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

Challenges and recent advances in methods for handling imbalanced multiclass classification problems: a

Sachin Acharya1, Satyanarayana Poojari2, Vani Lakshmi R3

  • 1Department of Applied Statistics and Data Science, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India.

BMC Medical Research Methodology
|June 20, 2026
PubMed
Summary

Related Concept Videos

Strategies for Assessing and Addressing Confounding01:25

Strategies for Assessing and Addressing Confounding

Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Classification of Systems-I01:26

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Effect of ESR1 and ESR2 polymorphisms on ovarian response in assisted reproductive technology cycles: a systematic review and meta-analysis.

Scientific reports·2026
Same author

Triglyceride-glucose-based indices in relation to vitamin D concentrations among adults with metabolic syndrome.

PloS one·2026
Same author

Prediction of polycystic ovary syndrome using machine learning models: Addressing class imbalance and high dimensionality.

Journal of education and health promotion·2026
Same author

Impact of repeated ovulation induction and superovulation on ovarian reserve and early embryo development in obese and PCOS-like mouse models.

Reproduction, fertility, and development·2026
Same author

Impact of EGFR Mutations on Survival and Clinical Response in Non-Small Cell Lung Cancer in a Tertiary Care Hospital.

Clinical and translational science·2026
Same author

Dysfunctional breathing in patients with moderate and severe obstructive sleep apnea: a cross sectional study.

Sleep & breathing = Schlaf & Atmung·2026
This summary is machine-generated.

Class imbalance in multiclass classification poses significant challenges in health science. This review synthesizes methods to improve model robustness and predictive accuracy for imbalanced data.

Area of Science:

  • Machine Learning
  • Data Science
  • Health Informatics

Background:

  • Class imbalance is prevalent in health science applications like medical diagnosis and rare disease detection.
  • Multiclass imbalance presents unique challenges due to multiple minority classes, leading to biased models and reduced accuracy.
  • Existing classification models often struggle with imbalanced data, limiting real-world application effectiveness.

Purpose of the Study:

  • To review methodological studies on imbalanced multiclass classification.
  • To synthesize key challenges and recent advances in algorithmic strategies and performance evaluation.
  • To provide practical insights for developing robust and generalizable models for imbalanced datasets.

Main Methods:

  • A structured literature search was performed on Scopus and Web of Science up to 2024.
Keywords:
BinarizationClass imbalanceImbalance measureImbalance ratioMulticlass classificationMulticlass imbalance

Related Experiment Videos

  • Keywords focused on imbalanced multiclass classification, algorithmic strategies, and performance evaluation.
  • 75 studies were included after screening and backward citation searching for methodological relevance.

    • Main Results:

    • The Imbalance Ratio (IR) remains the primary metric for imbalance severity, despite other metrics' introduction.
    • Balancing techniques include distance-based, cluster-based, and distribution-based approaches.
    • Strategies like class weight adjustments can introduce bias; effectiveness depends on data characteristics, with insufficient reporting limiting generalizability.

    Conclusions:

    • Existing methods for imbalanced multiclass classification have varying strengths and limitations.
    • Effective class imbalance management is crucial for equitable decision-making and reliable analysis in health, societal, and environmental domains.
    • Developing robust and generalizable models requires careful consideration of data characteristics and methodological choices.