AN APPROACH TO SEIZURE DETECTION USING AN ARTIFICIAL NEURAL-NETWORK (ANN)

We have developed an EEG seizure detector based on an artificial neura l network. The input layer of the ANN has 31 nodes quantifying the amp litude, slope, curvature, rhythmicity, and frequency components of EEG in a 2 sec epoch. The hidden layer has 30 nodes and the output layer has 8 nodes representing various patterns of EEG activity (e.g. seizur e, muscle, noise, normal). The value of the output node representing s eizure activity is averaged over 3 consecutive epochs and a seizure is declared when that average exceeds 0.65. Among 78 randomly selected f iles from 50 patients not in the original training set, the detector d eclared at least one seizure in 76% of 34 files containing seizures. I t declared no seizures in 93% of 44 files not containing seizures. Fou r false detections during 4.1 h of recording yielded a false detection rate of 1.0/h. The detector can continuously process 40 channels of E EG with a 33 MHz 486 CPU. Although this method is still in its early s tages of development, our results represent proof of the principle tha t ANN could be utilized to provide a practical approach for automatic, on-line, seizure detection.