biology and Medicine, 2016, 77: 116-124.
［7］Hassan AR. Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting[J]. Biomedical Signal Processing and Control, 2016, 29: 22-30.
［8］Khalighi S, Sousa T, Santos JM, et al. ISRUC-sleep: a comprehensive public dataset for sleep researchers[J]. Computer Methods and Programs in Biomedicine, 2016, 124: 180-192.
［9］周静,吴效明. 睡眠呼吸暂停综合征脑电关联维特性研究[J].生物医学工程学杂志,2017,34(2): 168-172.
Zhou J, Wu XM. Study on the property of correlation dimension of sleep apnea syndrome electroencephalogram[J]. Journal of Biomedical Engineering, 2017, 34 (2): 168-172.
［10］康志钦,黄丽媚,陈昆龙,等.阻塞性睡眠呼吸暂停综合征的心率变异性分析[J].心血管病防治知识(学术版), 2019(3): 41-43.
［11］梁晓花. 基于脑电心电数据融合的睡眠分期[D]. 镇江：江苏大学, 2008.
［12］Yücelba, Yücelba C, Tezel G, et al. Automatic sleep staging based on SVD, VMD, HHT and morphological features of single-lead ECG signal[J]. Expert Systems with Applications, 2018, 102: 193-206.
［13］Hassan AR, Haque A. An expert system for automated identification of obstructive sleep apnea from single-lead ECG using random under sampling boosting[J]. Neurocomputing, 2017, 235: 122-130.
［14］余晓敏, 涂岳文,黄超, 等. 基于心电信号的睡眠呼吸暂停综合征检测算法[J].生物医学工程学杂志, 2013, 30(5): 999-1002.
Yu XM, Tu YW, Huang C, et al. An algorithm based on ECG signal for sleep apnea syndrome detection[J]. Journal of Biomedical Engineering, 2013, 30(5): 999-1002.
［15］董孝彤, 曲新亮, 魏守水. 用于睡眠呼吸暂停检测的心电特征稳定性分析[J]. 生物医学工程研究, 2020, 39(1): 6-10.
Dong XT, Qu XL, Wei SS. Stability analysis of electrocardiogram features for sleep apnea detection[J]. Biomedical Engineering Research, 2020, 39(1): 6-10.
［16］李晓岚. 基于Relief特征选择算法的研究与应用[D].大连: 大连理工大学, 2013.
Li XL. The study and application of feature selection algorithms based on relief[D]. Dalian: Dalian University of Technology, 2013.
［17］Huang W, Guo B, Shen Y, et al. Sleep staging algorithm based on multichannel data adding and multifeature screening[J]. Computer Methods and Programs in Biomedicine, 2020, 187: 105253.
［18］Kumar TS, Kanhangad V. Automated obstructive sleep apnea detection using symmetrically weighted local binary patterns[J]. Electronics Letters, 2017, 53(4): 212-214.
［19］Bsoul M, Minn H, Tamil L. Apnea MedAssist: real-time sleep apnea monitor using single-lead ECG[J]. IEEE Transactions on Information Technology in Biomedicine, 2011, 15(3): 416-427.
［20］Hassan AR, Haque MA. Computer-aided obstructive sleep apnea screening from single-lead electrocardiogram using statistical and spectral features and bootstrap aggregating [J]. Biocybernetics and Biomedical Engineering, 2016, 36(1): 256-266.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录