DecisionTheoretic Refinement Planning: A New Method for Clinical Decision Analysis
AnHai Doan, B.S., Peter Haddawy, Ph.D., Charles E. Kahn, Jr.,M.D.
Department of Electrical Engineering and Computer Science, University of Wisconsin Milwaukee, Milwaukee, Wisconsin
Clinical decision analysis seeks to identify the optimal management strategy by modelling the un certainty and risks entailed in the diagnosis, natu ral history, and treatment of a particular problem or disorder. Decision trees are the most frequently used model in clinical decision analysis, but can be tedious to construct, cumbersome to use, and computationally prohibitive, especially with large, complex decision problems. We present a new method for clinical decision analysis that combines the techniques of decision theory and artificial in telligence. Our model uses a modular represen tation of knowledge that simplifies model building and enables more fully automated decision mak ing. Moreover, the model exploits problem struc tures to yield better computational efficiency. As an example we apply our techniques to the problem of management of acute deep venous thrombosis.