Utility of multilayer perceptron neural network classifiers in the diagnosis of the obstructive sleep apnoea syndrome from nocturnal oximetry

The aim of this study is to assess the ability of multilayer perceptron (MLP) neural networks as an assistant tool in the diagnosis of the obstructive sleep apnoea syndrome (OSAS). Non-linear features from nocturnal oxygen saturation (SaO(2)) recordings were used to discriminate between OSAS positive and negative patients. A total of 187 subjects suspected of suffering from OSAS (111 with a positive diagnosis of OSAS and 76 with a negative diagnosis of OSAS) took part in the study. The initial population was divided into training, validation and test sets for deriving and testing our neural network classifier. Three methods were applied to extract non-linear features from SaO(2) signals: approximate entropy (ApEn), central tendency measure (CTM) and Lempel-Ziv complexity (LZC). The selected MLP-based classifier provided a diagnostic accuracy of 85.5% (89.8% sensitivity and 79.4% specificity). Our neural network algorithm could represent a useful technique for OSAS detection. It could contribute to reduce the demand for polysomnographic studies in OSAS screening.

[1]  B. Grant,et al.  Prediction of the apnea-hypopnea index from overnight pulse oximetry. , 2003, Chest.

[2]  J. M. Rodríguez González-Moro,et al.  Utilidad del análisis visual de la oximetría nocturna como método de cribado en enfermos con sospecha clínica de SAOS , 1996 .

[3]  R. Hornero,et al.  Obstructive Sleep Apnea Detection Using Clustering Classification of Nonlinear Features from Nocturnal Oximetry , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  R. Pauwels,et al.  Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: National Heart, Lung, and Blood Institute and World Health Organization Global Initiative for Chronic Obstructive Lung Disease (GOLD): executive summary. , 2001, Respiratory care.

[5]  D. Shucard,et al.  Validity of neural network in sleep apnea. , 1999, Sleep.

[6]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[7]  W. Baxt.  Application of artificial neural networks to clinical medicine , 1995, The Lancet.

[8]  A. Chesson,et al.  The American Academy of Sleep Medicine (AASM) Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications , 2007 .

[9]  T. Young,et al.  Epidemiology of obstructive sleep apnea: a population health perspective. , 2002, American journal of respiratory and critical care medicine.

[10]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[11]  W A Whitelaw,et al.  Automated analysis of digital oximetry in the diagnosis of obstructive sleep apnoea , 2000, Thorax.

[12]  K G van Houwelingen,et al.  Sleep Apnoea Syndromes , 1979, The Lancet.

[13]  W. Flemons,et al.  Home diagnosis of sleep apnea: a systematic review of the literature. An evidence review cosponsored by the American Academy of Sleep Medicine, the American College of Chest Physicians, and the American Thoracic Society. , 2003, Chest.

[14]  E. Bixler,et al.  Prevalence of sleep-disordered breathing in women: effects of gender. , 2001, American journal of respiratory and critical care medicine.

[15]  Roberto Hornero,et al.  Oxygen saturation regularity analysis in the diagnosis of obstructive sleep apnea , 2006, Artif. Intell. Medicine.

[16]  Roberto Hornero,et al.  Radial basis function classifiers to help in the diagnosis of the obstructive sleep apnoea syndrome from nocturnal oximetry , 2008, Medical & Biological Engineering & Computing.

[17]  David Hinkley,et al.  Bootstrap Methods: Another Look at the Jackknife , 2008 .

[18]  J. Haze,et al.  Obstructive sleep apnea. , 1987, Cranio : the journal of craniomandibular practice.

[19]  R. Hornero,et al.  Applying Neural Network Classifiers in the Diagnosis of the Obstructive Sleep Apnea Syndrome from Nocturnal Pulse Oximetric Recordings , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[20]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[21]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[22]  John Moody,et al.  Note on generalization, regularization and architecture selection in nonlinear learning systems , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.

[23]  J. Mitchell,et al.  Evaluation of the Ohmeda 3700 pulse oximeter. , 1987, Thorax.

