睡眠呼吸暂停的人工智能分析
Classification of Sleep Apnea with Artificial Intelligence
DOI: 10.12677/BIPHY.2020.81001, PDF,  被引量    国家自然科学基金支持
作者: 张 少杰, 尤欢欢, 钱镶玉, 何情祖, 胡 桓：厦门大学，物理科学与技术学院物理系，福建 厦门；林 海, 熊富海：厦门中翎易优创科技有限公司，福建 厦门；曹玉萍：中南大学湘雅二医院精神卫生研究所，国家精神心理疾病临床医学研究中心，湖南省精神医学中心，湖南 ；帅建伟*：厦门大学，物理科学与技术学院物理系，福建 厦门；厦门大学健康医疗大数据国家研究院，福建 厦门
关键词: 睡眠呼吸暂停；自动分类；机器学习；深度学习；Sleep Apnea； Automatic Classification； Machine Learning； Deep Learning
摘要: 睡眠呼吸暂停是一种与睡眠相关的呼吸障碍，如果同时引起慢性低氧血症及高碳酸血症，则通常被称为睡眠呼吸暂停综合征。睡眠多导图监测通常被用于睡眠呼吸暂停的判定和确诊，但睡眠多导图人工分析是一项耗时耗力的工作，因此自动判定睡眠呼吸暂停显得尤为重要。本文介绍了睡眠呼吸暂停的各种人工智能分类方法，包括基于统计规则的分类和基于深度学习的分类，而分析的数据可成单通道生理数据和多通道睡眠数据。通过对不同方法的分类结果进行对比讨论，显示基于深度学习对多通道数据进行多任务分析是未来关于睡眠呼吸暂停研究的主流方法。
Abstract: Sleep apnea is a breathing disorder associated with sleep, commonly known as sleep apnea syn-drome, which affects about 4% of the general population. It requires professionals to manually an-alyze the patients’ sleep polysomnography recorded in the hospital to diagnose sleep apnea, which is a time-consuming and labor-consuming process. Thus, it is important to develop methods to au-tomatically classify sleep apnea. This paper introduces a variety of artificial intelligence classifica-tion methods of sleep apnea, including classification based on statistical rules and classification based on deep learning, and the analysis data can be single channel physiological data and mul-ti-channel sleep data. We compare the classification results of different methods, and point out that the multi task analyses with deep learning algorithms on multi-channel data should be the main-stream of sleep apnea classification in the future.
文章引用：张少杰, 尤欢欢, 林海, 钱镶玉, 何情祖, 胡桓, 熊富海, 曹玉萍, 帅建伟. 睡眠呼吸暂停的人工智能分析[J]. 生物物理学, 2020, 8(1): 1-17. https://doi.org/10.12677/BIPHY.2020.81001

参考文献

[1] AASM (1999) Sleep-Related Breathing Disorders in Adults: Recommendations for Syndrome Definition and Measure-ment Techniques in Clinical Research. Sleep, 22, 667-689. [Google Scholar] [CrossRef] 
[2] White, D.P. (2005) Pathogenesis of Obstructive and Central Sleep Apnea. American Journal of Respiratory & Critical Care Medicine, 172, 1363-1370. [Google Scholar] [CrossRef] 
[3] 夏俊娣, 杜钟珍. 睡眠呼吸暂停综合征的综述[J]. 临床肺科杂志, 1999(2): 86-88.
