Real-time obstructive sleep apnea detection from frequency analysis of EDR and HRV using Lomb Periodogram

Area of Science:

• Biomedical Engineering
• Cardiology
• Sleep Medicine

Background:

• Obstructive sleep apnea (OSA) diagnosis traditionally relies on Polysomnography (PSG), which is cumbersome and requires multiple physiological signals.
• There is a need for simpler, more accessible methods for real-time OSA detection, particularly for portable applications.

Purpose of the Study:

• To propose an effective real-time obstructive sleep apnea (OSA) detection method using only electrocardiogram (ECG) signals.
• To develop a portable and hardware-feasible OSA detection system by analyzing frequency characteristics of ECG-derived respiratory (EDR) and heart rate variability (HRV).

Main Methods:

• Frequency analysis of EDR and HRV using a simplified Lomb Periodogram.
• Utilizing only ECG signals for OSA detection, eliminating the need for multiple physiological measurements.
• Integration of EDR and HRV indexes for enhanced detection accuracy.

Main Results:

• Achieved high diagnostic performance with Specificity (Sp) of 91%, Sensitivity (Se) of 95.7%, and Accuracy of 93.2%.
• Demonstrated the feasibility of real-time OSA detection using a simplified frequency analysis method.
• Validated the effectiveness of combining EDR and HRV for improved OSA detection.

Conclusions:

• The proposed method offers an effective, accurate, and portable solution for real-time OSA detection using solely ECG signals.
• The integration of EDR and HRV frequency analysis provides a significant improvement over traditional methods in terms of simplicity and accessibility.
• This approach holds promise for widespread clinical application and remote patient monitoring for OSA.