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

Automatic knowledge acquisition from MEDLINE

J J Cimino1, G O Barnett

  • 1Center for Medical Informatics, Columbia University, Columbia-Presbyterian Medical Center, New York, NY.

Methods of Information in Medicine
|April 1, 1993
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

The Harvard-MIT-NEMC Research Training Program in Medical Informatics.

Yearbook of medical informatics·2016
Same author

Coding Systems in Health Care.

Yearbook of medical informatics·2016
Same author

Medical Informatics Training at Columbia University and the Columbia-Presbyterian Medical Center.

Yearbook of medical informatics·2016
Same author

Point-of-Care Knowledge-Based Resource Needs of Clinicians: A Survey from a Large Academic Medical Center.

Applied clinical informatics·2015
Same author

A complementary graphical method for reducing and analyzing large data sets. Case studies demonstrating thresholds setting and selection.

Methods of information in medicine·2014
Same author

The false security of blind dates: chrononymization's lack of impact on data privacy of laboratory data.

Applied clinical informatics·2013

This study introduces an automated method to extract medical knowledge from MEDLINE citations using pattern matching. This approach efficiently generates semantic relationships between medical concepts for expert systems.

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Knowledge Representation

Background:

  • Building medical knowledge bases for expert systems is challenging.
  • Existing methods for knowledge acquisition are often manual and time-consuming.

Purpose of the Study:

  • To develop an automated procedure for extracting medical knowledge from the MEDLINE database.
  • To represent extracted knowledge as semantic relationships between medical concepts.

Main Methods:

  • Automated analysis of citations from the National Library of Medicine's MEDLINE database.
  • Detection of keyword and subheading co-occurrence patterns within citation descriptors.
  • Application of 504 pattern-matching rules to 673 MEDLINE citations.

Related Experiment Videos

Main Results:

  • Successfully produced 2,795 facts representing semantic relationships between medical concepts.
  • Analysis of syntactic and semantic features of the extracted knowledge.
  • Demonstrated the feasibility of automated medical knowledge extraction.

Conclusions:

  • The proposed method offers an efficient way to build medical knowledge bases.
  • Potential uses and limitations of the extracted knowledge for expert systems were discussed.
  • Automated analysis of MEDLINE citations can yield valuable structured medical knowledge.