Portocarrero-Bonifaz Andres, Syed Salman, Kassel Maxwell, McKenzie Grant W, Shah Vishwa M, Forry Bryce M, Gaskins Jeremy T, Sowards Keith T, Avula Thulasi Babitha, Masters Adrianna, Schneider Jose G, Silva Scott R
Department of Radiation Oncology, Brown Cancer Center, University of Louisville School of Medicine, Louisville, Kentucky, United States of America.
Department of Radiation Oncology, Mayo Clinic, Jacksonville, Florida, United States of America.
PLoS One. 2025 May 14;20(5):e0312208. doi: 10.1371/journal.pone.0312208. eCollection 2025.
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.
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.
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.
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.
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.
妇科癌症是全球女性中最常见的癌症之一。近距离放射治疗通常作为外照射放疗的补充，是治疗的重要组成部分。计算、算法和数据可用性的进步使机器学习在预测患者预后方面的应用得到普及。最近的研究应用了逻辑回归、支持向量机和深度学习网络等模型来预测接受近距离放射治疗患者的特定毒性。
开发并比较用于预测接受高剂量率（HDR）近距离放射治疗的妇科癌症患者3级或更高毒性的机器学习模型，旨在为个性化放射治疗做出贡献。
对2009年至2023年使用Syed-Neblett或串联卵圆体施源器接受HDR近距离放射治疗的妇科癌症患者进行回顾性分析。应用排除标准后，233例患者纳入分析。收集高危临床靶区（HR-CTV）和危及器官的剂量学变量，以及肿瘤、患者和毒性数据，并使用统计检验比较有和没有3级或更高毒性的组之间的数据。构建并评估了7种监督分类机器学习模型（逻辑回归、随机森林、K近邻、支持向量机、高斯朴素贝叶斯、多层感知器神经网络和XGBoost）。训练过程在适当的时候包括顺序特征选择（SFS），然后进行超参数调整。使用25%的保留测试数据集来表征最终模型的性能。
排名前三的模型是支持向量机、随机森林和逻辑回归，F1测试分数分别为0.63、0.57和0.52；规范MCC测试分数分别为0.75、0.77和0.71；准确率测试分数分别为0.80、0.85和0.81。SFS算法为排名最高的模型选择了10个特征。在传统统计分析中，有和没有3级或更高毒性的组之间，HR-CTV体积、Charlson合并症指数、随访时间和直肠D2cc有显著差异。
开发了机器学习模型来预测3级或更高毒性，取得了令人满意的性能。机器学习为创建用于个性化放射治疗的多变量模型提供了一种新的解决方案。
