The objective of this project has been to build an expert system to analyze and interpret the Auditory Brainstem Response (ABR), an electrophysiological response of the brainstem to acoustic stimuli. Expert reading of the ABR is essential in clinical decisions concerning retrocochlear disorders. We developed a rule-based expert system that performs neurodiagnostic interpretation of the auditory brainstem response. The system was developed on the IBM PC with the commercial expert system shell GURU and is now operational in the NIH audiology clinic. A talk entitled, """"""""An Expert System Approach to Auditory Brainstem Response Interpretation"""""""", which describes our expert system was given at the 1988 American Audiologic Society Meeting in Boston. Experience in developing and using the system has suggested the possibility of generating more accurate ABR neurodiagnostic interpretation paradigms directly from ABR data using machine-learning methods. Accordingly, a study to derive diagnostic expert system rules directly from ABR data has been initiated. An abstract for a talk entitled, """"""""Receiver Operating Characteristic Analysis of Auditory Brainstem Response Latency"""""""", has been submitted for presentation at the 1989 American Auditory Society Meeting in New Orleans. This talk covers our early experience with high-accuracy, data-derived rules for the critical differentiation of retrocochlear and cochlear disorders.