[4] Young, T., Peppard, P.E. and Gottlieb, D.J. (2002) Epidemiology of Ob-structive Sleep Apnea: A Population Health Perspective. American Journal of Respiratory and Critical Care Medicine, 165, 1217-1239. [Google Scholar] [CrossRef] [PubMed]
[5] Malhotra, A. and White, D.P. (2002) Obstructive Sleep Apnea. The Lancet, 360, 237-245. [Google Scholar] [CrossRef] 
[6] Bloch, K.E. (1997) Polysomnography: A Systematic Review. Technology Health Care Official Journal of the European Society for Engineering Medicine, 5, 285-305. [Google Scholar] [CrossRef] 
[7] Block, A.J., Boysen, P.G., Wynne, J.W. and Hunt, L.A. (1980) Sleep Apnea, Hypopnea and Oxygen Desaturation in Normal Subjects. Survey of Anesthesiology, 24, 147. [Google Scholar] [CrossRef] 
[8] Gould, G.A., Whyte, K.F., Rhind, G.B., Airlie, M.A., Catterall, J.R., Shapiro, C.M. and Douglas, N.J. (1988) The Sleep Hypopnea Syndrome. American Review of Respiratory Disease, 137, 895. [Google Scholar] [CrossRef] [PubMed]
[9] Berry, R.B., Budhiraja, R., et al. (2012) Rules for Scoring Respira-tory Events in Sleep: Update of the 2007 AASM Manual for the Scoring of Sleep and Associated Events. Deliberations of the Sleep Apnea Definitions Task Force of the American Academy of Sleep Medicine. Journal of Clinical Sleep Medi-cine, 8, 597-619. [Google Scholar] [CrossRef] [PubMed]
[10] Penzel, T., Moody, G.B., Mark, R.G. and Peter, J.H. (2000) The Ap-nea-ECG Database. Computers in Cardiology, 27, 255-258. [Google Scholar] [CrossRef] 
[11] Ghassemi, M.M., Moody, B.E., Lehman, L.-W.H., Song, C., Li, Q., Sun, H.Q., Westover, M.B. and Clifford, G. (2018) You Snooze, You Win: The PhysioNet/Computing in Cardiology Challenge 2018. Computing in Cardiology Conference, Vol. 45, 1-4. [Google Scholar] [CrossRef] 
[12] Penzel, T., Mcnames, J., Chazal, P.D., Raymond, B., Murray, A. and Moody, G. (2002) Systematic Comparison of Different Algorithms for Apnoea Detection Based on Electrocardiogram Recordings. Medical Biological Engineering Computing, 40, 402-407. [Google Scholar] [CrossRef] 
[13] Yildiz, A., Akin, M. and Poyraz, M. (2011) An Expert System for Au-tomated Recognition of Patients with Obstructive Sleep Apnea Using Electrocardiogram Recordings. Expert Systems with Applications, 38, 12880-12890. [Google Scholar] [CrossRef] 
[14] Marcos, J.V., Hornero, R., Álvarez, D., Aboy, M. and Campo, F.D. (2012) Automated Prediction of the Apnea-Hypopnea Index from Nocturnal Oximetry Recordings. IEEE Transac-tions on Bio-Medical Engineering, 59, 141-149. [Google Scholar] [CrossRef] 
[15] Park, J.U., Lee, H.K., Lee, J., Urtnasan, E., Kim, H. and Lee, K.J. (2015) Automatic Classification of Apnea/Hypopnea Events through Sleep/Wake States and Severity of SDB from a Pulse Oximeter. Physiological Measurement, 36, 2009-2025. [Google Scholar] [CrossRef] [PubMed]
[16] Koley, B.L. and Dey, D. (2013) Automatic Detection of Sleep Apnea and Hypopnea Events from Single Channel Measurement of Respiration Signal Employing Ensemble Binary SVM Classifiers. Measurement, 46, 2082-2092. [Google Scholar] [CrossRef] 
[17] Solà-Soler, J., Fiz, J.A., Morera, J. and Jane, R. (2012) Multiclass Classification of Subjects with Sleep Apnoea-Hypopnoea Syndrome through Snoring Analysis. Medical En-gineering Physics, 34, 1213-1220. [Google Scholar] [CrossRef] [PubMed]
