Date of Award
Doctor of Philosophy
Sleep is a circadian rhythm essential for human life. Many events occur in the body during this state. In the past, significant efforts have been made to provide clinicians with reliable and less intrusive tools to automatically classify the sleep stages and detect apnea events. A few systems are available in the market to accomplish this task. However, sleep specialists may not have full confidence and trust in such systems due to issues related to their accuracy, sensitivity and specificity. The main objective of this work is to explore possible relationships among sleep stages and apneic events and improve on the clinical accuracy, sensitivity and specificity of algorithms for sleep classification and apnea detection. Electroencephalograms (EEGs) and Heart Rate Variability (HRV) signals will be assessed using advanced signal processing approaches. In this research work, we present a compendium of features extracted from EEG and Heart Rate Variability (HRV) data acquired from twenty five patients (21 males and 4 females) suffering from sleep apnea (age: 50 Â± 10 years, range 28-68 years undergoing polysomnography). Polysomnographic data were available online from the Physionet database. Results show that trends detected by these features could distinguish between different sleep stages at a very significant level (p<0.01). This study showed that inclusion of HRV features as inputs to the classifier system increased the performance of the ANN system by improving the accuracy by 5.8 % when considering data from all 25 subjects whereas for sensitivity, specificity, and geometric mean the increments were 7.5%, 2.1%, and 5.2% respectively. The work presented here contributes to the ultimate goal of the project, which is to find novel and more reliable tools to assess sleep quality and sleep breathing disorders by means of less invasive techniques requiring minimal number of sensors.
Received from ProQuest
Edson F. Estrada
Estrada, Edson F., "Computer-Aided Detection Of Sleep Apnea And Sleep Stage Classification Using HRV And EEG Signals" (2010). Open Access Theses & Dissertations. 2482.