Pulse transit time and heart rate variability in sleep staging.

Area of Science:

• Biomedical Engineering
• Sleep Medicine
• Signal Processing

Background:

• Accurate sleep stage detection is crucial for diagnosing sleep disorders.
• Traditional polysomnography (PSG) is resource-intensive and not suitable for long-term monitoring.
• Non-invasive, wearable methods for sleep analysis are highly desirable.

Purpose of the Study:

• To develop and validate a novel algorithm for automated sleep stage detection.
• To utilize Electrocardiography (ECG) and Photoplethysmography (PPG) signals for sleep analysis.
• To assess the feasibility of implementing this algorithm in a wearable device.

Main Methods:

• Extraction of Heart Rate Variability (HRV) and Pulse Transit Time (PTT) biomarkers from ECG and PPG signals.
• Feature extraction and classification using Distance Weighted k-Nearest Neighbours (DWk-NN).
• Validation using overnight Polysomnography (PSG) recordings from 20 healthy and insomniac subjects.

Main Results:

• Achieved an average accuracy of 73.4% (±6.4% SD) in sleep stage classification.
• Demonstrated high sensitivity (almost 80%) for distinguishing non-rapid eye movement sleep stages 2 and 3.
• Showed a mean sensitivity of 53% for stage 1 sleep.

Conclusions:

• The developed algorithm effectively classifies sleep stages using PTT and HRV spectral analysis.
• The approach offers high accuracy and sensitivity, suitable for distinguishing key sleep stages.
• The algorithm's potential for integration into affordable, wearable sleep screening instruments is highlighted.