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

Relevant information for decision support systems: application in cardiology.

J Zvárová1, M Tomeèková, F Boudík

  • 1European Center for Medical Informatics, Statistics and Epidemiology of Charles University, Prague, Czech Republic. jana.zvarova@euromise.cz

Studies in Health Technology and Informatics
|June 29, 1999
PubMed
Summary

This study introduces information theory tools to identify key features in medical databases for decision support systems. The CORE software package aids in selecting relevant data for improved medical decision-making.

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

Medical Informatics, Statistics and Epidemiology Education: In the Framework of the Tempus-Phare Joint European Project.

Yearbook of medical informatics·2016
Same author

Serum levels of matrix metalloproteinases 2 and 9 in patients with acute myocardial infarction.

Folia biologica·2013
Same author

Serum levels of matrix metalloproteinases 2 and 9 and TGFBR2 gene screening in patients with ascending aortic dilatation.

Folia biologica·2013
Same author

eHealth: combining health telematics, telemedicine, biomedical engineering and bioinformatics to the edge.

Methods of information in medicine·2010
Same author

[Pilot register of acute myocardial infarction--a 5-year evaluation of quality of care in non-PCI hospitals].

Vnitrni lekarstvi·2010
Same author

Overdenture - implants versus teeth - quality of life and objective therapy evaluation.

Prague medical report·2010

Area of Science:

  • Computer Science
  • Medical Informatics
  • Information Theory

Background:

  • Decision support systems require efficient methods for extracting relevant information from large medical databases.
  • Feature selection is crucial for improving the performance and interpretability of these systems.
  • Information theory offers a powerful framework for quantifying feature relevance.

Purpose of the Study:

  • To present novel information theory-based algorithms for feature selection in medical databases.
  • To introduce the CORE software package designed to support feature selection for decision-making.
  • To demonstrate the application of these methods in a real-world cardiovascular risk study.

Main Methods:

  • Development of feature selection algorithms using information-theoretical characteristics as score functions.

Related Experiment Videos

  • Classification of algorithms based on influence-preferring or weight-preferring criteria and selection methods (forward, backward, combined).
  • Implementation of the CORE (COnstitution and REduction) software package.

    • Main Results:

    • Algorithms effectively extract relevant features from medical data using information-theoretic principles.
    • The CORE package provides a practical tool for implementing these feature selection methods.
    • Successful application demonstrated on a dataset of 1417 middle-aged men in a cardiovascular risk study.

    Conclusions:

    • Information theory provides robust tools for feature selection in decision support systems.
    • The CORE software facilitates the application of these methods for data analysis and decision support.
    • The methodology is broadly applicable to various decision-making problems requiring relevant information extraction from data.