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

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. 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.

[1]  A. Oulhaj,et al.  Discriminating between positional and non-positional obstructive sleep apnea using some clinical characteristics , 2017, Sleep and Breathing.

[2]  Z. Šidák.  On Probabilities of Rectangles in Multivariate Student Distributions: Their Dependence on Correlations , 1971 .

[3]  Hartmut Schneider,et al.  Obesity and obstructive sleep apnea: pathogenic mechanisms and therapeutic approaches. , 2008, Proceedings of the American Thoracic Society.

[4]  M. Mazumdar,et al.  A Rude Awakening: The Perioperative Sleep Apnea Epidemic , 2013 .

[5]  T. Davidson,et al.  Computed Tomography Imaging of Patients With Obstructive Sleep Apnea , 2008, The Laryngoscope.

[6]  J. Stradling,et al.  The relationship between neck circumference, radiographic pharyngeal anatomy, and the obstructive sleep apnoea syndrome. , 1990, The European respiratory journal.

[7]  G. Berger,et al.  Velopharyngeal anatomy in patients with obstructive sleep apnea versus normal subjects. , 2014, Journal of oral and maxillofacial surgery : official journal of the American Association of Oral and Maxillofacial Surgeons.

[8]  B. Goldstein,et al.  Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges , 2016, European heart journal.

[9]  A. Lowe,et al.  Prevalence of obstructive sleep apnea in the general population: A systematic review. , 2017, Sleep medicine reviews.

[10]  Raanan Arens,et al.  Identification of upper airway anatomic risk factors for obstructive sleep apnea with volumetric magnetic resonance imaging. , 2003, American journal of respiratory and critical care medicine.

[11]  A. Malhotra,et al.  Defining phenotypic causes of obstructive sleep apnea. Identification of novel therapeutic targets. , 2013, American journal of respiratory and critical care medicine.

[12]  Christian Guilleminault,et al.  Diagnostic accuracy of the Berlin questionnaire, STOP-BANG, STOP, and Epworth sleepiness scale in detecting obstructive sleep apnea: A bivariate meta-analysis. , 2017, Sleep medicine reviews.

[13]  Peter Bühlmann.  Regression shrinkage and selection via the Lasso: a retrospective (Robert Tibshirani): Comments on the presentation , 2011 .

[14]  E. Teugels,et al.  Influence of RT-qPCR primer position on EGFR interference efficacy in lung cancer cells , 2010, Biological Procedures Online.

[15]  A I Pack,et al.  Upper airway and soft tissue anatomy in normal subjects and patients with sleep-disordered breathing. Significance of the lateral pharyngeal walls. , 1995, American journal of respiratory and critical care medicine.

[16]  C. O’Brien.  Statistical Learning with Sparsity: The Lasso and Generalizations , 2016 .

[17]  Zahra Moussavi,et al.  Obstructive Sleep Apnea Screening and Airway Structure Characterization During Wakefulness Using Tracheal Breathing Sounds , 2016, Annals of Biomedical Engineering.

[18]  A. Malhotra,et al.  Clinical guideline for the evaluation, management and long-term care of obstructive sleep apnea in adults. , 2009, Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine.

[19]  M. Littner,et al.  Practice parameters for the indications for polysomnography and related procedures: an update for 2005. , 2005, Sleep.

[20]  Azadeh Yadollahi,et al.  Respiratory Flow–Sound Relationship During Both Wakefulness and Sleep and Its Variation in Relation to Sleep Apnea , 2012, Annals of Biomedical Engineering.

[21]  D. Hui,et al.  OBSTRUCTIVE SLEEP APNEA (OSA) IS A COMMON FORM OF SLEEP-DISORDERED BREATHING CHARACTERIZED BY REPETITIVE EPISODES OF PARTIAL OR COMPLETE upper airway obstruction causing sleep fragmentation and symp- , 2007 .

[22]  P. Guo,et al.  Sleep duration, daytime napping, markers of obstructive sleep apnea and stroke in a population of southern China , 2016, Scientific Reports.

