基于LSTM-CNN的睡眠呼吸暂停与低通气事件实时检测算法研究

doi:10.3969/j.issn.0258-8021.2020.03.07

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (6166 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要睡眠呼吸暂停与低通气综合征(SAHS)严重影响睡眠质量, 是一种潜在的致死性呼吸疾病。为了兼顾对睡眠呼吸暂停与低通气(AH)事件检测的准确率与时间分辨率, 提出一种长短时记忆-卷积神经网络(LSTM-CNN)方法, 实现对AH事件的精准预测;同时基于事件检测结果, 提出一种呼吸紊乱指数(AHI)估计方法, 进而实现对SAHS严重程度的定量评估。选取美国国家心肺血液研究所睡眠健康数据库中54名受试者的腹部位移信号对LSTM-CNN算法进行测试。对于处理得到的超过90万数据片段, 正确率、敏感度、特异度分别为88.6%、88.2%、88.7%;54名被试的AHI预测结果与多导睡眠图(PSG)标注结果相比, 皮尔逊相关指数达到0.98;观察SAHS严重程度诊断结果, kappa系数达到0.95。结果表明, 所提出的方法不仅可以实现对AH事件的高精度检测, 而且可以对AHI指数与SAHS严重程度做出准确估计, 有望用于PSG检测之前SAHS的初步诊断以及成为家用SAHS长期监护工具。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	余辉
	王硕
	李心蕊
	邓晨阳
	孙敬来
	张力新
	曹玉珍

关键词 ：长短时记忆网络, 卷积神经网络, 睡眠呼吸暂停与低通气综合征, 多导睡眠图

Abstract：Sleep apnea and hypopnea syndrome (SAHS) is a potentially fatal disease as well as affects sleep quality. In order to balance the accuracy and time resolution of apnea and hypopnea (AH) event detection, this paper proposed a long-short term memory-convolutional neural network (LSTM-CNN) to predict AH event precisely, meanwhile an apnea-hypopnea index (AHI) estimation method based on event detection results was adopted to quantitatively assess the SAHS severity. The algorithm was tested using 54 subjects’ abdomen movement signals from National Heart Lung & Blood Institute. For over 900, 000 data fragments after preprocessing, the accuracy, sensitivity and specificity were 88.6%, 88.2% and 88.7% respectively. For the 54 subjects’ AHI, the Pearson correlation coefficient between estimated AHI and AHI scored from polysomnography (PSG) reached 0.98 and the Cohen's kappa coefficient for SAHS severity was 0.95. The results showed that this method not only realized a high-precision detection of AH event, but also accurately estimated the AHI and the severity of SAHS, therefore held the potential to be used for SAHS diagnosis before PSG or long-term monitoring of SAHS at home.

Key words： long-short term memory convolutional neural network sleep apnea and hypopnea syndrome polysomnography

收稿日期: 2019-04-19

PACS:

R318

基金资助:天津科技重大专项与工程(18ZXZNSY00240, 16ZXCXSF00040, 20ZXGBSY00060);国家重点研发计划(2019YFC0119402)

通讯作者: *, E-mail: yuzhenCao18@126.com

引用本文:

余辉, 王硕, 李心蕊, 邓晨阳, 孙敬来, 张力新, 曹玉珍. 基于LSTM-CNN的睡眠呼吸暂停与低通气事件实时检测算法研究[J]. 中国生物医学工程学报, 2020, 39(3): 303-310.
Yu Hui, Wang Shuo, Li Xinrui, Deng Chenyang, Sun Jinglai, Zhang Lixin, Cao Yuzhen. Algorithm Study of Real-Time Detection of Sleep Apnea-Hypopnea Event Based on Long-Short Term Memory-Convolutional Neural Network. Chinese Journal of Biomedical Engineering, 2020, 39(3): 303-310.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2020.03.07 或 http://cjbme.csbme.org/CN/Y2020/V39/I3/303

