Application of bhattacharyya distance as a dissimilarity index for automated prediction of epileptic seizures in rats

Abstract

Seizures are defined as manifest of excessive and hypersynchronous activity of neurons in the cerebral cortex and represent a frequent malfunction of the human central nervous system. Therefore, the search for precursors and predictors of a seizure is of utmost clinical relevance and may even guide us to a deep understanding of the seizure generating mechanisms. In this study we analyzed invasive electroencephalogram (EEG) recordings in rats with experimentally induced generalized epilepsy with a nonlinear method called, dissimilarity index. In order to predict epileptic seizures automatically, Bhattacharyya distance between trajectory matrix of reference window, during an interval quite distant in time from any seizure, and trajectory matrix of present window is employed to measure dynamical dissimilarity index. It is found that employed the method can detect the dissimilarity changes of the neural activity prior to epileptic seizures.