Sleep stage and obstructive apneaic epoch classification using single-lead ECG

Abstract

Background: Polysomnography (PSG) is used to define physiological sleep and different physiological sleep stages, to assess sleep quality and diagnose many types of sleep disorders such as obstructive sleep apnea. However, PSG requires not only the connection of various sensors and electrodes to the subject but also spending the night in a bed that is different from the subject's own bed. This study is designed to investigate the feasibility of automatic classification of sleep stages and obstructive apneaic epochs using only the features derived from a single-lead electrocardiography (ECG) signal.

Methods: For this purpose, PSG recordings (ECG included) were obtained during the night's sleep (mean duration 7 hours) of 17 subjects (5 men) with ages between 26 and 67. Based on these recordings, sleep experts performed sleep scoring for each subject. This study consisted of the following steps: (1) Visual inspection of ECG data corresponding to each 30-second epoch, and selection of epochs with relatively clean signals, (2) beat-to-beat interval (RR interval) computation using an R-peak detection algorithm, (3) feature extraction from RR interval values, and (4) classification of sleep stages (or obstructive apneaic periods) using one-versus-rest approach. The features used in the study were the median value, the difference between the 75 and 25 percentile values, and mean absolute deviations of the RR intervals computed for each epoch. The k-nearest-neighbor (kNN), quadratic discriminant analysis (QDA), and support vector machines (SVM) methods were used as the classification tools. In the testing procedure 10-fold cross-validation was employed.

Results: QDA and SVM performed similarly well and significantly better than kNN for both sleep stage and apneaic epoch classification studies. The classification accuracy rates were between 80 and 90% for the stages other than non-rapid-eye-movement stage 2. The accuracies were 60 or 70% for that specific stage. In five obstructive sleep apnea (OSA) patients, the accurate apneaic epoch detection rates were over 89% for QDA and SVM.

Conclusion: This study, in general, showed that RR-interval based classification, which requires only single-lead ECG, is feasible for sleep stage and apneaic epoch determination and can pave the road for a simple automatic classification system suitable for home-use.

Figure 1

Simultaneous display of the hypnogram from one healthy subject and the associated values of the features computed from each epoch. The red lines show wake, NREM 1 to 4, and REM sleep stages with respect to epoch numbers throughout the night's sleep (hypnogram). Because of simultaneous display, on the hypnogram wake and REM are at the levels of 500 and 250 ms, respectively. NREM 1 to 4 stages are shown at 400 to 100 ms levels, respectively. Blue, green, and black graphs indicate median (values are halved for better representation), interquartile range (iqr), and mean absolute deviation (mad) of RR values obtained from each epoch.

Figure 2

Classification performance of one healthy subject with respect to the epoch number using QDA as the method of choice. The red lines show the actual stage as wake or other stage, and blue lines show the estimated stage as wake or other stages. We imposed an offset between the actual and classification results in order to make them easy to differentiate.

Figure 3

Classification performance of one subject from OSA group with respect to the epoch number using SVM as the method of choice. The red and blue lines show the actual and estimated class of an epoch as with apnea or without apnea, respectively. We imposed an offset between the actual situation and classification results in order to make them easy to differentiate.