A New Model for Diagnosing Sleep Apnea through Features Extraction of the SpO2 Signal
Loading...
Authors
Almazaydeh, Laiali
Elleithy, Khaled M.
Faezipour, Miad
Issue Date
2012
Type
Presentation
Language
Keywords
Faculty research day
Alternative Title
Abstract
Description
Obstructive Sleep Apnea (OSA), is thenmost common form of different types of sleep-related breathing disorders. It is characterized by repetitive cessations of respiratory flow during sleep, which occur due to a collapse of the upper airway at the level of the oropharynx. The traditional diagnosis of OSA requires an expensive and complex overnight procedure called polysomnography (PSG). PSG contains several biomedical signals recording set, such as EEG, EOG, EMG, ECG, respiration and SpO2. In contrast,simple monitoring systems can be built as cheaper alternatives to the current PSGs in the diagnosis of OSA, which can also reduce the abundant burdens of hospital sleep centers.In this study, we develop a comprehensive feature set based on the arterial oxygen saturation signal measured by pulse oximetry (SpO2) to obtain high quality signal features in discriminating the OSA. The three features of Spo2 signal which are Delta Index, Central Tendency Measure with radius 0.5 (ctm50) and Oxygen Desaturation Index(odi3) are extracted, tested and evaluated using the MATLAB toolset. It was found that SpO2 signal characteristics could be helpful in order to evaluate sleep quality.
Citation
Poster 45