Advertisement

Diagnosis of Obstructive Sleep Apnea Using Logistic Regression and Artificial Neural Networks Models

  • Alaa ShetaEmail author
  • Hamza Turabieh
  • Malik Braik
  • Salim R. Surani
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1069)

Abstract

Regrettably, a large proportion of likely patients with sleep apnea are underdiagnosed. Obstructive sleep apnea (OSA) is one of the main causes of hypertension, type II diabetes, stroke, coronary artery disease, and heart failure. OSA affects not only adults but also children where it forms one of the sources of learning disabilities for children. This study aims to provide a classification model for one of the well-known sleep disorders known as OSA, which causes a serious malady that affects both men and women. OSA affects both genders with different scope. Men versus women diagnosed with OSA are about 8:1. In this research, logistic regression (LR) and artificial neural networks were applied successfully in several classification applications with promising results, particularly in the bio-statistics area. LR was used to derive a membership probability for a potential OSA system from a range of anthropometric features including weight, height, body mass index (BMI), hip, waist, age, neck circumference, modified Friedman, snoring, Epworth sleepiness scale (ESS), sex, and daytime sleepiness. We developed two models to predict OSA, one for men and one for women. The proposed sleep apnea diagnosis model has yielded accurate classification results and possibly a prototype software module that can be used at home. These findings shall reduce the patient’s need to spend a night at a laboratory and make the study of sleep apnea to implement at home.

Keywords

Sleep apnea Logistic regression Artificial neural networks Classification Features selection 

