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 5, 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

8.0K

An Interpretable Multimodal Machine-Learning Model for Non-Invasive Preoperative Glioma Grading.

Xianfeng Rao1, Min Yang2, Hao Chen1

  • 1Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China.

Cancers
|May 4, 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

Effects of Different Fattening Periods on Slaughtering Performance, Meat Quality, and Muscle Histochemical Characteristics of Yanbian Cattle.

Animals : an open access journal from MDPI·2026
Same author

From Microbial Dysbiosis to Host Pathogenesis: Unraveling the Gut Microbiome's Role in Environmental Toxicology.

Environment & health (Washington, D.C.)·2026
Same author

Effect of ultrasonic-assisted H<sub>2</sub>O<sub>2</sub>/ascorbic acid modification on Platycodon grandiflorum polysaccharide: structural characterization and in vitro functional activities.

Ultrasonics sonochemistry·2026
Same author

ACE-Inhibitory Peptides from Yanbian Cattle Hemoglobin: Screening, Kinetics, and Molecular Dynamics Simulation.

Foods (Basel, Switzerland)·2026
Same author

How host-guest interaction types shape value co-creation in urban tourism: The moderating role of AI technology stimuli.

PloS one·2026
Same author

Effects of protein phosphorylation on lactate dehydrogenase activity glycolysis in postmortem Yanbian yellow cattle muscle.

International journal of biological macromolecules·2026
Same journal

Correction: Adeluola et al. Chemoprevention of 4-NQO-Induced Oral Cancer by the Combination of Resveratrol and EGCG: In Vivo, In Silico and In Vitro Studies. <i>Cancers</i> 2026, <i>18</i>, 1098.

Cancers·2026
Same journal

Correction: Peñalver et al. Guidelines for Diagnosis, Treatment, and Follow-Up of Patients with Follicular Lymphoma-Spanish Lymphoma Group (GELTAMO) 2026. <i>Cancers</i> 2026, <i>18</i>, 395.

Cancers·2026
Same journal

Correction: Accorsi Buttini et al. Development of a Simplified Geriatric Score-4 (SGS-4) to Predict Outcomes After Allogeneic Hematopoietic Stem Cell Transplantation in Patients Aged over 50. <i>Cancers</i> 2025, <i>17</i>, 3278.

Cancers·2026
Same journal

Age-Stratified Long-Term Outcomes of Immune Checkpoint Inhibitors for Stage IV Melanoma and NSCLC in The Netherlands: A Population-Based Study.

Cancers·2026
Same journal

Targeting Ferroptosis in Glioblastoma: Molecular Mechanisms, Tumor Microenvironment, and Therapeutic Opportunities.

Cancers·2026
Same journal

Neoadjuvant Immunotherapy-Based Treatment Versus Chemotherapy Alone in Resectable Locally Advanced dMMR/MSI-H Gastric Cancer: A Real-World Study with Meta-Analysis.

Cancers·2026
See all related articles
This summary is machine-generated.

A new machine learning model accurately predicts glioma grade using clinical and imaging data. This tool aids in preoperative risk stratification for brain tumors, but requires external validation before clinical use.

Area of Science:

  • Neuro-oncology
  • Medical imaging
  • Machine learning

Background:

  • Gliomas are primary malignant brain tumors requiring accurate preoperative grading for treatment.
  • Current non-invasive methods for glioma grading are limited.
  • Multimodal data integration offers potential for improved non-invasive prediction.

Purpose of the Study:

  • Develop and validate an interpretable machine learning model for non-invasive glioma grading.
  • Integrate clinical, structural imaging, and magnetic resonance spectroscopy (MRS) data.
  • Assess the model's performance and clinical utility for preoperative risk stratification.

Main Methods:

  • Retrospective analysis of clinical and imaging data from 400 glioma patients.
  • Feature selection using Boruta algorithm and logistic regression.
Keywords:
gliomamachine learningmagnetic resonance spectroscopypredictive modelpreoperative grading

Related Experiment Videos

Last Updated: May 5, 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

8.0K
  • Benchmarking 17 machine learning algorithms, with Random Forest selected as optimal.
  • Internal validation using ROC analysis, calibration, precision-recall curves, and decision curve analysis.

    • Main Results:

    • Identified eight key predictors: age, neurological deficits, midline shift, tumor characteristics, and MRS ratios (Cho/NAA, Cho/Cr).
    • The Random Forest model achieved an AUC of 0.946 in the validation cohort.
    • Demonstrated good calibration, high average precision (0.98), and clinical utility via decision curve analysis.

    Conclusions:

    • A validated multimodal machine learning model can non-invasively predict glioma grade.
    • The model shows promise for preoperative risk stratification and individualized treatment planning.
    • Further external validation is necessary before widespread clinical adoption.