Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Using concept relations to improve ranking in information retrieval.

Susan L Price1, Lois M Delcambre

  • 1Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, USA.

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|June 17, 2006
PubMed
Summary

This study improves search result relevance by modeling queries as concept relationships. Identifying medical

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Computer science education for medical informaticians.

International journal of medical informatics·2004
Same author

SmartQuery: context-sensitive links to medical knowledge sources from the electronic patient record.

Proceedings. AMIA Symposium·2002
See all related articles

Area of Science:

  • Information Retrieval
  • Medical Informatics
  • Natural Language Processing

Background:

  • Search engines often return irrelevant documents, hindering information access.
  • Ranking relevant documents higher is crucial for effective information retrieval.
  • Clinical questions frequently involve understanding causal and treatment relationships.

Purpose of the Study:

  • To improve the ranking of medical documents by modeling queries as concept relationships.
  • To investigate techniques for identifying 'causes' and 'treats' relations in medical text.
  • To enhance the relevance of search results for clinical queries.

Main Methods:

  • Proposed modeling queries and information needs as relationships between concepts.
  • Investigated four techniques to identify 'causes' and 'treats' relations.
  • Matched query relations to document relations to improve search result ranking.

Main Results:

  • Preliminary results indicate that identifying relation instances can enhance search result ranking.
  • The proposed method shows potential for improving the retrieval of relevant medical information.
  • Successful identification of specific medical relationships ('causes', 'treats') contributes to better document relevance.

Conclusions:

  • Modeling queries as concept relationships is a viable strategy for improving search result ranking.
  • Identifying specific medical relations like 'causes' and 'treats' can significantly boost the relevance of medical search results.
  • This approach offers a promising direction for more effective clinical information retrieval.

Related Experiment Videos