Detection of Sleep Apnea Using Sonar Smartphone Technology

Area of Science:

• Biomedical Engineering
• Sleep Medicine
• Signal Processing

Background:

• Sleep Disordered Breathing (SDB) is a prevalent condition requiring accessible screening tools.
• Current SDB screening methods can be invasive or costly, limiting widespread adoption.
• Noncontact sensing technologies offer a potential solution for unobtrusive sleep monitoring.

Purpose of the Study:

• To evaluate the performance of a novel noncontact sonar-based system for screening Sleep Disordered Breathing (SDB).
• To assess the system's ability to accurately detect SDB patterns and measure sleep stages using smartphone technology.
• To determine the feasibility of using this system as a low-cost, scalable SDB screener.

Main Methods:

• A custom smartphone app utilizing proprietary algorithms was developed to analyze sonar data.
• The system was trained on 94 overnight recordings from a sleep laboratory, validated against polysomnography (PSG).
• Independent testing was performed on 68 recordings across various SDB severity classes.

Main Results:

• The sonar-based SDB screener demonstrated excellent performance on the independent test set.
• Sensitivity reached 94% and specificity reached 97% for an Apnea Hypopnea Index (AHI) threshold of 15 events/hour.
• Results were comparable to existing ambulatory SDB screening devices.

Conclusions:

• The smartphone-based sonar system shows high accuracy and potential as an effective SDB screener.
• The non-invasive, contactless, and low-cost nature of the technology facilitates scalable, longitudinal monitoring.
• This approach could improve SDB diagnosis, patient adherence to therapy, and provide insights into sleep quality.