Sleep Staging Using Noncontact-Measured Vital Signs

Area of Science:

• Biomedical Engineering
• Sleep Medicine
• Signal Processing

Background:

• Sleep is crucial for health, occupying 30% of life.
• Polysomnography (PSG) is the gold standard for sleep staging but is inconvenient for home use.
• There is a need for noninvasive, comfortable sleep monitoring solutions.

Purpose of the Study:

• To develop and validate a noncontact vital signs monitoring system for sleep staging.
• To assess the feasibility of using piezoelectric sensors for sleep analysis.
• To improve the accuracy and convenience of sleep quality assessment.

Main Methods:

• A noncontact vital signs monitoring system using piezoelectric sensors was deployed.
• Heartbeat interval (HI), respiratory interval (RI), and body movements (BM) were recorded.
• A novel feature, coordination of heartbeat and respiratory intervals (CHR), was extracted.
• Wake-REM-NREM sleep staging was performed using extracted features and a staging fusion algorithm.

Main Results:

• The noncontact system achieved an average accuracy of 82.42% and a Cohen's Kappa of 0.63 compared to PSG.
• The proposed sleep staging method demonstrated robustness in subjects with sleep-disordered breathing.
• Independent features (HI, RI, BM) and coordinated features (CHR) were effectively utilized for classification.

Conclusions:

• The noncontact piezoelectric sensing system offers a promising and accurate alternative to PSG for sleep staging.
• This technology enhances the potential for convenient and effective in-home sleep monitoring.
• The developed system is suitable for diverse populations, including those with sleep-disordered breathing.