Regularized logistic regression for obstructive sleep apnea screening during wakefulness using daytime tracheal breathing sounds and anthropometric information

  • Farahnaz Hajipour
  • Mohammad Jafari Jozani
  • Ahmed Elwali
  • Zahra MoussaviEmail author
Original Article


Obstructive sleep apnea (OSA) is a prevalent health problem. Developing a technology for quick OSA screening is momentous. In this study, we used regularized logistic regression to predict the OSA severity level of 199 individuals (116 males) with apnea/hypopnea index (AHI) ≥ 15 (moderate/severe OSA) and AHI < 5 (non-OSA) using their tracheal breathing sounds (TBS) recorded during daytime, while they were awake. The participants were guided to breathe through their nose, and then through their mouth at their deep breathing rate. The least absolute shrinkage and selection operator (LASSO) feature selection approach was used to select the discriminative features from the power spectra of the TBS and the anthropometric information. Using a five-fold cross-validation procedure, five different training sets and their corresponding blind-testing sets were formed. The average blind-testing classification accuracy over the five different folds was found to be 79.3% ± 6.1 with the sensitivity (specificity) of 82.2% ± 7.2% (75.8% ± 9.9%). The accuracy for the entire dataset was found to be 81.1% with sensitivity (specificity) of 84.4% (77.0%). The feature selection and classification procedures were intelligible and fast. The selected features were physiologically meaningful. Overall, the results show that TBS analysis can be used as a quick and reliable prediction of the presence and severity of OSA during wakefulness without a sleep study.

Graphical abstract

Wakefulness screening of obstructive sleep apnea using tracheal breathing sounds and anthropometric information by means of regularized logistic regression with the least absolute shrinkage and selection operator approach for feature selection and classification.


Obstructive sleep apnea Tracheal breathing sounds Wakefulness screening Regularized logistic regression LASSO feature selection 




