Pulse photopletismography amplitude decrease detector for sleep apnea evaluation in children

Area of Science:

• Biomedical Engineering
• Medical Signal Processing
• Sleep Medicine

Background:

• Sleep apnea is a prevalent sleep disorder requiring accurate diagnostic methods.
• Current diagnostic tools can be invasive or resource-intensive.
• Pulse photoplethysmography (PPG) offers a non-invasive approach for physiological monitoring.

Purpose of the Study:

• To develop and validate an automated method for detecting sleep apnea using PPG signals.
• To assess the efficacy of the proposed detector in classifying children with and without sleep apnea.
• To establish the clinical utility of PPG-based sleep apnea detection in pediatric populations.

Main Methods:

• A three-stage automatic detector was designed: pre-processing, envelope detection (RMS or Hilbert transform), and adaptive thresholding.
• The detector analyzes decreases in PPG amplitude fluctuations.
• Performance was evaluated using simulated and real PPG signals, including a clinical study on children.

Main Results:

• The detector achieved a sensitivity of 76% and a positive predictive value of 73% on real signals.
• The ratio of PPG attenuation events per hour (Eh) was statistically significant (p < 0.05) in differentiating between normal (13.5 ± 6.35 Eh) and pathological (21.1 ± 8.93 Eh) cases in children.
• The method demonstrated potential for classifying sleep apnea severity in pediatric patients.

Conclusions:

• The proposed automatic PPG-based method shows promise for non-invasive sleep apnea detection.
• PPG signal analysis offers a viable tool for sleep apnea diagnosis, particularly in children.
• Further research can refine this technique for broader clinical application in sleep disorder diagnosis.