Abstract:
Chronic and common obstructive sleep apnea (OSA) has many comorbidities. Polysomnography (PSG), the gold standard for OSA diagnosis, is unavailable in many severe cases. Home-based OSA screening methods that identify high-risk patients who need PSG are needed. Several OSA screening methods have examined speech or breathing sounds. However, these methods have limitations that limit their use in homes (e.g., they require specialized equipment, are obtrusive, are not robust to background noise, or require tightly controlled conditions). This paper proposes a smartphone-based OSA screening method. A deep neural network classifies OSA in nightlong audio recordings by segment. Screening for OSA uses the estimated apnea-hypopnea index from segments predicted to have OSA. The proposed system was developed and tested using 103 participants’ home sleep apnea recordings from 1 or 2 nights. The acoustics-based moderate OSA screening system had 0.79 sensitivity and 0.80 specificity. Severe OSA screening had 0.78 sensitivity and 0.93 specificity. It works on consumer smartphones.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
