Sleep Stage Classification Based on Heart Rate Variability Analysis and Model Performance Validation
Zheng Jiewen1,2, Zhang Yuezhou1, Lan Ke1, Liu Xiaoli3, Zhang Zhengbo4#*, Yu Mengsun2#*
1(Bejing SensEcho Science & Technology Co.,Ltd,Beijing 100041,China) 2(Air Force Medical Center,PLA,Beijing 100037,China) 3(School of Biological Science and Medical Engineering,Beihang University,Beijing 100119,China) 4(Department of Biomedical Engineering,Chinese PLA General Hospital,Beijing 100853,China)
Abstract To conduct sleep stage classification and provide technical support for the application of wearable physiological monitoring technology in the field of chronic disease monitoring and management,a sleep stage classification algorithm based on heart rate variability (HRV) analysis and support vector machine (SVM) was developed. In order to ensure the quality of the training set,67 polysomnography (PSG) records were extracted by experts from the SHHS (Sleep Heart Health Study) PSG database for model training and internal validation. The sleep stages (wake,rapid eye movement and non-rapid eye movement) classified by EEG signals were used as labels to train the SVM model. Totally 86 features were derived from HRV analysis,including time domain,frequency domain and nonlinear domain. To test the generalization of the model,another 939 PSG records were further randomly extracted from the SHHS PSG database for model external validation. The accuracy of the 5-fold cross-validation on the training dataset of the 67 PSG records was 84.00%±1.33%,with a Kappa coefficient:0.70±0.03,and the accuracy of the algorithm on the 939 PSG records was 76.10%±10.8%,with a Kappa coefficient:0.57±0.15. The accuracy and the Kappa coefficient increased to 82.00%±5.6% and 0.67±0.14 when some records were excluded from the test dataset,including 110 records with abnormal RR intervals and 29 records with apparent abnormal sleep structures. These results showed that the model of heart rate variability analysis based sleep stage classification proposed in this paper exhibited a good performance,and the external validation by a dataset with large sample size demonstrated the generalization of the model.
Zheng Jiewen,Zhang Yuezhou,Lan Ke, et al. Sleep Stage Classification Based on Heart Rate Variability Analysis and Model Performance Validation[J]. Chinese Journal of Biomedical Engineering, 2020, 39(4): 432-439.
[1] Denes P.Sleep and cardiac arrhythmias in adults[J].Journal of Cardiovascular Electrophysiology,2010,2(6):481-495. [2] Harrison Y,Horne JA.Sleep loss and temporal memory[J].Quarterly Journal of Experimental Psychology,2000,53(1):271-279. [3] Breslau N,Roth T,Rosenthal L,et al.Sleep disturbance and psychiatric disorders:A longitudinal epidemiologic study of young adults[J].Biological Psychiatry,1996,39(6):411-418. [4] 美国睡眠医学会.睡眠及其相关事件判读手册:规则、术语和技术规范(2.3版)[M].北京:人民卫生出版社,2017:1-4. [5] Hori T,Sugita Y,Koga E,et al.Proposed supplements and amendments to ‘A Manual of Standardized Terminology,Techniques and Scoring System for Sleep Stages of Human Subjects’,the Rechtschaffen &Kales (1968) standard[J].Psychiatry &Clinical Neurosciences,2001,55(3):305-310. [6] Tataraidze A,Korostovtseva L,Anishchenko L,et al.Sleep architecture measurement based on cardiorespiratory parameters[C]//Engineering in Medicine and Biology Society.Orlando:IEEE,2016:3478-3481. [7] Bsoul M,Minn H,Nourani M,et al.Real-time sleep quality assessment using single-lead ECG and multi-stage SVM classifier[C]//IEEE Engineering in Medicine and Biology.Buenos Aires:IEEE,2010:1178-1181. [8] Adnane M,Jiang Z,Yan Z.Sleep-wake stages classification and sleep efficiency estimation using single-lead electrocardiogram[J].Expert Systems with Applications,2012,39(1):1401-1413. [9] Xiao M,Yan H,Song J,et al.Sleep stages classification based on heart rate variability and random forest[J].Biomedical Signal Processing and Control,2013,8(6):624-633. [10] Willemen T,Van Deun D,Verhaert V,et al.An evaluation of cardiorespiratory and movement features with respect to sleep-stage classification[J].IEEE Journal of Biomedical and Health Informatics,2014,18(2):661-669. [11] 杨军,俞梦孙,王宏山,等.多参数信息融合实现非脑电的睡眠结构分期[J].中国生物医学工程学报,2006,25(3):315-321. [12] 王金海,孙微,韦然,等.基于心率变异性分析的睡眠分期方法研究[J].