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

An automated indexing system utilizing semantic net expansion.

J K Vries1, B Marshalek, J C D'Abarno

  • 1University of Pittsburgh, Pennsylvania 15261.

Computers and Biomedical Research, an International Journal
|April 1, 1992
PubMed
Summary

Automated subject indexing and natural language search interfaces can improve medical information retrieval. A clinical neuroscience thesaurus and semantic net were developed for indexing and searching MEDLINE articles effectively.

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

Using computer modeling to help identify patient subgroups in clinical data repositories.

Proceedings. AMIA Symposium·1999
Same author

Clinical event monitoring at the University of Pittsburgh.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same author

Linear intracerebral calcification after depth electrode implantation.

Epilepsia·1995
Same author

Building a medical multimedia database system to integrate clinical information: an application of high-performance computing and communications technology.

Bulletin of the Medical Library Association·1995
Same author

Using agent-based technology to create a cost effective, integrated, multimedia view of the electronic medical record.

Proceedings. Symposium on Computer Applications in Medical Care·1995
Same author

Image engine: an integrated multimedia clinical information system.

Medinfo. MEDINFO·1995

Area of Science:

  • Medical Informatics
  • Information Science
  • Computational Linguistics

Background:

  • Medical information retrieval faces challenges with large volumes of data.
  • Automated subject indexing and natural language search interfaces offer potential solutions.
  • Developing specialized vocabularies is crucial for accurate medical literature searching.

Purpose of the Study:

  • To describe the construction of an automated indexing and natural language search interface.
  • To utilize a clinical neuroscience thesaurus and semantic net expansion for specialized vocabulary.
  • To enhance the retrieval of information from MEDLINE articles.

Main Methods:

  • Construction of a clinical neuroscience thesaurus by nonexperts using a rule-based approach.

Related Experiment Videos

  • Development of a semantic net for vocabulary expansion.
  • Integration of the thesaurus and semantic net into an "intelligent" front-end for database searching.
  • Automated indexing of MEDLINE articles using the developed system.

    • Main Results:

    • The thesaurus was successfully built by nonexperts, despite expert review.
    • Testing demonstrated the accuracy of the thesaurus content and semantic net.
    • The system provided a specialized vocabulary for indexing and searching MEDLINE abstracts.

    Conclusions:

    • Automated subject indexing and natural language search interfaces can address medical information retrieval problems.
    • A rule-based approach enables nonexperts to build specialized thesauri.
    • The developed system shows promise for improving access to clinical neuroscience literature.