Using Linked Data for Integrating Educational Medical Web Databases Based on BioMedical Ontologies. (6th December 2016)

• Record Type: Journal Article
• Authors: Al Fayez, Reem Q.; Joy, Mike
• Is Part Of: Computer journal. Volume 60:Number 3(2017)
• Page Start: 369
• Page End: 388
• Publication Date: 2016-12-06
• Subjects: Linked Data -- biomedical ontologies -- medical education -- web databases -- data model -- data integration; Computers -- Periodicals; 005.1
• DOI: 10.1093/comjnl/bxw096
• Languages: English
• ISSNs: 0010-4620

Abstract

Abstract: Open data are playing a vital role in different communities, including governments, businesses and education. This revolution has had a high impact on the education field. Recently, Linked Data are being adopted for publishing and connecting data on the web by exposing and connecting data, which were not previously linked. In the context of education, applying Linked Data to the growing amount of open data used for learning is potentially highly beneficial. This paper proposes a system that tackles the challenges of data acquisition and integration from distributed web data sources into one linked data set. The application domain of this work is medical education, and the focus is on integrating educational content in the form of articles published in online educational libraries and Web 2.0 content that can be used for education. The process of integrating a collection of heterogeneous resources is to create links that connect the resources collected from distributed web data sources based on their semantics. The proposed system harvests metadata from distributed web sources and enriches it with concepts from biomedical ontologies, such as Systematized Nomenclature of Medicine—Clinical Terms (SNOMED CT), that enable its linking. The final result of building this system is a linked data set of more than 10 000 resources collected from PubMed Library, YouTube channels and Blogging platforms. The final linked data set is evaluated by developing information retrieval methods that exploit the SNOMED CT hierarchical relations for accessing and querying the data set. Ontology-based browsing method has been developed for exploring the data set, and the browsing results have been clustered to evaluate its linkages. Furthermore, ontology-based query searching method has been developed and tested to enhance the discoverability of the data. The results were promising and had shown that using SNOMED CT for integrating distributed resources on the web is beneficial.