References

  1. 1.
    Dempsey, J.A., Veasey, S.C., Morgan, B.J., O’Donnell, C.P.: Pathophysiology of sleep apnea. Physiol. Rev. 90(1), 47–112 (2010)CrossRefGoogle Scholar
  2. 2.
    Berry, R.B., Budhiraja, R., Gottlieb, D.J., Gozal, D., Iber, C., Kapur, V.K., Marcus, C.L., Mehra, R., Parthasarathy, S., Quan, S.F., et al.: Rules for scoring respiratory events in sleep: update of the 2007 AASM manual for the scoring of sleep and associated events. J. Clin. Sleep Med. 8(05), 597–619 (2012)Google Scholar
  3. 3.
    McNicholas, W., Bonsignore, M., M. C. of EU Cost Action B26, et al.: Sleep apnoea as an independent risk factor for cardiovascular disease: current evidence, basic mechanisms and research priorities. Europ. Respir. J. 29(1), 156–178 (2007)Google Scholar
  4. 4.
    Ye, L., Pien, G.W., Ratcliffe, S.J., Björnsdottir, E., Arnardottir, E.S., Pack, A.I., Benediktsdottir, B., Gislason, T.: The different clinical faces of obstructive sleep apnoea: a cluster analysis. Eur. Respir. J. 44(6), 1600–1607 (2014)CrossRefGoogle Scholar
  5. 5.
    Eckert, D.J., White, D.P., Jordan, A.S., Malhotra, A., Wellman, A.: Defining phenotypic causes of obstructive sleep apnea. Identification of novel therapeutic targets. Am. J. Respir. Crit. Care Med. 188(8), 996–1004 (2013)CrossRefGoogle Scholar
  6. 6.
    Vavougios, G.D., Natsios, G., Pastaka, C., Zarogiannis, S.G., Gourgoulianis, K.I.: Phenotypes of comorbidity in osas patients: combining categorical principal component analysis with cluster analysis. J. Sleep Res. 25(1), 31–38 (2016)CrossRefGoogle Scholar
  7. 7.
    Fietze, I., Penzel, T., Alonderis, A., Barbe, F., Bonsignore, M., Calverly, P., De Backer, W., Diefenbach, K., Donic, V., Eijsvogel, M., et al.: Management of obstructive sleep apnea in Europe. Sleep Med. 12(2), 190–197 (2011)CrossRefGoogle Scholar
  8. 8.
    Borgström, A., Nerfeldt, P., Friberg, D.: Questionnaire OSA-18 has poor validity compared to polysomnography in pediatric obstructive sleep apnea. Int. J. Pediatr. Otorhinolaryngol. 77(11), 1864–1868 (2013)CrossRefGoogle Scholar
  9. 9.
    Song, C., Liu, K., Zhang, X., Chen, L., Xian, X.: An obstructive sleep apnea detection approach using a discriminative hidden markov model from ECG signals. IEEE Trans. Biomed. Eng. 63(7), 1532–1542 (2016)CrossRefGoogle Scholar
  10. 10.
    Karamanli, H., Yalcinoz, T., Yalcinoz, M.A., Yalcinoz, T.: A prediction model based on artificial neural networks for the diagnosis of obstructive sleep apnea. Sleep Breathing 20(2), 509–514 (2016)CrossRefGoogle Scholar
  11. 11.
    Längkvist, M., Karlsson, L., Loutfi, A.: A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recogn. Lett. 42, 11–24 (2014)CrossRefGoogle Scholar
  12. 12.
    de Chazal, P., Penzel, T., Heneghan, C.: Automated detection of obstructive sleep apnoea at different time scales using the electrocardiogram. Physiol. Meas. 25(4), 967 (2004)CrossRefGoogle Scholar
  13. 13.
    Karmakar, C., Khandoker, A., Penzel, T., Schöbel, C., Palaniswami, M.: Detection of respiratory arousals using photoplethysmography (PPG) signal in sleep apnea patients. IEEE J. Biomed. Health Inform. 18(3), 1065–1073 (2014)CrossRefGoogle Scholar
  14. 14.
    Lázaro, J., Gil, E., Vergara, J.M., Laguna, P.: OSAS detection in children by using PPG amplitude fluctuation decreases and pulse rate variability. In: 2012 IEEE Computing in Cardiology, pp. 185–188. IEEE (2012)Google Scholar
  15. 15.
    Shelley, K.H.: Photoplethysmography: beyond the calculation of arterial oxygen saturation and heart rate. Anesth. Analg. 105(6), S31–S36 (2007)CrossRefGoogle Scholar
  16. 16.
    Gaurav, G., Mohanasankar, S., Kumar, V.J.: Apnea sensing using photoplethysmography. In: 2013 Seventh International Conference on Sensing Technology (ICST), pp. 285–288. IEEE (2013)Google Scholar
  17. 17.
    Bsoul, M., Minn, H., Tamil, L.: Apnea medassist: real-time sleep apnea monitor using single-lead ECG. IEEE Trans. Inf. Technol. Biomed. 15(3), 416–427 (2011)CrossRefGoogle Scholar
  18. 18.
    Mendez, M.O., Bianchi, A.M., Matteucci, M., Cerutti, S., Penzel, T.: Sleep apnea screening by autoregressive models from a single ECG lead. IEEE Trans. Biomed. Eng. 56(12), 2838–2850 (2009)CrossRefGoogle Scholar
  19. 19.
    Isa, S.M., Fanany, M.I., Jatmiko, W., Arymurthy, A.M.: Sleep apnea detection from ECG signal: analysis on optimal features, principal components, and nonlinearity. In: 2011 5th International Conference on Bioinformatics and Biomedical Engineering, pp. 1–4. IEEE (2011)Google Scholar
  20. 20.
    Siegwart, D.,  Tarassenko, D., Roberts, S., Stradling, J., Partlett, J.: Sleep apnoea analysis from neural network post-processing (1995)Google Scholar
  21. 21.
    Tagluk, M.E., Akin, M., Sezgin, N.: Classıfıcation of sleep apnea by using wavelet transform and artificial neural networks. Expert Syst. Appl. 37(2), 1600–1607 (2010)CrossRefGoogle Scholar
  22. 22.
    Liu, D., Pang, Z., Lloyd, S.R.: A neural network method for detection of obstructive sleep apnea and narcolepsy based on pupil size and eeg. IEEE Trans. Neural Networks 19(2), 308–318 (2008)CrossRefGoogle Scholar
  23. 23.
    Shokrollahi, M., Saha, S., Hadi, P., Rudzicz, F., Yadollahi, A.: Snoring sound classification from respiratory signal. In: 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3215–3218. IEEE (2016)Google Scholar
  24. 24.
