Abstract
Polysomnography (PSG)-based sleep stage scoring is time-consuming and it suffers from variability in results. With the help of automated PSG scoring, which is based on deep learning techniques, it is possible to reduce labor costs and variability inherent to this task. Instead of using publicly available sleep databases, we created our database by using the Philips Alice clinic device, which employs 19 sensor channels connected to subjects. Since every sensor channel creates a huge amount of data, we limited our work to 50 patients and pre-processed this data. The deep learning sleep-based sleep stage classifier demonstrates excellent accuracy and agreement with the sleep expert’s scoring. Average accuracy, precision, recall, and F1-measure were defined as 91.6, 90.9, 91.6, and 90.7% respectively. The proposed work has novelty when it is compared with similar deep learning-based automatic sleep staging studies by using 19 channels as input rather than employing only EEG, EOG, or EMG data. The proposed model is scientifically created for making job quite similar to the sleep doctors during sleep stage scoring automatically instead of manual steps used by them. Furthermore, as explained, our database is created by using a local hospital, which has a sleep clinic, rather than using publicly available databases. The proposed work will allow a fully automated PSG scoring system by having its own database and employing all PSG inputs.
Similar content being viewed by others
Data availability
All the research data presented in the work can be reached when contacting the author by email with a reasonable request.
References
Guilleminault C, Tilkian A, Dement WC (1976) The sleep apnea syndromes. Annu Rev Med 27(1):465–484
Jackson ML, Tolson J, Bartlett D, Berlowitz DJ, Varma P, Barnes M (2019) Clinical depression in untreated obstructive sleep apnea: examining predictors and a meta-analysis of prevalence rates. Sleep Med 62:22–28
Latina JM, Estes N, Garlitski AC (2013) The relationship between obstructive sleep apnea and atrial fibrillation: a complex interplay. Pulm Med. https://doi.org/10.1155/2013/621736
Teodorescu M, Polomis DA, Gangnon RE, Fedie JE, Consens FB, Chervin RD, Teodorescu MC (2013) Asthma control and its relationship with obstructive sleep apnea (OSA) in older adults. Sleep Disord. https://doi.org/10.1155/2013/251567
Al Lawati NM, Patel SR, Ayas NT (2009) Epidemiology, risk factors, and consequences of obstructive sleep apnea and short sleep duration. Prog Cardiovasc Dis 51(4):285–293
Sharma M, Raval M, Acharya UR (2019) A new approach to identify obstructive sleep apnea using an optimal orthogonal wavelet filter bank with ECG signals. Inform Med Unlocked 16:100170
Pearson M, Faust O (2019) Heart rate based sleep apnea detection using Arduino. J Mech Med Biol 19(01):1940006
Zarei A, Asl BM (2020) Performance evaluation of the spectral autocorrelation function and autoregressive models for automated sleep apnea detection using single-lead ECG signal. Comput Method Program Biomed 195:105626
Keles T, Durmaz T, Bayram NA, Ciftci B, Yeter E, Akcay M, Bozkurt E (2009) Effect of continuous positive airway pressure therapy on aortic stiffness in patients with obstructive sleep apnea syndrome. Echocardiography 26(10):1217–1224
Iber C (2007) The AASM manual for the scoring of sleep and associated events: rules. Terminol Tech Specif 2007:1–10
Ramachandran A, Karuppiah A (2021) A survey on recent advances in machine learning based sleep apnea detection systems. Healthcare. Multidisciplinary Digital Publishing Institute, Basel, Switzerland, p 914
Schmidt J, Marques MR, Botti S, Marques MA (2019) Recent advances and applications of machine learning in solid-state materials science. NPJ Comput Mater 5(1):1–36
Rim B, Sung NJ, Min S, Hong M (2020) Deep learning in physiological signal data: a survey. Sensors 20(4):969
Nielsen MA (2015) Neural networks and deep learning, vol 25. Determination press, San Francisco, CA
Hatcher WG, Yu W (2018) A survey of deep learning: platforms, applications and emerging research trends. IEEE Access 6:24411–24432
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Ozturk T, Talo M, Yildirim EA, Baloglu UB, Yildirim O, Acharya UR (2020) Automated detection of COVID-19 cases using deep neural networks with X-ray images. Comput Biol Med 121:103792
