Detection of epileptiform activities in the EEG using neural network and expert system

This paper proposes a multichannel spike detection in long term EEG monitoring for epilepsy. It is achieved by wavelet transform(WT), artificial neural network(ANN) and the expert system. First, a small set of wavelet coefficients is used to represent the characteristics of a single channel epileptic spikes and normal activities. The purpose of this WT is to reduce the number of inputs to the ANN. Next, three layer feed-forward network employing the error back propagation algorithm is trained and tested using parameters obtained by the WT. Spikes are identified in individual EEG channels by 16 identical neural networks. Finally, 16-channel expert system based on the context information of adjacent channels is introduced to reject artifacts and produce reliable results. In this study, epileptic spikes and normal activities were selected from 32 patient's EEGs (the seizure disorder: 12, normal: 20) in consensus among experts. The result shows that the WT reduced data input size and the preprocessed ANN had 97% sensitivity and 89.5% selectivity, which were more accurate than that of ANN with the same input size of raw data. In clinical result, our expert rule system, which uses neighboring channel informations, was capable of rejecting artifacts commonly found in EEG recordings.