Respiration amplitude analysis for REM and NREM sleep classification

In previous work, single-night polysomnography recordings (PSG) of respiratory effort and electrocardiogram (ECG) signals combined with actigraphy were used to classify sleep and wake states. In this study, we aim at classifying rapid-eye-movement (REM) and non-REM (NREM) sleep states. Besides the existing features used for sleep and wake classification, we propose a set of new features based on respiration amplitude. This choice is motivated by the observation that the breathing pattern has a more regular amplitude during NREM sleep than during REM sleep. Experiments were conducted with a data set of 14 healthy subjects using a linear discriminant (LD) classifier. Leave-one-subject-out cross-validations show that adding the new features into the existing feature set results in an increase in Cohen’s Kappa coefficient to a value of kappa = 0.59 (overall accuracy of 87.6%) compared to that obtained without using these features (kappa of 0.54 and overall accuracy of 86.4%). In addition, we compared the results to those reported in some other studies with different features and signal modalities.