Improving the Diagnostic Ability of the Sleep Apnea Screening System Based on Oximetry by Using Physical Activity Data

Abstract

Polysomnography (PSG) is the gold standard for diagnosing sleep apnea (SA), but it is costly and time-consuming. An oximeter as alternative diagnostic tool is small in size and user friendly. However, using an oximeter alone can easily underestimate SA severity. Therefore, we aimed to develop a SA screening system to solve the problem of underestimating SA severity. We developed a wireless oximetry system to record peripheral oxygen saturation, heart rate, and physical activity. Physical activity was used to remove artifacts and derive total sleep time. After artifact removal, an algorithm estimated the apnea–hypopnea index (AHI). 56 participants with different severities of SA underwent overnight inspection using home-based PSG and wireless oximetry for more than 6 h. In the four SA severity groups, the overall accuracy, sensitivity, and specificity of AHI estimated by our system (AHIEsti) were 81.25%, 69.64%, and 92.86%, respectively. AHIEsti was positively related to AHI of PSG. Receiver operating characteristic curves were plotted based on the threshold of AHI of PSG being greater than 5, 10, 15, and 30, and the corresponding areas under the curve were 0.910, 0.800, 0.794, and 0.970. This SA screening system can determine whether a patient has SA but cannot evaluate SA severity precisely. Our system is a potential screening tool for SA, supporting PSG at a lower cost.