Abstract
An expert system for the automated detection of spikes and sharp waves in the EEG has been developed. The system consists of two distinct stages. The first is a feature extractor, written in the conventional procedural language Fortran, which uses parts of previously published spike-detection, algorithms to produce a list of all spike-like occurrences in the EEG. The second stage, written in the production system language OPS5, reads the list and uses rules incorporating knowledge elicited from an electroencephalographer (EEGer) to confirm or exclude each of the possible spikes. Information such as the time of occurrence, polarity and channel relationship are used in this process. A summary of thedetected epileptiform events is produced which is available to the EEGer in interpreting the EEG. The performance of the expert system is compared with an EEGer using a 320s segment from an EEG containing epileptiform activity. The system detected 19 events and missed seven (false negative) which the EEGer considered epileptiform. There were no false positive detections.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Arakawa, K., Fender, D. H., Harashima, H., Miyakawa, H. andSaitoh, Y. (1986) Separation of a nonstationary component from the EEG by a nonlinear digital filter.IEEE Trans.,BME-33, 724–726.
Brownston, L., Farrell, R., Kant, E. andMartin, N. (1985)Programming expert systems in OPS5: an introduction to rulebased programming. Addison-Wesley, Reading Massachusetts.
Chatrian, G. E., Bergamini, L., Dondey, M., Klass, D. W., Lennox-Buchthal, M. andPetersen, I. (1974) A glossary of terms most commonly used by clinical electroencephalographers.Electroenceph. Clin. Neurophysiol.,37 538–548.
Forgy, C. L. (1981) OPS5 user's manual. Technical report CMU-CS-81-135, Department of Computer Science, Carnegie-Mellon University.
Glover, J. R., Ktonas, P.Y., Raghavan, N., Urunela, J. M., Velamuri, S. S. andReilly, E. L. (1986) A multichannel signal processor for the detection of epileptogenic sharp transients in the EEG.IEEE Trans.,BME-12, 1121–1128.
Glover, J. R., Raghavan N. andKtonas, P. Y. (1987) Context-based detection of epileptogenic EEG sharp transients. Proc. IEEE/9th Annual Conf. Eng. in Med. & Biol. Soc., Boston, 1274–1275.
Gotman, J. andGloor, P. (1976) Automatic recognition and quantification of interictal, epileptic activity in the human scalp EEG.Electroenceph. Clin. Neurophysiol.,41, 513–529.
Gotman, J. (1985) Automatic recognition of interictal spikes. InLong-term monitoring in epilepsy (EEG supplement No. 37).Gotman, J., Ives, J. R. andGloor, P. (Eds.), Elsevier Science Publishers B. V. (Biomedical Division), 93–114.
Hayes-Roth, F. (1985) Rule-based systems.Comm. Assoc. Comput. Mach.,28, 921–932.
Hill, A. G. andTownsend, H. A. (1973) The automatic estimation of epileptic spike activity.Int. J. Bio-med. Comput.,4, 149–156.
Ktonas, P. Y., Luoh, W. M., Kejariwal, M. L., Reilly, E. L. andSeward, M. A. (1981) Computer-aided quantification of EEG spike and sharp wave characteristics.Electroenceph. Clin. Neurophysiol.,51, 237–243.
Ktonas, P. Y. (1983) Automated analysis of abnormal electroencephalograms.CRC Crit. Rev in Biomed. Eng.,9, 39–97.
Proc. IEEE/EMBS (1987) Proc. IEEE/9th Ann. Conf. Eng. in Med. & Biol. Soc., Boston.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Davey, B.L.K., Fright, W.R., Carroll, G.J. et al. Expert system approach to detection of epileptiform activity in the EEG. Med. Biol. Eng. Comput. 27, 365–370 (1989). https://doi.org/10.1007/BF02441427
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02441427