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

MedlineQBE (Query-by-Example).

E Bernstam1

  • 1Stanford Medical Informatics, Stanford University School of Medicine, CA, USA.

Proceedings. AMIA Symposium
|February 5, 2002
PubMed
Summary
This summary is machine-generated.

Improving medical information retrieval from Medline (Medical Literature Analysis and Retrieval System Online) is crucial. MedlineQBE, a novel research workbench, facilitates the development and evaluation of custom interfaces and relevance feedback algorithms to enhance search effectiveness.

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

Sharable representation of clinical guidelines in GLIF: relationship to the Arden Syntax.

Journal of biomedical informatics·2001
Same author

Toward the standardization of electronic guidelines.

M.D. computing : computers in medical practice·2001
Same author

Guideline classification to assist modeling, authoring, implementation and retrieval.

Proceedings. AMIA Symposium·2000
Same author

GLIF3: the evolution of a guideline representation format.

Proceedings. AMIA Symposium·2000

Area of Science:

  • Biomedical Informatics
  • Information Science

Background:

  • Effective information retrieval from Medline is challenging despite its potential to improve medical care.
  • Existing approaches like custom interfaces and relevance feedback have limitations in implementation and evaluation.

Purpose of the Study:

  • To introduce MedlineQBE, a research workbench designed for rapid implementation and evaluation of novel information retrieval (IR) strategies.
  • To facilitate the development of custom interfaces and relevance feedback algorithms for Medline.

Main Methods:

  • MedlineQBE abstracts user interface, database access, and results display, allowing developers to focus on algorithm coding.
  • Implemented custom interfaces, search-refinement strategies, and a result-ordering algorithm.
  • Evaluated an oncology-patient interface and a relevance feedback algorithm leveraging PubMed's 'related articles' feature.

Related Experiment Videos

Main Results:

  • Preliminary evaluations of the oncology-patient interface and the novel relevance feedback algorithm are promising.
  • The MedlineQBE workbench enables efficient development and testing of IR strategies.

Conclusions:

  • Custom interfaces and advanced relevance feedback strategies show significant potential for improving Medline information retrieval.
  • MedlineQBE can accelerate research progress in developing better IR tools for medical literature.