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

Evolutionary computing for knowledge discovery in medical diagnosis.

K C Tan1, Q Yu, C M Heng

  • 1Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, 117576, Singapore, Singapore. eletankc@nus.edu.sg <eletankc@nus.edu.sg>

Artificial Intelligence in Medicine
|March 15, 2003
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

Influence of bariatric surgery on weight reduction and control of chronic disease among obese patients in Malaysia.

The Medical journal of Malaysia·2019
Same author

Pre-β1 HDL in type 2 diabetes mellitus.

Atherosclerosis·2017
Same author

Depression, anxiety and stress among patients with diabetes in primary care: A cross-sectional study.

Malaysian family physician : the official journal of the Academy of Family Physicians of Malaysia·2016
Same author

Coherent chemical kinetics as quantum walks. I. Reaction operators for radical pairs.

Physical review. E·2016
Same author

Multiple regression analysis in modeling of columnar ozone in Peninsular Malaysia.

Environmental science and pollution research international·2014
Same author

A spike-timing-based integrated model for pattern recognition.

Neural computation·2012

A new hybrid evolutionary classification technique extracts understandable medical knowledge from diagnosis data. This method improves clinical practice by creating accurate and interpretable classification rules for disease prevention.

Area of Science:

  • Medical Informatics
  • Machine Learning
  • Computational Biology

Background:

  • Extracting comprehensible knowledge from medical diagnosis data presents a significant challenge.
  • Clinical practice requires accurate and interpretable models for understanding and preventing adverse medical events.

Purpose of the Study:

  • To propose a two-phase hybrid evolutionary classification technique for extracting understandable classification rules from medical diagnosis data.
  • To enhance clinical decision-making and the prevention of unwanted medical events through improved knowledge extraction.

Main Methods:

  • A hybrid evolutionary algorithm (EA) was employed in a two-phase approach.
  • Phase one utilized genetic programming (GP) for nominal attributes and genetic algorithm (GA) for numeric attributes to evolve candidate rules without discretization.

Related Experiment Videos

  • Phase two optimized the order and number of rules for accurate and comprehensible rule sets, forming the evolutionary classifier (EvoC).

    • Main Results:

    • The evolutionary classifier (EvoC) was validated on hepatitis and breast cancer datasets from the UCI machine-learning repository.
    • Simulation results demonstrated that EvoC generates comprehensible rules and achieves good classification accuracy.
    • T-tests confirmed the robustness and invariance of EvoC to random data partitioning.

    Conclusions:

    • The proposed two-phase hybrid evolutionary classification technique effectively extracts comprehensible and accurate classification rules from medical data.
    • EvoC shows promise for improving clinical practice by providing interpretable insights for disease understanding and prevention.
    • The method's robustness and accuracy are validated, suggesting its utility in real-world medical applications.