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: Jun 23, 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

Developing classifiers for the detection of cancer using multi-analytes.

Adi Laurentiu Tarca1, Sorin Draghici, Roberto Romero

  • 1Department of Computer Science, Wayne State University, Detroit, MI, USA.

Methods in Molecular Biology (Clifton, N.J.)
|April 22, 2009
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

Placenta-Specific Genes, Their Regulation During Villous Trophoblast Differentiation and Dysregulation in Preterm Preeclampsia.

International journal of molecular sciences·2020
Same author

Integrated Systems Biology Approach Identifies Novel Maternal and Placental Pathways of Preeclampsia.

Frontiers in immunology·2018
Same author

Longitudinal Changes in Placental Magnetic Resonance Imaging Relaxation Parameter in Murine Pregnancy: Compartmental Analysis.

Gynecologic and obstetric investigation·2015
Same author

Cross-hemispheric functional connectivity in the human fetal brain.

Science translational medicine·2013
Same author

Evidence for a role for the adaptive immune response in human term parturition.

American journal of reproductive immunology (New York, N.Y. : 1989)·2013
Same author

Maternal plasma concentrations of angiogenic/antiangiogenic factors in the third trimester of pregnancy to identify the patient at risk for stillbirth at or near term and severe late preeclampsia.

American journal of obstetrics and gynecology·2013

Developing accurate predictive classifiers with limited data requires careful planning. This study outlines key steps and common challenges in building reliable models using multiple predictors, emphasizing validation strategies.

Area of Science:

  • Biostatistics
  • Machine Learning
  • Bioinformatics

Background:

  • Classifier development involves multiple predictors (analytes) but is often hindered by limited data samples.
  • Selecting appropriate validation strategies, prediction models, training algorithms, and marker selection methods are critical decisions.
  • Common pitfalls in classifier development need to be understood to ensure reliable results.

Purpose of the Study:

  • To describe the fundamental principles of classifier development.
  • To highlight common challenges and pitfalls encountered during the process.
  • To illustrate supervised classification concepts using a simulated dataset.

Main Methods:

  • Review of classifier development principles.
  • Discussion of common pitfalls in model building and validation.

Related Experiment Videos

Last Updated: Jun 23, 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

  • Application of supervised classification on a simulated dataset.

    • Main Results:

    • Limited data presents a significant challenge in developing robust classifiers.
    • The choice of validation strategy critically impacts the assessment of classifier utility.
    • Careful consideration of model type, training algorithm, and marker selection is essential.

    Conclusions:

    • Successful classifier development necessitates a rigorous approach to data handling and validation.
    • Understanding common pitfalls can prevent erroneous conclusions about classifier performance.
    • Supervised classification techniques offer powerful tools for predictive modeling when applied correctly.