A perspective on automated rapid eye movement sleep assessment

Area of Science:

• Neuroscience
• Biomedical Engineering
• Computer Science

Background:

• Rapid eye movement (REM) sleep exhibits unique biomedical signal changes.
• These signals are suitable for automated sleep staging using machine learning.
• Automated systems are crucial for objective sleep analysis.

Purpose of the Study:

• To review critical biomedical signals for REM sleep detection.
• To discuss the evolution and clinical utility of automated sleep staging.
• To explore the potential of consumer sleep trackers and AI in sleep assessment.

Main Methods:

• Analysis of biomedical signals during REM sleep.
• Review of historical developments in automated sleep staging algorithms.
• Discussion of machine learning applications in sleep analysis.
• Evaluation of consumer sleep tracker capabilities for REM sleep.

Main Results:

• Automated sleep staging now rivals human expert accuracy.
• Consumer sleep trackers offer potential for large-scale sleep assessment.
• AI systems are poised to advance computerised REM sleep analysis.

Conclusions:

• Biomedical signals provide a robust basis for automated REM sleep staging.
• Machine learning and AI are transforming sleep assessment.
• Consumer technology democratizes sleep monitoring and research.