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

A semantic lexicon for medical language processing.

S B Johnson1

  • 1Columbia University, New York, New York 10032, USA. stephen.johnson@columbia.edu

Journal of the American Medical Informatics Association : JAMIA
|May 20, 1999
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

Ethical Reasoning During a Pandemic: Results of a Five Country European Study.

AJOB empirical bioethics·2022
Same author

COVID-19 contact tracing apps: UK public perceptions.

Critical public health·2022
Same author

Estimating survival in advanced cancer: a comparison of estimates made by oncologists and patients.

Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer·2019
Same author

First Report of White Mold (Sclerotinia sclerotiorum) on Soybean in Maine.

Plant disease·2019
Same author

First Report of Potato mop-top virus on Potato from the United States.

Plant disease·2019
Same author

The 2009 Late Blight Pandemic in the Eastern United States - Causes and Results.

Plant disease·2019
Same journal

Digital divide in clinical and operational artificial intelligence adoption and implementation stages: US hospital diffusion patterns and AI deserts.

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

Extending the fundamental theorem of biomedical informatics: a proposal and illustrative examples.

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

Human factors methods for designing safe health information technology: what do the experts think?

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

Equity-by-design for socially assistive robots as digital health tools.

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

Orchestrator multi-agent clinical decision support system for secondary headache diagnosis in primary care.

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

CUI-Curate: a GraphRAG-based framework for automated clinical concept curation for NLP applications.

Journal of the American Medical Informatics Association : JAMIA·2026
See all related articles

This study developed a semantic lexicon from the Unified Medical Language System (UMLS) to improve medical natural language processing. Semantic preference rules significantly reduced ambiguity in medical terms, enhancing computer analysis of clinical narratives.

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Natural Language Processing

Background:

  • Medical narrative analysis requires robust semantic understanding of clinical terms.
  • Existing lexicons may lack comprehensive semantic information for automated processing.
  • The Unified Medical Language System (UMLS) provides a foundation for medical terminology.

Purpose of the Study:

  • To construct a semantic lexicon for enhanced computer processing of medical narrative.
  • To associate medical lexemes with syntactic and semantic types.
  • To reduce ambiguity in medical terms within clinical reports.

Main Methods:

  • Matched Specialist Lexicon against the UMLS Metathesaurus to create a semantic lexicon.
  • Assigned semantic types to lexemes in a corpus of discharge summaries.

Related Experiment Videos

  • Developed semantic preference rules to resolve lexemes with multiple semantic types.

    • Main Results:

    • The initial semantic lexicon contained 75,711 lexical forms; 30.1% had multiple semantic types.
    • Application of semantic preference rules reduced multi-type entries to 1.5%.
    • Occurrences of lexemes with multiple semantic types in discharge summaries decreased from 9.41% to 1.46%.

    Conclusions:

    • Automated construction of semantic lexicons from UMLS is feasible.
    • Minimized semantic type ambiguity is crucial for natural language processing of medical text.
    • Semantic preference rules effectively refine type selection for clinical reports.