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

Background: 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 grad...

Full description

Saved in:
Bibliographic Details
Main Authors: Mostafa Alizade-Harakiyan, Amin Khodaei, Ali Yousefi, Hamed Zamani, Asghar Mesbahi
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Biochemistry and Biophysics Reports
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405580825000780
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850111359438553088
author Mostafa Alizade-Harakiyan
Amin Khodaei
Ali Yousefi
Hamed Zamani
Asghar Mesbahi
author_facet Mostafa Alizade-Harakiyan
Amin Khodaei
Ali Yousefi
Hamed Zamani
Asghar Mesbahi
author_sort Mostafa Alizade-Harakiyan
collection DOAJ
description Background: 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. Methods: 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. Results: 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. Conclusions: 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.
format Article
id doaj-art-8b7b4782508b46e5adb7386f852ed708
institution OA Journals
issn 2405-5808
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Biochemistry and Biophysics Reports
spelling doaj-art-8b7b4782508b46e5adb7386f852ed7082025-08-20T02:37:38ZengElsevierBiochemistry and Biophysics Reports2405-58082025-06-014210199110.1016/j.bbrep.2025.101991Decision tree-based machine learning algorithm for prediction of acute radiation esophagitisMostafa Alizade-Harakiyan0Amin Khodaei1Ali Yousefi2Hamed Zamani3Asghar Mesbahi4Department of Radiation Oncology, Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, IranFaculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, IranDepartment of Medicinal Chemistry, School of Pharmacy, Tabriz University of Medical Sciences, Tabriz, IranMedical Physics Department, Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, IranMedical Physics Department, Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, Iran; Molecular Medicine Research Center, Tabriz University of Medical Sciences, Tabriz, Iran; Corresponding author. Medical Physics Department, Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, Iran.Background: 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. Methods: 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. Results: 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. Conclusions: 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.http://www.sciencedirect.com/science/article/pii/S2405580825000780Radiation-induced esophagitisDecision tree classifierPredictive modelingMachine learningRadiotherapyTreatment planning
spellingShingle Mostafa Alizade-Harakiyan
Amin Khodaei
Ali Yousefi
Hamed Zamani
Asghar Mesbahi
Decision tree-based machine learning algorithm for prediction of acute radiation esophagitis
Biochemistry and Biophysics Reports
Radiation-induced esophagitis
Decision tree classifier
Predictive modeling
Machine learning
Radiotherapy
Treatment planning
title Decision tree-based machine learning algorithm for prediction of acute radiation esophagitis
title_full Decision tree-based machine learning algorithm for prediction of acute radiation esophagitis
title_fullStr Decision tree-based machine learning algorithm for prediction of acute radiation esophagitis
title_full_unstemmed Decision tree-based machine learning algorithm for prediction of acute radiation esophagitis
title_short Decision tree-based machine learning algorithm for prediction of acute radiation esophagitis
title_sort decision tree based machine learning algorithm for prediction of acute radiation esophagitis
topic Radiation-induced esophagitis
Decision tree classifier
Predictive modeling
Machine learning
Radiotherapy
Treatment planning
url http://www.sciencedirect.com/science/article/pii/S2405580825000780
work_keys_str_mv AT mostafaalizadeharakiyan decisiontreebasedmachinelearningalgorithmforpredictionofacuteradiationesophagitis
AT aminkhodaei decisiontreebasedmachinelearningalgorithmforpredictionofacuteradiationesophagitis
AT aliyousefi decisiontreebasedmachinelearningalgorithmforpredictionofacuteradiationesophagitis
AT hamedzamani decisiontreebasedmachinelearningalgorithmforpredictionofacuteradiationesophagitis
AT asgharmesbahi decisiontreebasedmachinelearningalgorithmforpredictionofacuteradiationesophagitis