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 randomized controlled trial of automated term composition

P L Elkin1, K R Bailey, C G Chute

  • 1Mayo Foundation, Rochester, MN, USA.

Proceedings. AMIA Symposium
|February 3, 1999
PubMed
Summary

Automated Term Composition (ATC) significantly improved the accuracy of mapping clinical terms to a controlled vocabulary, doubling correct concept identification. This enhances access to medical information and supports the development of better clinical tools.

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

Novel approach for tracking interdisciplinary research productivity using institutional databases.

Journal of clinical and translational science·2022
Same author

The WHO ICD-11 Classification of Dermatological Diseases: a new comprehensive online skin disease taxonomy designed by and for dermatologists.

The British journal of dermatology·2021
Same author

Pregnancy history, coronary artery calcification and bone mineral density in menopausal women.

Climacteric : the journal of the International Menopause Society·2017
Same author

Neuregulin-2 ablation results in dopamine dysregulation and severe behavioral phenotypes relevant to psychiatric disorders.

Molecular psychiatry·2017
Same author

Health Concept and Knowledge Management: Twenty-five Years of Evolution.

Yearbook of medical informatics·2016
Same author

Genetic variation among 82 pharmacogenes: The PGRNseq data from the eMERGE network.

Clinical pharmacology and therapeutics·2016

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Controlled Vocabularies

Background:

  • Clinical notes contain free-text entries crucial for patient care and research.
  • Accurate mapping of these terms to controlled vocabularies is essential for data retrieval and analysis.
  • Existing methods may lack sufficient coverage and accuracy for complex medical terms.

Purpose of the Study:

  • To compare the effectiveness of Automated Term Composition (ATC) against non-compositional mappings.
  • To evaluate the coverage and accuracy of mapping free-text clinical entries to a controlled vocabulary.
  • To assess inter-observer variability and failure analysis reliability in term mapping.

Main Methods:

  • A random selection of 1,000 terms from clinical notes (Impression/Report/Plan sections) was used.

Related Experiment Videos

  • Terms were divided into two sets (A and B) and mapped using interfaces with and without ATC.
  • Four expert indexers performed mappings, with varied assignments to assess system performance and variability.

    • Main Results:

    • The system with ATC achieved 54.0% correct concept mapping, significantly outperforming the 27.6% accuracy without ATC (p < 0.0001).
    • Failures in the non-ATC system were primarily due to missing base concepts (58.7%).
    • Failures in the ATC system were more often due to missing modifiers/qualifiers (26.1%) compared to missing base concepts (73.9%).

    Conclusions:

    • Automated Term Composition significantly enhances the coverage of patient problems in clinical notes.
    • These findings highlight the value of the UMLS Metathesaurus and the need for improved tools like ATC.
    • Further development in structuring, normalizing UMLS content, and utilizing tools like ATC is crucial for viable clinical information access.