Cargando…

Augmenting Quality Assurance Measures in Treatment Review with Machine Learning in Radiation Oncology

PURPOSE: Pretreatment quality assurance (QA) of treatment plans often requires a high cognitive workload and considerable time expenditure. This study explores the use of machine learning to classify pretreatment chart check QA for a given radiation plan as difficult or less difficult, thereby alert...

Descripción completa

Detalles Bibliográficos
Autores principales: Pillai, Malvika, Shumway, John W., Adapa, Karthik, Dooley, John, McGurk, Ross, Mazur, Lukasz M., Das, Shiva K., Chera, Bhishamjit S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10185740/
https://www.ncbi.nlm.nih.gov/pubmed/37205277
http://dx.doi.org/10.1016/j.adro.2023.101234
_version_ 1785042420430274560
author Pillai, Malvika
Shumway, John W.
Adapa, Karthik
Dooley, John
McGurk, Ross
Mazur, Lukasz M.
Das, Shiva K.
Chera, Bhishamjit S.
author_facet Pillai, Malvika
Shumway, John W.
Adapa, Karthik
Dooley, John
McGurk, Ross
Mazur, Lukasz M.
Das, Shiva K.
Chera, Bhishamjit S.
author_sort Pillai, Malvika
collection PubMed
description PURPOSE: Pretreatment quality assurance (QA) of treatment plans often requires a high cognitive workload and considerable time expenditure. This study explores the use of machine learning to classify pretreatment chart check QA for a given radiation plan as difficult or less difficult, thereby alerting the physicists to increase scrutiny on difficult plans. METHODS AND MATERIALS: Pretreatment QA data were collected for 973 cases between July 2018 and October 2020. The outcome variable, a degree of difficulty, was collected as a subjective rating by physicists who performed the pretreatment chart checks. Potential features were identified based on clinical relevance, contribution to plan complexity, and QA metrics. Five machine learning models were developed: support vector machine, random forest classifier, adaboost classifier, decision tree classifier, and neural network. These were incorporated into a voting classifier, where at least 2 algorithms needed to predict a case as difficult for it to be classified as such. Sensitivity analyses were conducted to evaluate feature importance. RESULTS: The voting classifier achieved an overall accuracy of 77.4% on the test set, with 76.5% accuracy on difficult cases and 78.4% accuracy on less difficult cases. Sensitivity analysis showed features associated with plan complexity (number of fractions, dose per monitor unit, number of planning structures, and number of image sets) and clinical relevance (patient age) were sensitive across at least 3 algorithms. CONCLUSIONS: This approach can be used to equitably allocate plans to physicists rather than randomly allocate them, potentially improving pretreatment chart check effectiveness by reducing errors propagating downstream.
format Online
Article
Text
id pubmed-10185740
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-101857402023-05-17 Augmenting Quality Assurance Measures in Treatment Review with Machine Learning in Radiation Oncology Pillai, Malvika Shumway, John W. Adapa, Karthik Dooley, John McGurk, Ross Mazur, Lukasz M. Das, Shiva K. Chera, Bhishamjit S. Adv Radiat Oncol Scientific Article PURPOSE: Pretreatment quality assurance (QA) of treatment plans often requires a high cognitive workload and considerable time expenditure. This study explores the use of machine learning to classify pretreatment chart check QA for a given radiation plan as difficult or less difficult, thereby alerting the physicists to increase scrutiny on difficult plans. METHODS AND MATERIALS: Pretreatment QA data were collected for 973 cases between July 2018 and October 2020. The outcome variable, a degree of difficulty, was collected as a subjective rating by physicists who performed the pretreatment chart checks. Potential features were identified based on clinical relevance, contribution to plan complexity, and QA metrics. Five machine learning models were developed: support vector machine, random forest classifier, adaboost classifier, decision tree classifier, and neural network. These were incorporated into a voting classifier, where at least 2 algorithms needed to predict a case as difficult for it to be classified as such. Sensitivity analyses were conducted to evaluate feature importance. RESULTS: The voting classifier achieved an overall accuracy of 77.4% on the test set, with 76.5% accuracy on difficult cases and 78.4% accuracy on less difficult cases. Sensitivity analysis showed features associated with plan complexity (number of fractions, dose per monitor unit, number of planning structures, and number of image sets) and clinical relevance (patient age) were sensitive across at least 3 algorithms. CONCLUSIONS: This approach can be used to equitably allocate plans to physicists rather than randomly allocate them, potentially improving pretreatment chart check effectiveness by reducing errors propagating downstream. Elsevier 2023-04-06 /pmc/articles/PMC10185740/ /pubmed/37205277 http://dx.doi.org/10.1016/j.adro.2023.101234 Text en © 2023 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Scientific Article
Pillai, Malvika
Shumway, John W.
Adapa, Karthik
Dooley, John
McGurk, Ross
Mazur, Lukasz M.
Das, Shiva K.
Chera, Bhishamjit S.
Augmenting Quality Assurance Measures in Treatment Review with Machine Learning in Radiation Oncology
title Augmenting Quality Assurance Measures in Treatment Review with Machine Learning in Radiation Oncology
title_full Augmenting Quality Assurance Measures in Treatment Review with Machine Learning in Radiation Oncology
title_fullStr Augmenting Quality Assurance Measures in Treatment Review with Machine Learning in Radiation Oncology
title_full_unstemmed Augmenting Quality Assurance Measures in Treatment Review with Machine Learning in Radiation Oncology
title_short Augmenting Quality Assurance Measures in Treatment Review with Machine Learning in Radiation Oncology
title_sort augmenting quality assurance measures in treatment review with machine learning in radiation oncology
topic Scientific Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10185740/
https://www.ncbi.nlm.nih.gov/pubmed/37205277
http://dx.doi.org/10.1016/j.adro.2023.101234
work_keys_str_mv AT pillaimalvika augmentingqualityassurancemeasuresintreatmentreviewwithmachinelearninginradiationoncology
AT shumwayjohnw augmentingqualityassurancemeasuresintreatmentreviewwithmachinelearninginradiationoncology
AT adapakarthik augmentingqualityassurancemeasuresintreatmentreviewwithmachinelearninginradiationoncology
AT dooleyjohn augmentingqualityassurancemeasuresintreatmentreviewwithmachinelearninginradiationoncology
AT mcgurkross augmentingqualityassurancemeasuresintreatmentreviewwithmachinelearninginradiationoncology
AT mazurlukaszm augmentingqualityassurancemeasuresintreatmentreviewwithmachinelearninginradiationoncology
AT dasshivak augmentingqualityassurancemeasuresintreatmentreviewwithmachinelearninginradiationoncology
AT cherabhishamjits augmentingqualityassurancemeasuresintreatmentreviewwithmachinelearninginradiationoncology