[18] Erdenebayar, J.L. (2017) Obstructive Sleep Apnea Screen-ing Using a Piezo-Electric Sensor. Journal of Korean Medical Science, 32, 893-899. [Google Scholar] [CrossRef] [PubMed]
[19] Khandoker, A.H., Gubbi, J. and Palaniswami, M. (2009) Auto-mated Scoring of Obstructive Sleep Apnea and Hypopnea Events Using Short-Term Electrocardiogram Recordings. IEEE Transactions on Information Technology in Biomedicine, 13, 1057-1067. [Google Scholar] [CrossRef] 
[20] Alvarez-Estevez, D. and Moret-Bonillo, V. (2009) Fuzzy Rea-soning Used to Detect Apneic Events in the Sleep Apnea-Hypopnea Syndrome. Expert Systems with Applications, 36, 7778-7785. [Google Scholar] [CrossRef] 
[21] Mendez, M.O., Corthout, J., Huffel, S.V., Matteucci, M., Penzel, T., Cerutti, S. and Bianchi, A.M. (2010) Automatic Screening of Obstructive Sleep Apnea from the ECG Based on Em-pirical Mode Decomposition and Wavelet Analysis. Physiological Measurement, 31, 273-289. [Google Scholar] [CrossRef] [PubMed]
[22] Al-Angari, H.M. and Sahakian, A.V. (2012) Automated Recog-nition of Obstructive Sleep Apnea Syndrome Using Support Vector Machine Classifier. IEEE Transactions on Infor-mation Technology in Biomedicine: A Publication of the IEEE Engineering in Medicine Biology Society, 16, 463-468. [Google Scholar] [CrossRef] 
[23] Moody, G.B., Mark, R.G., Zoccola, A. and Mantero, S. (1985) Derivation of Respiratory Signals from Multi-Lead ECGs. Computers in Cardiology, 12, 113-116.
[24] Khandoker, A.H., Palaniswami, M. and Karmakar, C.K. (2009) Support Vector Machines for Automated Recognition of Obstructive Sleep Apnea Syndrome from ECG Recordings. IEEE Transactions on Information Technology in Biomedicine, 13, 37-48. [Google Scholar] [CrossRef] 
[25] Chen, L., Zhang, X. and Wang, H. (2015) An Obstructive Sleep Apnea Detection Approach Using Kernel Density Classification Based on Single-Lead Electrocardiogram. Journal of Medical Systems, 39, 47. [Google Scholar] [CrossRef] [PubMed]
[26] Bsoul, M., Minn, H. and Tamil, L. (2011) Apnea Med-Assist: Real-Time Sleep Apnea Monitor Using Single-Lead ECG. IEEE Transactions on Information Technology in Biomedi-cine, 15, 416-427. [Google Scholar] [CrossRef] 
[27] Maier, C. and Dickhaus, H. (2006) Recurrence Analysis of Noc-turnal Heart Rate in Sleep Apnea Patients. Biomedizinische Technik Biomedical Engineering, 51, 224-228. [Google Scholar] [CrossRef] 
[28] Varon, C., Caicedo, A., Testelmans, D., Buyse, B. and Huffel, S.V. (2015) A Novel Algorithm for the Automatic Detection of Sleep Apnea from Single-Lead ECG. IEEE Transactions on Biomedical Engineering, 62, 2269-2278. [Google Scholar] [CrossRef] 
[29] Shannon, C.E. (1948) A Mathematical Theory of Communica-tion. Bell System Technical Journal, 27, 379-423. [Google Scholar] [CrossRef] 
[30] Mendez, M.O., Bianchi, A.M., Matteucci, M., Cerutti, S. and Penzel, T. (2009) Sleep Apnea Screening by Autoregressive Models from a Single ECG Lead. IEEE Transactions on Biomedical Engineering, 56, 2838-2850. [Google Scholar] [CrossRef] 
[31] Nguyen, H.D., Wilkins, B.A., Cheng, Q. and Benjamin, B.A. (2014) An Online Sleep Apnea Detection Method Based on Recurrence Quantification Analysis. IEEE Journal of Bio-medical and Health Informatics, 18, 1285-1293. [Google Scholar] [CrossRef] 