Apnea/hypopnea index


Area under the curve


Confidence interval


Fast Fourier transform


Least absolute shrinkage and selection operator


Logarithm of the sound’s variance


Multivariate analysis of variance


Obstructive sleep apnea


Power spectrum density




Receiver operating characteristic


Oxygen saturation level of blood


Support vector machine


Tracheal breathing sounds


Upper airway


  1. 1.
    Malhotra A, White DP (2002) Obstructive sleep apnoea. Lancet 360:237–245. CrossRefPubMedGoogle Scholar
  2. 2.
    Eckert DJ, Younes MK (2014) Arousal from sleep: implications for obstructive sleep apnea pathogenesis and treatment. J Appl Physiol 116:302–313. CrossRefPubMedGoogle Scholar
  3. 3.
    Young T, Palta M, Dempsey J et al (2010) Burden of sleep apnea: rationale, design, and major findings of the Wisconsin Sleep Cohort Study. WMJ Off Publ State Med Soc Wisconsin 108:246–249Google Scholar
  4. 4.
    Senaratna CV, Perret JL, Lodge CJ et al (2017) Prevalence of obstructive sleep apnea in the general population: a systematic review. Sleep Med Rev 34:70–81. CrossRefPubMedGoogle Scholar
  5. 5.
    Memtsoudis SG, Besculides MC, Mazumdar M (2013) A rude awakening — the perioperative sleep apnea epidemic. N Engl J Med 368:2352–2353. CrossRefPubMedGoogle Scholar
  6. 6.
    Sullivan F (2016) Hidden health crisis costing america billions. Underdiagnosing and Undertreating Obstructive Sleep Apnea Draining Healthcare SystemGoogle Scholar
  7. 7.
    Kushida CA, Littner MR, Morgenthaler T, Alessi CA, Bailey D, Coleman J Jr, Friedman L, Hirshkowitz M, Kapen S, Kramer M, Lee-Chiong T, Loube DL, Owens J, Pancer JP, Wise M (2005) Practice parameters for the indications for polysomnography and related procedures: an update for 2005. Sleep 28:499–523. CrossRefGoogle Scholar
  8. 8.
    Chiu HY, Chen PY, Chuang LP, Chen NH, Tu YK, Hsieh YJ, Wang YC, Guilleminault C (2017) Diagnostic accuracy of the Berlin questionnaire, STOP-BANG, STOP, and Epworth sleepiness scale in detecting obstructive sleep apnea: a bivariate meta-analysis. Sleep Med Rev 36:57–70. CrossRefPubMedGoogle Scholar
  9. 9.
    Young T, Shahar E, Nieto J et al (2002) Predictors of Sleep-disordered breathing in community-dwelling adults: the Sleep Heart Health Study. Arch Intern Med 162:893–900. CrossRefPubMedGoogle Scholar
  10. 10.
    Elwali A, Moussavi Z (2017) Obstructive sleep apnea screening and airway structure characterization during wakefulness using tracheal breathing sounds. Ann Biomed Eng 45:839–850. CrossRefPubMedGoogle Scholar
  11. 11.
    Montazeri A, Giannouli E, Moussavi Z (2012) Assessment of Obstructive sleep apnea and its severity during wakefulness. Ann Biomed Eng 40:916–924. CrossRefPubMedGoogle Scholar
  12. 12.
    Sola-Soler J, Fiz JA, Torres A, Jane R (2014) Identification of obstructive sleep apnea patients from tracheal breath sound analysis during wakefulness in polysomnographic studies. Conf Proc Annu Int Conf IEEE Eng Med Biol Soc IEEE Eng Med Biol Soc Annu Conf 2014:4232–4235. CrossRefGoogle Scholar
  13. 13.
    Yadollahi A, Montazeri A, Azarbarzin A, Moussavi Z (2013) Respiratory flow–sound relationship during both wakefulness and sleep and its variation in relation to sleep apnea. Ann Biomed Eng 41:537–546. CrossRefPubMedGoogle Scholar
  14. 14.
    Yadollahi A, Moussavi ZMK (2007) Acoustical flow estimation: review and validation. IEEE Eng Med Biol Mag 26:56–61. CrossRefPubMedGoogle Scholar
  15. 15.
    Wang Y, Mcdonald JP, Liu Y et al (2014) Dynamic alterations of the tongue in obstructive sleep apnea-hypopnea syndrome during sleep: analysis using ultrafast MRI. Genet Mol Res 13:4552–4563. CrossRefPubMedGoogle Scholar
  16. 16.
    Wu Z, Chen W, Khoo MCK, Davidson Ward SL, Nayak KS (2016) Evaluation of upper airway collapsibility using real-time MRI. J Magn Reson Imaging 44:158–167. CrossRefPubMedGoogle Scholar
  17. 17.
    Barkdull GC, Kohl C, Patel M, Davidson TM (2008) Computed tomography imaging of patients with obstructive sleep apnea. Laryngoscope 118:1486–1492. CrossRefPubMedGoogle Scholar
  18. 18.
    Liu K-H, Chu WCW, To K-W et al (2007) Sonographic measurement of lateral parapharyngeal wall thickness in patients with obstructive sleep apnea. J Sleep 30:1503–1508CrossRefGoogle Scholar
  19. 19.
    Schwab RJ, Pasirstein M, Pierson R, Mackley A, Hachadoorian R, Arens R, Maislin G, Pack AI (2003) Identification of upper airway anatomic risk factors for obstructive sleep apnea with volumetric magnetic resonance imaging. Am J Respir Crit Care Med 168:522–530. CrossRefPubMedGoogle Scholar
  20. 20.
    Finkelstein Y, Wolf L, Nachmani A, Lipowezky U, Rub M, Shemer S, Berger G (2014) Velopharyngeal anatomy in patients with obstructive sleep apnea versus normal subjects. J Oral Maxillofac Surg 72:1350–1372. CrossRefPubMedGoogle Scholar
  21. 21.
    Tibshirani R (2011) Regression shrinkage and selection via the lasso: a retrospective. J R Stat Soc Ser B (Statistical Methodol) 73:273–282. CrossRefGoogle Scholar
