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 distributional analysis to semantically classify UMLS concepts.

Jung-Wei Fan1, Hua Xu, Carol Friedman

  • 1Department of Biomedical Informatics, Columbia University, USA. fan@dbmi.columbia.edu

Studies in Health Technology and Informatics
|October 4, 2007
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

Ensembles of natural language processing systems for portable phenotyping solutions.

Journal of biomedical informatics·2019
Same author

Crowdsourcing Public Opinion for Sharing Medical Records for the Advancement of Science.

Studies in health technology and informatics·2019
Same author

A two-site survey of medical center personnel's willingness to share clinical data for research: implications for reproducible health NLP research.

BMC medical informatics and decision making·2019
Same author

Validation of the Behavior of a Knowledge Base Implementing Clinical Guidelines for Point-of-Care Antiretroviral Toxicity Monitoring.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2019
Same author

Deep Phenotyping on Electronic Health Records Facilitates Genetic Diagnosis by Clinical Exomes.

American journal of human genetics·2018
Same author

Pharmacogenomic Approaches for Automated Medication Risk Assessment in People with Polypharmacy.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2018
Same journal

A GenAI Pipeline for Violinist Kinematic Data Management.

Studies in health technology and informatics·2026
Same journal

AMAL-For-Qatar: A Comprehensive AI Ecosystem for Fetal Ultrasound Analysis - Project Overview and Achievements.

Studies in health technology and informatics·2026
Same journal

Longitudinal Treatment-Aware Multimodal AI for Dermatology: A Scoping Review.

Studies in health technology and informatics·2026
Same journal

Predicting Postpartum Depression Using Imbalance-Aware Machine Learning.

Studies in health technology and informatics·2026
Same journal

Validation of Deep-Learning Models for Autosegmentation of Brain Metastases.

Studies in health technology and informatics·2026
Same journal

Delay-Dependent Gating in Modular RNNs.

Studies in health technology and informatics·2026
See all related articles

This study developed an automated method to improve the accuracy of biomedical concept classification within the Unified Medical Language System (UMLS). The approach enhances Natural Language Processing (NLP) by refining semantic categorization for better system performance.

Area of Science:

  • Biomedical Informatics
  • Natural Language Processing
  • Computational Linguistics

Background:

  • The Unified Medical Language System (UMLS) is a critical resource for biomedical Natural Language Processing (NLP).
  • Inaccurate semantic classification within the UMLS can negatively impact the performance of NLP and knowledge-based systems.
  • Automated validation and reclassification of UMLS concepts are needed to enhance data accuracy.

Purpose of the Study:

  • To develop and evaluate an automated method for semantically classifying UMLS concepts.
  • To distinguish between biologic functions and disorders within the T033 Finding class.
  • To improve the accuracy of UMLS semantic categorization for NLP applications.

Main Methods:

  • Applied a distributional similarity method utilizing syntactic dependencies and -skew divergence.

Related Experiment Videos

  • Classified concepts within the UMLS T033 Finding semantic category.
  • Created a gold standard dataset through expert annotation of 100 randomly sampled concepts.

    • Main Results:

    • The top prediction achieved a precision of 0.54 and recall of 0.654.
    • Incorporating the top 2 predictions improved performance to a precision of 0.64 and recall of 0.769.
    • Error analysis identified limitations and areas for future methodological refinement.

    Conclusions:

    • The developed distributional similarity method shows promise for automated UMLS concept reclassification.
    • Further improvements are necessary to address identified errors and enhance classification accuracy.
    • Accurate semantic classification is crucial for advancing biomedical NLP and knowledge systems.