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

Decision-theoretic refinement planning is a new technique for finding optimal courses of action. The authors sought to determine whether this technique could identify optimal strategies for medical diagnosis and therapy. An existing model of acute deep venous thrombosis of the lower extremities was encoded for analysis by the decision-theoretic refinement planning system (DRIPS). The encoding represented 6,206 possible plans. The DPIPS planner used artificial intelligence techniques to eliminate 5,150 plans (63%) from consideration without examining them explicitly. The DRIPS system identified the five strategies that minimized cost and mortality. The authors conclude that decisiontheoretic planning is useful for examining large medical-decision problems.