A Review of Automated Sleep Stage Scoring Using Machine Learning Techniques Based on Physiological Signals

Summary

The background and goal of this research are to address the importance of sleep in our lifestyle and health. To analyze sleep problems, legitimate scoring of sleep stages is fundamental, and this is usually finished through a tedious visual survey of, for the time being, polysomnograms by a human expert. However, this process can be improved with artificial intelligence algorithms. To accurately interpret the physiological signals associated with sleep disorders, it is essential to understand how changes in sleep stages are reflected in the signal waveform. With this knowledge, automated sleep stage scoring systems can be developed, making the diagnosis of sleep disorders more efficient and providing insight into the amount of information about sleep stages that can be gleaned from a particular physiological signal. The review study thoroughly examines automated sleep stage rating systems developed since 2000. These systems were created to analyze electrocardiograms (ECGs), electroencephalograms (EEGs), electrooculograms (EOGs), and signal combinations. The review discusses the most effective methods for sleep stage preprocessing, feature extraction and selection, and classifier selection. This chapter indicates that all the signals examined contain relevant information to determine sleep stage scoring. The conclusion emphasizes the significance of this discovery, as it enables a shift in research focus from information extraction methods to advances in patient comfort, redundancy, safety, and affordability.