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

Clustering WHO-ART terms using semantic distance and machine learning algorithms.

Jimison Iavindrasana1, Cedric Bousquet, Patrice Degoulet

  • 1University Hospitals of Geneva - CH-1211 Geneva 4, Switzerland.

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|January 24, 2007
PubMed
Summary
This summary is machine-generated.

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

Clarifying the relationship between biomedical and health informatics and digital health: expert perspectives.

BMJ health & care informatics·2026
Same author

Generation of Training Data to Distinguish Adverse Events from Medical Conditions.

Studies in health technology and informatics·2026
Same author

Letter to the Editor on "Can a Large Language Model Interpret Data in the Electronic Health Record to Infer Minimum Clinically Important Difference Achievement of Knee Osteoarthritis Outcome Score Joint Replacement Score Following Total Knee Arthroplasty?"

The Journal of arthroplasty·2026
Same author

Comment on "Performance and Reproducibility of Large Language Models in Named Entity Recognition: Considerations for the Use in Controlled Environments".

Drug safety·2025
Same author

Foundation Models for Generative AI in Time-Series Forecasting.

Journal of medical Internet research·2025
Same author

Large Language Models Could Revolutionize Health Care, but Technical Hurdles May Limit Their Applications.

Journal of medical Internet research·2025

Semantic distance clustering of World Health Organization-Adverse Drug Reactions Terminology (WHO-ART) terms can group related medical conditions. This approach aids in improving adverse drug reaction signal detection within the WHO database.

Area of Science:

  • Pharmacovigilance and Drug Safety
  • Medical Informatics
  • Computational Linguistics

Background:

  • Adverse drug reactions (ADRs) require efficient monitoring.
  • The World Health Organization-Adverse Drug Reactions Terminology (WHO-ART) is used for coding ADRs.
  • Grouping related WHO-ART terms could enhance ADR signal detection.

Purpose of the Study:

  • To develop a method for clustering WHO-ART terms based on semantic proximity.
  • To evaluate the effectiveness of machine learning algorithms for this task.

Main Methods:

  • Formal definitions of 758 WHO-ART terms were created using SNOMED international axes concepts.
  • Two unsupervised machine learning algorithms, K-Means and Pvclust, were applied.
  • Clustering was performed using a previously described semantic distance operator on a J2EE server.

Related Experiment Videos

Main Results:

  • Pvclust successfully grouped 51% of WHO-ART terms.
  • K-Means grouped 100% of terms, with varying cluster heterogeneity (25% at k=180, 6% at k=32).
  • Both algorithms demonstrated potential for grouping WHO-ART terms.

Conclusions:

  • Clustering algorithms combined with semantic distance offer a promising method for grouping WHO-ART terms.
  • These groupings require user validation for specific applications in pharmacovigilance.
  • The approach can potentially improve the efficiency of ADR signal detection.