[1] Jordan AS, Mcsharry DG, Malhotra A. Adult obstructive sleep apnoea [J]. Lancet, 2014, 383(9918): 736-747.
[2] Young T, Palta M, Dempsey J, et al. The occurrence of sleep-disordered breathing among middle-aged adults [J]. The New England Journal of Medicine, 1993, 328(17): 1230-1235.
[3] Mcnames JN, Fraser AM. Obstructive sleep apnea classification based on spectrogram patterns in the electrocardiogram[C]//Computers in Cardiology. Cambridge:IEEE, 2000:749-752.
[4] Timus O, Dogru Bolat E. k-NN-based classification of sleep apnea types using ECG [J]. Turkish Journal of Electrical Engineering and Computer Sciences, 2017, 25(4): 3008-3023.
[5] 周洪建, 黄大同. 利用ECG信号检测睡眠呼吸暂停的小波包分析方法 [J]. 中国医学物理学杂志, 2003, 20(4): 71-72, 84.
[6] Choi SH, Yoon H, Kim HS, et al. Real-time apnea-hypopnea event detection during sleep by convolutional neural networks [J]. Computers in Biology and Medicine, 2018, 100: 123-131.
[7] Gutierrez-Tobal GC, Alvarez D, Del Campo F, et al. Utility of AdaBoost to detect sleep apnea-hypopnea syndrome from single-channel airflow [J]. IEEE Trans Biomed Eng, 2016, 63(3): 636-646.
[8] Lee H, Park J, Kim H, et al. New rule-based algorithm for real-time detecting sleep apnea and hypopnea events using a nasal pressure signal [J]. Journal of Medical Systems, 2016, 40(12): 282.
[9] Nakano H, Tanigawao T, Furukawa T, et al. Automatic detection of sleep-disordered breathing from a single-channel airflow record [J]. European Respiratory Journal, 2007, 29(4): 728-736.
[10] Jung DW, Hwang SH, Cho JG, et al. Real-time automatic apneic event detection using nocturnal pulse oximetry [J]. IEEE Trans Biomed Eng, 2018, 65(3): 706-712.
[11] Sola-Soler J, Antonio Fiz J, Morera J, et al. Multiclass classification of subjects with sleep apnoea-hypopnoea syndrome through snoring analysis [J]. Medical Engineering & Physics, 2012, 34(9): 1213-1220.
[12] 陈伟伟. 基于鼾声检测的睡眠呼吸暂停低通气综合症诊断 [D]; 大连:大连理工大学, 2010.
[13] Huang W, Guo B, Shen Y, et al. A novel method to precisely detect apnea and hypopnea events by airflow and oximetry signals [J]. Computers in Biology and Medicine, 2017, 88: 32-40.
[14] 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.
[15] 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.
[16] Hoa Dinh N, Wilkins BA, Cheng Q, et al. An online sleep apnea detection method based on recurrence quantification analysis [J]. IEEE Journal of Biomedical and Health Informatics, 2014, 18(4): 1285-1293.
[17] 金海龙, 张志慧. 基于希尔伯特-黄变换和BP神经网络的运动想象脑电研究 [J]. 生物医学工程学杂志, 2013, 30(2): 249-253.
[18] 魏琛, 陈兰岚, 张傲. 基于集成卷积神经网络的脑电情感识别 [J]. 华东理工大学学报(自然科学版), 2019, 45(4):614-622.
[19] 余明, 陈锋, 张广, 等. 应用遗传算法优化神经网络的致死性心电节律辨识算法研究 [J]. 生物医学工程学杂志, 2017, 34(3): 421-430.
[20] Zhang GQ, Cui L, Mueller R, et al. The National Sleep Research Resource: Towards a sleep data commons [J].JAMIA, 2018, 25(10): 1351-1358.
[21] Dean DA, Goldberger AL, Mueller R, et al. Scaling up scientific discovery in sleep medicine: The National Sleep Research Resource [J]. Sleep, 2016, 39(5): 1151-1164.
[22] Graves A. Long short-term memory [J]. Neural Computation, 1997, 9(8): 1735-1780.
[23] 米切尔.机器学习[M].北京:机械工业出版社, 2003:276-278.
[24] Yu H, Deng C, Sun J, et al. Cascading detection model for prediction of apnea-hypopnea events based on nasal flow and arterial blood oxygen saturation [J]. Sleep & Breathing, 2019, 7(5):1-8.