A novel approach to automatic sleep stage classification using forehead electrophysiological signals

Hengyan Guo; Yang Di; Xingwei An; Zhongpeng Wang; Dong Ming

doi:10.1016/j.heliyon.2022.e12136

A novel approach to automatic sleep stage classification using forehead electrophysiological signals

Heliyon. 2022 Dec 16;8(12):e12136. doi: 10.1016/j.heliyon.2022.e12136. eCollection 2022 Dec.

Authors

Hengyan Guo¹, Yang Di¹, Xingwei An^{1

2}, Zhongpeng Wang^{3

2}, Dong Ming^{1

3

2}

Affiliations

¹ Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China.
² TianJin Center for Brain Science, Tianjin, China.
³ Department of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin, China.

Abstract

Background: Sleep stage scoring is very important for the effective diagnosis and intervention of sleep disorders. However, the current automatic sleep staging methods generally have the problems of poor model generalization ability and non-portable acquisition equipment.

Method: In this paper, we propose a novel automatic sleep scoring system based on forehead electrophysiological signals that is more effective and convenient than other systems. We extract 3 channel signals from the forehead, named forehead electroencephalogram 1 (Fh1), forehead electroencephalogram 2 (Fh2), and forehead center electrooculogram (Fhz). Spectral features, statistical features, and entropy features are extracted using the discrete wavelet transform (DWT) method. Light gradient boosting machine (LGB), random forest (RF), and support vector machine (SVM) are employed to classify four stages: awake, light sleep (LS), deep sleep (DS), and rapid eye movement (REM).

Result: The performance of the proposed method is validated using databases of the Sleep-EDFX and our Own-data, which include polysomnograms (PSGs) and forehead signals of 28 subjects. The overall classification accuracy of using the combination of Fh1, Fh2, and Fhz can reach up to 90.25% accuracy with a kappa coefficient of 0.857.

Conclusions: The proposed method could provide state-of-art multichannel sleep stage scoring performance with higher portability. This will facilitate the application of long-term monitoring of sleep quality in the future.

Keywords: Discrete wavelet transform (DWT); Electrooculogram (EOG); Forehead electrophysiological signal; Light gradient boosting machine (LGB); Sleep stages.