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

Natural language processing to extract medical problems from electronic clinical documents: performance evaluation.

Stéphane Meystre1, Peter J Haug

  • 1Department of Medical Informatics, University of Utah School of Medicine, Salt Lake City, UT, USA. s.meystre@utah.edu <s.meystre@utah.edu>

Journal of Biomedical Informatics
|December 20, 2005
PubMed
Summary

This study shows a Natural Language Processing (NLP) tool can extract medical problems from clinical notes. Customizing the tool significantly improved its accuracy for electronic problem lists.

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 Implications of Small Language Models (SLMs) in Healthcare Applications.

Studies in health technology and informatics·2026
Same author

Towards a ModernBERT Model Adapted to the Biomedical Domain in Italian.

Studies in health technology and informatics·2026
Same author

Large language models for biomedicine: foundations, opportunities, challenges, and best practices.

Journal of the American Medical Informatics Association : JAMIA·2024
Same author

High Accuracy Open-Source Clinical Data De-Identification: The CliniDeID Solution.

Studies in health technology and informatics·2024
Same author

AI-Based Gut-Brain Axis Digital Twins.

Studies in health technology and informatics·2023
Same author

Computer clinical decision support that automates personalized clinical care: a challenging but needed healthcare delivery strategy.

Journal of the American Medical Informatics Association : JAMIA·2022

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Clinical Data Management

Background:

  • Electronic medical records (EMRs) contain valuable patient data.
  • Maintaining accurate and up-to-date patient problem lists is crucial for care.
  • Manual problem list maintenance is time-consuming and prone to errors.

Purpose of the Study:

  • To evaluate a Natural Language Processing (NLP) application for extracting medical problems from clinical documents.
  • To assess the performance of the NLP system in populating electronic patient problem lists.
  • To improve the accuracy, completeness, and timeliness of patient problem lists.

Main Methods:

  • Utilized the UMLS MetaMap Transfer (MMTx) application for concept extraction.
  • Incorporated the NegEx algorithm for negation detection.

Related Experiment Videos

  • Extracted 80 high-frequency medical problems from narrative clinical text.
  • Evaluated performance using recall and precision metrics.
  • Compared a default MMTx dataset against a custom-created subset.

    • Main Results:

    • The default MMTx dataset achieved a recall of 0.74 and precision of 0.756.
    • A custom MMTx data subset significantly improved recall to 0.896.
    • The custom subset resulted in a non-significant reduction in precision.
    • The customized NLP application demonstrated enhanced performance.

    Conclusions:

    • Natural Language Processing (NLP) shows promise for automating medical problem extraction.
    • Customizing NLP tools, like MMTx, can significantly enhance performance for clinical applications.
    • Optimized NLP systems can contribute to more accurate and efficient electronic problem list management.