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

Classification of multiple cancer types by multicategory support vector machines using gene expression data.

Yoonkyung Lee1, Cheol-Koo Lee

  • 1Department of Statistics, The Ohio State University, Columbus, OH 43210, USA. yklee@stat.ohio-state.edu

Bioinformatics (Oxford, England)
|June 13, 2003
PubMed
Summary

Multicategory Support Vector Machines (SVM) offer a novel approach to classifying multiple cancer types using gene expression data. This method demonstrates comparable accuracy to existing techniques, providing a flexible alternative for cancer diagnosis.

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

Hypoperfusion Intensity Ratio as a Predictive Marker in Pre-Endovascular Treatment Perfusion MRI for Acute Middle Cerebral Artery Occlusion with Intracranial Atherosclerosis.

Cerebrovascular diseases extra·2026
Same author

Changes in postoperative pneumonia incidence after the pandemic: a retrospective observational study using a common data model.

Anesthesia and pain medicine·2026
Same author

A school-based respect-for-life program integrating deceased organ donation awareness in South Korea: a post-class mixed-methods evaluation.

Scientific reports·2026
Same author

Continuous REM sleep without atonia quantification improves prediction of phenoconversion to α-synucleinopathies in isolated REM sleep behavior disorder.

Sleep medicine·2025
Same author

Delayed door to puncture time during off-duty hours is associated with unfavorable outcomes after mechanical thrombectomy in the early window of acute ischemic stroke.

BMC neurology·2024
Same author

TOR2 plays the central role in rapamycin-induced lifespan extension in budding yeast.

Biochemical and biophysical research communications·2024

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • High-density DNA microarrays measure thousands of gene activities simultaneously.
  • Gene expression profiles are increasingly used for accurate cancer classification and improved therapeutic strategies.
  • Traditional Support Vector Machines (SVM) are effective for binary classification but face challenges in multiclass tumor diagnosis.

Purpose of the Study:

  • To introduce and apply the Multicategory Support Vector Machine (MSVM), an extension of binary SVM, to multiclass cancer diagnosis.
  • To evaluate the effectiveness of MSVM in classifying different types of cancer using gene expression data.

Main Methods:

  • Application of the Multicategory Support Vector Machine (MSVM) algorithm.
  • Utilizing gene expression profiles from high-density DNA microarrays for classification.

Related Experiment Videos

  • Testing the MSVM on established cancer datasets, including leukemia and small round blue cell tumors.

    • Main Results:

    • The MSVM demonstrated comparable classification accuracy on the tested datasets.
    • The flexibility of the MSVM makes it a viable alternative for multiclass cancer diagnosis.
    • Successful application to leukemia and childhood tumor datasets validates the MSVM approach.

    Conclusions:

    • The Multicategory Support Vector Machine (MSVM) is a promising method for multiclass cancer diagnosis.
    • MSVM offers a flexible and accurate alternative to existing classification methods in cancer research.
    • This approach enhances the potential for improved cancer subtyping and personalized treatment strategies.