    Cheng, M., Sori, W.J., Jiang, F., Khan, A.,  Liu, A.: Recurrent neural network based classification of ECG signal features for obstruction of sleep apnea detection. In: 2017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC), vol. 2, pp. 199–202. IEEE (2017)Google Scholar
  25. 25.
    Khandoker, A.H., Palaniswami, M., Karmakar, C.K.: Support vector machines for automated recognition of obstructive sleep apnea syndrome from ECG recordings. IEEE Trans. Inf. Technol. Biomed. 13(1), 37–48 (2009)CrossRefGoogle Scholar
  26. 26.
    Maali, Y., Al-Jumaily, A.: Hierarchical parallel PSO-SVM based subject-independent sleep apnea classification. In: International Conference on Neural Information Processing, pp. 500–507. Springer (2012)Google Scholar
  27. 27.
    Fontenla-Romero, O., Guijarro-Berdiñas, B., Alonso-Betanzos, A., Moret-Bonillo, V.: A new method for sleep apnea classification using wavelets and feedforward neural networks. Artif. Intell. Med. 34(1), 65–76 (2005)CrossRefGoogle Scholar
  28. 28.
    Avcı, C., Akbaş, A.: Sleep apnea classification based on respiration signals by using ensemble methods. Bio-Med. Mater. Eng. 26(s1), S1703–S1710 (2015)CrossRefGoogle Scholar
  29. 29.
    Tian, J., Liu, J.: Apnea detection based on time delay neural network. In: IEEE Engineering in Medicine and Biology 27th Annual Conference 2006, pp. 2571–2574. IEEE (2005)Google Scholar
  30. 30.
    Morsy, A.A., Al-Ashmouny, K.M.: Sleep apnea detection using an adaptive fuzzy logic based screening system. In: IEEE Engineering in Medicine and Biology 27th Annual Conference 2006, pp. 6124–6127. IEEE (2005)Google Scholar
  31. 31.
    Pradhan, B., Lee, S.: Delineation of landslide hazard areas using frequency ratio, logistic regression and artificial neural network model at Penang Island, Malaysia. Environ. Earth Sci. 60, 1037–1054 (2009)CrossRefGoogle Scholar
  32. 32.
    Sheta, A., Aljahdali, S.,  Braik, S.: Utilizing faults and time to finish estimating the number of software test workers using artificial neural networks and genetic programming. In: International Conference Europe Middle East & North Africa Information Systems and Technologies to Support Learning, pp. 613–624. Springer (2018)Google Scholar
  33. 33.
    Sheta, A., Braik, M., Al-Hiary, H.: Modeling the tennessee eastman chemical process reactor using bio-inspired feedforward neural network (BI-FF-NN). Int. J. Adv. Manuf. Technol., 1–22 (2019) Google Scholar
  34. 34.
    Sheta, A.,  Eghneem, A.: Training artificial neural networks using genetic algorithms to predict the price of the general index for amman stock exchange. In: Proceedings of the Midwest Artificial Intelligence and Cognitive Science Conference, DePaul University, Chicago, IL, USA, 21–22 April, pp. 7–13 (2007)Google Scholar
  35. 35.
    Sheta, A.F., Braik, M., Al-Hiary, H.: Identification and model predictive controller design of the tennessee eastman chemical process using ANN. In: IC-AI, pp. 25–31 (2009)Google Scholar
  36. 36.
    Sheta, A.F., Braik, M., Öznergiz, E., Ayesh, A.,  Masud, A.: Design and automation for manufacturing processes: an intelligent business modeling using adaptive neuro-fuzzy inference systems. In: Business Intelligence and Performance Management, pp. 191–208. Springer (2013)Google Scholar
  37. 37.
    Alkasassbeh, M., Alaa, H.F., Sheta, F., Turabieh, H.: Prediction of PM10 and TSP air pollution parameters using artificial neural network autoregressive, external input models: a case study in salt, jordan. Middle-East J. Sci. Res. 14(7), 999–1009 (2013)Google Scholar
  38. 38.
    Kovač-Andrić, E., Sheta, A., Faris, H., Gajdošik, M.Š.: Forecasting ozone concentrations in the east of croatia using nonparametric neural network models. J. Earth Syst. Sci. 125, 997–1006 (2016)CrossRefGoogle Scholar
  39. 39.
    Norgaard, M., Ravn, O., Poulsen, N.K., Hansen, L.K.: Neural Networks for Modelling and Control of Dynamic Systems. Springer, London (2000)CrossRefGoogle Scholar
  40. 40.
    Kudo, M., Sklansky, J.: Comparison of algorithms that select features for pattern classifiers. Pattern Recogn. 33(1), 25–41 (2000)CrossRefGoogle Scholar
  41. 41.
    Peng, H., Long, F., Ding, C.: Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1226–1238 (2005)CrossRefGoogle Scholar
  42. 42.
    Zhang, F., Mockus, F., Keivanloo, I., Zou, Y.: Towards building a universal defect prediction model with rank transformed predictors. Empirical Softw. Eng. 21(5), 2107–2145 (2016).  https://doi.org/10.1007/s10664-015-9396-2CrossRefGoogle Scholar
  43. 43.
    Fawcett, T.: Roc graphs: notes and practical considerations for researchers. Technical report (2004)Google Scholar
  44. 44.
    Turabieh, H., Mafarja, M., Li, X.: Iterated feature selection algorithms with layered recurrent neural network for software fault prediction. Expert Syst. Appl. 122, 27–42 (2019). http://www.sciencedirect.com/science/article/pii/S0957417418308030CrossRefGoogle Scholar
  45. 45.
    Hosmer, D.W., Lemeshow, S.: Applied Logistic Regression. Wiley Series in Probability and Statistics, 2nd edn. Wiley-Interscience Publication, New York (2000)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Alaa Sheta
    • 1
    Email author
  • Hamza Turabieh
    • 2
  • Malik Braik
    • 3
  • Salim R. Surani
    • 4
  1. 1.Computer Science DepartmentSouthern Connecticut State UniversityNew HavenUSA
  2. 2.Department of Information TechnologyTaif UniversityTaifSaudi Arabia
  3. 3.Department of Computer ScienceAl-Balqa Applied UniversitySaltJordan
  4. 4.Department of MedicineTexas A&M UniversityCorpus ChristiUSA

Personalised recommendations