Abstract
Methods developed for automatic sleep stage detection make use of large amounts of data in the form of polysomnographic (PSG) recordings to build predictive models. In this study, we investigate the effect of several dimensionality reduction techniques, i.e., principal component analysis (PCA), factor analysis (FA), and autoencoders (AE) on common classifiers, e.g., random forests (RF), multilayer perceptron (MLP), long-short term memory (LSTM) networks, for automated sleep stage detection. Experimental testing is carried out on the MGH Dataset provided in the “You Snooze, You Win: The PhysioNet/Computing in Cardiology Challenge 2018”. The signals used as input are the six available (EEG) electoencephalographic channels and combinations with the other PSG signals provided: ECG – electrocardiogram, EMG – electromyogram, respiration based signals – respiratory efforts and airflow. We observe that a similar or improved accuracy is obtained in most cases when using all dimensionality reduction techniques, which is a promising result as it allows to reduce the computational load while maintaining performance and in some cases also improves the accuracy of automated sleep stage detection. In our study, using autoencoders for dimensionality reduction maintains the performance of the model, while using PCA and FA the accuracy of the models is in most cases improved.
Research funding: None declared.
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
Competing interests: Authors state no conflict of interest.
References
1. Berry Brooks, RB, Gamaldo, R, Harding, CE, Lloyd, SM, Quan, RM, Troester, SF, et al. The AASM manual for the scoring of sleep and associated events. Version 2.4. Darien: American Academy of Sleep Medicine; 2017.Search in Google Scholar
2. Louis Erik, K, Boeve, FB. REM sleep behavior disorder: diagnosis, clinical implications and future directions. Mayo Clinic Proc;11:1723–36.Search in Google Scholar
3. Fiorillo, L, Puiatti, A, Papandrea, M, Ratti, PL, Favaro, P, Roth, C, et al. Automated sleep scoring: a review of the latest approaches. Sleep Med Rev 2019;48. https://doi.org/10.1016/j.smrv.2019.07.007.Search in Google Scholar
4. Rahman, MM, Bhuiyan, MIH, Hassan, AR. Sleep stage classification using single-channel EOG. Comput Med Biol 2018;102:211–20. https://doi.org/10.1016/j.compbiomed.2018.08.022.Search in Google Scholar
5. Tsinalis, O, Matthews, PM, Guo, Y, Zafeiriou, S. Automatic sleep stage scoring with single-channel EEG using convolutional neural networks. arXiv 2016, arXiv:1610.01683.Search in Google Scholar
6. Hassan, AR, Subasi, A. A decision support system for automated identification of sleep stages from single-channel EEG signals. Knowl Base Syst 2017;128:115–24. https://doi.org/10.1016/j.knosys.2017.05.005.Search in Google Scholar
7. Biswal, S, Kulas, J, Sun, H, Goparaju, B, Westover, MB, Bianchi, MT, et al. SLEEPNET: automated sleep staging system via deep learning. arXiv 2017, arXiv:1707.08262v1.Search in Google Scholar
8. Zhao, D, Wang, Y, Wang, Q, Wang, X. Comparative analysis of different characteristics of automatic sleep stages. Comput Methods Progr Biomed 2019;175:53–72. https://doi.org/10.1016/j.cmpb.2019.04.004.Search in Google Scholar
9. Aboalayon, K, Faezipour, M, Almuhammadi, W, Moslehpour, S. Sleep stage classification using EEG signal analysis: a comprehensive survey and new investigation. Entropy 2016;18:272. https://doi.org/10.3390/e18090272.Search in Google Scholar
10. Memar, P, Faradji, F. A novel multi-class EEG-based sleep stage classification system. IEEE Trans Neural Syst Rehabil Eng 2017;26:84–95. https://doi.org/10.1109/TNSRE.2017.2776149.Search in Google Scholar