[24]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[25]  Roberto Hornero,et al.  Utility of Approximate Entropy From Overnight Pulse Oximetry Data in the Diagnosis of the Obstructive Sleep Apnea Syndrome , 2007, IEEE Transactions on Biomedical Engineering.

[26]  A. Chesson,et al.  The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology, and Techinical Specifications , 2007 .

[27]  Abraham Lempel,et al.  On the Complexity of Finite Sequences , 1976, IEEE Trans. Inf. Theory.

[28]  C. Brambilla,et al.  Accuracy of oximetry for detection of respiratory disturbances in sleep apnea syndrome. , 1996, Chest.

[29]  C. Guilleminault,et al.  EEG arousals: scoring rules and examples: a preliminary report from the Sleep Disorders Atlas Task Force of the American Sleep Disorders Association. , 1992, Sleep.

[30]  D. Navajas,et al.  Accuracy of thermistors and thermocouples as flow-measuring devices for detecting hypopnoeas. , 1998, The European respiratory journal.

[31]  R. Pauwels,et al.  Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease. NHLBI/WHO Global Initiative for Chronic Obstructive Lung Disease (GOLD) Workshop summary. , 2001, American journal of respiratory and critical care medicine.

[32]  Don D. Sin,et al.  Getting the Most Out of Nocturnal Pulse Oximetry , 2003 .

[33]  K. G. van Houwelingen,et al.  Sleep apnoea syndromes. , 1999, Lancet.

[34]  Anil K. Jain,et al.  Dimensionality reduction using genetic algorithms , 2000, IEEE Trans. Evol. Comput..

[35]  D. L. Hudson,et al.  Applying continuous chaotic modeling to cardiac signal analysis , 1996 .

[36]  J M Rodríguez González-Moro,et al.  [Usefulness of the visual analysis of night oximetry as a screening method in patients with suspected clinical obstructive sleep apnea syndrome]. , 1996, Archivos de bronconeumologia.

[37]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[38]  T. Young,et al.  Estimation of the clinically diagnosed proportion of sleep apnea syndrome in middle-aged men and women. , 1997, Sleep.

[39]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[40]  D. Kristo,et al.  Overnight pulse oximetry for sleep-disordered breathing in adults: a review. , 2001, Chest.

[41]  Steven M. Pincus.  Assessing Serial Irregularity and Its Implications for Health , 2001, Annals of the New York Academy of Sciences.

[42]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[43]  W. Kinnear,et al.  Sleep on the cheap: the role of overnight oximetry in the diagnosis of sleep apnoea hypopnoea syndrome , 1999, Thorax.

[44]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[45]  A. Rechtschaffen.  A manual of Standardized Terminology , 1968 .

[46]  D. Abásolo,et al.  Nonlinear characteristics of blood oxygen saturation from nocturnal oximetry for obstructive sleep apnoea detection , 2006, Physiological measurement.

[47]  Bernard Fleury,et al.  Home unattended vs hospital telemonitored polysomnography in suspected obstructive sleep apnea syndrome: a randomized crossover trial. , 2002, Chest.

[48]  Roberto Hornero,et al.  Improving diagnostic ability of blood oxygen saturation from overnight pulse oximetry in obstructive sleep apnea detection by means of central tendency measure , 2007, Artif. Intell. Medicine.

[49]  K. Ferguson,et al.  Neural network prediction of obstructive sleep apnea from clinical criteria. , 1999, Chest.

[50]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[51]  M. Wogan,et al.  Agency for Health Care Policy and Research (AHCPR) , 2015 .

[52]  Nicolas Roche,et al.  Prospective testing of two models based on clinical and oximetric variables for prediction of obstructive sleep apnea. , 2002, Chest.

[53]  E. Wolpert.  A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. , 1969 .

[54]  S. Hurd,et al.  Global Strategy for the Diagnosis, Management and Prevention of COPD: 2003 update , 2003, European Respiratory Journal.