Skip to main content

SC3: self-configuring classifier combination for obstructive sleep apnea

Abstract

Obstructive sleep apnea is considered to be one of the most prevalent sleep-related disorders that can affect the general population. However, the gold standard for the diagnosis, polysomnography, is an expensive and complicated process that is commonly unavailable to a large group of the population. Alternatively, automatic approaches have been developed to address this issue. One of the goals of this research is to perform the classification of the apnea events with the lowest possible number of sensors. Therefore, the blood oxygen saturation signal was employed in this work since it is correlated with the occurrence of apnea events and it can be measured from a single noninvasive sensor. The events detection was performed by a combination of classifiers. However, choosing the type of classifier to combine and select the most relevant features for each classifier is considered to be a well-known problem in the field of machine learning. A self-configuring classifier combination technique based on genetic algorithms was developed for multiple classifiers and features selection which was tested along with different databases and input sizes. The best performance for obstructive sleep apnea detection was achieved using maximum voting independent feature selection with 1 min time window having the best sensitivity of 82.48% similar database in the literature. This model was later tested on another database for cross-database accuracy. With an average accuracy of 91.33%, the system proved its capabilities for clinical diagnosis since the model was developed and validated with both subject and database independence.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. 1.

    Sateia MJ (2014) International classification of sleep disorders-third edition: highlights and modifications. Chest 146(5):1387–1394

    Article  Google Scholar 

  2. 2.

    Gastaut H, Tassinari C, Duron B (1965) Polygraphic study of the episodic diurnal and nocturnal (hypnic and respiratory) manifestations of the Pickwickian syndrome. Brain Res 2:167–186

    Google Scholar 

  3. 3.

    Young T, Palta M, Dempsey J, Skatrud J, Weber S, Badr S (1993) The occurrence of sleep-disordered breathing among middle-aged adults. N Engl J Med 328:1230–1235

    Article  Google Scholar 

  4. 4.

    Zhang J, Zhang Q, Wang Y, Qiu C (2013) A real-time auto-adjustable smart pillow system for sleep apnea detection and treatment. In: Proceedings of the 12th international conference on Information processing in sensor networks (IPSN), 2013, pp 179–190

  5. 5.

    Mooe T, Franklin KA, Holmström K, Rabben T, Wiklund U (2001) Sleep-disordered breathing and coronary artery disease. Am J Respir Crit Care Med 164(10):1910–1913

    Article  Google Scholar 

  6. 6.

    Grote L, Ploch T, Heitmann J, Knaack L, Penzel T, Peter J (1999) Sleep-related breathing disorder is an independent risk factor for systemic hypertension. Am J Respir Crit Care Med 160(6):1875–1882

    Article  Google Scholar 

  7. 7.

    Mohsenin V (2001) Sleep-related breathing disorders and risk of stroke. Stroke 32(6):1271–1278

    Article  Google Scholar 

  8. 8.

    Findley L, Barth J, Powers D, Wilhoit S, Boyd D, Suratt P (1986) Cognitive impairment in patients with obstructive sleep apnea and associated hypoxemia. Chest 90:686–690

    Article  Google Scholar 

  9. 9.

    Agarwal R, Gotman J (2001) Computer-Assisted Sleep Staging. IEEE Trans Biomed Eng 48(12):1412–1423

    Article  Google Scholar 

  10. 10.

    Mendonça F, Mostafa SS, Ravelo-García AG, Morgado-Dias F, Penzel T (2018) Devices for home detection of obstructive sleep apnea: a review. Sleep Med Rev 41:149–160

    Article  Google Scholar 

  11. 11.

    Mendonca F, Mostafa SS, Ravelo-Garcia AG, Morgado-Dias F, Penzel T (2019) A review of obstructive sleep apnea detection approaches. IEEE J Biomed Health Informat 23(2):825–837

    Article  Google Scholar 

  12. 12.

    Uddin MB, Chow CM, Su SW (2018) Classification methods to detect sleep apnea in adults based on respiratory and oximetry signals: a systematic review. Physiol Meas 39(3):03TR01

    Article  Google Scholar 

  13. 13.

