Discrimination between migraine patients and normal subjects based on steady state visual evoked potentials: discriminant analysis and artificial neural network classifiers

Abstract

Fifty-one migraine patients and 19 control subjects were examined by steady state visual evoked potentials (SSVEPs) procedure. The aim of this study was to develop a discriminant analysis and an artificial neural network (NN) classifier in order to discriminate between migraneurs during attack-free periods and normal subjects. Discriminant analysis correctly classified 72.5% of migraine patients with a false positive rate of 36.8%. The NN method had a sensitivity of 100% with a false positive rate of 15%. The results of this study confirm SSVEP pattern as a marker of migraine and demonstrate that NNs could be a useful method in the statistical analysis of topographic EEG data.