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 base refinement: learning from examples and deep knowledge in rheumatology

G Widmer1, W Horn, B Nagele

  • 1Department of Medical Cybernetics and Artificial Intelligence, University of Vienna, Austria.

Artificial Intelligence in Medicine
|June 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

Early local activation of complement in aqueous humour of patients with age-related macular degeneration.

Eye (London, England)·2019
Same author

Genotypic Characterization of Cryptosporidium Species in Humans and Peri-Domestic Animals in Ekiti and Oyo States, Nigeria.

The Journal of parasitology·2018
Same author

Application of a novel reference material in an international round robin test on material emissions testing.

Indoor air·2017
Same author

A comparison of sequence and length polymorphism for genotyping Cryptosporidium isolates.

Parasitology·2015
Same author

[Not Available].

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik·2014
Same author

Activated sludge rheology: a critical review on data collection and modelling.

Water research·2012

This study introduces MESICAR-LEARN, an expert system that uses machine learning to improve rheumatological diagnoses. It enhances diagnostic speed and accuracy for common conditions by creating specific disease descriptions.

Area of Science:

  • Artificial Intelligence in Medicine
  • Medical Informatics
  • Rheumatology

Background:

  • Expert systems aid in medical diagnosis.
  • General rheumatological knowledge bases exist.
  • Automating specific disease description is challenging.

Purpose of the Study:

  • To develop a machine learning system (MESICAR-LEARN) to automatically generate specific disease descriptions for common rheumatological cases.
  • To integrate learned concepts into a hierarchical disease description framework.
  • To enhance the diagnostic capabilities of the MESICAR expert system.

Main Methods:

  • Utilized machine learning techniques, integrating analytical and empirical learning.
  • Employed cases diagnosed by the MESICAR system as training examples.

Related Experiment Videos

  • Leveraged MESICAR's existing knowledge base as the domain theory.

    • Main Results:

    • Successfully constructed more specific disease descriptions for frequently occurring rheumatological conditions.
    • Integrated learned concepts into a hierarchical structure.
    • Demonstrated support for efficient and fast reasoning on common cases.

    Conclusions:

    • MESICAR-LEARN effectively enhances diagnostic support for rheumatological disorders in primary care.
    • The system improves reasoning efficiency for common cases.
    • This approach integrates machine learning with expert systems for advanced medical diagnostics.