AN AUTOMATED-SYSTEM FOR ANALYSIS AND INTERPRETATION OF EPILEPTIFORM ACTIVITY IN THE EEG

Electroencephalography is an important clinical tool for the evaluatio n and treatment of neurophysiological disorders related to epilepsy. H owever, the analysis and interpretation of the electroencephalogram (E EG) is not an easy task due to the variety of waveforms that are possi ble. Consequently, EEG analysis is in need of an objective and quantit ative methodology. In this paper, an automated system for diagnosing e pilepsy is presented. The system combines both the electrocerebral act ivity related to epilepsy resulting from EEG and other neurophysiologi cal expertise, mainly based on clinical symptoms that occur during the patient's clinical attack, to avoid misdiagnosis. The system consists of two major stages. The first is a feature extractor in which half-w aves are detected and artefacts are eliminated. The second and most im portant stage is a knowledge-based system for recognising and classify ing epileptiform events. In particular, the analysis is based on the d etected EEG patterns representing epileptiform activity, localization information of discharge focus and clinical symptoms. Once a diagnosis is established, the system also proposes a therapy. The proposed syst em has been tested using many different clinical cases, and the obtain ed experimental results are acceptable. (C) 1997 Elsevier Science Ltd.