Advancing patient care: Machine learning models for predicting grade 3+ toxicities in gynecologic cancer patients treated with HDR brachytherapy.

<h4>Background</h4>Gynecological cancers are among the most prevalent cancers in women worldwide. Brachytherapy, often used as a boost to external beam radiotherapy, is integral to treatment. Advances in computation, algorithms, and data availability have popularized the use of machine l...

Full description

Saved in:
Bibliographic Details
Main Authors: Andres Portocarrero-Bonifaz, Salman Syed, Maxwell Kassel, Grant W McKenzie, Vishwa M Shah, Bryce M Forry, Jeremy T Gaskins, Keith T Sowards, Thulasi Babitha Avula, Adrianna Masters, Jose G Schneider, Scott R Silva
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0312208
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849328761312378880
author Andres Portocarrero-Bonifaz
Salman Syed
Maxwell Kassel
Grant W McKenzie
Vishwa M Shah
Bryce M Forry
Jeremy T Gaskins
Keith T Sowards
Thulasi Babitha Avula
Adrianna Masters
Jose G Schneider
Scott R Silva
author_facet Andres Portocarrero-Bonifaz
Salman Syed
Maxwell Kassel
Grant W McKenzie
Vishwa M Shah
Bryce M Forry
Jeremy T Gaskins
Keith T Sowards
Thulasi Babitha Avula
Adrianna Masters
Jose G Schneider
Scott R Silva
author_sort Andres Portocarrero-Bonifaz
collection DOAJ
description <h4>Background</h4>Gynecological cancers are among the most prevalent cancers in women worldwide. Brachytherapy, often used as a boost to external beam radiotherapy, is integral to treatment. Advances in computation, algorithms, and data availability have popularized the use of machine learning to predict patient outcomes. Recent studies have applied models such as logistic regression, support vector machines, and deep learning networks to predict specific toxicities in patients who have undergone brachytherapy.<h4>Objective</h4>To develop and compare machine learning models for predicting grade 3 or higher toxicities in gynecological cancer patients treated with high dose rate (HDR) brachytherapy, aiming to contribute to personalized radiation treatments.<h4>Methods</h4>A retrospective analysis was performed on gynecological cancer patients who underwent HDR brachytherapy with Syed-Neblett or Tandem and Ovoid applicators from 2009 to 2023. After applying exclusion criteria, 233 patients were included in the analysis. Dosimetric variables for the high-risk clinical target volume (HR-CTV) and organs at risk, along with tumor, patient, and toxicity data, were collected and compared between groups with and without grade 3 or higher toxicities using statistical tests. Seven supervised classification machine learning models (Logistic Regression, Random Forest, K-Nearest Neighbors, Support Vector Machines, Gaussian Naive Bayes, Multi-Layer Perceptron Neural Networks, and XGBoost) were constructed and evaluated. The training process involved sequential feature selection (SFS) when appropriate, followed by hyperparameter tuning. Final model performance was characterized using a 25% withheld test dataset.<h4>Results</h4>The top three ranking models were Support Vector Machines, Random Forest, and Logistic Regression, with F1 testing scores of 0.63, 0.57, and 0.52; normMCC testing scores of 0.75, 0.77, and 0.71; and accuracy testing scores of 0.80, 0.85, and 0.81, respectively. The SFS algorithm selected 10 features for the highest-ranking model. In traditional statistical analysis, HR-CTV volume, Charlson Comorbidity Index, Length of Follow-Up, and D2cc - Rectum differed significantly between groups with and without grade 3 or higher toxicities.<h4>Conclusions</h4>Machine learning models were developed to predict grade 3 or higher toxicities, achieving satisfactory performance. Machine learning presents a novel solution to creating multivariable models for personalized radiation therapy.
format Article
id doaj-art-e57088fe81df41e0b74064d171be2755
institution Kabale University
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-e57088fe81df41e0b74064d171be27552025-08-20T03:47:28ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01205e031220810.1371/journal.pone.0312208Advancing patient care: Machine learning models for predicting grade 3+ toxicities in gynecologic cancer patients treated with HDR brachytherapy.Andres Portocarrero-BonifazSalman SyedMaxwell KasselGrant W McKenzieVishwa M ShahBryce M ForryJeremy T GaskinsKeith T SowardsThulasi Babitha AvulaAdrianna MastersJose G SchneiderScott R Silva<h4>Background</h4>Gynecological cancers are among the most prevalent cancers in women worldwide. Brachytherapy, often used as a boost to external beam radiotherapy, is integral to treatment. Advances in computation, algorithms, and data availability have popularized the use of machine learning to predict patient outcomes. Recent studies have applied models such as logistic regression, support vector machines, and deep learning networks to predict specific toxicities in patients who have undergone brachytherapy.