Gangstad SW, Mikkelsen KB, Kidmose P, Tabar YR, Weisdorf S, Lauritzen MH, Duun-Henriksen J (2019) Automatic sleep stage classification based on subcutaneous EEG in patients with epilepsy. Biomed Eng Online 18(1):1–17
Ankitha V, Manimegalai P, Jose PSH, Raji P (2021) Literature review on sleep APNEA analysis by machine learning algorithms using ECG signals. J Phys Conf Ser 1937(1):012054
Xia B, Li, Q, Jia J, Wang J, Chaudhary U, Ramos-Murguialday A, and Birbaumer N (2015) Electrooculogram based sleep stage classification using deep belief network. In: 2015 international joint conference on neural networks (IJCNN), IEEE, p 1–5
Mostafa SS, Mendonça F, Morgado-Dias F, and Ravelo-García A (2017) SpO2 based sleep apnea detection using deep learning. In: 2017 IEEE 21st international conference on intelligent engineering systems (INES), p 000091–000096
Hassan AR, Bashar SK, and Bhuiyan MIH (2017) Computerized obstructive sleep apnea diagnosis from single-lead ECG signals using dual-tree complex wavelet transform. In: 2017 IEEE region 10 humanitarian technology conference (R10-HTC), p 43–46
Li K, Pan W, Li Y, Jiang Q, Liu G (2018) A method to detect sleep apnea based on deep neural network and hidden Markov model using single-lead ECG signal. Neurocomputing 294:94–101
Kim T, Kim JW, Lee K (2018) Detection of sleep disordered breathing severity using acoustic biomarker and machine learning techniques. Biomed Eng Online 17(1):1–19
Erdenebayar U, Kim YJ, Park JU, Joo EY, Lee KJ (2019) Deep learning approaches for automatic detection of sleep apnea events from an electrocardiogram. Comput Method Program Biomed 180:105001
Rahman MM, Bhuiyan MIH, Hassan AR (2018) Sleep stage classification using single-channel EOG. Comput Biol Med 102:211–220
Wang T, Lu C, Shen G (2019) Detection of sleep apnea from single-lead ECG signal using a time window artificial neural network. BioMed Res Int. https://doi.org/10.1155/2019/9768072
Phan H, Andreotti F, Cooray N, Chén OY, De Vos M (2019) SeqSleepNet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging. IEEE Trans Neural Syst Rehabil Eng 27(3):400–410
Mostafa SS, Mendonça F, Ravelo-García AG, Morgado-Dias F (2019) A systematic review of detecting sleep apnea using deep learning. Sensors 19(22):4934
Sridhar N, Shoeb A, Stephens P, Kharbouch A, Shimol DB, Burkart J, Myers L (2020) Deep learning for automated sleep staging using instantaneous heart rate. NPJ Digit Med 3(1):1–10
Tuncer SA, Akılotu B, Toraman S (2019) A deep learning-based decision support system for diagnosis of OSAS using PTT signals. Med Hypothese 127:15–22
Loh HW, Ooi CP, Vicnesh J, Oh SL, Faust O, Gertych A, Acharya UR (2020) Automated detection of sleep stages using deep learning techniques: a systematic review of the last decade (2010–2020). Appl Sci 10(24):8963
Supratak A, Dong H, Wu C, Guo Y (2017) DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Trans Neural Syst Rehabil Eng 25(11):1998–2008
Vilamala A, Madsen KH, and Hansen LK (2017) Deep convolutional neural networks for interpretable analysis of EEG sleep stage scoring. In: 2017 IEEE 27th international workshop on machine learning for signal processing (MLSP), p 1–6
Biswal S, Kulas J, Sun H, Goparaju B, Westover MB, Bianchi MT, and SunJ (2017) SLEEPNET: automated sleep staging system via deep learning. arXiv preprint arXiv:1707.08262
Tripathy RK, Acharya UR (2018) Use of features from RR-time series and EEG signals for automated classification of sleep stages in deep neural network framework. Biocybern Biomed Eng 38(4):890–902
Chambon S, Galtier MN, Arnal PJ, Wainrib G, Gramfort A (2018) A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Trans Neural Syst Rehabil Eng 26(4):758–769
Biswal S, Sun H, Goparaju B, Westover MB, Sun J, Bianchi MT (2018) Expert-level sleep scoring with deep neural networks. J Am Med Inform Assoc 25(12):1643–1650
Yildirim O, Baloglu UB, Acharya UR (2019) A deep learning model for automated sleep stages classification using PSG signals. Int J Environ Res Public Health 16(4):599
Mousavi S, Afghah F, Acharya UR (2019) SleepEEGNet: automated sleep stage scoring with sequence-to-sequence deep learning approach. PLoS ONE 14(5):e0216456
