Hidden Markov modelling of intra-snore episode behavior of acoustic characteristics of obstructive sleep apnea patients

Obstructive sleep apnea (OSA) is a breathing disorder that can cause serious medical consequences. It is caused by full (apnea) or partial (hypopnea) obstructions of the upper airway during sleep. The gold standard for diagnosis of OSA is the polysomnography (PSG). The main measure for OSA diagnosis is the apnea-hypopnea index (AHI). However, the AHI is a time averaged summary measure of vast amounts of information gathered in an overnight PSG study. It cannot capture the dynamic characteristics associated with apnea/hypopnea events and their overnight distribution. The dynamic characteristics of apnea/hypopnea events are affected by the structural and functional characteristics of the upper airway. The upper airway characteristics also affect the upper airway collapsibility. These effects are manifested in snoring sounds generated from the vibrations of upper airway structures which are then modified by the upper airway geometric and physical characteristics. Hence, it is highly likely that the acoustical behavior of snoring is affected by the upper airway structural and functional characteristics. In the current work, we propose a novel method to model the intra-snore episode behavior of the acoustic characteristics of snoring sounds which can indirectly describe the instantaneous and temporal dynamics of the upper airway. We model the intra-snore episode acoustical behavior by using hidden Markov models (HMMs) with Mel frequency cepstral coefficients. Assuming significant differences in the anatomical and physiological upper airway configurations between low-AHI and high-AHI subjects, we defined different snorer groups with respect to AHI thresholds 15 and 30 and also developed HMM-based classifiers to classify snore episodes into those groups. We also define a measure called instantaneous apneaness score (IAS) in terms of the log-likelihoods produced by respective HMMs. IAS indicates the degree of class membership of each episode to one of the predefined groups as well as the instantaneous OSA severity. We then assigned each patient to an overall AHI band based on the majority vote of each episode of snoring. The proposed method has a diagnostic sensitivity and specificity between 87-91%.

[1]  A. Malhotra,et al.  Upper airway function in the pathogenesis of obstructive sleep apnea: a review of the current literature , 2008, Current opinion in pulmonary medicine.

[2]  T. Douglas Bradley,et al.  Sleep Apnea and Heart Failure: Part I: Obstructive Sleep Apnea , 2003, Circulation.

[3]  Atul Malhotra,et al.  Pathophysiology of adult obstructive sleep apnea. , 2008, Proceedings of the American Thoracic Society.

[4]  M. Hiltunen,et al.  The severity of individual obstruction events is related to increased mortality rate in severe obstructive sleep apnea , 2013, Journal of sleep research.

[5]  K. Clark,et al.  Association of Sleep-Disordered Breathing, Sleep Apnea, and Hypertension in a Large Community- Based Study , 2000 .

[6]  Indu Ayappa,et al.  The upper airway in sleep: physiology of the pharynx. , 2003, Sleep medicine reviews.

[7]  Milena Milanova,et al.  Sleep-Disordered Breathing and Acute Ischemic Stroke: Diagnosis, Risk Factors, Treatment, Evolution, and Long-Term Clinical Outcome , 2006, Stroke.

[8]  Cathy Goldstein,et al.  Obstructive sleep apnea-hypopnea and incident stroke: the sleep heart health study. , 2010, American journal of respiratory and critical care medicine.

[9]  José Antonio Fiz,et al.  Snoring analysis for the screening of sleep apnea hypopnea syndrome with a single-channel device developed using polysomnographic and snoring databases , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[10]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[11]  W D Duckitt,et al.  Automatic detection, segmentation and assessment of snoring from ambient acoustic data , 2006, Physiological measurement.

[12]  Effect of surfactant on pharyngeal mechanics in sleeping humans: implications for sleep apnoea , 2002, European Respiratory Journal.

[13]  S. Moebus,et al.  Association of obstructive sleep apnoea with subclinical coronary atherosclerosis. , 2013, Atherosclerosis.

[14]  Y. Zigel,et al.  OSA ESTIMATION BY ANALYSIS OF NOCTURNAL SNORING SIGNALS IN ADULTS , 2012 .

