Determination of predominant coronary arterial stenosis by a knowledge based system

A medical diagnostic system was constructed using the multiplication model of support logic programming in order to determine the predominant stenosis in one of the three main coronary arteries. The features considered in the determination of the diagnosis were data obtained from preprocessed scintigraphic myocardial perfusion images of the left ventrical taken in three views: anterior, left lateral, and left lateral anterior oblique. Stress thallium-201 planar scintigrams from patients who had coronary arterial stenosis proven by coronary arteriography were the data set used for this study. A Prolog-based system was constructed to explore the knowledge base in order to determine the site of the predominant stenosis. With the current set of production rules, the system properly recognized the site of coronary artery stenosis in over 90% of the patients presented.<>