[23]  Frank Rudzicz,et al.  Subject independent identification of breath sounds components using multiple classifiers , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[24]  P. Lu,et al.  Isolation of Live Premature Senescent Cells Using FUCCI Technology , 2016, Scientific Reports.

[25]  José Antonio Fiz,et al.  Identification of Obstructive Sleep Apnea patients from tracheal breath sound analysis during wakefulness in polysomnographic studies , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[26]  Atul Malhotra,et al.  Obstructive sleep apnoea , 2002, The Lancet.

[27]  Krishna S Nayak,et al.  Evaluation of upper airway collapsibility using real‐time MRI , 2016, Journal of magnetic resonance imaging : JMRI.

[28]  Vain,et al.  Computerized endopharyngeal myotonometry (CEM): A new method to evaluate the tissue tone of the soft palate in patients with obstructive sleep apnoea syndrome , 2000, Journal of sleep research.

[29]  P. L. Smith,et al.  Computerized tomography in obstructive sleep apnea. Correlation of airway size with physiology during sleep and wakefulness. , 1983, The American review of respiratory disease.

[30]  Shyamala Doraisamy,et al.  Frequency shifting approach towards textual transcription of heartbeat sounds , 2011, Biological Procedures Online.

[31]  H. Helmholtz.  Theorie der Luftschwingungen in Röhren mit offenen Enden. , 1860 .

[32]  Zahra Moussavi,et al.  Acoustic breath-phase detection using tracheal breath sounds , 2012, Medical & Biological Engineering & Computing.

[33]  Z. Moussavi,et al.  Spectral and Higher Order Statistical Characteristics of Expiratory Tracheal Breathing Sounds During Wakefulness and Sleep in People with Different Levels of Obstructive Sleep Apnea , 2019 .

[34]  H. Pasterkamp,et al.  Tracheal sound spectra depend on body height. , 1993, The American review of respiratory disease.

[35]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[36]  Z. Moussavi,et al.  Obstructive Sleep Apnea Screening and Airway Structure Characterization During Wakefulness Using Tracheal Breathing Sounds , 2016, Annals of Biomedical Engineering.

[37]  H. Pasterkamp,et al.  Respiratory sounds. Advances beyond the stethoscope. , 1997, American journal of respiratory and critical care medicine.

[38]  T. Young,et al.  Risk factors for obstructive sleep apnea in adults. , 2004, JAMA.

[39]  R. Tibshirani,et al.  Regression shrinkage and selection via the lasso: a retrospective , 2011 .

[40]  John G. Proakis,et al.  Digital signal processing (3rd ed.): principles, algorithms, and applications , 1996 .

[41]  T. Young,et al.  Burden of sleep apnea: rationale, design, and major findings of the Wisconsin Sleep Cohort study. , 2009, WMJ : official publication of the State Medical Society of Wisconsin.

[42]  R. Simes,et al.  An improved Bonferroni procedure for multiple tests of significance , 1986 .

[43]  Y. Wang,et al.  Dynamic alterations of the tongue in obstructive sleep apnea-hypopnea syndrome during sleep: analysis using ultrafast MRI. , 2014, Genetics and molecular research : GMR.

[44]  M. Younes,et al.  Arousal from sleep: implications for obstructive sleep apnea pathogenesis and treatment. , 2014, Journal of applied physiology.

[45]  J. Stradling,et al.  Neck circumference and other clinical features in the diagnosis of the obstructive sleep apnoea syndrome. , 1992, Thorax.

[46]  Terry Young,et al.  Predictors of sleep-disordered breathing in community-dwelling adults: the Sleep Heart Health Study. , 2002, Archives of internal medicine.

[47]  Azadeh Yadollahi,et al.  Acoustical Respiratory Flow , 2007 .

[48]  Zahra Moussavi,et al.  Assessment of Obstructive Sleep Apnea and its Severity during Wakefulness , 2011, Annals of Biomedical Engineering.