Automatic detection of REM sleep in subjects without atonia

Jacob Kempfner; Poul Jennum; Miki Nikolic; Julie A E Christensen; Helge B D Sorensen

doi:10.1109/EMBC.2012.6346903

Automatic detection of REM sleep in subjects without atonia

Annu Int Conf IEEE Eng Med Biol Soc. 2012:2012:4242-5. doi: 10.1109/EMBC.2012.6346903.

Authors

Jacob Kempfner¹, Poul Jennum, Miki Nikolic, Julie A E Christensen, Helge B D Sorensen

Affiliation

¹ Department of Electrical Engineering, Technical University of Denmark, Kgs. Lyngby, Denmark.

PMID: 23366864
DOI: 10.1109/EMBC.2012.6346903

Abstract

Idiopathic Rapid-Rye-Movement (REM) sleep Behavior Disorder (iRBD) is a strong early marker of Parkinson's Disease and is characterized by REM sleep without atonia (RSWA) and increased phasic muscle activity. Current proposed methods for detecting RSWA assume the presence of a manually scored hypnogram. In this study a full automatic REM sleep detector, using the EOG and EEG channels, is proposed. Based on statistical features, combined with subject specific feature scaling and post-processing of the classifier output, it was possible to obtain an mean accuracy of 0.96 with a mean sensitivity and specificity of 0.94 and 0.96 respectively.

MeSH terms

Diagnosis, Computer-Assisted / methods*
Electroencephalography / methods*
Electrooculography / methods*
Epilepsy, Generalized / diagnosis
Epilepsy, Generalized / physiopathology
Female
Humans
Male
Middle Aged
Polysomnography / methods*
REM Sleep Parasomnias / diagnosis*
REM Sleep Parasomnias / physiopathology
Reproducibility of Results
Sensitivity and Specificity
Sleep, REM*