A MULTISTAGE SYSTEM TO DETECT EPILEPTIFORM ACTIVITY IN THE EEG

A PC-based system has been developed to automatically detect epileptif orm activity in sixteen-channel bipolar EEG's. The system consists of three stages: data collection, feature extraction, and event detection . The feature extractor employs a mimetic approach to detect candidate epileptiform transients on individual channels, while an expert syste m is used to detect focal and nonfocal multichannel epileptiform event s. Considerable use of spatial and temporal contextual information pre sent in the EEG aids both in the detection of epileptiform events and in the rejection of artifacts and background activity as events. Class ification of events as definite or probable overcomes, to some extent, the problem of maintaining high detection rates while eliminating fal se detections. So far, the system has only been evaluated on developme nt data but, although this does not provide a true measure of performa nce, the results are nevertheless impressive. Data from 11 patients, t otaling 180 minutes of sixteen-channel bipolar EEG's, have been analyz ed. A total of 45-71% (average 58%) of epileptiform events reported by the human expert in any EEG were detected as definite with no false d etections (i.e., 100% selectivity) and 60-100% (average 80%) as either definite or probable but at the expense of up to nine false detection s per hour. Importantly, the highest detection rates were achieved on EEG's containing little epileptiform activity and no false detections were made on normal EEG's.