A Representation of Uncertainty to Aid Insight into Decision Models

Abstr act: Many real world models can be characterized as weak, m�aning that there is significant uncertainty in both the data input and inferences. This lack of determinism makes it especially difficult for users of computer decision aids to understand and have confidence in the models. This paper presents a representation for uncertainty and utilities that serves as a framework for graphical summary and computer-generated explanation of decision models. The implementation described is a computer decision aid designed to enhance the clinician-patient consultation process for patients with suspected angina (chest pain due to lack of blood flow to the heart muscle). The generic angina model is represented as a Bayesian decision network, where the probabilities and utilities are treated as random variables with probability distributions on t. heir range of possible values.· The initial distributions represent information on all patients with anginal symptoms, and the approach allows for rapid customization to more patient-specific distributions. The framework provides a metric for judging the importance of each variable in the model dynamically.