A Bayesian Network Model for Diagnosis of Liver Disorders

Abstract

Probabilistic graphical models, such as Bayesian networks and influence diagrams, offer coherent representation of domain knowledge under uncertainty. They are based on the sound foundations of probability theory and they readily combine available statistics with expert judgment. This paper describes our work in progress on a probabilistic causal model for diagnosis of liver disorders that we plan to apply in both clinical practice and medical training. The network, and especially its numerical parameters, is based on data from a clinical database. We present the Bayesian model and report initial results of our diagnostic performance tests.