Detection of Obstructive Sleep Apnea Using Deep Neural Network

  • Mashail Alsalamah
  • Saad Amin
  • Vasile Palade


Sleep apnea is a serious sleep disorder phenomena that occurs when a person’s breathing is interrupted during sleep. The most common diagnostic technique that is used to deal with sleep apnea is polysomnography (PSG) which is done at special sleeping labs. This technique is expensive and uncomfortable. New automated methods have been developed for sleep apnea detection using artificial intelligence algorithms, which are more convenient and comfortable for patients. This chapter proposes a novel scheme based on deep learning for sleep apnea detection and quantification using statistical features of ECG signals. The proposed approach is experimented with three phases: (1) minute-based apnea classification, (2) class identification and minute-by-minute detection for each ECG recording unlike state-of-the-art methods which either identify apnea class or detect its presence at each minute, and (3) comparison of the proposed scheme with the well-known methods that have been proposed in the literature, which may have not used the same features and/or the same dataset. The results obtained show that the newly proposed approach provides significant accuracy improvements compared to state-of-the-art methods. Because of its noninvasive and low-cost nature, this algorithm has the potential for numerous applications in sleep medicine.


Obstructive sleep apnea Deep learning Neural networks 


  1. 1.
    Derrer, D. (2014, September). WebMD medical reference. [Online].
  2. 2.
    Caples, S. M. (2007). Sleep-disordered breathing and cardiovascular risk. Sleep, 30(3), 291–303.CrossRefGoogle Scholar
  3. 3.
    Morgenthaler, T., Kagramanov, V., Hanak, V., & Decker, P. (2006). Complex sleep apnea syndrome: Is it a unique clinical syndrome? Pub Med Center, 29(09), 1203–1209.Google Scholar
  4. 4.
    Chazal, P., Penzel, T., & Heneghan, C. (2004, August). Automated Detection of Obstructive Sleep Apnoea at Different Time Scales Using the Electrocardiogram. Institute of Physics Publishing, 25(4), 967–983.Google Scholar
  5. 5.
    (2012, January) Detecting and quantifying apnea based on the ECG. [Online].
  6. 6.
    De Chazal, P., et al. (2000). Automatic classification of sleep apnea epochs using the electrocardiogram. Computers in Cardiology, 27, 745–748.Google Scholar
  7. 7.
    Jarvis, M., & Mitra, P. (2000). Apnea patients characterized by 0.02 Hz peak in the multitaper spectrogram of electrocardiogram signals. Computers in Cardiology, 27, 769–772.Google Scholar
  8. 8.
    Mcnames, J., & Fraser, A. (2000). Obstructive sleep apnea classification based on spectrogram patterns in the electrocardiogram. Computers in Cardiology, 27, 749–752.Google Scholar
  9. 9.
    Mietus, J., Peng, C., Ivanov, P., & Goldberger, A. (2000). Detection of obstructive sleep apnea from cardiac interbeat interval time series. Computers in Cardiology, 27, 753–756.Google Scholar
  10. 10.
    Schrader, M., Zywietz, C., Einem, V., Widiger, B., & Joseph, G. (2000). Detection of sleep apnea in single channel ECGs from the PhysioNet data base. Computers in Cardiology, 27, 263–266.Google Scholar
  11. 11.
    Raymond, B., Cayton, R., Bates, R., & Chappell, M. (2000). Screening for obstructive sleep apnoea based on the electrocardiogram – The computers in cardiology challenge. Computers in Cardiology, 27, 267–270.Google Scholar
  12. 12.
    A Khandoker, C Karmakar, and M Palaniswami, “Automated recognition of patients with obstructive sleep apnoea using wavelet-based features of electrocardiogram recordings,” Computers in Biology and Medicine, vol. 39, no. 3, pp. 88–96, 2009.CrossRefGoogle Scholar
  13. 13.
    Xie, B., & Minn, H. (2012). Real-time sleep apnea detection by classifier combination. Information Technology in Biomedicine, 16(3), 469–477.CrossRefGoogle Scholar
  14. 14.
    Manrique, Q, Hernandez, A, Gonzalez, T, Pallester, F, & Dominquez, C. (2009). Detection of obstructive sleep apnea in ECG recordings using time-frequency distributions and dynamic features. In IEEE International Conference on Engineering in Medicine and Biology Society( EMBS 2009), pp. 5559–5562.Google Scholar
