Detection of flow limitation in obstructive sleep apnea with an artificial neural network

During sleep, the development of a plateau on the inspiratory airflow/time contour provides a non-invasive indicator of airway collapsibility. Humans recognize this abnormal contour easily, and this study replicates this with an artificial neural network (ANN) using a normalized shape. Five 10 min segments were selected from each of 18 sleep records (respiratory airflow measured with a nasal cannula) with varying degrees of sleep disordered breathing. Each breath was visually scored for shape, and breaths split randomly into a training and test set. Equally spaced, peak amplitude normalized flow values (representing breath shape) formed the only input to a back propagation ANN. Following training, breath-by-breath agreement of the ANN with the manual classification was tabulated for the training and test sets separately. Agreement of the ANN was 89% in the training set and 70.6% in the test set. When the categories of 'probably normal' and 'normal', and 'probably flow limited' and 'flow limited' were combined, the agreement increased to 92.7% and 89.4% respectively, similar to the intra- and inter-rater agreements obtained by a visual classification of these breaths. On a naive dataset, the agreement of the ANN to visual classification was 57.7% overall and 82.4% when the categories were collapsed. A neural network based only on the shape of inspiratory airflow succeeded in classifying breaths as to the presence/absence of flow limitation. This approach could be used to provide a standardized, reproducible and automated means of detecting elevated upper airway resistance.

[1]  J. N. Zhang,et al.  Detection of inspiratory flow limitation during sleep by computer assisted respiratory inductive plethysmography. , 2000, The European respiratory journal.

[2]  R. Berry,et al.  The use of auto-titrating continuous positive airway pressure for treatment of adult obstructive sleep apnea. An American Academy of Sleep Medicine review. , 2002, Sleep.

[3]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[4]  W. D. Winters,et al.  A Practical Method for Automatic Real-Time EEG Sleep State Analysis , 1980, IEEE Transactions on Biomedical Engineering.

[5]  J. Rowley,et al.  A mathematical model to detect inspiratory flow limitation during sleep. , 2002, Journal of applied physiology.

[6]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[7]  D. Rapoport,et al.  Non-Invasive detection of respiratory effort-related arousals (REras) by a nasal cannula/pressure transducer system. , 2000, Sleep.

[8]  C. Robert,et al.  Review of neural network applications in sleep research , 1998, Journal of Neuroscience Methods.

[9]  D. Rapoport,et al.  Classification of sleep-disordered breathing. , 2001, American journal of respiratory and critical care medicine.

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

[11]  J. Stradling,et al.  Sleep fragmentation indices as predictors of daytime sleepiness and nCPAP response in obstructive sleep apnea. , 1998, American journal of respiratory and critical care medicine.

[12]  Yves Verbandt,et al.  Automated breath detection on long-duration signals using feedforward backpropagation artificial neural networks , 2002, IEEE Transactions on Biomedical Engineering.

[13]  D. Rapoport,et al.  Detection of flow limitation with a nasal cannula/pressure transducer system. , 1998, American journal of respiratory and critical care medicine.

[14]  T. Aittokallio,et al.  Analysis of inspiratory flow shapes in patients with partial upper-airway obstruction during sleep. , 2001, Chest.

[15]  L. Tarassenko,et al.  New method of automated sleep quantification , 1992, Medical and Biological Engineering and Computing.

[16]  A. Muzet,et al.  Sleep stage scoring using the neural network model: comparison between visual and automatic analysis in normal subjects and patients. , 1996, Sleep.

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

[18]  J. Rowley,et al.  Noninvasive determination of upper airway resistance and flow limitation. , 2004, Journal of applied physiology.

[19]  Ross Ihaka,et al.  Gentleman R: R: A language for data analysis and graphics , 1996 .

[20]  D. Rapoport,et al.  Flow limitation as a noninvasive assessment of residual upper-airway resistance during continuous positive airway pressure therapy of obstructive sleep apnea. , 1994, American journal of respiratory and critical care medicine.

[21]  J. Dempsey,et al.  Assessment of inspiratory flow limitation invasively and noninvasively during sleep. , 1998, American journal of respiratory and critical care medicine.