    Patil D, Wadhai VM, Gujar S, Surana K, Devkate P, Waghmare S (2012) APNEA detection on smart phone. Int J Comput Appl 59(7):15–19

    Google Scholar 

  14. 14.

    Ravelo-García A et al (2015) Oxygen saturation and RR intervals feature selection for sleep apnea detection. Entropy 17(5):2932–2957

    Article  Google Scholar 

  15. 15.

    Cover TM (1974) The best two independent measurements are not the two best. IEEE Trans Syst Man Cybern SMC-4(1):116–117

    Article  Google Scholar 

  16. 16.

    Peng H, Long F, Ding C (2005) 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

    Article  Google Scholar 

  17. 17.

    Mostafa SS, Morgado-Dias F, Ravelo-García AG (2018) Comparison of SFS and mRMR for oximetry feature selection in obstructive sleep apnea detection. Neural Comput Appl. https://doi.org/10.1007/s00521-018-3455-8

    Article  Google Scholar 

  18. 18.

    Mostafa SS, Carvalho JP, Morgado-Dias F, Ravelo-García A (2017) Optimization of sleep apnea detection using SpO2 and ANN. In: 2017 XXVI international conference on information, communication and automation technologies (ICAT), 2017, pp 1–6

  19. 19.

    Mostafa SS et al (2017) SpO2 based sleep apnea detection using deep learning. In: 2017 IEEE 21st international conference on intelligent engineering systems (INES), pp 91–96

  20. 20.

    Elleithy K, Almazaydeh L, Faezipour M (2012) A neural network system for detection of obstructive sleep apnea through SpO2 signal features. Int J Adv Comput Sci Appl 3(5):7–11

    Google Scholar 

  21. 21.

    Xie B, Minn H (2012) Real-time sleep apnea detection by classifier combination. IEEE Trans Inf Technol Biomed 16(3):469–477

    Article  Google Scholar 

  22. 22.

    Pathinarupothi RK et al (2017) Single sensor techniques for sleep apnea diagnosis using deep learning. In: 2017 IEEE international conference on healthcare informatics (ICHI), 2017, pp 524–529

  23. 23.

    Stanley H, Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng C-K (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):215–220

    Google Scholar 

  24. 24.

    Penzel T, Moody G, Mark R, Goldberger A, Peter J (2000) The apnea-ECG database. Comput Cardiol 2000:255–258

    Google Scholar 

  25. 25.

    Alvarez D, Hornero R, Abásolo D, del Campo F, Zamarrón C (2006) Nonlinear characteristics of blood oxygen saturation from nocturnal oximetry for obstructive sleep apnoea detection. Physiol Meas 27(4):399–412

    Article  Google Scholar 

  26. 26.

    Warley AR, Mitchell JH, Stradling JR (1987) Evaluation of the Ohmeda 3700 pulse oximeter. Thorax 42(11):892–896

    Article  Google Scholar 

  27. 27.

    Olson LG, Ambrogetti A, Gyulay SG (1999) Prediction of sleep-disordered breathing by unattended overnight oximetry. J Sleep Res 8(1):51–55

    Article  Google Scholar 

  28. 28.

    Gyulay S, Olson LG, Hensley MJ, King MT, Allen KM, Saunders NA (1993) A comparison of clinical assessment and home oximetry in the diagnosis of obstructive sleep apnea. Am Rev Respir Dis 147(1):50–53

    Article  Google Scholar 

  29. 29.

    Ravelo-Garcia AG, Navarro-Mesa JL, Murillo-Diaz MJ, Julia-Serda JG (2004) Application of RR series and oximetry to a statistical classifier for the detection of sleep apnoea/hypopnoea. Comput Cardiol 2004:305–308

    Google Scholar 

  30. 30.

    Gupta M, Jin L, Homma N (2004) Static and dynamic neural networks: from fundamentals to advanced theory. Wiley, London

    Google Scholar 

  31. 31.

    Kuncheva LI (2004) Combining pattern classifiers: methods and algorithms. Wiley, London

    Book  Google Scholar 

  32. 32.

