Title :
EEG seizure prediction: Measures and challenges
Author :
Aarabi, A. ; Fazel-Rezai, R. ; Aghakhani, Y.
Author_Institution :
Electr. & Comput. Eng., Univ. of Manitoba, Winnipeg, MB, Canada
Abstract :
Different types of analyses of scalp and intracranial electroencephalography (EEG) recordings using linear and nonlinear time series analysis method have been done. They showed strong evidence of detectable changes in the EEG dynamics from minutes up to several hours in advance of seizure onset. The predictive performance of univariate and bivariate measures, comprising both linear and non-linear approaches have been carried in different studies Direct comparison among different measures and methods in seizure prediction is not possible, unless they are applied to the same dataset. In this review paper, we describe different seizure prediction measures briefly and discuss the existing challenges.
Keywords :
electroencephalography; medical signal processing; reviews; time series; EEG seizure prediction; electroencephalography; intracranial recordings; review; scalp; time series analysis; Analysis of Variance; Brain; Electroencephalography; Humans; Models, Neurological; Nonlinear Dynamics; Predictive Value of Tests; Seizures; Signal Transduction; Statistics as Topic;
Conference_Titel :
Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE
Conference_Location :
Minneapolis, MN
Print_ISBN :
978-1-4244-3296-7
Electronic_ISBN :
1557-170X
DOI :
10.1109/IEMBS.2009.5332620