0276 Detecting Apnea Hypopnea Index for Classified the Severity of Obstructive Sleep Apnea using PPG signals

Abstract

Abstract Introduction A polysomnography or home sleep apnea study provides multiple pieces of information to diagnose obstructive sleep apnea (OSA), but the tests are costly with limited access. The study aims to use an automated AHI model with only PPG signals and can be applied to a wearable device. Methods We have included patients with different OSA severity to build an algorithm detecting ODI based on the scoring criteria with varying sizes of windows ranging from 10 to 60 seconds. For patients without ODI events, the automated CPC for detecting low-frequency oscillation is included to support the automated AHI model. Results The automated ODI and the combination of automated CPC are highly correlated with the AHI. When a CPC is detected without the ODI, the low-frequency coupling can assist in detecting AHI. The accuracy of the automated AHI is 86% compared to the actual AHI, with the sensitivity, specificity and precision at 92%, 73% and 89%, respectively. Conclusion The automated AHI algorithm with PPG signals as input can have a high sensitivity and accuracy in screening patients with OSA (AHI≥5), which can considerably be implied in a PPG wearable device. Support (if any)