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

Knowledge-based understanding of radiology text.

D L Ranum1

  • 1Department of Medical Informatics, LDS Hospital/University of Utah, Salt Lake City 84143.

Computer Methods and Programs in Biomedicine
|October 1, 1989
PubMed
Summary

A new tool extracts diagnostic data from radiology reports using semantic parsing. This system automates data acquisition for the HELP medical expert system, improving diagnostic information retrieval.

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

Strength of a liberal arts education in preparing future physicians.

Academic medicine : journal of the Association of American Medical Colleges·1993
Same author

"Pre-medical" informatics.

Proceedings. Symposium on Computer Applications in Medical Care·1993
Same author

Computerized extraction of coded findings from free-text radiologic reports. Work in progress.

Radiology·1990
See all related articles

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Natural Language Processing

Background:

  • Radiology reports contain crucial diagnostic information.
  • Manual extraction of this data is time-consuming and prone to errors.
  • Automated methods are needed to efficiently capture clinical data for expert systems.

Purpose of the Study:

  • To design and implement a data acquisition tool for extracting diagnostic information from radiology reports.
  • To enable the HELP medical expert system to utilize free-text clinical data.
  • To automate the process of identifying pertinent diagnostic information.

Main Methods:

  • Developed a data acquisition tool employing memory-based semantic parsing.
  • Utilized a special purpose compiler to automatically generate memory structures and lexicons.
  • Integrated the tool with a diagnostic knowledge base for expert system direction.

Main Results:

  • Successfully implemented a system for extracting pertinent diagnostic information from free text.
  • The system automatically generates necessary linguistic components from the knowledge base.
  • Data extraction is effectively guided by the expert system's diagnostic goals.

Conclusions:

  • The designed tool successfully automates diagnostic data extraction from radiology reports.
  • Semantic parsing and automated knowledge base compilation enhance data acquisition efficiency.
  • This approach facilitates the integration of free-text radiology data into medical expert systems for improved diagnosis.

Related Experiment Videos