Sleep –wake stage detection with single channel ECG and hybrid machine learning model in patients with obstructive sleep apnea

This study aims to develop a new method based on hybrid machine learning with single-channel ECG for sleep –wake detection, which is an alternative to the sleep staging procedure used in hospitals today. For this purpose, the heart rate variability signal was derived using electrocardiography (ECG) signals of 10 OSA patients. Then, QRS components in different frequency bands were obtained from the ECG signal by digital filtering. In this way, nine more signals were obtained in total. 25 features from each of the 9 signals, a total of 225 features have been extracted. Fisher feature selection algorithm and principal component analysis were used to reduce the number of features. Finally, features w ere classified with decision tree, support vector machines, k-nearest neighborhood algorithm and ensemble classifiers. In addition, the proposed model has been checked with the leave one out method. At the end of the study, it was shown that sleep–wake detection can be performed with 81.35% accura cy with only three features and 87.12% accuracy with 10 features. The sensitivity and specificity values for the 3 features were 0.85 and 0.77, and for 10 features the sensitivity and specificity values were 0.90 and 0.85 respectively. These results suggested that the proposed model could be used to detect sleep–wake stages during the OSA diagnostic process.

Source: Australasian Physical and Engineering Sciences in Medicine - January 4, 2021 Category: Biomedical Engineering Source Type: research