Application of the EXPERT consultation system to accelerated laboratory testing and interpretation.

Abstract

The EXPERT consultation system-building tool, a knowledge-based artificial intelligence program developed at Rutgers University, has been applied to the development of a laboratory consultation system facilitating sequential laboratory testing and interpretation. Depending on the results of a basic panel of laboratory tests, the system requests that specific secondary tests be performed. Input of these secondary findings can result in requests for tertiary testing, to complete the database necessary for interpretation. Interpretation of all results is based upon final inferences from the collected findings through a series of rules, a hierarchical network that yields an efficient production system not easily obtained through conventional programming. The rules included in this model are based upon initial results for total protein, calcium, glucose, total bilirubin, alkaline phosphatase, lactate dehydrogenase, aspartate aminotransferase, thyroxin, hemoglobin, mean corpuscular volume, and the concentrations of four drugs. Pertinent clinical history items included are jaundice, diabetes, thyroid disease, medications, and ethanol. Implementing this system in a laboratory-based accelerated testing program involving outpatients maximized the effective use of laboratory resources, eliminated useless testing, and provided the patient with low-cost laboratory information.