Welcome to the InfoSci Platform
Reference Hub3
Learning a Lightweight Ontology for Semantic Retrieval in Patient-Centered Information Systems

Learning a Lightweight Ontology for Semantic Retrieval in Patient-Centered Information Systems

Ulrich Reimer, Edith Maier, Stephan Streit, Thomas Diggelmann, Manfred Hoffleisch
Copyright: © 2011 |Volume: 7 |Issue: 3 |Pages: 16
ISSN: 1548-0666|EISSN: 1548-0658|EISBN13: 9781613508213|DOI: 10.4018/jkm.2011070102
Cite Article Cite Article

MLA

Reimer, Ulrich, et al. "Learning a Lightweight Ontology for Semantic Retrieval in Patient-Centered Information Systems." IJKM vol.7, no.3 2011: pp.11-26. http://doi.org/10.4018/jkm.2011070102

APA

Reimer, U., Maier, E., Streit, S., Diggelmann, T., & Hoffleisch, M. (2011). Learning a Lightweight Ontology for Semantic Retrieval in Patient-Centered Information Systems. International Journal of Knowledge Management (IJKM), 7(3), 11-26. http://doi.org/10.4018/jkm.2011070102

Chicago

Reimer, Ulrich, et al. "Learning a Lightweight Ontology for Semantic Retrieval in Patient-Centered Information Systems," International Journal of Knowledge Management (IJKM) 7, no.3: 11-26. http://doi.org/10.4018/jkm.2011070102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The paper introduces a web-based eHealth platform currently being developed that will assist patients with certain chronic diseases. The ultimate aim is behavioral change. This is supported by online assessment and feedback which visualizes actual behavior in relation to target behavior. Disease-specific information is provided through an information portal that utilizes lightweight ontologies (associative networks) in combination with text mining. The paper argues that classical word-based information retrieval is often not sufficient for providing patients with relevant information, but that their information needs are better addressed by concept-based retrieval. The focus of the paper is on the semantic retrieval component and the learning of a lightweight ontology from text documents, which is achieved by using a biologically inspired neural network. The paper concludes with preliminary results of the evaluation of the proposed approach in comparison with traditional approaches.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.