Application of the spreading activation technique for recommending concepts of well-known ontologies in medical systems
José María Álvarez-Rodríguez, Luis Polo, Weena Jimenez, Pablo Abella, José Emilio Labra Gayo · 2011
The aim of this paper is to present the application of the Spreading Activation Technique in the scope of medical systems. This technique is implemented through the ONTOSPREAD framework for the development, configuration, customization and execution of the Spreading Activation technique over graph-based structures, more specifically over RDF graphs and ontologies arising from the Semantic Web area. It has been used to the efficient exploration and querying of large and heterogeneous knowledge bases based on semantic networks in the Information and Document Retrieval domains. ONTOSPREAD implements the double process of activation and spreading of concepts in ontologies applying different restrictions of the original model like weight degradation according to the distance or others coming from the extension of this technique like the converging paths reward. It is considered to be relevant to support the recommendation of concepts for tagging clinical records and to provide a tool for decision-support in clinical diagnosis. Finally an evaluation methodology and two examples using the well-known ontologies Galen and SNOMED CT are presented to validate the goodness, the improvement and the capabilities of this technique applied to medical systems.