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

Acquiring background knowledge for machine learning using function decomposition: a case study in rheumatology

B Zupan1, S Dzeroski

  • 1Department of Intelligent Systems, Jozef Stefan Institute, Ljubljana, Slovenia. blaz.zupan@ijs.si

Artificial Intelligence in Medicine
|October 21, 1998
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

Contaminants of emerging concern: Silylation procedures, evaluation of the stability of silyl derivatives and associated measurement uncertainty.

The Science of the total environment·2023
Same author

Low prevalence of active COVID-19 in Slovenia: a nationwide population study of a probability-based sample.

Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases·2020
Same author

Programming social behavior by the maternal fragile X protein.

Genes, brain, and behavior·2016
Same author

The discriminatory value of cardiorespiratory interactions in distinguishing awake from anaesthetised states: a randomised observational study.

Anaesthesia·2015
Same author

Genome-Wide Localization Study of Yeast Pex11 Identifies Peroxisome-Mitochondria Interactions through the ERMES Complex.

Journal of molecular biology·2015
Same author

Supporting regenerative medicine by integrative dimensionality reduction.

Methods of information in medicine·2012
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

This study automates acquiring medical background knowledge for diagnosing rheumatic diseases. The proposed method identifies attribute co-occurrences, improving machine learning algorithm performance compared to expert-provided knowledge.

Area of Science:

  • Medical Informatics
  • Machine Learning
  • Rheumatology

Background:

  • Medical diagnostic rule learning often requires domain knowledge.
  • Previous studies showed expert-provided background knowledge aids rheumatic disease diagnosis.
  • Typical attribute co-occurrences represent a key form of background knowledge.

Purpose of the Study:

  • To explore automating the acquisition of background knowledge for medical diagnosis.
  • To evaluate the utility of automated background knowledge in rheumatic disease diagnosis.
  • To compare automated methods with expert-provided knowledge.

Main Methods:

  • A function decomposition method was developed to identify typical attribute co-occurrences.
  • The method was applied to the domain of rheumatic diseases.

Related Experiment Videos

  • Performance was evaluated by comparing identified co-occurrences and their impact on machine learning algorithms against expert-derived knowledge.

    • Main Results:

    • The function decomposition method successfully identified typical attribute co-occurrences.
    • Automated knowledge acquisition demonstrated comparable or improved utility in machine learning for rheumatic disease diagnosis.
    • The study validates the proposed method for generating useful background knowledge.

    Conclusions:

    • Automating background knowledge acquisition is feasible and beneficial for medical diagnosis.
    • The function decomposition approach offers a promising alternative to manual expert input.
    • This facilitates the development of more effective machine learning models in rheumatology.