[32] Kesper, K., Canisius, S. and Penzel, T. (2012) ECG Signal Anal-ysis for the Assessment of Sleep-Disordered Breathing and Sleep Pattern. Medical & Biological Engineering & Compu-ting, 50, 135-144. [Google Scholar] [CrossRef] [PubMed]
[33] Hassan, A.R. (2015) Automatic Screening of Obstructive Sleep Apnea from Single-Lead Electrocardiogram. International Conference on Electrical Engineering & Information Commu-nication Technology, Dhaka, 21-23 May 2015, 1-6. [Google Scholar] [CrossRef] 
[34] Hassan, A.R. and Haque, M.A. (2015) Computer-Aided Ob-structive Sleep Apnea Screening from Single-Lead Electrocardiogram Using Statistical and Spectral Features and Boot-strap Aggregating. Biocybernetics Biomedical Engineering, 36, 256-266. [Google Scholar] [CrossRef] 
[35] Babaeizadeh, S., White, D.P., Pittman, S.D. and Zhou, S.H. (2010) Automatic Detection and Quantification of Sleep Apnea Using Heart Rate Variability. Journal of Electrocardiology, 43, 535-541. [Google Scholar] [CrossRef] [PubMed]
[36] Marcos, J.V., Hornero, R., Álvarez, D., Campo, F.D. and Zamarron, C. (2009) Assessment of Four Statistical Pattern Recognition Techniques to Assist in Obstructive Sleep Ap-noea Diagnosis from Nocturnal Oximetry. Medical Engineering Physics, 31, 971-978. [Google Scholar] [CrossRef] [PubMed]
[37] Hornero, R., Álvarez, D., Abasolo, D.D., Campo, F.D. and Zamarron, C. (2007) Utility of Approximate Entropy from Overnight Pulse Oximetry Data in the Diagnosis of the Ob-structive Sleep Apnea Syndrome. IEEE Transactions on Biomedical Engineering, 45, 107-113. [Google Scholar] [CrossRef] 
[38] Álvarez, D., Hornero, R., Abásolo, D., Campo, F.D. and Zamar-ron, C. (2006) Nonlinear Characteristics of Blood Oxygen Saturation from Nocturnal Oximetry for Obstructive Sleep Apnoea Detection. Physiological Measurement, 27, 399-412. [Google Scholar] [CrossRef] [PubMed]
[39] Kaimakamis, E., Bratsas, C., Sichletidis, L., Karvounis, C. and Maglaveras, N. (2009) Screening of Patients with Obstructive Sleep Apnea Syndrome Using C4.5 Algorithm Based on Non Linear Analysis of Respiratory Signals during Sleep. IEEE Engineering in Medicine and Biology Society, Minneap-olis, 3-6 September 2009, 3465-3469. [Google Scholar] [CrossRef] 
[40] Xie, B. and Minn, H. (2012) Real-Time Sleep Apnea Detection by Classifier Combination. IEEE Transactions on Information Technology in Biomedicine: A Publication of the IEEE Engineering in Medicine Biology Society, 16, 469-477. [Google Scholar] [CrossRef] 
[41] 葛晓丽, 邱召运, 索智鹏, 樊晓伟，修东铭. 睡眠呼吸暂停时间对血氧饱和度和心率的影响[J]. 生物医学工程与临床, 2020.
[42] 代长敏, 苏民民, 李彦如, 董宇涵. 脉搏波检测小儿阻塞性呼吸睡眠障碍综合征进展[J]. 生物医学工程与临床, 2020.
[43] Cohen, G. and De, C.P. (2013) Automated Detection of Sleep Apnea in Infants: A Multi-Modal Approach. Computers in Biology and Medicine, 63, 118-123. [Google Scholar] [CrossRef] [PubMed]
[44] Mendona, F., Mostafa, S.S., Ravelo-García, A.G., Mor-gado Dias, F. and Penzel, T. (2018) Devices for Home Detection of Obstructive Sleep Apnea: A Review. Sleep Medicine Reviews, 41, 149-160. [Google Scholar] [CrossRef] [PubMed]
[45] 荆斌, 张鹏, 李巍, 查玉华, 周双勤, 尚学义. 基于智能算法睡眠呼吸暂停监测系统设计[J]. 中国医学装备, 2011, 8(9): 21-24.
[46] Bawaskar, N.P. (2014) Analog Implicit Functional Testing Using Supervised Machine Learning. Dissertations and Theses.
