Medical Decision Making Using Ignorant Influence Diagrams

Bayesian Belief Networks (bbns) play a relevant role in the field of Artificial Intelligence in Medicine and they have been successfully applied to a wide variety of medical domains. An appealing character of bbns is that they easily extend into a complete decision-theoretic formalism known as Influence Diagrams (ids). Unfortunately, bbns and ids require a large amount of information that is not always easy to obtain either from human experts or from the statistical analysis of databases. In order to overcome this limitation, we developed a class of ids, called Ignorant Influence Diagrams (iids), able to reason on the basis of incomplete information and to to improve the accuracy of the decisions as a monotonically increasing function of the available information. The aim of this paper is show how iids can be useful to model medical decision making with incomplete information.