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 28, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning-Based Classification of Gliomas and Tumor Grades with SHAP-Guided Feature Interpretation.

Ghaya Al-Rumaihi1, Md Shaheenur Islam Sumon2, Ahmed Hassanein3

  • 1Neurosurgery Department, Hamad Medical Corporation, Doha 3050, Qatar.

Genes
|May 27, 2026
PubMed
Summary

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

The Framework of Policy Transition in TBI: From GCS to CBI-M.

Neurocritical care·2026
Same author

Global mitochondrial connectivity map reveals the landscape of yeast functional assemblies and conserved protein communities.

Nature communications·2026
Same author

Genomic characterization of Comamonas kerstersii isolated from diarrheal patients in Bangladesh.

PloS one·2026
Same author

Beyond oxygen transport: red blood cells as emerging players in mediating endothelial dysfunction in diabetes.

Annals of medicine·2026
Same author

Integrated Assessment of Wall Shear Stress-Related Hemodynamic Parameters in Abdominal Aortic Aneurysms: A Retrospective Cross-Sectional Study on Ruptured Cases.

International journal for numerical methods in biomedical engineering·2026
Same author

Hidden Triplets: Coexisting Spinal Epidural and Dural Arteriovenous Fistulae - A Rare Case Report and Literature Review.

Vascular health and risk management·2026

Machine learning models accurately classify brain tumor subtypes and grades using gene expression data. This approach aids in understanding glioma heterogeneity and supports precision oncology.

Area of Science:

  • Neuro-oncology
  • Computational biology
  • Genomics

Background:

  • Gliomas are common, heterogeneous primary brain tumors with complex molecular profiles.
  • Substantial transcriptomic diversity complicates glioma diagnosis, grading, and treatment.
  • Artificial intelligence (AI) and machine learning (ML) offer tools for analyzing high-dimensional gene expression data.

Purpose of the Study:

  • Develop an interpretable ML framework for classifying glioma subtypes (glioblastoma, astrocytoma, oligodendroglioma).
  • Predict tumor grades (II, III, IV) using gene expression data.
  • Identify key genes and pathways driving tumor classification and grading.

Main Methods:

  • Utilized the REMBRANDT dataset with microarray-based gene expression data.
Keywords:
SHAP analysisartificial intelligenceastrocytomabrain tumorgene expressiongenesglioblastomagliomamachine learningoligodendroglioma

Related Experiment Videos

Last Updated: May 28, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

  • Applied an interpretable ML framework for classification and grade prediction.
  • Employed SHAP analysis for feature importance and KEGG enrichment for pathway analysis.

    • Main Results:

    • ML models achieved high accuracy in classifying glioma subtypes (e.g., 99.6% for glioblastoma).
    • Strong performance in predicting tumor grades (e.g., 91.3% accuracy for grade II vs. IV).
    • SHAP analysis identified key genes (e.g., WIF1, STX6) and pathways (vesicular transport, metabolism, immune signaling).

    Conclusions:

    • Interpretable ML models accurately differentiate glioma subtypes and grades.
    • SHAP analysis provides insights into critical predictive genes and pathways.
    • Findings enhance understanding of glioma molecular landscape, complementing histopathology.