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

Auto-segmentation of organs-of-interest clinical acceptability & reproducibility framework in head and neck cancer.

Physics and imaging in radiation oncology·2026
Same author

Making head and neck cancer clinical data Findable-Accessible-Interoperable-Reusable to support multi-institutional collaboration and federated learning.

BJR artificial intelligence·2026
Same author

Deep Learning of Histopathology Predicts Outcomes After Surgery for Pancreatic Cancer.

JCO clinical cancer informatics·2026
Same author

A practical framework for operationalising responsible and equitable artificial intelligence in health care: tackling bias, inequity, and implementation challenges.

The Lancet. Digital health·2026
Same author

Evaluation of ensilication technology for ambient DNA preservation.

NAR molecular medicine·2026
Same author

Identification of a Cytokine Biomarker for Prognostic Modeling of Breast Cancer-Related Lymphedema.

Cancer research communications·2026

Related Experiment Video

Updated: May 2, 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

Development of Machine Learning Models for Predicting Radiation Dermatitis in Breast Cancer Patients Using Clinical

Neil Lin1, Farnoosh Abbas-Aghababazadeh2, Jie Su3

  • 1Institute of Medical Science, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada; Temerty Faculty of Medicine, University of Toronto, Toronto, Canada.

Clinical Breast Cancer
|March 28, 2025
PubMed
Summary

Predicting severe radiation dermatitis in breast cancer patients is possible using clinical factors, patient-reported outcomes, and serum cytokines. Machine learning and logistic regression models showed similar effectiveness in identifying patients at risk.

Keywords:
Cancer survivorshipOncologyPredictive modelingRadiotherapySkin toxicity

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

5.8K
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

5.5K

Related Experiment Videos

Last Updated: May 2, 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
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

5.8K
Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model
08:32

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

5.5K

Area of Science:

  • Oncology
  • Radiotherapy
  • Biomarkers
  • Machine Learning

Background:

  • Radiation dermatitis (RD) is a common and debilitating side effect of radiotherapy for breast cancer patients.
  • Severe RD symptoms like skin desquamation or ulceration significantly reduce quality of life and increase healthcare costs.
  • Early identification of patients at high risk for severe RD is crucial for implementing preventive strategies.

Purpose of the Study:

  • To evaluate the predictive utility of patient-reported outcomes (PROs) and serum cytokines for identifying breast cancer patients at risk of severe RD.
  • To compare the performance of machine learning (ML) models against logistic regression for predicting clinically significant RD.

Main Methods:

  • Analysis of data from 147 breast cancer patients undergoing radiotherapy.
  • Development and comparison of prognostic models using ML algorithms (neural networks, random forest, XGBoost) and logistic regression.
  • Inclusion of clinical factors, PROs, and serum cytokine biomarkers in the predictive models; evaluation via nested cross-validation.

Main Results:

  • Eighteen predictors for Grade 2+ RD were identified, including smoking, radiotherapy boost, reduced motivation, and specific cytokines (IL-4, IL-17, IL-1RA, IFN-γ, SDF-1α).
  • The XGBoost model achieved the highest Area Under the Curve (AUC) of 0.780.
  • Performance of the XGBoost model was comparable to the logistic regression model (AUC 0.714), indicating similar predictive capabilities.

Conclusions:

  • Clinical risk factors, PROs, and serum cytokine levels offer complementary information for predicting severe RD in breast cancer patients.
  • Both ML and logistic regression models demonstrate effective and comparable performance (AUC > 0.70) in predicting clinically significant RD.