11. Tautan, A-M, Rossi, AC, De Franciso, R, Ionescu, B. Automatic sleep stage detection using a single channel frontal EEG. In: The 7th IEEE International Conference on E-Health and Bioengineering – EHB Iasi, Romania: IEEE; 2019.10.1109/EHB47216.2019.8969973Search in Google Scholar
12. Hassan, AR, Bhuiyan, MIH. A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral features. J Neurosci Methods 2016;271:107–18. https://doi.org/10.1016/j.jneumeth.2016.07.012.Search in Google Scholar
13. Alickovic, E, Subasi, A. Ensemble SVM method for automatic sleep stage classification. IEEE Trans Instrum Meas 2018;667:1258–65. https://doi.org/10.1109/tim.2018.2799059.Search in Google Scholar
14. Hassan, AR, Bhuiyan, MIH. Automated identification of sleep states from EEG signals by means of ensemble empirical mode decomposition and random under sampling boosting. Comput Methods Progr Biomed 2017;140:201–10. https://doi.org/10.1016/j.cmpb.2016.12.015.Search in Google Scholar
15. Yang, Y, Zheng, X, Yuan, F. A study on automatic sleep stage classification based on CNN-LSTM. In: Proceedings of the 3rd International Conference on Crowd Science and Engineering Singapore, New York, NY, USA: Association for Computing Machinery; 2018. pp. 1–5.10.1145/3265689.3265693Search in Google Scholar
16. Vilamala, A, Madsen, KH, Hansen, LK. Deep convolutional neural networks for interpretable analysis of EEG sleep stage scoring. arXiv 2018, arXiv:1710.00633.10.1109/MLSP.2017.8168133Search in Google Scholar
17. Patanaik, A, Ong, JL, Gooley, JJ, Ancoli-Israel, S, Chee, MWL. An end-to-end framework for real-time automatic sleep stage classification. Sleep 2018:41. https://dx.doi.org/10.1093%2Fsleep%2Fzsy041.10.1093/sleep/zsy041Search in Google Scholar PubMed PubMed Central
18. Sun, Y, Wang, B, Jin, J, WAng, X. Deep convolutional network method for automatic sleep stage classification based on neurophysiological signals. In: 11th International congress on image and signal processing. Beijing, China: BioMedical Engineering and Informatics; 2018.10.1109/CISP-BMEI.2018.8633058Search in Google Scholar
19. Van Der Maaten, LJP, Postma, EO, Van Den Herik, HJ. Dimensionality reduction: a comparative review. J Mach Learn Res 2009;10:1–41. https://lvdmaaten.github.io/publications/papers/TR_Dimensionality_Reduction_Review_2009.pdf.Search in Google Scholar
20. Khosla, N. Dimensionality reduction using factor analysis. Australia: Griffith University Queensland; 2006. Thesis (Masters).Search in Google Scholar
21. Fan, Y. Research on feature extraction of EEG signals using MSE-PCA and sleep staging. IEEE International Conference on Signal Processing, Communications and Computing,Qingdao, China: ICSPCC, IEEE; 2018,2. p. 1–5.10.1109/ICSPCC.2018.8567757Search in Google Scholar
22. Najdi, S, Gharbali, AA, Fonseca, JM. Feature transformation based on stacked sparse autoencoders for sleep stage classification. IFIP Int Fed Inf Process 2017;499:144–53. https://doi.org/10.1007/978-3-319-56077-9_18.Search in Google Scholar
23. Prabhudesai, KS, Collins, LM, Mainsah, BO. Automated feature learning using deep convolutional auto-encoder neural network for clustering electroencephalograms into sleep stages. In: 9th International IEEE EMBS Conference on Neural Engineering, San Francisco, CA, USA: IEEE; 2019.10.1109/NER.2019.8716996Search in Google Scholar
24. Najdi, S. Feature extraction and selection in automatic sleep stage classification. Lisbon: Universidade Nova de Lisboa; 2018. Master Thesis.Search in Google Scholar
