A Novel Decision Making Procedure during Wakefulness for Screening Obstructive Sleep Apnea using Anthropometric Information and Tracheal Breathing Sounds

Abstract

Obstructive sleep apnea (OSA) is an underdiagnosed common disorder. Undiagnosed OSA, in particular, increases the perioperative morbidity and mortality risks for OSA patients undergoing surgery requiring full anesthesia. OSA screening using the gold standard, Polysomnography (PSG), is expensive and time-consuming. This study offers an objective and accurate tool for screening OSA during wakefulness by a few minutes of breathing sounds recording. Our proposed algorithm (AWakeOSA) extracts an optimized set (3–4) of breathing sound features specific to each anthropometric feature (i.e. age, sex, etc.) for each subject. These personalized group (e.g. age) classification features are then used to determine OSA severity in the test subject for that anthropomorphic parameter. Each of the anthropomorphic parameter classifications is weighted and summed to produce a final OSA severity classification. The tracheal breathing sounds of 199 individuals (109 with apnea/hypopnea index (AHI) < 15 as non-OSA and 90 with AHI ≥ 15 as moderate/severe-OSA) were recorded during wakefulness in the supine position. The sound features sensitive to OSA were extracted from a training set (n = 100). The rest were used as a blind test dataset. Using Random-Forest classification, the training dataset was shuffled 1200–6000 times to avoid any training bias. This routine resulted in 81.4%, 80.9%, and 82.1% classification accuracy, sensitivity, and specificity, respectively, on the blind-test dataset which was similar to the results for the out-of-bag-validation applied to the training dataset. These results provide a proof of concept for AWakeOSA algorithm as an accurate, reliable and quick OSA screening tool that can be done in less than 10 minutes during wakefulness.