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

Validation of clinical problems using a UMLS-based semantic parser

H S Goldberg1, C Hsu, V Law

  • 1Center for Clinical Computing, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.

Proceedings. AMIA Symposium
|February 3, 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

Association of CFRD development among females with CF who use hormonal contraception.

Journal of cystic fibrosis : official journal of the European Cystic Fibrosis Society·2026
Same author

Corrigendum to "Pan-Asian adapted ESMO Clinical Practice Guidelines for the diagnosis, treatment and follow-up of patients with biliary tract cancer": [ESMO Open 9 (2024) 103647].

ESMO open·2025
Same author

Pan-Asian adapted ESMO Clinical Practice Guidelines for the diagnosis, treatment and follow-up of patients with biliary tract cancer.

ESMO open·2024
Same author

Evidence of an Off-Resonant Electronic Transport Mechanism in Helicenes.

The journal of physical chemistry letters·2024
Same author

Nivolumab plus ipilimumab combination therapy in patients with advanced hepatocellular carcinoma previously treated with sorafenib: 5-year results from CheckMate 040.

Annals of oncology : official journal of the European Society for Medical Oncology·2024
Same author

Nivolumab in sorafenib-naive and sorafenib-experienced patients with advanced hepatocellular carcinoma: 5-year follow-up from CheckMate 040.

Annals of oncology : official journal of the European Society for Medical Oncology·2023
Same journal

Progressive display of very high resolution images using wavelets.

Proceedings. AMIA Symposium·2002
Same journal

The Chronus II temporal database mediator.

Proceedings. AMIA Symposium·2002
Same journal

Gene expression levels in different stages of progression in oral squamous cell carcinoma.

Proceedings. AMIA Symposium·2002
Same journal

An assessment of the visibility of MeSH-indexed medical web catalogs through search engines.

Proceedings. AMIA Symposium·2002
Same journal

Filtering for medical news items using a machine learning approach.

Proceedings. AMIA Symposium·2002
Same journal

Enriching the structure of the UMLS semantic network.

Proceedings. AMIA Symposium·2002
See all related articles

This study developed a semantic parser to identify disease-related clinical problems from electronic health records. The parser achieved 49.8% accuracy in recognizing diseases and 93% in excluding non-diseases, with potential for improvement.

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Clinical Data Management

Background:

  • Clinical problem lists are crucial for patient summaries and decision support.
  • Standardizing clinical data requires effective methods for data capture and symbolization.
  • Existing systems often struggle with the variability of provider-entered clinical problems.

Purpose of the Study:

  • To develop and evaluate a Unified Medical Language System (UMLS)-based semantic parser.
  • To assess the parser's accuracy in recognizing and validating disease-related clinical problems from electronic health records.
  • To identify limitations and propose improvements for clinical data symbolization.

Main Methods:

  • A random sample of 4122 clinical problem labels from the Online Medical Record (OMR) was analyzed.

Related Experiment Videos

  • A UMLS-based semantic parser was developed to process these labels.
  • The parser's performance was evaluated based on its ability to correctly recognize disease-related and exclude non-disease-related labels.

    • Main Results:

    • The parser correctly identified 49.8% of disease-related labels and excluded 93.0% of non-disease-related labels.
    • Match failures were primarily due to terms absent from UMLS or unrecognized label patterns.
    • Enriching the UMLS lexicon with common provider terms is expected to enhance parser performance.

    Conclusions:

    • The developed semantic parser shows promise for symbolizing clinical data from problem lists.
    • Further research and local lexicon enrichment are needed to improve accuracy and applicability.
    • This work provides a foundation for enhancing clinical data symbolization and decision support systems.