Sleep Apnea Detection Based on Thoracic and Abdominal Movement Signals of Wearable Piezoelectric Bands

Physiologically, the thoracic (THO) and abdominal (ABD) movement signals, captured using wearable piezoelectric bands, provide information about various types of apnea, including central sleep apnea (CSA) and obstructive sleep apnea (OSA). However, the use of piezoelectric wearables in detecting sleep apnea events has been seldom explored in the literature. This study explored the possibility of identifying sleep apnea events, including OSA and CSA, by solely analyzing one or both the THO and ABD signals. An adaptive nonharmonic model was introduced to model the THO and ABD signals, which allows us to design features for sleep apnea events. To confirm the suitability of the extracted features, a support vector machine was applied to classify three categories – normal and hypopnea, OSA, and CSA. According to a database of 34 subjects, the overall classification accuracies were on average <inline-formula><tex-math notation="LaTeX">${\text{75.9}}\%\pm {\text{11.7}}\%$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">${\text{73.8}}\%\pm {\text{4.4}}\%$</tex-math></inline-formula>, respectively, based on the cross validation. When the features determined from the THO and ABD signals were combined, the overall classification accuracy became <inline-formula><tex-math notation="LaTeX">${\text{81.8}}\%\pm {\text{9.4}}\%$</tex-math></inline-formula>. These features were applied for designing a state machine for online apnea event detection. Two event-by-event accuracy indexes, <italic>S</italic> and <italic>I</italic>, were proposed for evaluating the performance of the state machine. For the same database, the <italic>S</italic> index was <inline-formula><tex-math notation="LaTeX">${\text{84.01}}\%\pm {\text{9.06}}\%$</tex-math></inline-formula> and the <italic>I</italic> index was <inline-formula><tex-math notation="LaTeX">${\text{77.21}}\%\pm {\text{19.01}}\%$ </tex-math></inline-formula>. The results indicate the considerable potential of applying the proposed algorithm to clinical examinations for both screening and homecare purposes.