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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Shared decision-making for lung cancer screening in a pre-implementation context: A mixed-methods study.

Patient education and counseling·2026
Same author

Vulnerability, protection and fairness: ethical and regulatory limits in small-N gene therapy trials.

Trials·2026
Same author

Supporting the Implementation and Addressing the Challenges of the EU HTA Regulation.

Journal of market access & health policy·2026
Same author

Why advanced therapy medicinal products struggle in clinical translation: an in-depth analysis of developmental challenges in the EU.

Frontiers in medicine·2026
Same author

Advancing the systematic implementation of patient experience data in healthcare decision-making: multi-stakeholder insights on barriers, opportunities and policy ways forward.

Health research policy and systems·2026
Same author

Two-faced Janus? Consent to participate in research and consent to data processing in the EHDS era: a comparative analysis of requirements and standards in eight European countries.

Journal of law and the biosciences·2026

Related Experiment Video

Updated: Dec 27, 2025

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

8.6K

Patient-Level Effectiveness Prediction Modeling for Glioblastoma Using Classification Trees.

Tine Geldof1,2, Nancy Van Damme3, Isabelle Huys2

  • 1Healthcare Management Centre, Vlerick Business School, Ghent, Belgium.

Frontiers in Pharmacology
|March 3, 2020
PubMed
Summary

Machine learning, specifically classification trees, can predict individual glioblastoma patient responses to temozolomide. This approach offers interpretability and identifies age-related treatment patterns, improving personalized oncology care.

Keywords:
decision treeexploratory studymachine learningoncologypropensity score modelingreal world evidence

More Related Videos

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.6K
The Clinical Application of Tumor Treating Fields Therapy in Glioblastoma
08:00

The Clinical Application of Tumor Treating Fields Therapy in Glioblastoma

Published on: April 16, 2019

19.0K

Related Experiment Videos

Last Updated: Dec 27, 2025

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

8.6K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.6K
The Clinical Application of Tumor Treating Fields Therapy in Glioblastoma
08:00

The Clinical Application of Tumor Treating Fields Therapy in Glioblastoma

Published on: April 16, 2019

19.0K

Area of Science:

  • Pharmacoepidemiology
  • Oncology
  • Machine Learning

Background:

  • Limited pharmacoepidemiology research exists on machine learning for cancer drug effectiveness.
  • Glioblastoma treatment with temozolomide requires better understanding of individual patient responses.

Purpose of the Study:

  • To explore the added value of machine learning methods in investigating individual treatment responses for glioblastoma patients treated with temozolomide.
  • To assess the utility of classification trees in predicting patient-level response to temozolomide.

Main Methods:

  • A retrospective observational registry of 3090 glioblastoma patients treated with temozolomide was used.
  • A two-step iterative learning process involved initialization (propensity score matching) and a machine learning phase.
  • A classification tree algorithm was trained and validated to group patients into response and non-response categories.

Main Results:

  • The classification tree model achieved an AUC of 67%, outperforming logistic regression (AUC 64%).
  • The model identified age as a confounding factor and revealed age-related chemotherapy-treatment dependencies.
  • The model's predictive performance was limited by the lack of genetic information.

Conclusions:

  • Classification trees are suitable for analyzing patient-level glioblastoma treatment effectiveness due to interpretability and handling of covariate interdependencies.
  • Including genetic information and primary treatment response data can improve model accuracy.
  • This machine learning approach can aid clinical practice in predicting personalized treatment pathways.