AUTHOR=Ye Fengsong , Xu Lixia , Ren Yao , Xia Bing , Chen Xueqin , Ma Shenlin , Deng Qinghua , Li Xiadong 

TITLE=Predicting radiation pneumonitis in lung cancer: a EUD-based machine learning approach for volumetric modulated arc therapy patients

JOURNAL=Frontiers in Oncology

VOLUME=Volume 14 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2024.1343170

DOI=10.3389/fonc.2024.1343170

ISSN=2234-943X

ABSTRACT=This study aims to develop an optimal machine learning model that uses lung equivalent uniform dose (LEUDlung EUD) to predict radiation pneumonitis (RP) occurrence in lung cancer patients treated with volumetric modulated arc therapy (VMAT). We analyzed a cohort of 77 patients diagnosed with locally advanced squamous cell lung cancer (LASCLC) receiving concurrent chemoradiotherapy with VMAT. Patients were categorized based on the onset of grade II or higher radiation pneumonitis (RP 2+). Dose volume histogram data, extracted from the treatment planning system, were used to compute the lung LEUDEUD values for both groups using a specialized numerical analysis code. We identified the parameter α, representing the most significant relative difference in LEUDlung EUD between the two groups. The predictive potential of variables for RP2+, including physical dose metrics, LEUDlung EUD, normal tissue complication probability (NTCP) from the Lyman-Kutcher-Burman (LKB) model, and LEUDlung EUD-calibrated NTCP for affected and whole lung, underwent both univariate and multivariate analyses. Relevant variables were then employed as inputs for machine learning models: multiple logistic regression (MLR), support vector machine (SVM), decision tree (DT), and Knearest neighbor (KNN). Each model's performance was gauged using the area under the curve (AUC), determining the best-performing model. The optimal α-value for LEUDlung EUD was 0.3, maximizing the relative LEUDlung EUD difference between the RP 2+ and non-RP 2+ groups. A strong correlation coefficient of 0.929 (P < 0.01) was observed between LEUDlung EUD (α = 0.3) and physical dose metrics. When examining predictive capabilities, LEUDlung EUD-based NTCP for the affected lung (AUC: 0.862) and whole lung (AUC: 0.815) surpassed LKB-based NTCP for the respective lungs. The decision tree (DT) model using LEUDlung EUD-based predictors emerged as the superior model, achieving an AUC of 0.98 in both training and validation datasets. The optimal decision tree (DT) model leveraging LEUDlung EUD indicators presents excellent predictive capabilities for RP 2+ in LASCLC patients undergoing VMAT. This model underscores the significance of LEUDlung EUD in enhancing RP prediction accuracy and refining treatment strategies.