  15. 15.
    Mendez, M., et al.. (2007). Detection of sleep apnea from surface ECG based on features extracted by an autoregressive model. In IEEE International Conference on Engineering in Medicine and Biology Society (EMBS 2007), pp. 6105–6108.Google Scholar
  16. 16.
    Almazaydeh, L., Elleithy, K.H., & Faezipour, M. (2012). Obstructive sleep apnea detection. In IEEE International Conference on Engineering in Medicine and Biology Society (EMBS 2012).Google Scholar
  17. 17.
    Babaeizadeh, S., White, D., Pittman, S., & Zhou, S. (2010). Automatic detection and quantification of sleep apnea using heart rate variability. Journal of Electrocardiology, 43, 535–541.CrossRefGoogle Scholar
  18. 18.
    Rachim, V., Li, G., & Chung, W. (2014). Sleep apnea classification using ECG-signal wavelet-PCA features. Bio-Medical Materials and Engineering, 24, 2875–2882.Google Scholar
  19. 19.
    Zeiler M.D., Fergus R. (2014) Visualizing and Understanding Convolutional Networks. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8689. Springer, Cham.Google Scholar
  20. 20.
    Simonyan K., Vedaldi A, Zisserman A. (2014) Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. Computer Vision and Pattern Recognition
  21. 21.
    Hinton, G., et al. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29, 82–97.CrossRefGoogle Scholar
  22. 22.
    Brébisson, A. D., & Montana, G. (2015). Deep neural networks for anatomical brain segmentation. In 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 20–28).Google Scholar
  23. 23.
    Wang L, et al. (2011) Growth propagation of yeast in linear arrays of microfluidic chambers over many generations. Biomicrofluidics 5(4):44118-441189.CrossRefGoogle Scholar
  24. 24.
    Fukushima, K., & Miyake, S. (1982). Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position. Pattern Recognition, 15(6), 455–469.CrossRefGoogle Scholar
  25. 25.
    Bengio, Y., Courville, A., & Vincent, P. (2013). Representation Learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), 1798–1828.CrossRefGoogle Scholar
  26. 26.
    Goldberger, A., et al. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23), e215–e220.CrossRefGoogle Scholar
  27. 27.
    MedicineNet. (2016, September) Definition of QRS complex. [Online]. http://www.medi
  28. 28.
    Thuraisingham, R. (2006). Preprocessing RR interval time series for heart rate variability analysis and estimates of standard deviation of RR intervals. Computer Methods and Programs in Biomedicine, 83(1), 78–82.CrossRefGoogle Scholar
  29. 29.
    (2015, July) The WFDB Software Package. [Online].
  30. 30.
    Kaguara, A., Myoung Nam, K., & Reddy, S. (2014, December). A deep neural network classifier for diagnosing sleep apnea from ECG data on smartphones and small embedded systems. Thesis.Google Scholar
  31. 31.
    (2013). Statistics solutions. [Online].
  32. 32.
    Hayat, M., Bennamoun, M., & An, S. (2015). Deep reconstruction models for image set classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 713–727.CrossRefGoogle Scholar
  33. 33.
    Bai, J., Wu, Y., Zhang, J., & Chen, F. (2015). Subset based deep learning for RGB-D object recognition. Neurocomputing, 165, 280–292.CrossRefGoogle Scholar
  34. 34.
    Huang, Z., Wang, R., Shan, S., & Chen, X. (2015). Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning. Pattern Recognition, 48, 3113–3124.CrossRefGoogle Scholar
  35. 35.
    Deng, J., Zhang, Z., Eyben, F., & Schuller, B. (2014). Autoencoder-based unsupervised domain adaptation for speech emotion recognition. IEEE Signal Processing Letters, 21, 1068–1072.CrossRefGoogle Scholar
  36. 36.
    Keras Documentation. [Online].
  37. 37.
    (2016). TensorFlow. [Online].
  38. 38.
    LISA Lab. (2016, August). Theano. [Online].
  39. 39.
    (2016, August). Orange data mining. [Online].
  40. 40.
    Geoffrey, E., Hinton, N. S., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. Neural and Evolutionary Computing.

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Mashail Alsalamah
    • 1
  • Saad Amin
    • 1
  • Vasile Palade
    • 1
  1. 1.Faculty of Engineering and ComputingCoventry UniversityCoventryUK

Personalised recommendations