Automatic recognition of epileptic seizures in the EEG

Abstract

During prolonged EEG monitoring of epileptic patients, the continuous EEG tracing may be replaced by a selective recording of ictal and interictal epileptic activity. We have described previously methods for the EEG recording of seizures with overt clinical manifestations and for the automatic detection of spikes. This paper describes a method for the automatic detection of seizures in the EEG, independently of the presence of clinical signs; it is based on the decomposition of the EEG into elementary waves and the detection of paroxysmal bursts of rhythmic activity having a frequency between 3 and 20 c/sec. Simple procedures are used to measure the amplitude of waves relative to the background, their duration and rhythmicity. The evaluation of the method on 24 surface recordings (average duration 12.4 h) and 44 recordings from intracerebral electrodes (average duration 18.7 h) indicated that it was capable of recognizing numerous types of seizures. False detections due to non-epileptiform rhythmic EEG bursts and to artefacts were quite frequent but were not a serious problem because they did not unduly lengthen the EEG tracing and they could be easily identified by the electroencephalographer. The program can perform on-line and simultaneously the automatic recognition of spikes and of seizures in 16 channels.