Sleep apnea screening based on Photoplethysmography data from wearable bracelets using an information-based similarity approach

Background and Objective: Sleep apnea (SA) is a common sleep disorder in daily life and is also an aggra-vating factor for various diseases. Having the potential to replace traditional but complicated diagnostic equipment, portable medical devices are receiving increasing attention, and thus, the demand for sup-porting algorithms is growing. This study aims to identify SA with wearable devices. Methods: Static information-based similarity (sIBS) and dynamic information-based similarity (dIBS) were proposed to analyze short-term fluctuations in heart rate (HR) with wearable devices. This study included overnight photoplethysmography (PPG) signals from 92 subjects obtained from wearable bracelets. Results: The results showed that sIBS achieved the highest correlation coefficient with the apnea-hypopnea index (R =-0.653, p = 0). dIBS showed a good balance in sensitivity and specificity (75.0% and 72.1%, respectively). Combining sIBS and dIBS with other classical time-frequency domain indices could simultaneously achieve good accuracy and balance (84.7% accuracy, 76.7% sensitivity and 89.6% speci-ficity). Conclusions: This research showed that both classic time-frequency domain indices and IBS indices changed significantly only in the severe SA group. This novel method could serve as an effective way to assess SA and provide new insight into its pathophysiology. (c) 2021 Elsevier B.V. All rights reserved.