[47] Kurtanovic, Z. and Maalej, W. (2017) Automatically Classifying Functional and Non-Functional Requirements Using Supervised Machine Learning. 2017 IEEE 25th International Requirements Engineering Conference, Lisbon, 4-8 September 2017, 490-495. [Google Scholar] [CrossRef] 
[48] Lecun, Y., Bengio, Y. and Hinton, G. (2015) Deep Learning. Nature, 521, 436. [Google Scholar] [CrossRef] [PubMed]
[49] Koch, H., Jennum, P. and Christensen, J.E. (2017) Automatic Sleep Classification Using Adaptive Segmentation Reveals Increased Number of Sleep Stage Transitions. Sleep Medicine, 40, e66. [Google Scholar] [CrossRef] 
[50] 王抒伟, 徐富献, 钱镶钰, 胡桓, 何情祖, 林海, 帅建伟. 应用深度神经网络对多导睡眠图的睡眠分期研究[J]. 生物物理报, 2019, 7(2): 11-25.
[51] 徐富献, 王抒伟, 钱镶钰, 胡桓, 何情祖, 林海, 帅建伟. 睡眠自动分期方法综述[J]. 生物物理报, 2019, 7(3): 34-48.
[52] Bahrami Rad, A., Zabihi, M., Zhao, Z., Gabbouj, M., Katsaggelos, A. and Sarkka, S. (2019) Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals Using Feature Engineering and a Bidirectional LSTM Net-work.
[53] Zabihi, M., Bahrami Rad, A., Kiranyaz, S. and Sarkka, S. (2019) 1D Convolutional Neural Network Models for Sleep Arousal Detection.
[54] Mousavi, S., Afghah, F. and Acharya, U.R. (2019) SleepEEGNet: Automated Sleep Stage Scoring with Sequence to Sequence Deep Learning Approach. PLoS ONE, 14, e0216456. [Google Scholar] [CrossRef] [PubMed]
[55] Dey, D., Chaudhuri, S. and Munshi, S. (2017) Obstructive Sleep Apnoea Detection Using Convolutional Neural Network Based Deep Learning Framework. Biomedical Engineer-ing Letters, 8, 95-100. [Google Scholar] [CrossRef] [PubMed]
[56] Erdenebayar, U., Jong-Uk, P. and Kyoung-Joung, L. (2018) Mul-ticlass Classification of Obstructive Sleep Apnea/Hypopnea Based on a Convolutional Neural Network from a Sin-gle-Lead Electrocardiogram. Physiological Measurement, 39, Article ID: 065003.
[57] Urtnasan, E., Park, J.U., Joo, E.Y. and Lee, K.J. (2018) Automated Detection of Obstructive Sleep Apnea Events from a Single-Lead Electrocardio-gram Using a Convolutional Neural Network. Journal of Medical Systems, 42, 104. [Google Scholar] [CrossRef] [PubMed]
[58] Ho, C.S., Heenam, Y., Seok, K.H., Kim, H.B., Kwon, H.B., Oh, S.M., Lee, Y.J. and Park, K.S. (2018) Real-Time Apnea-Hypopnea Event Detection during Sleep by Convolutional Neu-ral Networks. Computers in Biology and Medicine, 100, 123-131.
[59] Haidar, R., Koprinska, I. and Jeffries, B. (2017) Sleep Apnea Event Detection from Nasal Airflow Using Convolutional Neural Networks. International Conference on Neural Information Processing, Guangzhou, 14-18 November 2017, 819-827. [Google Scholar] [CrossRef] 
[60] Cen, L., Yu, Z.L., Kluge, T. and Ser, W. (2018) Automatic System for Obstructive Sleep Apnea Events Detection Using Convolutional Neural Network. Annual International Con-ference of the IEEE Engineering in Medicine Biology Society. IEEE Engineering in Medicine Biology Society. Annual Conference, Honolulu, 18-21 July 2018, 3975-3978. [Google Scholar] [CrossRef] 
[61] Mccloskey, S., Haidar, R., Koprinska, I. and Jeffries, B. (2018) Detecting Hypopnea and Obstructive Apnea Events Using Convolutional Neural Networks on Wavelet Spectrograms of Nasal Airflow. Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Mel-bourne, 3-6 June 2018, 361-372. [Google Scholar] [CrossRef] 
[62] 王佳珺. 面向鼾声识别的麦克风阵列干扰抑制方法研究[D]: [硕士学位论文]. 南京: 南京理工大学, 2017.
