Exploring Diseases Relationships

Abstract

Developing an efficient algorithm for traversing large ontologies is a key challenge for many semantic-based applications. This chapter introduces an approach, spreading activation over ontology (SAOO), to explore the relationship between two human diseases using an ontology-based spreading activation approach. SAOO comprises two phases: semantic matching and diseases relatedness detection. In the semantic matching phase, user-submitted diseases are semantically identified in the ontology graph using the proposed matching algorithm. Semantic matching conducts more analysis in the matching process, which comprises term normalization; phrase analysis, and word sense disambiguation. In the diseases relatedness detection phase, the URIs of these diseases are passed to the relatedness detector to detect the relationship connecting them. SAOO improves healthcare systems by considering semantic domain knowledge and a set of SWRL rules to infer diseases relatedness. We present a use case that outlines how SAOO can be used to explore relationships between vaccines in the vaccine ontology.