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 25, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Feature selection methods for optimizing clinicopathologic input variables in oral cancer prognosis.

Siow-Wee Chang1, Sameem Abdul Kareem, Thomas George Kallarakkal

  • 1Department of Artificial Intelligence, Faculty of Computer Science and Information Technology and Bioinformatics Division, Institute of Biological Science, University of Malaya, Kuala Lumpur, Malaysia. changsiowwee@yahoo.com

Asian Pacific Journal of Cancer Prevention : APJCP
|February 11, 2012
PubMed
Summary

Related Concept Videos

Cancer Survival Analysis01:21

Cancer Survival Analysis

Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...

You might also read

Related Articles

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

Sort by
Same author

Oral microbiome profiling of primary oral candidiasis during infection and post-antifungal therapy.

Clinical oral investigations·2026
Same author

Protein Expression of MAGEB2 in Normal Oral Mucosa, Oral Epithelial Dysplasia, and Oral Squamous Cell Carcinoma and Its Association with Clinicopathological Parameters.

Asian Pacific journal of cancer prevention : APJCP·2026
Same author

MeMoSA dataset: A multi-country collection of over 30,000 oral mucosa images with clinically labelled lesions.

Scientific data·2026
Same author

A scoping review of systematic reviews on artificial intelligence in orthopaedics.

Journal of orthopaedic surgery (Hong Kong)·2026
Same author

Metabolomic profiling reveals alterations in Candida pathophysiology and host interactions during primary oral candidiasis and following antifungal treatment.

Scientific reports·2026
Same author

Prediction of Extranodal Extension in Oral Squamous Cell Carcinoma Using Demographic and Clinicopathological Variables-Evidence From a Multicentre Study.

Journal of oral pathology & medicine : official publication of the International Association of Oral Pathologists and the American Academy of Oral Pathology·2025

This study identifies key variables for predicting oral cancer prognosis in Malaysia. Feature selection methods, particularly Pearson

Area of Science:

  • Oncology
  • Biostatistics
  • Medical Informatics

Background:

  • Oral cancer incidence is notably high among individuals of Indian ethnic origin in Malaysia.
  • Clinical and pathological data are crucial for oral cancer prognosis but often limited by time, cost, and tissue availability.
  • Reducing the number of prognostic variables is essential for efficient and effective patient management.

Purpose of the Study:

  • To demonstrate the utility of feature selection methods for identifying highly predictive variables in oral cancer prognosis.
  • To reduce the number of input variables for oral cancer prognosis models.
  • To identify key clinicopathological variables for oral cancer prognosis within the Malaysian context.

Main Methods:

  • Implemented two feature selection methods: genetic algorithm (wrapper approach) and Pearson's correlation coefficient (filter approach).

Related Experiment Videos

Last Updated: May 25, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

  • Compared the performance of reduced models against single-input and full-input models.
  • Evaluated the accuracy of prognostic predictions based on selected variable subsets.

    • Main Results:

    • Reduced models utilizing feature selection demonstrated superior accuracy in oral cancer prognosis compared to full-input models.
    • The Pearson's correlation coefficient method yielded the most promising and accurate prognostic results.
    • Feature selection effectively identified a subset of variables highly predictive of oral cancer prognosis.

    Conclusions:

    • Feature selection methods are effective in reducing variables for oral cancer prognosis, enhancing accuracy and efficiency.
    • Pearson's correlation coefficient is a valuable tool for identifying key prognostic factors in oral cancer.
    • The findings provide a more streamlined approach to oral cancer prognosis, particularly relevant for the Malaysian population.