生物医学工程学杂志,2016,33(3):420-425. [13] Fonseca P,Long X,Radha M,et al.Sleep stage classification with ECG and respiratory effort[J].Physiological Measurement,2015,36(10):2027-2040. [14] Penzel T,Moody GB,Mark RG,et al.The Apnea-ECG Database[C]//Computers in Cardiology 2000.Cambridge:IEEE,2000,27(Cat.00CH37163):255-258. [15] 杨军,俞梦孙.多分辨分析提取心率变异性中的睡眠结构信息[J].北京生物医学工程,2002,21(2):92-97. [16] Sankar AB,Kumar D,Seethalakshmi K.Enhanced method for extracting features of respiratory signals and detection of obstructive sleep apnea using threshold based automatic classification algorithm[J].International Journal of Computer Science &Emerging Technologies,2010,1(4):38-43. [17] Redmond SJ,Chazal P,Brien C,et al.Sleep staging using cardiorespiratory signals[J].Somnologie,2007,11(4):245-256. [18] Long X,Foussier J,Fonseca P,et al.Analyzing respiratory effort amplitude for automated sleep stage classification[J].Biomedical Signal Processing and Control,2014,14:197-205. [19] Long X,Fonseca P,Haakma R,et al.Time-frequency analysis of heart rate variability for sleep and wake classification[C]//Bioinformatics &Bioengineering (BIBE).Larnaca:IEEE,2012:85-90. [20] Quan SF,Howard BV,Iber C,et al.The sleep heart health study:design,rationale,and methods[J].Sleep,1997,20(12):1077-1085. [21] Redline S,Sanders MH,Lind BK,et al.Methods for obtaining and analyzing unattended polysomnography data for a multicenter study.Sleep Heart Health Research Group[J].Sleep,1998,21(7):759-767. [22] 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. [23] Zhang GQ,Cui L,Mueller R,et al.The National Sleep Research Resource:towards a sleep data commons[J].Journal of the American Medical Informatics Association,2018,25(10):1351-1358. [24] Hamilton P.Open source ECG analysis[C]//Computers in Cardiology.Memphis:IEEE,2002:101-104. [25] Hamilton PS,Tompkins WJ.Quantitative investigation of QRS detection rules using the MIT/BIH arrhythmia database[J].IEEE Transactions on Bio-medical Engineering,1986,33(12):1157-1165. [26] Camm AJ,Malik M,Bigger JT,et al.Heart rate variability:Standards of measurement,physiological interpretation and clinical use.Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology[J].Circulation,1996,93(5):1043-1065. [27] Willemen T,Van Deun D,Verhaert V,et al.Automatic sleep stage classification based on easy to register signals as a validation tool for ergonomic steering in smart bedding systems[J].Work,2012,41(S1):1985-1989. [28] Yilmaz B,Asyali MH,Arikan E,et al.Sleep stage and obstructive apneaic epoch classification using single-lead ECG[J].Biomedical Engineering Online,2010,9(39):1-14. [29] Long X.On the analysis and classification of sleep stages from cardiorespiratory activity[D].Eindhoven:Eindhoven University of Technology,2015. [30] Schulz H,Dirlich G,Balteskonis S,et al.The REM-NREM sleep cycle:renewal process or periodically driven process?[J].Sleep,1980,2(3):319-328. [31] Cortes C,Vapnik V.Support vector machine[J].Machine Learning,1995,20(3):273-297. [32] Platt JC.Probabilistic Output for Support Vector Machine and Comparisons to Regularized Likelihood Methods[M].Cambridge:MIT Press,1999:61-74. [33] Isa SM,Wasito I,Arymurthy AM.Kernel Dimensionality Reduction on Sleep Stage Classification using ECG Signal[J].International Journal of Computer Science Issues (IJCSI),2011,8(4):1178-1181. [34] Takeda T,Mizuno O,Tanaka T.Time-dependent sleep stage transition model based on heart rate variability[C]//Engineering in Medicine and Biology Society.Milan:IEEE,2015:2343-2346. [35] Tataraidze A,Anishchenko L,Korostovtseva L,et al.Sleep stage classification based on respiratory signal[C]//Engineering in Medicine and Biology Society.Milan:IEEE,2015:358-361. [36] Wei R,Zhang XH,Wang JH,et al.The research of sleep staging based on single-lead electrocardiogram and deep neural network[J].Biomedical Engineering Letters,2018,8(1):87-93. [37] Bianchi AM,Mendez MO,Cerutti S.Processing of signals recorded through smart devices:sleep-quality assessment[J].IEEE Transactions on Information Technology in Biomedicine,2010,14(3):741-747. [38] Aktaruzzaman M,Rivolta MW,Karmacharya R,et al.Performance comparison between wrist and chest actigraphy in combination with heart rate variability for sleep classification[J].Computers in Biology and Medicine,2017,89:212-221. [39] Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
