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 expert study evaluating the UMLS lexical metaschema.

Li Zhang1, George Hripcsak, Yehoshua Perl

  • 1Computer Science Department, New Jersey Institute of Technology, University Heights, Newark, NJ 07102, USA.

Artificial Intelligence in Medicine
|July 6, 2005
PubMed
Summary

A new lexical metaschema closely approximates expert-defined subject areas within the Unified Medical Language System (UMLS) Semantic Network (SN). This automated approach validates well against human expert consensus, offering an efficient alternative for organizing biomedical knowledge.

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

PDA (Privacy-Preserving Distributed Algorithms) in action: ten principles for high-quality multi-site clinical evidence generation.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Promoting Problem-Solving Among Low-Income Adults With Type 2 Diabetes: Cluster-Randomized Controlled Trial of a Mobile Health Intervention With SMS Text Messaging (Mobile Diabetes Detective).

Journal of medical Internet research·2026
Same author

Real-world performance of large-scale propensity score adjustment strategies: Matching, weighting, and stratification.

Research square·2026
Same author

A comparison of Fast Healthcare Interoperability Resources and Observational Medical Mutcomes Partnership electronic health record data within the All of Us Research Program.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Heterogeneity of Treatment Effects Across Nine Glucose-Lowering Drug Classes in Type 2 Diabetes: Extension of the LEGEND-T2DM Network Study.

Diabetes, obesity & metabolism·2026
Same author

Semaglutide and Neovascular Age-Related Macular Degeneration Among Adults with Type 2 Diabetes: An OHDSI Network Study.

Ophthalmology·2026

Area of Science:

  • Biomedical Informatics
  • Knowledge Representation
  • Natural Language Processing

Background:

  • The Unified Medical Language System (UMLS) Semantic Network (SN) organizes biomedical concepts.
  • A lexical metaschema, derived from word usage in semantic type names and definitions, offers a potential automated method for partitioning the SN.
  • Evaluating this lexical metaschema against expert-defined structures is crucial for its validation.

Purpose of the Study:

  • To statistically evaluate a previously derived lexical metaschema.
  • To compare the lexical metaschema with expert-derived metaschemas and a consensus metaschema.
  • To assess the performance of the lexical metaschema against human expert judgment.

Main Methods:

  • Experts identified subject areas within the UMLS SN based on their understanding of semantic types.

Related Experiment Videos

  • Expert responses were aggregated to form individual and consensus metaschemas.
  • Statistical analysis was performed to compare the lexical metaschema with the expert and consensus metaschemas.

    • Main Results:

    • The lexical metaschema showed high similarity to the consensus metaschema, with 81% of meta-semantic types overlapping and 79% of semantic types covered.
    • Statistical analysis indicated that the lexical metaschema did not significantly underperform compared to expert-derived structures.
    • The findings suggest a strong agreement between the automated lexical approach and human expert consensus.

    Conclusions:

    • The lexical metaschema serves as a robust approximation for meaningful subject area partitions within the UMLS SN.
    • It aligns well with the consensus derived from human expert opinions.
    • This validates the utility of lexical analysis for organizing complex biomedical terminologies.