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

A constrained-syntax genetic programming system for discovering classification rules: application to medical data

Celia C Bojarczuk1, Heitor S Lopes, Alex A Freitas

  • 1Laboratório de Bioinformática/CPGEI, Centro Federal de Educação Tecnológica do Paraná, CEFET-PR, Av. 7 de Setembro 3165, 80230-901 (PR), Curitiba, Brazil. celiacri@cefetpr.br

Artificial Intelligence in Medicine
|December 20, 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

Predicting the pro-longevity or anti-longevity effect of model organism genes with enhanced Gaussian noise augmentation-based contrastive learning on protein-protein interaction networks.

NAR genomics and bioinformatics·2024
Same author

Positive-Unlabelled learning for identifying new candidate Dietary Restriction-related genes among ageing-related genes.

Computers in biology and medicine·2024
Same author

Predicting lifespan-extending chemical compounds for <i>C. elegans</i> with machine learning and biologically interpretable features.

Aging·2023
Same author

Machine learning-based predictions of dietary restriction associations across ageing-related genes.

BMC bioinformatics·2022
Same author

Ageing transcriptome meta-analysis reveals similarities and differences between key mammalian tissues.

Aging·2021
Same author

A Novel Feature Selection Method for Uncertain Features: An Application to the Prediction of Pro-/Anti-Longevity Genes.

IEEE/ACM transactions on computational biology and bioinformatics·2020
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 introduces a constrained-syntax genetic programming (GP) algorithm for medical data classification. The novel GP approach enhances rule interpretability and predictive accuracy compared to existing methods.

Area of Science:

  • Computer Science
  • Medical Informatics
  • Bioinformatics

Background:

  • Accurate classification of medical data is crucial for diagnosis and treatment.
  • Existing algorithms like C4.5 and Boolean genetic programming (BGP) have limitations in rule interpretability and accuracy.
  • Genetic programming (GP) offers a flexible framework for rule discovery but requires careful design for medical applications.

Purpose of the Study:

  • To propose and evaluate a novel constrained-syntax genetic programming (GP) algorithm for discovering interpretable classification rules in medical datasets.
  • To compare the performance of the proposed GP algorithm against C4.5 and BGP in terms of predictive accuracy and rule comprehensibility.
  • To introduce a new preprocessing step for survival prediction using the pediatric adrenocortical tumor dataset.

Related Experiment Videos

Main Methods:

  • Development of a constrained-syntax GP algorithm enforcing syntactic constraints and using a disjunctive normal form representation.
  • Application of the GP algorithm to five diverse medical datasets: chest pain, Ljubljana breast cancer, dermatology, Wisconsin breast cancer, and pediatric adrenocortical tumor.
  • Comparative analysis of the proposed GP with C4.5 and BGP, including a specific preprocessing step for survival prediction on one dataset.

Main Results:

  • The constrained-syntax GP algorithm demonstrated competitive predictive accuracy across the evaluated medical datasets.
  • The GP-generated classification rules were found to be highly comprehensible, facilitating easier interpretation by medical professionals.
  • The proposed GP algorithm showed overall favorable results when compared to both C4.5 and BGP in terms of accuracy and interpretability.

Conclusions:

  • The constrained-syntax GP algorithm is an effective tool for discovering accurate and interpretable classification rules in medical data.
  • The disjunctive normal form representation and syntactic constraints contribute to the interpretability of the discovered rules.
  • This approach holds promise for improving machine learning applications in medical data analysis and decision support.