A new method for sleep apnea classification using wavelets and feedforward neural networks

OBJECTIVES This paper presents a novel approach for sleep apnea classification. The goal is to classify each apnea in one of three basic types: obstructive, central and mixed. MATERIALS AND METHODS Three different supervised learning methods using a neural network were tested. The inputs of the neural network are the first level-5-detail coefficients obtained from a discrete wavelet transformation of the samples (previously detected as apnea) in the thoracic effort signal. In order to train and test the systems, 120 events from six different patients were used. The true error rate was estimated using a 10-fold cross validation. The results presented in this work were averaged over 100 different simulations and a multiple comparison procedure was used for model selection. RESULTS The method finally selected is based on a feedforward neural network trained using the Bayesian framework and a cross-entropy error function. The mean classification accuracy, obtained over the test set was 83.78+/-1.90%. CONCLUSION The proposed classifier surpasses, up to the author's knowledge, other previous results. Finally, a scheme to maintain and improve this system during its clinical use is also proposed.

[1]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[2]  B. Everitt,et al.  Statistical methods for rates and proportions , 1973 .

[3]  KrkovVra.  Kolmogorov's theorem is relevant , 1991 .

[4]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[5]  V. Moret-Bonillo,et al.  Intelligent diagnosis of sleep apnea syndrome , 2004, IEEE Engineering in Medicine and Biology Magazine.

[6]  Jens Timmer,et al.  Diagnosis of sleep apnea by automatic analysis of nasal pressure and forced oscillation impedance. , 2002, American journal of respiratory and critical care medicine.

[7]  Daniel J Buysse,et al.  Sleep-related breathing disorders in adults: recommendations for syndrome definition and measurement techniques in clinical research. The Report of an American Academy of Sleep Medicine Task Force. , 1999, Sleep.

[8]  Elena Hernández-Pereira,et al.  An intelligent system for the detection and interpretation of sleep apneas , 2003, Expert Syst. Appl..

[9]  Zoltán Benyó,et al.  A novel method for the detection of apnea and hypopnea events in respiration signals , 2002, IEEE Transactions on Biomedical Engineering.

[10]  Vra Krkov.  Kolmogorov's Theorem Is Relevant , 1991, Neural Computation.

[11]  J. Stradling,et al.  New approaches to monitoring sleep-related breathing disorders. , 1996, Sleep.

[12]  Tardi Tjahjadi,et al.  Cadosa: A fuzzy expert system for differential diagnosis of obstructive sleep apnoea and related conditions , 1997 .

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

[14]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[15]  W R Fright,et al.  Apnoea detection: human performance and reliability of a computer algorithm , 1995, Acta paediatrica.

[16]  Hans Bruun Nielsen,et al.  UCMINF - an Algorithm for Unconstrained, Nonlinear Optimization , 2000 .

[17]  Thomas Zemen,et al.  Classification of Sleep Apnea Events by Means of Radial Basis Function Networks , 1998, NC.

[18]  David J. C. MacKay,et al.  The Evidence Framework Applied to Classification Networks , 1992, Neural Computation.

[19]  A. Brzecka,et al.  [Treatment of obstructive sleep apnea syndrome]. , 1989, Pneumonologia polska.

[20]  Wolfgang Popp,et al.  Computerized detection of respiratory events during sleep from rapid increases in oxyhemoglobin saturation , 2007, Lung.

[21]  Françoise Fogelman-Soulié,et al.  Neurocomputing : algorithms, architectures and applications , 1990 .

[22]  M. Thorpy,et al.  Handbook of sleep disorders , 1990 .

[23]  Amparo Alonso-Betanzos,et al.  An Auto-learning System for the Classification of Fetal Heart Rate Decelerative Patterns , 2001, IWANN.

[24]  Karina Waldemark,et al.  Treatment of obstructive sleep apnea syndrome by monitoring patients airflow signals , 2000, Pattern Recognit. Lett..

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

[26]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[27]  John Scott Bridle,et al.  Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.

[28]  Ajit S. Bopardikar,et al.  Wavelet transforms - introduction to theory and applications , 1998 .

[29]  L. Groome,et al.  Behavioral state organization in normal human term fetuses: the relationship between periods of undefined state and other characteristics of state control. , 1995, Sleep.

[30]  T. Penzel,et al.  The SleepStripTM: an apnoea screener for the early detection of sleep apnoea syndrome , 2002, European Respiratory Journal.

[31]  A. Murray,et al.  Systematic comparison of different algorithms for apnoea detection based on electrocardiogram recordings , 2002, Medical and Biological Engineering and Computing.

[32]  D. Mackay,et al.  A Practical Bayesian Framework for Backprop Networks , 1991 .

[33]  D. Wolfe,et al.  Nonparametric Statistical Methods. , 1974 .

[34]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[35]  Geoffrey E. Hinton.  Learning Translation Invariant Recognition in Massively Parallel Networks , 1987, PARLE.

[36]  J. Hsu.  Multiple Comparisons: Theory and Methods , 1996 .