An EEG based nonlinearity analysis method for schizophrenia diagnosis

In this paper, the complexity and chaos of EEG (electroencephalogram) signals exhibited in schizophrenic patients are analyzed using four nonlinear features: C0-complexity, Kolmogorov entropy together with an estimation of the correlation dimension and Lempel-Ziv complexity. The first two of these being novel applications of these measures. EEGs from 31 schizophrenic patients (18 males, 13 females, mean age 25.9 ±3.6 years) and 31 age/sex matched control subjects were recorded using 12 electrodes. In a t-test, it was found that all four nonlinear features had a significant variance between the schizophrenics and the control set (p ≤ 0.05). A classification accuracy of 91.7% was obtained by Back Propagation Neural Networks. Our results show that the discrimination of schizophrenic behavior is possible with respect to a control set using nonlinear analysis of EEG signals. We also assert that these methods may be the basis for a valuable tool set of EEG methods that could be used by psychiatrists when diagnosing schizophrenic patients.