[63] 贺冲. 基于人工智能的鼾声数据分析方法研究[D]: [硕士学位论文]. 南京: 南京理工大学, 2019.
[64] Gao, Y. and Glowacka, D. (2016) Deep Gate Recurrent Neural Network. Asian Conference on Machine Learning.
[65] Tom, V.S., Willemijn, G., Deschrijver, D. and Dhaene, T. (2018) Auto-mated Sleep Apnea Detection in Raw Respiratory Signals Using Long Short-Term Memory Neural Networks. IEEE Journal of Biomedical Health Informatics, 23, 2354-2364.
[66] Kang, C.-H., Erdenebayar, U., Park, J.-U. and Lee, K.J. (2020) Multi-Class Classification of Sleep Apnea/Hypopnea Events Based on Long Short-Term Memory Using a Photo-plethysmography Signal. Journal of Medical Systems, 44, 14. [Google Scholar] [CrossRef] [PubMed]
[67] Cheng, M., Sori, W.J., Feng, J. and Khan, A. (2017) Recurrent Neural Network Based Classification of ECG Signal Features for Obstruction of Sleep Apnea Detection. IEEE Interna-tional Conference on Computational Science & Engineering & IEEE International Conference on Embedded & Ubiqui-tous Computing, Guangzhou, 21-24 July 2017, 199-202. [Google Scholar] [CrossRef] 
[68] Urtnasan, E., Park, J.-U. and Lee, K.-J. (2018) Automatic Detec-tion of Sleep-Disordered Breathing Events Using Recurrent Neural Networks from an Electrocardiogram Signal. Neural Computing and Applications, 32, 4733-4742. [Google Scholar] [CrossRef] 
[69] Biswal, S., Sun, H., Goparaju, B., Westover, M.B., Sun, J. and Bianchi, M.T. (2018) Expert-Level Sleep Scoring with Deep Neural Networks. Journal of the American Medical Infor-matics Association, 25, 1643-1650. [Google Scholar] [CrossRef] [PubMed]
[70] Banluesombatkul, N., Rakthanmanon, T. and Wilaiprasitporn, T. (2018) Single Channel ECG for Obstructive Sleep Apnea Severity Detection Using a Deep Learning Approach. 2018 IEEE Re-gion 10 Conference, Jeju, 28-31 October 2018, 2011-2016. [Google Scholar] [CrossRef] 
[71] Pourbabaee, B., Howe-Patterson, M., Patterson, M. and Benard, F. (2019) SleepNet: Automated Sleep Analysis via Dense Convolutional Neural Network Using Physiological Time Series. Physiological Measurement, 40, Article ID: 084005. [Google Scholar] [CrossRef] [PubMed]
[72] Jayatilaka, G., Weligampola, H., Sritharan, S. and Isuru, N. (2019) Non-Contact Infant Sleep Apnea Detection. 14th Conference on Industrial and Information Systems, Kandy, 18-20 De-cember 2019, 260-265. [Google Scholar] [CrossRef] 
[73] Nikolaidis, K., Kristiansen, S., Goebel, V., Plagemann, T., Liestø, K. and Kankanhalli, M. (2019) Augmenting Physiological Time Series Data: A Case Study for Sleep Apnea De-tection.
[74] 袁钦湄, 洪志令, 王星, 帅建伟, 曹玉萍. 人工智能在精神疾病中的应用与展望[J]. 国际精神病学杂志, 2020(1): 4-7.
[75] 袁钦湄, 王星, 帅建伟, 林海, 曹玉萍. 基于人工智能技术的抑郁症研究进展[J]. 中国临床心理学杂志, 2020, 28(1): 82-86.

为你推荐