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

Balanced gradient boosting from imbalanced data for clinical outcome prediction.

Reiji Teramoto1

  • 1Bio-IT Center, NEC Corporation. rteramotjp@gmail.com

Statistical Applications in Genetics and Molecular Biology
|May 5, 2009
PubMed
Summary

Balanced Gradient Boosting (BalaBoost) effectively addresses imbalanced clinical data, improving prediction accuracy for minority classes. This method enhances disease diagnosis and prognosis by mitigating bias in machine learning models.

Related Concept Videos

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches01:23

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches

Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...
Regression Toward the Mean01:52

Regression Toward the Mean

Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when researchers try to extrapolate results...

You might also read

Related Articles

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

Sort by
Same author

Safe model based optimization balancing exploration and reliability for protein sequence design.

Scientific reports·2025
Same author

Monte Carlo Thompson sampling-guided design for antibody engineering.

mAbs·2023
Same author

Antibody design using LSTM based deep generative model from phage display library for affinity maturation.

Scientific reports·2021
Same author

A prospective compound screening contest identified broader inhibitors for Sirtuin 1.

Scientific reports·2019
Same author

An iterative compound screening contest method for identifying target protein inhibitors using the tyrosine-protein kinase Yes.

Scientific reports·2017
Same author

Identification of potential inhibitors based on compound proposal contest: Tyrosine-protein kinase Yes as a target.

Scientific reports·2015

Area of Science:

  • Biomedical Informatics
  • Machine Learning in Healthcare
  • Computational Biology

Background:

  • Clinical outcome prediction often assumes balanced class distributions, which is rarely true in practice.
  • Highly skewed data in biological and clinical datasets leads to biased supervised learning models favoring majority classes.
  • Standard algorithms struggle with imbalanced data, necessitating methods that appropriately incorporate class distribution.

Purpose of the Study:

  • To develop a novel approach for clinical outcome prediction using imbalanced data.
  • To introduce Balanced Gradient Boosting (BalaBoost) to overcome the limitations of standard algorithms with skewed datasets.
  • To improve model sensitivity to minority classes in clinical prediction tasks.

Main Methods:

Related Experiment Videos

  • Proposed Balanced Gradient Boosting (BalaBoost), a reformulation of gradient boosting.
  • BalaBoost utilizes equal class distribution instead of empirical distribution to prevent majority class overfitting.
  • Applied BalaBoost to diverse clinical datasets: miRNA data for cancer diagnosis, biochemical data for diabetes mortality, and tumor markers for renal cell carcinoma grading.

    • Main Results:

    • BalaBoost demonstrated superior performance compared to standard gradient boosting, Random Forests, and Support Vector Machines.
    • The method effectively handled highly skewed class distributions across multiple clinical prediction tasks.
    • Experimental results confirmed BalaBoost's ability to be sensitive to minority classes.

    Conclusions:

    • Balanced Gradient Boosting (BalaBoost) is a promising technique for clinical outcome prediction from imbalanced data.
    • The proposed method offers improved accuracy and reduced bias in challenging clinical datasets.
    • BalaBoost provides a robust solution for leveraging skewed biological and clinical data.