Robustness of Machine Learning Predictions for Determining Whether Deep Inspiration Breath-Hold Is Required in Breast Cancer Radiation Therapy

<b>Background/Objectives:</b> Deep inspiration breath-hold (DIBH) is a commonly used technique to reduce the mean heart dose (MHD), which is critical for minimizing late cardiac side effects in breast cancer patients undergoing radiation therapy (RT). Although previous studies have explo...

Full description

Saved in:
Bibliographic Details
Main Authors: Wlla E. Al-Hammad, Masahiro Kuroda, Ghaida Al Jamal, Mamiko Fujikura, Ryo Kamizaki, Kazuhiro Kuroda, Suzuka Yoshida, Yoshihide Nakamura, Masataka Oita, Yoshinori Tanabe, Kohei Sugimoto, Irfan Sugianto, Majd Barham, Nouha Tekiki, Miki Hisatomi, Junichi Asaumi
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/6/668
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849341544468840448
author Wlla E. Al-Hammad
Masahiro Kuroda
Ghaida Al Jamal
Mamiko Fujikura
Ryo Kamizaki
Kazuhiro Kuroda
Suzuka Yoshida
Yoshihide Nakamura
Masataka Oita
Yoshinori Tanabe
Kohei Sugimoto
Irfan Sugianto
Majd Barham
Nouha Tekiki
Miki Hisatomi
Junichi Asaumi
author_facet Wlla E. Al-Hammad
Masahiro Kuroda
Ghaida Al Jamal
Mamiko Fujikura
Ryo Kamizaki
Kazuhiro Kuroda
Suzuka Yoshida
Yoshihide Nakamura
Masataka Oita
Yoshinori Tanabe
Kohei Sugimoto
Irfan Sugianto
Majd Barham
Nouha Tekiki
Miki Hisatomi
Junichi Asaumi
author_sort Wlla E. Al-Hammad
collection DOAJ
description <b>Background/Objectives:</b> Deep inspiration breath-hold (DIBH) is a commonly used technique to reduce the mean heart dose (MHD), which is critical for minimizing late cardiac side effects in breast cancer patients undergoing radiation therapy (RT). Although previous studies have explored the potential of machine learning (ML) to predict which patients might benefit from DIBH, none have rigorously assessed ML model performance across various MHD thresholds and parameter settings. This study aims to evaluate the robustness of ML models in predicting the need for DIBH across different clinical scenarios. <b>Methods</b>: Using data from 207 breast cancer patients treated with RT, we developed and tested ML models at three MHD cut-off values (240, 270, and 300 cGy), considering variations in the number of independent variables (three vs. six) and folds in the cross-validation (three, four, and five). Robustness was defined as achieving high F2 scores and low instability in predictive performance. <b>Results</b>: Our findings indicate that the decision tree (DT) model demonstrated consistently high robustness at 240 and 270 cGy, while the random forest model performed optimally at 300 cGy. At 240 cGy, a threshold critical to minimize late cardiac risks, the DT model exhibited stable predictive power, reducing the risk of overestimating DIBH necessity. <b>Conclusions</b>: These results suggest that the DT model, particularly at lower MHD thresholds, may be the most reliable for clinical applications. By providing a tool for targeted DIBH implementation, this model has the potential to enhance patient-specific treatment planning and improve clinical outcomes in RT.
format Article
id doaj-art-d39322ae127e446fa6b4d1d8cb0e4b03
institution Kabale University
issn 2075-4418
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-d39322ae127e446fa6b4d1d8cb0e4b032025-08-20T03:43:36ZengMDPI AGDiagnostics2075-44182025-03-0115666810.3390/diagnostics15060668Robustness of Machine Learning Predictions for Determining Whether Deep Inspiration Breath-Hold Is Required in Breast Cancer Radiation TherapyWlla E. Al-Hammad0Masahiro Kuroda1Ghaida Al Jamal2Mamiko Fujikura3Ryo Kamizaki4Kazuhiro Kuroda5Suzuka Yoshida6Yoshihide Nakamura7Masataka Oita8Yoshinori Tanabe9Kohei Sugimoto10Irfan Sugianto11Majd Barham12Nouha Tekiki13Miki Hisatomi14Junichi Asaumi15Department of Oral and Maxillofacial Radiology, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700-8558, JapanRadiological Technology, Graduate School of Health Sciences, Okayama University, Okayama 700-8558, JapanDepartment of Oral Medicine and Oral Surgery, Faculty of Dentistry, Jordan University of Science and Technology, Irbid 22110, JordanDepartment of Oral and Maxillofacial Radiology, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700-8558, JapanRadiological Technology, Graduate School of Health Sciences, Okayama University, Okayama 700-8558, JapanRadiological Technology, Graduate School of Health Sciences, Okayama University, Okayama 700-8558, JapanDepartment of Oral and Maxillofacial Radiology, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700-8558, JapanDepartment of Oral and Maxillofacial Radiology, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700-8558, JapanGraduate School of Interdisciplinary Sciences and Engineering in Health Systems, Okayama University, Okayama 770-8558, JapanRadiological Technology, Graduate School of Health Sciences, Okayama University, Okayama 700-8558, JapanRadiological Technology, Graduate School of Health Sciences, Okayama University, Okayama 700-8558, JapanDepartment of Oral Radiology, Faculty of Dentistry, Hasanuddin