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 Video

Updated: May 29, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Evaluating the effect of unbalanced data in biomedical document classification.

Rosalía Laza1, Reyes Pavón, Miguel Reboiro-Jato

  • 1ESEI, Escuela Superior de Ingeniería Informática, University of Vigo, Edificio Politécnico, Campus Universitario As Lagoas s/n, 32004, Ourense, Spain. rlaza@uvigo.es

Journal of Integrative Bioinformatics
|September 20, 2011
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

PolyDeep Advance 3: Randomized Clinical Trial comparing PolyDeep-assisted and conventional colonoscopy for adenoma detection rate in a colorectal cancer screening program.

Endoscopy·2026
Same author

PIBAdb: a public cohort of multimodal colonoscopy videos and images including polyps with histological information.

Computer methods and programs in biomedicine·2026
Same author

Clinical Evaluation of PolyDeep, A Computer-Aided Detection System: A Multicenter Randomized Tandem Colonoscopy Trial.

Diagnostics (Basel, Switzerland)·2025
Same author

PolyDeep Advance 1: Clinical Validation of a Computer-Aided Detection System for Colorectal Polyp Detection with a Second Observer Design.

Diagnostics (Basel, Switzerland)·2025
Same author

Tracking the Spread of Pollen on Social Media Using Pollen-Related Messages From Twitter: Retrospective Analysis.

Journal of medical Internet research·2024
Same author

An enhanced algorithm for semantic-based feature reduction in spam filtering.

PeerJ. Computer science·2024
Same journal

Fusion of computational and experimental provenance in RO-Crate.

Journal of integrative bioinformatics·2026
Same journal

Updates and validation of the Compi RNA-seq pipeline with a case study in Alzheimer's disease.

Journal of integrative bioinformatics·2026
Same journal

Fragment-level FAIRness: annotating scientific data and its provenance using data fragment selectors.

Journal of integrative bioinformatics·2026
Same journal

Integrating cross-omics research through FAIR Digital Objects with DataPLANT.

Journal of integrative bioinformatics·2026
Same journal

Pheno-App 2.0 - a mobile app for collecting phenotypic data in plant research.

Journal of integrative bioinformatics·2026
Same journal

Evolving bioinformatics services - the journey of KPI metrics with Scorpion.

Journal of integrative bioinformatics·2026
See all related articles

Bayesian Networks (BNs) effectively classify biomedical documents using MeSH terms. Techniques like under-sampling and cost-sensitive learning improve BN performance on imbalanced datasets, crucial for knowledge discovery.

Area of Science:

  • Biomedical Informatics
  • Machine Learning
  • Natural Language Processing

Background:

  • The increasing volume of digital biomedical information necessitates efficient document classification.
  • Machine learning techniques are commonly used for text classification, but often struggle with imbalanced datasets.
  • Imbalanced data significantly impacts the performance of standard classification models in knowledge discovery.

Purpose of the Study:

  • To investigate the efficacy of Bayesian Networks (BNs) for classifying biomedical documents represented by Medical Subject Headings (MeSH) terms.
  • To evaluate the challenges posed by imbalanced data in BN-based document classification.
  • To assess the impact of data balancing strategies on BN classifier performance.

Main Methods:

Related Experiment Videos

Last Updated: May 29, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

  • Utilized a Bayesian Network (BN) model for document triage, representing documents via associated MeSH terms.
  • Employed MeSH ontology for multi-level document representation.
  • Conducted an extensive experimental evaluation using under-sampling and cost-sensitive learning to address class imbalance.

    • Main Results:

    • Bayesian Networks effectively model conditional independencies between MeSH terms.
    • MeSH ontology provides a valuable hierarchical structure for representing biomedical documents.
    • BN classifiers are sensitive to class imbalance, but performance can be enhanced.

    Conclusions:

    • Bayesian Networks are suitable for biomedical document classification using MeSH terms.
    • Data balancing techniques, such as under-sampling and cost-sensitive learning, significantly improve BN classifier performance on imbalanced datasets.
    • The study highlights the importance of addressing data imbalance for effective knowledge discovery in biomedical text classification.