A KnowledgeBased Model Construction approach to Medical Decision Making
Liem Ngo, M.S., Peter Haddawy, Ph.D. Department of Electrical Engineering and Computer Science University of WisconsinMilwaukee, Milwaukee, Wisconsin 53201
We present a framework for representing the prob abilistic effects of actions and contingent treatment plans. Our language has a welldefined declarative semantics and we have developed an implemented al gorithm (named BNG) that generates Bayesian net works (BN) to compute the posterior probabilities of queries. In this paper we address the problem of pro jecting a contingent treatment plan by automatically constructing a structure of interrelated BNs, which we call a BNgraph, and applying the available propaga tion procedures on it. To address the optimal plan generation, we base our approach on the observation that normally the target plan space has a welldefined structure. We provide a language to describe plan spaces which resembles a programming language with loops and conditionals. We briefly present the proce dures for finding the optimal plan(s) from such speci fied plan spaces.