Data-driven modeling of sleep EEG and EOG reveals characteristics indicative of pre-Parkinson's and Parkinson's disease

• Published in: Journal of neuroscience methods Vol. 235; pp. 262 - 276
• Main Authors: Christensen, Julie A.E., Zoetmulder, Marielle, Koch, Henriette, Frandsen, Rune, Arvastson, Lars, Christensen, Søren R., Jennum, Poul, Sorensen, Helge B.D.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 30.09.2014
• Subjects: Aged; Algorithms; Artificial Intelligence; Automatic classification; Electroencephalography; Electroencephalography - methods; Electrooculography; Electrooculography - methods; Female; Humans; Male; Middle Aged; Models, Neurological; Nocturnal Myoclonus Syndrome - diagnosis; Nocturnal Myoclonus Syndrome - physiopathology; Parkinson Disease - diagnosis; Parkinson Disease - physiopathology; Parkinson's disease; Polysomnography; Polysomnography - methods; Regression Analysis; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Sleep Stages - physiology; Topic modeling; Topic modeling; Electrooculography; Automatic classification; Electroencephalography; Parkinson's disease; Polysomnography

•A data-driven topic modeling approach characterizing sleep EEG and EOG is proposed.•The approach showed potential for evaluating patients with neurodegeneration.•The number of topics linked with REM and N3 could be an early PD biomarker.•The ability to maintain NREM and REM sleep could be an early...