Expert System Detection of Eeg Sharp and Spike Waves

Period of Performance: 07/01/1991 - 12/31/1991

Unknown

Phase 1 SBIR

Recipient Firm

Persyst Consulting Services, Inc.
Belmar, NJ 07712
Principal Investigator

Abstract

"One of the major contributions of electroencephalography has been its application in the diagnosis and clinical evaluation of epilepsy." (Ktonas, 1987) However, descriptions of the rules used during the visual inspection of the EEG data are often subjective and can vary greatly from one EEG reader to the next. Computer automation is a means for objectifying this process; however, previous algorithms have failed to implement many of the visual interpretation methods used by humans, thus limiting their usefulness and often their abilities. The proposed research utilizes the PERSYST-Waveform Interpreter, an expert system shell designed specifically for modeling the visual perception and cognition processes of human experts who interpret waveforms, to aid the elicitation and validation of the rules used by EEG readers for the detection of epileptogenic spikes and sharp waves in scalp EEG recordings from humans. The proposed Phase I work covers the development of a SSW detection algorithm. Phase II work will address the development, to the point of commercialization, of a comprehensive EEG interpretation algorithm.