Jove
Visualize
Contact Us

Related Experiment Videos

Dynamic knowledge validation and verification for CBR teledermatology system.

Monica H Ou1, Geoff A W West, Mihai Lazarescu

  • 1Department of Computing, Curtin University of Technology, G.P.O. Box U1987, Perth 6845, Western Australia, Australia. ou@cs.curtin.edu.au

Artificial Intelligence in Medicine
|September 27, 2006
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

Gronuflex adhesive compression bandage.

Nursing standard (Royal College of Nursing (Great Britain) : 1987)·2016
Same author

Evaluation of TELEDERM for dermatological services in rural and remote areas.

Artificial intelligence in medicine·2008
Same author

A comparison of algorithms for calculating glaucoma change probability confidence intervals.

Journal of glaucoma·2006
See all related articles
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

This study introduces novel methods for validating knowledge bases in decision support systems, crucial for handling imperfect data in teledermatology. These techniques enhance diagnostic accuracy by ensuring knowledge consistency and comprehensiveness.

Area of Science:

  • Artificial Intelligence
  • Medical Informatics
  • Machine Learning

Background:

  • Case-based reasoning is vital for decision support systems.
  • Knowledge validation is underexplored but critical for diagnostic accuracy.
  • Imperfect data in teledermatology systems can lead to inconsistencies and reduced performance.

Purpose of the Study:

  • To develop interactive knowledge validation methods for domain experts in web-based teledermatology.
  • To introduce techniques for discovering hidden relationships in datasets for knowledge base enhancement.
  • To improve the diagnostic performance of teledermatology systems through robust knowledge management.

Main Methods:

  • Interactive validation using decision tree classification and formal concept analysis.

Related Experiment Videos

  • Techniques for discovering unusual relationships within datasets.
  • Web-based teledermatology system knowledge base development and updating.

    • Main Results:

    • Knowledge validation techniques were found effective in maintaining knowledge base consistency.
    • Query refinement techniques demonstrated utility in enhancing case base comprehensiveness.
    • Improved diagnostic performance is linked to a comprehensive and consistent knowledge base.

    Conclusions:

    • The developed validation methods are effective for ensuring knowledge base integrity.
    • Query refinement aids in building more complete and accurate diagnostic support systems.
    • This work addresses the critical need for reliable knowledge validation in AI-driven medical applications.