    Fumera G, Roli F (2005) A theoretical and experimental analysis of linear combiners for multiple classifier systems. IEEE Trans Pattern Anal Mach Intell 27(6):942–956

    Article  Google Scholar 

  33. 33.

    Santos AB, de A. Araújo A, Menotti D (2012) Combiner of classifiers using genetic algorithm for classification of remote sensed hyperspectral images. In: 2012 IEEE international geoscience and remote sensing symposium, 2012, pp 4146–4149

  34. 34.

    Mohandes M, Deriche M, Aliyu S (2018) Classifiers combination techniques: a comprehensive review. IEEE Access 6:19626–19639

    Article  Google Scholar 

  35. 35.

    Mostafa SS, Mendonça F, Ravelo-García A, Morgado-Dias F (2018) Combination of deep and shallow networks for cyclic alternating patterns detection. In: 13th APCA international conference on automatic control and soft computing (CONTROLO), 2018, pp 98–103

  36. 36.

    Hartmanis J, Van Leeuwen J (2000) Multiple classifier systems: first international workshop proceedings, 2000

  37. 37.

    Cen L, Yu ZL, Kluge T, Ser W (2018) Automatic system for obstructive sleep apnea events detection using convolutional neural network. In: 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC), 2018, pp 3975–3978

  38. 38.

    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 25:1643–1650

    Article  Google Scholar 

  39. 39.

    St. Vincent’s University Hospital/University College Dublin Sleep Apnea Database. https://physionet.org/pn3/ucddb/

Download references

Acknowledgements

This research has been supported by the Portuguese Foundation for Science and Technology through Projeto Estratégico UID/EEA/50009/2019, ARDITI—Agência Regional para o Desenvolvimento da Investigação, Tecnologia e Inovação under the scope of the Project M1420-09-5369-FSE-000001-PhD Studentship and MITIExcell—Excelencia Internacional de IDT&I NAS TIC (Project Number M1420-01-01450FEDER0000002), provided by the Regional Government of Madeira.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Sheikh Shanawaz Mostafa.

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

Appendix

The Acc, Sen and Spc for 1 min, 3 min and 5 min are presented in Fig. 5. The values of the performance metrics fluctuated over the generation. It did not have a steady increment or decrement such as \(CF\). Because the SC3 was trying to optimize \(CF\) instead of the accuracy, sensitivity and specificity. The highest Acc (85.22%) was achieved with the 3 min window of SF MaxV (MaxVSF). However, the same window had the lowest Sen (79.86%). MaxVIF 1 min achieved a similar Acc but with a better Sen (82.48%). The highest Acc, Sen, Spc among MaxV were achieved, respectively, by MaxVIF 1 min (85.30%), MaxVSF 1 min (83.51%) and MaxVSF 3 min (87.08%). For the WLC, WLCSF1 has the highest Acc (85.30%) and Spc (86.28%) among WLC SC3. The best Sen (86.33%) was achieved by WLCIF5 (Fig. 5). Selected features and classifiers for SC3 classifiers are presented in Table 5. For LDA classifier Figs. 6 and 7 represents performance information. 

Fig. 5
figure5

Accuracy (Acc), sensitivity (Sen) and specificity (Spc) of 1 min, 3 min and 5 min MaxV and WLC over the generations for the best performance objective

Fig. 6
figure6

Accuracy (Acc), sensitivity (Sen) and specificity (Spc) of 1 min, 3 min and 5 min LDA over the generations for the best performance objective

Fig. 7
figure7

a Cost and b number of features of 1 min, 3 min and 5 min LDA over the generations for the best performance objective

Table 5 Selected features and classifiers for different SC3

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Mostafa, S.S., Mendonça, F., Juliá-Serdá, G. et al. SC3: self-configuring classifier combination for obstructive sleep apnea. Neural Comput & Applic 32, 17825–17841 (2020). https://doi.org/10.1007/s00521-019-04582-2

Download citation

Keywords

  • Combined classifiers
  • Sleep apnea
  • Genetic algorithm
  • Machine learning