Detection of epileptiform discharges in the EEG by a hybrid system comprising mimetic, self-organized artificial neural network, and fuzzy logic stages

Objective: A multi-stage system for automated detection of epileptiform act ivity in the EEG has been developed and tested on prerecorded data from 43 patients. Methods: The system is centred on the use of an artificial neural network, known as the self-organising feature map (SOFM), as a novel pattern classif ier. The role of the SOFM is to assign a probability value to incoming cand idate epileptiform discharges (on a single channel basis), The multi-stage detection system consists of three major stages: mimetic, SOFM, and fuzzy l ogic. Fuzzy logic is introduced in order to incorporate spatial contextual information in the detection process. Through fuzzy logic it has been possi ble to develop an approximate model of the spatial reasoning performed by t he electroencephalographer. Results: The system was trained on 35 epileptiform EEGs containing over 300 0 epileptiform events and tested on a different set of eight EEGs containin g 190 epileptiform events (including one normal EEG). Results show that the system has a sensitivity of 55.3% and a selectivity of 82% with a false de tection rate of just over seven per hour. Conclusions: Based on these initial results the overall performance is favo urable when compared with other leading systems in the literature, This enc ourages us to further test the system on a larger population base with the ultimate aim of introducing it into routine clinical use. (C) 1999 Elsevier Science Ireland Ltd. All rights reserved.