ANALYSIS OF QUANTITATIVE EEG WITH ARTIFICIAL NEURAL NETWORKS AND DISCRIMINANT-ANALYSIS - A METHODOLOGICAL COMPARISON

Artificial neural networks (ANN) are widely used to solve problems of differentiating between groups. However, serious comparisons of this m ethod with the traditional procedure for such tasks (discriminant anal ysis) are rare. Discussing the results of both methods with the exampl e of highly topical data, we try to demonstrate advantages and drawbac ks of both methods. For this purpose, quantitative EEGs of 78 alcoholi cs were investigated in order to determine whether it is possible to p redict relapse of these patients at the beginning of treatment. ANN so ftware is available in Kassel (Institute for Computer Sciences and Mat hematics).