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

[16]  Alex Acero,et al.  Spoken Language Processing: A Guide to Theory, Algorithm and System Development , 2001 .

[17]  Mark J. F. Gales,et al.  The Application of Hidden Markov Models in Speech Recognition , 2007, Found. Trends Signal Process..

[18]  K M Hla,et al.  Sleep Apnea and Hypertension: A Population-based Study , 1994, Annals of Internal Medicine.

[19]  Radha M. Parikh,et al.  Decreased Surface Tension of Upper Airway Mucosal Lining Liquid Increases Upper Airway Patency in Anaesthetised Rabbits , 2003, The Journal of physiology.

[20]  Daniel J Buysse,et al.  Sleep–Related Breathing Disorders in Adults: Recommendations for Syndrome Definition and Measurement Techniques in Clinical Research , 2000 .

[21]  E. Hoffman,et al.  Dynamic imaging of the upper airway during respiration in normal subjects. , 1993, Journal of applied physiology.

[22]  K. Hurmerinta,et al.  Cephalometric comparison of pharyngeal changes in subjects with upper airway resistance syndrome or obstructive sleep apnoea in upright and supine positions. , 2004, European journal of orthodontics.

[23]  U. Abeyratne,et al.  Multi-feature snore sound analysis in obstructive sleep apnea-hypopnea syndrome. , 2011, Physiological measurement.

[24]  Ajith S. Wakwella,et al.  Pitch jump probability measures for the analysis of snoring sounds in apnea , 2005, Physiological measurement.

[25]  S. Furui,et al.  Cepstral analysis technique for automatic speaker verification , 1981 .

[26]  Esra Bilgin,et al.  Quick Diagnosis in Obstructive Sleep Apnea Syndrome: WatchPAT-200 , 2012, Iranian Red Crescent medical journal.

[27]  L. Baum,et al.  An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology , 1967 .

[28]  A. Newman,et al.  Prospective Study of Obstructive Sleep Apnea and Incident Coronary Heart Disease and Heart Failure: The Sleep Heart Health Study , 2010, Circulation.

[29]  Yi Wang,et al.  Diagnostic performance of single airflow channel recording (ApneaLink) in home diagnosis of sleep apnea , 2010, Sleep and Breathing.

[30]  J. Hedner,et al.  An independent association between obstructive sleep apnoea and coronary artery disease. , 1999, The European respiratory journal.

[31]  K. Bloch,et al.  Polysomnography: a systematic review. , 1997, Technology and health care : official journal of the European Society for Engineering and Medicine.

[32]  A. Rechtschaffen,et al.  A manual of standardized terminology, technique and scoring system for sleep stages of human subjects , 1968 .

[33]  U R Abeyratne,et al.  Obstructive sleep apnea screening by integrating snore feature classes , 2013, Physiological measurement.

[34]  S. Phurrough,et al.  Administrative File: CAG #00093R2 Continuous Positive Airway Pressure (CPAP) Therapy for Obstructive Sleep Apnea (OSA) , 2008 .

[35]  W. T. McNicholas,et al.  Sleep apnoea as an independent risk factor for cardiovascular disease: current evidence, basic mechanisms and research priorities , 2006, European Respiratory Journal.

[36]  Sadaoki Furui,et al.  Text-independent speaker recognition using vocal tract and pitch information , 1990, ICSLP.

[37]  R. Horner,et al.  Pathophysiology of obstructive sleep apnea. , 2008, Journal of cardiopulmonary rehabilitation and prevention.

[38]  Raimon Jané,et al.  Continuous analysis and monitoring of snores and their relationship to the apnea‐hypopnea index , 2010, The Laryngoscope.

[39]  E V Dunn,et al.  Snoring as a risk factor for disease: an epidemiological survey. , 1985, British medical journal.

[40]  M. Hiltunen,et al.  Adjustment of apnea-hypopnea index with severity of obstruction events enhances detection of sleep apnea patients with the highest risk of severe health consequences , 2014, Sleep and Breathing.

[41]  C. Guilleminault,et al.  Chapter 87 – Clinical Features and Evaluation of Obstructive Sleep Apnea-Hypopnea Syndrome and Upper Airway Resistance Syndrome , 2005 .