Abstract
The lack of oxygen caused by constricting of the upper respiratory system causes Obstructive Sleep Apnea (OSA), which mainly manifests as low concentration, sleepiness during the daytime, and irritability. Human lives can be saved and treatment costs can be reduced when OSA is detected early. OSA can be quickly detected by computer-aided diagnosis (CAD) using Electrocardiogram (ECG) and Photoplethysmogram (PPG) signals. Deep Learning (DL) has attracted dramatic attention due to its uses in biomedical applications and its efficiency in classifying OSA events. In this study, Convolutional Neural Networks with Long-Short Term Memory (CNN-LSTM) and Densely Connected Long-Short Term Memory (DC-LSTM) networks are used to detect apneic events using ECG and PPG signals. The study involves 200 recording of ECG signals and PPG signals collected from publically available apnea database. DC-LSTM network achieved accuracy of 98.2%, sensitivity of 97.4%, specificity of 97.5%, and Kappa coefficient of 0.92. In terms of performance, the algorithms employed here are comparable with those that are fully automated. This methodology can be easily incorporated with wearable medical devices, which makes it useful for e-health monitoring of OSA at home.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Varon, C., Caicedo, A., Testelmans, D., Buyse, B., Van Huffel, S.: A novel algorithm for the automatic detection computational intelligence and neuroscience of sleep apnea from single-lead ECG. IEEE Trans. Biomed. Eng. 62(9), 2269–2278 (2015)
Urtnasan, E., Park, J.-U., Joo, E.-Y., Lee, K.-J.: Automated detection of obstructive sleep apnea events from a single-lead electrocardiogram using a convolutional neural network. J. Med. Syst. 42(6), 1–8 (2018). https://doi.org/10.1007/s10916-018-0963-0
Kapur, V.K., et al.: Clinical practice guideline for diagnostic testing for adult obstructive sleep apnea: an American Academy of Sleep Medicine clinical practice guideline. J. Clin. Sleep Med. 13, 479–504 (2017)
Chen, L., Zhang, X., Song, C.: An automatic screening approach for obstructive sleep apnea diagnosis based on single-lead electrocardiogram. IEEE Trans. Autom. Sci. Eng. 12(1), 106–115 (2015)
Sheta, A., et al.: Diagnosis of obstructive sleep apnea from ECG signals using machine learning and deep learning classifiers. Appl. Sci. 11(14), 6622 (2021)
Zhang, J., et al.: Automatic detection of obstructive sleep apnea events using a deep CNN-LSTM model. Comput. Intell. Neurosci. 2021 (2021)
Lakhan, P., Ditthapron, A., Banluesombatkul, N., Wilaiprasitporn, T.: Deep neural networks with weighted averaged overnight airflow features for sleep apnea-hypopnea severity classification. In: Proceedings of the 2018 IEEE Region 10 Conference, Jeju, Korea, 28–31 October 2018
Banluesombatkul, N., Rakthanmanon, T., Wilaiprasitporn, T.: Single channel ECG for obstructive sleep apnea severity detection using a deep learning approach. In: Proceedings of the 2018 IEEE Region 10 Conference, Jeju Island, Korea, pp. 2011–2016, October 2018
Vattamthanam, S., Mrudula, G.B., Kumar, C.S.: Sleep apnea classification using deep neural network. In: Proceedings of the 2020 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER), Karnataka, India, 30–31 October 2020, pp. 133–136 (2020)
Christensen, B.: Normal Electrocardiography (ECG) Intervals. Medscape Hear. Drugs Dis. 2014, 20 (2020). http://emedicine.medscape.com/article/2172196-overview. Accessed 29 Nov 2020
Vulcan, R.S., André, S., Bruyneel, M.: Photoplethysmography in normal and pathological sleep. Sensors 21, 2928 (2021). https://doi.org/10.3390/s21092928
Goldberger, A., et al.: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000)
Gaurav, D., Rodriguez, F.O., Tiwari, S., Jabbar, M.A.: Review of machine learning approach for drug development process. In: Deep Learning in Biomedical and Health Informatics, pp. 53–77. CRC Press (2021)
Tiwari, S., et al.: Applications of machine learning approaches to combat COVID-19: a survey. Lessons from COVID-19, pp. 263–287 (2022)
Raoof, S.S., Jabbar, M.A., Tiwari, S.: Foundations of deep learning and its applications to health informatics. In: Deep Learning in Biomedical and Health Informatics, pp. 1–28. CRC Press (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jothi, E.S.J., Anitha, J., Priyadharshini, J., Hemanth, D.J. (2022). Deep Learning Based Obstructive Sleep Apnea Detection for e-health Applications. In: Ortiz-Rodríguez, F., Tiwari, S., Sicilia, MA., Nikiforova, A. (eds) Electronic Governance with Emerging Technologies. EGETC 2022. Communications in Computer and Information Science, vol 1666. Springer, Cham. https://doi.org/10.1007/978-3-031-22950-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-22950-3_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22949-7
Online ISBN: 978-3-031-22950-3
eBook Packages: Computer ScienceComputer Science (R0)