Authors:
Baile Xie
;
Wenxun Qiu
;
Hlaing Minn
;
Lakshman Tamil
and
Mehrdad Nourani
Affiliation:
University of Texas at Dallas, United States
Keyword(s):
Sleep anpea, SpO2, Real-time detection, Feature selection, Cost-sensitive.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Detection and Identification
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Real-Time Systems
Abstract:
The traditional diagnosis of sleep apnea and hypopnea syndrome (SAHS) requires an expensive and complex overnight procedure called polysomnography (PSG). Recently, finding valid alternatives for SAHS diagnosis has attracted much research attention. This paper focuses on the real-time monitoring and detection of SAHS based on the arterial oxygen saturation signal measured by pulse oximetry (SpO2). We develop a more comprehensive feature set and a more appropriate annotation criterion, if compared to the existing approaches in the literature. To enjoy competitiveness in computational complexity, we also propose a reduced feature set which provides a higher sensitivity and better adaptivity to distinct databases. The performances of 15 commonly used classifiers with different cost matrixes are assessed on different databases, offering detailed insights on the diagnostic abilities of these methods.