Introduction of a Bayesian network builder algorithm personalized infectious disease risk prediction

We introduce an algorithm for auto-generating a Bayesian Network (BN) structure from a knowledge-base represented as an ontology with rules. The ontology and rules represent the assumptions of infectious disease risk in the epidemiology domain. The resulting BN will be the computational model for an infectious disease risk prediction service. The BN structure consists of one child node, to represent the chosen infectious disease, with multiple parent nodes to represent the contexts which affect infection risk. Thus, this BN generation algorithm is constrained to a relatively simple structure. The algorithm generates a BN using the API of BN modeler software, Netica-J. We evaluate two aspects of the generated BN: the network structure and the conditional probability tables (CPTs). The validation result shows that the algorithm generates an isomorphic BN compared with the ontology and the CPTs are populated with consistent ratios from epidemiological rules. Furthermore, the generated BN has resulted in a personalized infectious disease risk prediction based on the personal attributes and their environments.