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

Using POSTDOC to recognize biomedical concepts in medical school curricular documents

S L Kanter1, R A Miller, M Tan

  • 1University of Pittsburgh School of Medicine, Pennsylvania 15261.

Bulletin of the Medical Library Association
|July 1, 1994
PubMed
Summary

POSTDOC, a tool using the Unified Medical Language System (UMLS), identifies biomedical concepts in documents. Its current ability to recognize concepts in medical lectures needs further development for database creation.

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

Air pollution and daily mortality: associations with particulates and acid aerosols.

Environmental research·1992
Same author

Growth hormone synergizes with serum growth factors in inducing c-fos transcription in 3T3-F442A cells.

Endocrinology·1992
Same author

The short-term psychological health of alcoholic and non-alcoholic liver transplant recipients.

Alcoholism, clinical and experimental research·1992
Same author

Caffeine intake and asthma symptoms.

Annals of epidemiology·1992
Same author

Dihydropyrimidine calcium channel blockers. 4. Basic 3-substituted-4-aryl-1,4-dihydropyrimidine-5-carboxylic acid esters. Potent antihypertensive agents.

Journal of medicinal chemistry·1992
Same author

Intercellular communication within the anterior pituitary influencing the secretion of hypophysial hormones.

Endocrine reviews·1992

Area of Science:

  • Biomedical Informatics
  • Natural Language Processing

Background:

  • Accurate recognition of biomedical concepts is crucial for medical education and clinical practice.
  • Applications include curriculum analysis, electronic health records, and literature retrieval.
  • Existing methods require robust concept identification from free-text documents.

Purpose of the Study:

  • To evaluate the effectiveness of the POSTDOC (POSTprocessor of DOCuments) system.
  • To assess POSTDOC's capability in recognizing Unified Medical Language System (UMLS) Metathesaurus biomedical concepts within medical school lecture outlines.
  • To determine the system's suitability for automated database creation from curricular documents.

Main Methods:

  • POSTDOC processes free-text documents using the UMLS Metathesaurus to identify main concept terms.

Related Experiment Videos

  • The system analyzes term co-occurrence to detect concept correlations.
  • References from MEDLINE can be retrieved based on identified concepts.

    • Main Results:

    • POSTDOC demonstrated a wide range of performance in recognizing UMLS biomedical concepts.
    • "Precision" and "recall" metrics indicated that automated database creation from lecture outlines is not yet feasible.
    • The system's performance suggests potential for future development and study.

    Conclusions:

    • POSTDOC shows promise for biomedical concept recognition but requires further refinement.
    • Continued development is warranted to improve accuracy for applications like automated database generation.
    • The formative evaluation provides a basis for enhancing the system's capabilities.