Accurate automatic identification of slow wave sleep using a single electro-oculogram channel

Mohamed Elmessidi, Sana Tmar Ben Hamida, Beena Ahmed, Thomas Penzel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Diagnosis and treatment of sleep disorders require analysis of the sleep stages and patterns in the polysomnographic (PSG) signals recorded over several hours. Traditionally, sleep is monitored based on PSG signals that require several measurements collected from different locations on the head and the body. These signals are used to evaluate the sleep quantity and quality. However, the need for unobtrusive monitoring and convenience motivates a variety of alternative approaches focused on the minimization of a number of monitored physiological signals. Previous studies have shown that the quantity and length of slow wave sleep (SWS) periods during sleep are the major indicators of the sleep quality. The aim of this paper is to present a new automatic method to detect SWS epochs using a single-channel electro-oculography (EOG). This method is based on a simple rule based algorithm with an adaptive method to adjust thresholds. The new method is evaluated through 9 healthy subjects and the results are compared to the clinical visual scoring. The agreement of our detection method for the validation data was 90.0%, the sensitivity was 90.5% and the specificity was 89.9% and the kappa value was 0.74.

Original languageEnglish
Title of host publication2014 Middle East Conference on Biomedical Engineering, MECBME 2014
PublisherIEEE Computer Society
Pages232-235
Number of pages4
ISBN (Print)9781479947997
DOIs
Publication statusPublished - 2014
Event2014 2nd Middle East Conference on Biomedical Engineering, MECBME 2014 - Doha, Qatar
Duration: 17 Feb 201420 Feb 2014

Other

Other2014 2nd Middle East Conference on Biomedical Engineering, MECBME 2014
CountryQatar
CityDoha
Period17/2/1420/2/14

    Fingerprint

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Elmessidi, M., Hamida, S. T. B., Ahmed, B., & Penzel, T. (2014). Accurate automatic identification of slow wave sleep using a single electro-oculogram channel. In 2014 Middle East Conference on Biomedical Engineering, MECBME 2014 (pp. 232-235). [6783247] IEEE Computer Society. https://doi.org/10.1109/MECBME.2014.6783247