Notes on Project VES (Video EEG Expert System)

OBJECTIVE: To develop the Video EEG Expert System (VES), a program to analyze patient data with the goal of finding anatomic seizure focus in the context of epilepsy pre-surgical evaluation. BACKGROUND: Numerous systems have been created to analyze electroencephalogram (EEG) data with the goal of searching for epileptiform discharges. Literature review does not reveal software dedicated to evaluation of data for a patient under consideration for temporal lobectomy surgery. METHODS: Patient data included MRI, PET, SPECT, and video EEG. The system is in Lisp and a logic programming module, Prolisp, that supports hypothesis-driven rules. Benchmark files (controls) and corresponding anatomic localization hypothesis trees were created. 23 experimental files were used to test correctness in localizing seizure focus. The principle developer was blind to these files. RESULTS: The system selected the correct localization for 100% of benchmark files. For the experimental files, the correct localization was selected in 78%, first place ties were computed in 13%, and incorrect localizations were found in 9%. Analysis of incorrect results yielded minor software problems and some incomplete knowledge concerning temporal lobe localization. CONCLUSIONS: VES performed well at identifying seizure focus. The tools developed for VES, especially Prolisp, should serve future neurological expert system development.