Bispectrum Quantification Analysis of EEG and Artificial Neural Network May Classify Ischemic States

This paper examines the relation between the degree of experimentally induced focal ischemia in the left-brain of 24 experimental rats and Higher Order Statistics (HOS) such as the bispectrum and the bicoherence index of scalp EEG recorded at the time of the ischemic event. The aim is to propose the assessment of HOS in non-invasive scalp EEG to facilitate identification and even classification of focal ischemic events in terms of the degree of tissue damage. The latter is achieved by a supervised, multilayer, feed-forward Artificial Neural Network (ANN). The ANN utilizes a back propagation algorithm to classify ischemic states of the brain. The target values used during the training session of the network are the degree of ischemic tissue damage (graded as serious, middle and slight) as assessed by histological and immunhistochemical methods in the brain slice of the experimental animals. The results show that the ANN can correctly identify and classify ischemic events with high precision 91.67% based on HOS measures of scalp EEG obtained during ischemia. These findings may potentially be of great scientific merit, especially due to their possibly very important medical implications: a potential non-invasive method that reliably identifies the presence and the degree of ischemia at the time of its occurrence.