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

Modeling principles for QMR medical findings

A M Rassinoux1, R A Miller, R H Baud

  • 1Division of Biomedical Informatics, Vanderbilt University, Nashville, TN, USA.

Proceedings : a Conference of the American Medical Informatics Association. AMIA Fall Symposium
|January 1, 1996
PubMed
Summary

Accurate medical information representation is key for reliable clinical decision support systems. This study proposes a hybrid model for indexing medical texts using controlled vocabularies.

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

Initial results from the New Horizons exploration of 2014 MU<sub>69</sub>, a small Kuiper Belt object.

Science (New York, N.Y.)·2019
Same author

Controlling the vocabulary for anatomy.

Proceedings. AMIA Symposium·2002
Same author

Looking back or looking all around: comparing two spell checking strategies for documents edition in an electronic patient record.

Proceedings. AMIA Symposium·2002
Same author

A light knowledge model for linguistic applications.

Proceedings. AMIA Symposium·2002
Same author

HONselect: a multilingual and intelligent search tool integrating heterogeneous web resources.

International journal of medical informatics·2001
Same author

"THE PILOT": a tool for connecting existing HIS to an extranet quickly, easily and smoothly.

Studies in health technology and informatics·2001

Area of Science:

  • Medical Informatics
  • Computational Linguistics

Background:

  • Computerized decision support systems rely on accurate medical information.
  • Existing medical models have limitations for natural language understanding and indexing.

Purpose of the Study:

  • To review current medical models for natural language understanding.
  • To identify key features for indexing medical texts with controlled vocabularies.
  • To propose a novel hybrid representation for medical terms.

Main Methods:

  • Review of existing frame-based and conceptual-graph-based medical models.
  • Analysis of modeling features crucial for controlled vocabulary indexing.
  • Development of a hybrid representation framework.

Main Results:

Related Experiment Videos

  • Identified essential modeling features for effective medical text indexing.
  • Proposed a hybrid model integrating frame-based and conceptual-graph approaches.
  • Demonstrated a method for representing expert-used medical terms.

Conclusions:

  • A hybrid representation model can enhance the accuracy of medical information for decision support.
  • This approach facilitates better indexing of medical texts with controlled vocabularies.
  • The proposed model supports reliable clinical decision-making through improved data representation.