  22. 22.
    Hastie T, Tibshirani R, Friedman J (2009) The Elements of Statistical LearninGoogle Scholar
  23. 23.
    Goldstein BA, Navar AM, Carter RE (2017) Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges. Eur Heart J 38:1805–1814. CrossRefPubMedGoogle Scholar
  24. 24.
    Wen Y, Pi FH, Guo P et al (2016) Sleep duration, daytime napping, markers of obstructive sleep apnea and stroke in a population of southern China. Sci Rep 6:1–9. CrossRefGoogle Scholar
  25. 25.
    Oulhaj A, Al Dhaheri S, Bin SB, Al-Houqani M (2017) Discriminating between positional and non-positional obstructive sleep apnea using some clinical characteristics. Sleep Breath 21:877–884. CrossRefPubMedGoogle Scholar
  26. 26.
    Arvin F, Doraisamy S, Safar Khorasani E (2011) Frequency shifting approach towards textual transcription of heartbeat sounds. Biol Proced Online 13:1–7. CrossRefGoogle Scholar
  27. 27.
    Pasterkamp H, Kraman SS, Wodicka GR (1997) Respiratory sounds, advances beyond the stethoscope. Am J Respir Crit Care Med 156:974–987CrossRefGoogle Scholar
  28. 28.
    Hajipour F, Moussavi Z (2018) Spectral and higher order statistical characteristics of expiratory tracheal breathing sounds during wakefulness and sleep in people with different levels of obstructive sleep apnea. J Med Biol Eng 1–7. CrossRefGoogle Scholar
  29. 29.
    Proakis JG, Manolakis DG (1996) Digital signal processingGoogle Scholar
  30. 30.
    Simes RJ (1986) An improved Bonferroni procedure for multiple tests of significance. Biometrika 73:751–754. CrossRefGoogle Scholar
  31. 31.
    Šidák Z (1971) On probabilities of rectangles in multivariate Student distributions: their dependence on correlations. Ann Math Stat:169–175. CrossRefGoogle Scholar
  32. 32.
    Hastie T, Tibshirani R, Wainwright M (2015) Statistical learning with sparsity: the Lasso and generalizationsGoogle Scholar
  33. 33.
    Sanchez I, Pasterkamp H (1993) Tracheal sound spectra depend on body height. Am Rev Respir Dis 148:1083–1087. CrossRefPubMedGoogle Scholar
  34. 34.
    Epstein LJ, Kristo D, Strollo PJ et al (2009) Clinical guideline for the evaluation, management and long-term care of obstructive sleep apnea in adults. J Clin Sleep Med 5:263–276PubMedGoogle Scholar
  35. 35.
    Alshaer H, Pandya A, Bradley TD, Rudzicz F (2014) Subject independent identification of breath sounds components using multiple classifiers. ICASSP, IEEE Int Conf Acoust Speech Signal Process - Proc 3577–3581.
  36. 36.
    Huq S, Moussavi Z (2012) Acoustic breath-phase detection using tracheal breath sounds. Med Biol Eng Comput 50:297–308. CrossRefPubMedGoogle Scholar
  37. 37.
    Young T, Skatrud J, Peppard PE (2004) Risk factors for obstructive sleep apnea. 291:2013–2016Google Scholar
  38. 38.
    Schwartz AR, Patil SP, Laffan AM, Polotsky V, Schneider H, Smith PL (2008) Obesity and Obstructive sleep apnea: pathogenic mechanisms and therapeutic approaches. Proc Am Thorac Soc 5:185–192. CrossRefPubMedPubMedCentralGoogle Scholar
  39. 39.
    Davies RJ, Stradling JR (1990) The relationship between neck circumference, radiographic pharyngeal anatomy, and the obstructive sleep apnoea syndrome. Eur Respir J Off J Eur Soc Clin Respir Physiol 3:509–514Google Scholar
  40. 40.
    Davies RJ, Ali NJ, Stradling JR (1992) Neck circumference and other clinical features in the diagnosis of the obstructive sleep apnoea syndrome. Thorax 47:101–105. CrossRefPubMedPubMedCentralGoogle Scholar
  41. 41.
    Eckert DJ, White DP, Jordan AS, Malhotra A, Wellman A (2013) Defining phenotypic causes of obstructive sleep apnea: identification of novel therapeutic targets. Am J Respir Crit Care Med 188:996–1004. CrossRefPubMedPubMedCentralGoogle Scholar
  42. 42.
    Schwab RJ, Gupta KB, Gefter WB, Metzger LJ, Hoffman EA, Pack AI (1995) Upper airway and soft tissue anatomy in normal subjects and patients with sleep-disordered breathing. Significance of the lateral pharyngeal walls. Am J Respir Crit Care Med 152:1673–1689CrossRefGoogle Scholar
  43. 43.
    Haponik EF, Smith PL, Bohlman ME, Allen RP, Goldman SM, Bleecker ER (1983) Computerized tomography in obstructive sleep apnea. Correlation of airway size with physiology during sleep and wakefulness. Am Rev Respir Dis 127:221–226. CrossRefPubMedGoogle Scholar
  44. 44.
    von Helmholtz H (1860) Theorie der Luftschwingungen in Röhren mit offenen Enden. J für die reine und Angew Math 57:1–72Google Scholar
  45. 45.
    Veldi, Vasar, Vain et al (2000) Computerized endopharyngeal myotonometry (CEM): a new method to evaluate the tissue tone of the soft palate in patients with obstructive sleep apnoea syndrome. J Sleep Res 9:279–284. CrossRefPubMedGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2019

Authors and Affiliations

  1. 1.Biomedical Engineering ProgramUniversity of ManitobaWinnipegCanada
  2. 2.Dept of StatisticsUniversity of ManitobaWinnipegCanada
  3. 3.Electrical and Computer Engineering DepartmentUniversity of ManitobaWinnipegCanada

Personalised recommendations