A neural network based Markov model of EEG hidden dynamic

The hidden dynamic of the couple (F3, F4) of EEG leeds is modeled by means of nonlinear Markov models, in order to investigate possible differences in case of meningeoma, malignant glioma, and intact brain. The conditional probabilities of the transition states of the Markov models are represented as sums of Gaussian distributions, whose parameters are estimated by means of multilayered Perceptrons. The dynamic of the pair (F3, F4) is tested against a hierarchy of null hypotheses corresponding to nonlinear Markov processes of increasing order. The minimum accepted order gives an indication of the organization degree of the hidden dynamic of the signal. A structured dynamic is detected in both leads (F3, F4) of normal EEGs, confirming the very complex structure of the underlying system. Different correlations between the two hemispheres activities seem to discriminate meningeoma, malignant glioma, and no pathological status. Moreover loss of structure can represent a good hint for glioma/meningeoma localization.