Mining novel connections from online biomedical text databases using semantic query expansion and semantic-relationship pruning

  • Authors:

  • Xiaohua Hu;Xuheng Xu

  • Affiliations:

  • College of Information Science and Technology, Drexel University, Philadelphia, PA 19036, USA.;College of Information Science and Technology, Drexel University, Philadelphia, PA 19036, USA

  • Venue:
  • International Journal of Web and Grid Services
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes a semantic-based approach for mining novel connections from biomedical literature. The method takes advantage of the biomedical ontologies, MeSH and UMLS, as the source of semantic knowledge. A prototype system, Biomedical Semantic-based Knowledge Discovery System (Bio-SbKDS), is designed to uncover novel hypotheses/connections hidden in biomedical literature through semantic query expansion and semantic-relationship pruning. Bio-SbKDS can automatically generate relevant search terms to retrieve the semantic-relevant articles from the online biomedical text databases. Using the semantic types and semantic relations of the biomedical concepts, Bio-SbKDS can identify the relevant concepts collected from Medline and generate the novel hypothesis between these concepts. Bio-SbKDS successfully replicates Dr. Swanson's two famous discoveries: Raynaud disease/fish oil and migraine/magnesium. Compared with previous approaches, our methods search much less articles, generate much less but more relevant novel hypotheses and require much less human intervention in the discovery procedure.