Ontology-Based Semi-automatic Construction of Bayesian Network Models for Diagnosing Diseases in E-health Applications

Bayesian network (BN) is one of the popular probabilistic methods of diagnosing diseases in e- health applications. However, it is normally a complex task to construct a BN for diagnosing a specific disease by collecting and analyzing domain knowledge. We propose a semi-automatic way of constructing BNs for diagnosing diseases. Our method automatically generates nodes in a BN out of e-health ontology, and allows developers to easily establish links among nodes based on a meta-model that represents cause- and-effect relationships among ontologies.