Decision tree-based machine learning algorithm for prediction of acute radiation esophagitis

Radiation-induced esophagitis remains a significant challenge in thoracic and neck cancer treatment, impacting patient quality of life and potentially limiting therapeutic efficacy. This study aimed to develop and validate a decision tree-based model for predicting acute esophagitis grades in patien...

Full description

Saved in:
Bibliographic Details
Published in:Biochemistry and biophysics reports Vol. 42; p. 101991
Main Authors: Alizade-Harakiyan, Mostafa, Khodaei, Amin, Yousefi, Ali, Zamani, Hamed, Mesbahi, Asghar
Format: Journal Article
Language:English
Published: Netherlands Elsevier B.V 01.06.2025
Elsevier
Subjects:
Decision tree classifier
Machine learning
Predictive modeling
Radiation-induced esophagitis
Radiotherapy
Treatment planning
Decision tree classifier
Predictive modeling
Radiotherapy
Radiation-induced esophagitis
Treatment planning
Machine learning
ISSN:2405-5808, 2405-5808
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Radiation-induced esophagitis remains a significant challenge in thoracic and neck cancer treatment, impacting patient quality of life and potentially limiting therapeutic efficacy. This study aimed to develop and validate a decision tree-based model for predicting acute esophagitis grades in patients undergoing chemoradiotherapy. Data from 100 patients receiving thoracic and neck radiotherapy were analyzed. The dataset comprised 33 features, including demographic, clinical, and dosimetric parameters. A decision tree classifier was implemented for both binary (Grade ≥2 vs. <2) and multi-class (Grades 1, 2, and 3) classification. Model performance was evaluated using standard metrics including accuracy, precision, recall, and F1-score. The binary classification model achieved 97 % accuracy in distinguishing acute esophagitis. The multi-class model demonstrated 98 % accuracy in predicting specific grades. Key predictive features included V40 (volume receiving 40 Gy), V60, and average esophageal dose. The model generated interpretable decision rules, with V60 ≥ 2.3 strongly indicating Grade 3 esophagitis. The decision tree model demonstrates high accuracy in predicting radiation-induced esophagitis grades while maintaining clinical interpretability. This approach offers potential for treatment optimization and personalized risk assessment in radiotherapy planning. The model's transparency and reliability make it a promising tool for clinical decision support in radiation oncology. •Development and Validation of a Decision Tree Model for Predicting Acute Radiation Esophagitis Grades in Thoracic and Neck Cancer Patients.•Prediction of acute esophagitis with machine learning algorithms.•Use clinical, pathological and physical data for prediction of esophagitis.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2405-5808
2405-5808
DOI:10.1016/j.bbrep.2025.101991