Pattern recognition classification schemes were developed and they were applied in a number of studies in an attempt to distinguish between patients from several neurological or psychological disorders and normal controls and to locate brain areas of possible dysfunction. Clinical material comprised patients with depression, patients with obsessive-compulsion disorder, one-month abstinent alcoholics, one-month abstinent heroin addicts and healthy controls. All subjects were evaluated by a computerized version of the digit span Wechsler test. The EEG activity was recorded and digitized from 15 scalp electrodes (leads) and signals were inverted into intracranial currents. Nineteen features related to the shape of the waveform were generated and were used as input to the classification schemes developed, which comprised single classifiers as well as more complex classification schemes. The best overall accuracies, achieved in specific brain areas, ranged between 94% and 100%, indicating that these techniques may significantly facilitate computer-aided analysis of EEG signals and suggesting specific brain areas as relative to the corresponding disorders.