25. Ghassemi, MM, Moody, BE, Lehman, LWH, Song, C, Li, Q, Sun, H, et al. You snooze, you win: the PhysioNet/computing in cardiology challenge 2018. Comput Cardiol 2018:20–3. https://doi.org/10.22489/CinC.2018.049.Search in Google Scholar
26. Goldberger, AL, Amaral, LA, Glass, L, Hausdorff, JM, Ivanov, PC, Mark, RG, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circ J Am Heart Assoc 2000;23:101. https://doi.org/10.1161/01.cir.101.23.e215.Search in Google Scholar
27. Colten, HR, Altevogt, BM. Sleep disorders and sleep deprivation: an unmet public health problem. Washington, D.C.: The National Academies Press; 2006. p. 34–9.Search in Google Scholar
28. Chouchou, F, Desseilles, M. Heart rate variability: a tool to explore the sleeping brain?. Front Neurosci 2014;8:402. https://doi.org/10.3389/fnins.2014.00402.Search in Google Scholar
29. Sedghamiz, H. Matlab implemenation of Pan Tompkins ECG QRS detector. “msc3”; 2014.Search in Google Scholar
30. Pan, J, Tompkins, WJ. Pan Tompkins 1985–QRS detection. IEEE (Inst Electr Electron Eng) Trans Biomed Eng 1985;32:230–6. https://doi.org/10.1109/tbme.1985.325532.Search in Google Scholar
31. Van Steenkiste, T, Groenendaal, W, Ruyssinck, J, Dreesen, P, Klerkx, S, Smeets, C, et al. Systematic comparison of respiratory signals for the automated detection of sleep apnea. In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Honolulu, HI, USA; 2018. pp. 449–52.10.1109/EMBC.2018.8512307Search in Google Scholar PubMed
32. Fonseca, P, Long, X, Radha, M, Haakma, R, Aarts, RM, Rolink, J. Sleep stage classification with ECG and respiratory effort. Physiol Meas 2015;36:2027–40. https://doi.org/10.1088/0967-3334/36/10/2027.Search in Google Scholar
33. Tautan, A-M, Rossi, AC, De Franciso, R, Ionescu, B. Automatic sleep stage detection: a study on the influence of various PSG input signals. In: 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, Montreal, QC, Canada; EMBC; 2020.10.1109/EMBC44109.2020.9175628Search in Google Scholar PubMed
34. Ross, D, Lim, J, Lin, R-S, Yang, M-H. Incremental learning for robust visual tracking. Int J Comput Vis 2008;77:125–41. https://doi.org/10.1007/s11263-007-0075-7.Search in Google Scholar
35. Hagan, MT, Demuth, HB, Beale, MH, De Jesus, O. Neural network design, 2nd ed, Sillwater, Oklahoma, USA: Martin Hagan; 1995.Search in Google Scholar
36. Bengio, Y. Learning deep architectures for AI trends in machine learning. Found Trends Mach Learn 2009;1:1–127. https://doi.org/10.1561/2200000006.Search in Google Scholar
37. Schroff, F, Criminisi, A, Zisserman, A. Object class segmentation using random forests. In: Proceedings of the British machine vision conference; 2008.10.5244/C.22.54Search in Google Scholar
38. Haykin, SO. Neural networks: a comprehensive foundation, 2nd ed., Delhi, India: Pearson Education (Singapore) Pte. Ltd.; 1999.Search in Google Scholar
39. Hochreiter, S, Schmidhuber, J. Long short-term memory. Neural Comput 1997;8:1735–80. https://doi.org/10.1162/neco.1997.9.8.1735.Search in Google Scholar
40. Chetlur, S, Woolley, C, Vandermersch, P, Cohen, J, Tran, J, Catanzaro, B, et al. cuDNN: efficient primitives for deep learning. arXiv 2014, arXiv:1410.0759v3.Search in Google Scholar
41. Kuo, CE, Chen, GT, Lin, NY. Automatic sleep staging using deep long short-term memory: validation in large-scale datasets. In: Proceedings of the 2019 3rd International conference on computational biology and bioinformatics, Nagoya, Japan; ACM;2019. pp. 58–64.10.1145/3365966.3365980Search in Google Scholar
42. Rosenburg, RS, Van Hour, S. The American Academy of sleep medicine inter-scorer reliability program: sleep stage scoring. J Clin Sleep Med 2013;9:81–7. https://doi.org/10.5664/jcsm.2350.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
