Midsagittal jaw movements as a sleep/wake marker

Area of Science:

• Biomedical Engineering
• Sleep Medicine
• Signal Processing

Background:

• Obstructive Sleep Apnea/Hypopnea Syndrome (OSAHS) severity is measured by the apnea-hypopnea index (AHI).
• Total sleep time (TST) assessment typically relies on polysomnography (PSG) or wrist actigraphy.
• Accurate TST determination is crucial for reliable OSAHS diagnosis and management.

Purpose of the Study:

• To develop and validate an automatic sleep/wake detection system using jaw movement signals.
• To assess the accuracy of jaw movement analysis for TST estimation and AHI calculation.
• To evaluate the utility of jaw movement signals in portable monitoring for sleep apnea diagnosis.

Main Methods:

• A wavelet-based complexity measure of midsagittal jaw movement signals was employed.
• Multilayer perceptrons were utilized for automatic sleep/wake classification.
• The method was trained and tested on 63 recordings and validated on an independent set of 38 recordings.

Main Results:

• The automatic sleep/wake detector achieved 85.1% sensitivity, 76.4% specificity, and 82.9% global agreement compared to PSG.
• AHI calculation using jaw movement analysis significantly improved when incorporating the sleep/wake detector (p < 0.0001).
• The system demonstrated 88.6% sensitivity and 83.6% specificity for diagnosing sleep apnea syndrome (AHI threshold of 15).

Conclusions:

• Jaw movement signals are accurate for differentiating sleep from wakefulness.
• Jaw movement analysis offers a valuable addition to portable monitoring systems for sleep apnea assessment.
• This approach enhances the accuracy of AHI calculation and sleep apnea diagnosis outside traditional PSG settings.