Decision­Theoretic Refinement Planning in Medical Decision Making: Management of Acute Deep Venous Thrombosis

Peter Haddawy, Ph.D. AnHai Doan, M.S. Charles E. Kahn, Jr., M.D. Decision Systems and Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, University of Wisconsin ­ Milwaukee, Milwaukee, Wisconsin 53201 Section of Information and Decision Sciences, Department of Radiology, Medical College of Wisconsin, Milwaukee, Wisconsin 53226 February 11, 1996

To appear in Medical Decision Making.

Abstract

Decision­theoretic refinement planning is a new technique for finding optimal courses of ac­ tion. The authors sought to determine whether this technique could identify optimal strate­ gies for medical diagnosis and therapy. An existing model of acute deep venous thrombosis of the lower extremities was encoded for analysis by the drips decision­theoretic refinement planning system. The encoding represented 6,206 possible plans. The drips planner used Artificial Intelligence techniques to eliminate 5,150 plans (83%) from consideration without examining them explicitly. drips identified the five strategies that minimized cost and mor­ tality. We conclude that decision­theoretic planning is useful for examining large medical decision problems.