Related Experiment Video
Updated: Jul 30, 2025
04:04
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
35
Contactless screening for sleep apnea with breathing vibration signals based on modified U-Net
Yuhang Chen1, Gang Ma1, Miao Zhang2
1School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, China; Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, China.
Sleep Medicine
|May 18, 2023
Summary
A new home-based screening tool uses breathing vibrations and AI to detect obstructive sleep apnea (OSA). This contactless method offers accurate screening, aiding early diagnosis and referral for further testing.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence in Medicine
- Sleep Medicine
Background:
- Obstructive sleep apnea (OSA) is a prevalent chronic sleep disorder.
- Polysomnography (PSG) is the gold standard for OSA diagnosis but is costly and inconvenient.
- There is a need for accessible, home-based screening devices for OSA.
Purpose of the Study:
- To develop and validate a novel home-based screening method for OSA using breathing vibration signals.
- To assess the efficacy of a modified U-Net deep learning model for detecting sleep apnea events and estimating the apnea-hypopnea index (AHI).
Main Methods:
- A contactless method was used to collect whole-night breathing vibration signals.
- A modified U-Net deep learning model was employed to detect sleep apnea-hypopnea events.
- The apnea-hypopnea index (AHI) was estimated and compared to manually obtained values for performance evaluation.
Main Results:
- The model achieved 97.5% accuracy and 76.4% sensitivity in detecting sleep apnea events.
- The mean absolute error for AHI estimation was 3.0 events/hour.
- An R-squared value of 0.95 was observed between predicted and ground truth AHI, with 88.9% of participants correctly classified into AHI categories.
Conclusions:
- The proposed breathing vibration-based screening method shows significant potential for accurate OSA detection.
- This non-intrusive, home-based approach can facilitate early identification of potential OSA patients.
- The tool can aid in referring patients for further diagnostic evaluations like home sleep apnea tests (HSAT) or PSG.