Sokolovsky M, Guerrero F, Paisarnsrisomsuk S, Ruiz C, Alvarez SA (2019) Deep learning for automated feature discovery and classification of sleep stages. IEEE/ACM Trans Comput Biol Bioinform 17(6):1835–1845
Zhang L, Fabbri D, Upender R, Kent D (2019) Automated sleep stage scoring of the sleep heart health study using deep neural networks. Sleep. https://doi.org/10.1093/sleep/zsz159
Yuan Y, Jia K, Ma F, Xun G, Wang Y, Su L, Zhang A (2019) A hybrid self-attention deep learning framework for multivariate sleep stage classification. BMC Bioinform 20(16):1–10
Zhang X, Xu M, Li Y, Su M, Xu Z, Wang C, Han D (2020) Automated multi-model deep neural network for sleep stage scoring with unfiltered clinical data. Sleep Breath 24(2):581–590
Fernandez-Blanco E, Rivero D, Pazos A (2020) Convolutional neural networks for sleep stage scoring on a two-channel EEG signal. Soft Comput 24(6):4067–4079
Fu M, Wang Y, Chen Z, Li J, Xu F, Liu X, Hou F (2021) Deep learning in automatic sleep staging with a single channel electroencephalography. Front Physiol 12:179
Kuo CE, Liao PY, and Lin YS (2021) A Self-attention-based ensemble convolution neural network approach for sleep stage classification with merged spectrogram. In: 2021 Asia-pacific signal and information processing association annual summit and conference (APSIPA ASC), p 1262–1268
Pei W, Li Y, Siuly S, Wen P (2022) A hybrid deep learning scheme for multi-channel sleep stage classification. Comput Mater Contin 71(1):889–905
Kwon K, Kwon S, Yeo WH (2022) Automatic and accurate sleep stage classification via a convolutional deep neural network and nanomembrane electrodes. Biosensors 12(3):155
Bahrami M, Forouzanfar M (2022) Sleep apnea detection from single-lead ECG: a comprehensive analysis of machine learning and deep learning algorithms. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2022.3151947
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A: All classification results for 50 subjects
Appendix A: All classification results for 50 subjects
No | Accuracy | Precision | Recall | F1-measure |
---|---|---|---|---|
1 | 0.880 | 0.865 | 0.876 | 0.864 |
2 | 0.920 | 0.922 | 0.921 | 0.915 |
3 | 0.880 | 0.868 | 0.875 | 0.864 |
4 | 0.910 | 0.907 | 0.909 | 0.900 |
5 | 0.910 | 0.890 | 0.905 | 0.894 |
6 | 0.930 | 0.925 | 0.927 | 0.918 |
7 | 0.930 | 0.928 | 0.930 | 0.925 |
8 | 0.890 | 0.870 | 0.888 | 0.869 |
9 | 0.940 | 0.939 | 0.943 | 0.939 |
10 | 0.920 | 0.920 | 0.925 | 0.921 |
11 | 0.890 | 0.881 | 0.891 | 0.882 |
12 | 0.890 | 0.876 | 0.886 | 0.868 |
13 | 0.950 | 0.953 | 0.954 | 0.952 |
14 | 0.940 | 0.929 | 0.939 | 0.931 |
15 | 0.950 | 0.944 | 0.948 | 0.943 |
16 | 0.920 | 0.904 | 0.916 | 0.909 |
17 | 0.920 | 0.921 | 0.924 | 0.919 |
18 | 0.900 | 0.891 | 0.903 | 0.895 |
19 | 0.890 | 0.893 | 0.895 | 0.888 |
20 | 0.940 | 0.934 | 0.936 | 0.931 |
21 | 0.930 | 0.926 | 0.929 | 0.925 |
22 | 0.890 | 0.887 | 0.892 | 0.885 |
23 | 0.920 | 0.910 | 0.915 | 0.908 |
24 | 0.920 | 0.911 | 0.922 | 0.916 |
25 | 0.890 | 0.885 | 0.893 | 0.885 |
26 | 0.940 | 0.922 | 0.939 | 0.925 |
27 | 0.920 | 0.911 | 0.921 | 0.911 |
28 | 0.910 | 0.903 | 0.912 | 0.902 |
29 | 0.900 | 0.895 | 0.901 | 0.892 |
30 | 0.920 | 0.904 | 0.915 | 0.904 |
31 | 0.880 | 0.869 | 0.876 | 0.864 |
32 | 0.880 | 0.870 | 0.882 | 0.870 |
33 | 0.900 | 0.880 | 0.897 | 0.883 |
34 | 0.900 | 0.886 | 0.901 | 0.890 |
35 | 0.910 | 0.911 | 0.912 | 0.907 |
36 | 0.920 | 0.914 | 0.920 | 0.913 |
37 | 0.920 | 0.920 | 0.923 | 0.918 |
38 | 0.960 | 0.955 | 0.959 | 0.951 |
39 | 0.940 | 0.934 | 0.941 | 0.931 |
40 | 0.930 | 0.921 | 0.926 | 0.917 |
41 | 0.890 | 0.890 | 0.895 | 0.880 |
42 | 0.920 | 0.916 | 0.924 | 0.916 |
43 | 0.920 | 0.916 | 0.922 | 0.914 |
44 | 0.970 | 0.966 | 0.967 | 0.965 |
45 | 0.930 | 0.927 | 0.930 | 0.923 |
46 | 0.900 | 0.896 | 0.901 | 0.896 |
47 | 0.940 | 0.936 | 0.936 | 0.931 |
48 | 0.890 | 0.877 | 0.893 | 0.877 |
49 | 0.930 | 0.924 | 0.931 | 0.925 |
50 | 0.880 | 0.871 | 0.881 | 0.868 |
Avg | 0.916 | 0.909 | 0.916 | 0.907 |
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Arslan, R.S., Ulutas, H., Köksal, A.S. et al. Sensitive deep learning application on sleep stage scoring by using all PSG data. Neural Comput & Applic 35, 7495–7508 (2023). https://doi.org/10.1007/s00521-022-08037-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-08037-z