<h4>Objective</h4>To develop and compare machine learning models for predicting grade 3 or higher toxicities in gynecological cancer patients treated with high dose rate (HDR) brachytherapy, aiming to contribute to personalized radiation treatments.<h4>Methods</h4>A retrospective analysis was performed on gynecological cancer patients who underwent HDR brachytherapy with Syed-Neblett or Tandem and Ovoid applicators from 2009 to 2023. After applying exclusion criteria, 233 patients were included in the analysis. Dosimetric variables for the high-risk clinical target volume (HR-CTV) and organs at risk, along with tumor, patient, and toxicity data, were collected and compared between groups with and without grade 3 or higher toxicities using statistical tests. Seven supervised classification machine learning models (Logistic Regression, Random Forest, K-Nearest Neighbors, Support Vector Machines, Gaussian Naive Bayes, Multi-Layer Perceptron Neural Networks, and XGBoost) were constructed and evaluated. The training process involved sequential feature selection (SFS) when appropriate, followed by hyperparameter tuning. Final model performance was characterized using a 25% withheld test dataset.<h4>Results</h4>The top three ranking models were Support Vector Machines, Random Forest, and Logistic Regression, with F1 testing scores of 0.63, 0.57, and 0.52; normMCC testing scores of 0.75, 0.77, and 0.71; and accuracy testing scores of 0.80, 0.85, and 0.81, respectively. The SFS algorithm selected 10 features for the highest-ranking model. In traditional statistical analysis, HR-CTV volume, Charlson Comorbidity Index, Length of Follow-Up, and D2cc - Rectum differed significantly between groups with and without grade 3 or higher toxicities.<h4>Conclusions</h4>Machine learning models were developed to predict grade 3 or higher toxicities, achieving satisfactory performance. Machine learning presents a novel solution to creating multivariable models for personalized radiation therapy.https://doi.org/10.1371/journal.pone.0312208
spellingShingle Andres Portocarrero-Bonifaz
Salman Syed
Maxwell Kassel
Grant W McKenzie
Vishwa M Shah
Bryce M Forry
Jeremy T Gaskins
Keith T Sowards
Thulasi Babitha Avula
Adrianna Masters
Jose G Schneider
Scott R Silva
Advancing patient care: Machine learning models for predicting grade 3+ toxicities in gynecologic cancer patients treated with HDR brachytherapy.
PLoS ONE
title Advancing patient care: Machine learning models for predicting grade 3+ toxicities in gynecologic cancer patients treated with HDR brachytherapy.
title_full Advancing patient care: Machine learning models for predicting grade 3+ toxicities in gynecologic cancer patients treated with HDR brachytherapy.
title_fullStr Advancing patient care: Machine learning models for predicting grade 3+ toxicities in gynecologic cancer patients treated with HDR brachytherapy.
title_full_unstemmed Advancing patient care: Machine learning models for predicting grade 3+ toxicities in gynecologic cancer patients treated with HDR brachytherapy.
title_short Advancing patient care: Machine learning models for predicting grade 3+ toxicities in gynecologic cancer patients treated with HDR brachytherapy.
title_sort advancing patient care machine learning models for predicting grade 3 toxicities in gynecologic cancer patients treated with hdr brachytherapy
url https://doi.org/10.1371/journal.pone.0312208
work_keys_str_mv AT andresportocarrerobonifaz advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT salmansyed advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT maxwellkassel advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT grantwmckenzie advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT vishwamshah advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT brycemforry advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT jeremytgaskins advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT keithtsowards advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT thulasibabithaavula advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT adriannamasters advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT josegschneider advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy
AT scottrsilva advancingpatientcaremachinelearningmodelsforpredictinggrade3toxicitiesingynecologiccancerpatientstreatedwithhdrbrachytherapy