University, Sulawesi 90245, IndonesiaDepartment of Dentistry and Dental Surgery, College of Medicine and Health Sciences, An-Najah National University, Nablus 44839, PalestineDepartment of Oral and Maxillofacial Radiology, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700-8558, JapanDepartment of Oral and Maxillofacial Radiology, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700-8558, JapanDepartment of Oral and Maxillofacial Radiology, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700-8558, Japan<b>Background/Objectives:</b> Deep inspiration breath-hold (DIBH) is a commonly used technique to reduce the mean heart dose (MHD), which is critical for minimizing late cardiac side effects in breast cancer patients undergoing radiation therapy (RT). Although previous studies have explored the potential of machine learning (ML) to predict which patients might benefit from DIBH, none have rigorously assessed ML model performance across various MHD thresholds and parameter settings. This study aims to evaluate the robustness of ML models in predicting the need for DIBH across different clinical scenarios. <b>Methods</b>: Using data from 207 breast cancer patients treated with RT, we developed and tested ML models at three MHD cut-off values (240, 270, and 300 cGy), considering variations in the number of independent variables (three vs. six) and folds in the cross-validation (three, four, and five). Robustness was defined as achieving high F2 scores and low instability in predictive performance. <b>Results</b>: Our findings indicate that the decision tree (DT) model demonstrated consistently high robustness at 240 and 270 cGy, while the random forest model performed optimally at 300 cGy. At 240 cGy, a threshold critical to minimize late cardiac risks, the DT model exhibited stable predictive power, reducing the risk of overestimating DIBH necessity. <b>Conclusions</b>: These results suggest that the DT model, particularly at lower MHD thresholds, may be the most reliable for clinical applications. By providing a tool for targeted DIBH implementation, this model has the potential to enhance patient-specific treatment planning and improve clinical outcomes in RT.https://www.mdpi.com/2075-4418/15/6/668breast cancerradiation therapyheart dosecut-off valuemachine learningrobustness
spellingShingle Wlla E. Al-Hammad
Masahiro Kuroda
Ghaida Al Jamal
Mamiko Fujikura
Ryo Kamizaki
Kazuhiro Kuroda
Suzuka Yoshida
Yoshihide Nakamura
Masataka Oita
Yoshinori Tanabe
Kohei Sugimoto
Irfan Sugianto
Majd Barham
Nouha Tekiki
Miki Hisatomi
Junichi Asaumi
Robustness of Machine Learning Predictions for Determining Whether Deep Inspiration Breath-Hold Is Required in Breast Cancer Radiation Therapy
Diagnostics
breast cancer
radiation therapy
heart dose
cut-off value
machine learning
robustness
title Robustness of Machine Learning Predictions for Determining Whether Deep Inspiration Breath-Hold Is Required in Breast Cancer Radiation Therapy
title_full Robustness of Machine Learning Predictions for Determining Whether Deep Inspiration Breath-Hold Is Required in Breast Cancer Radiation Therapy
title_fullStr Robustness of Machine Learning Predictions for Determining Whether Deep Inspiration Breath-Hold Is Required in Breast Cancer Radiation Therapy
title_full_unstemmed Robustness of Machine Learning Predictions for Determining Whether Deep Inspiration Breath-Hold Is Required in Breast Cancer Radiation Therapy
title_short Robustness of Machine Learning Predictions for Determining Whether Deep Inspiration Breath-Hold Is Required in Breast Cancer Radiation Therapy
title_sort robustness of machine learning predictions for determining whether deep inspiration breath hold is required in breast cancer radiation therapy
topic breast cancer
radiation therapy
heart dose
cut-off value
machine learning
robustness
url https://www.mdpi.com/2075-4418/15/6/668
work_keys_str_mv AT wllaealhammad robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT masahirokuroda robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT ghaidaaljamal robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT mamikofujikura robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT ryokamizaki robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT kazuhirokuroda robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT suzukayoshida robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT yoshihidenakamura robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT masatakaoita robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT yoshinoritanabe robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT koheisugimoto robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT irfansugianto robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT majdbarham robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT nouhatekiki robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT mikihisatomi robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy
AT junichiasaumi robustnessofmachinelearningpredictionsfordeterminingwhetherdeepinspirationbreathholdisrequiredinbreastcancerradiationtherapy