AUTHOR=Ni Qianxi , Zhu Jun , Chen Luqiao , Tan Jianfeng , Pang Jinmeng , Sun Xiangshang , Yang Xiaohua TITLE=Establishment and interpretation of the gamma pass rate prediction model based on radiomics for different intensity-modulated radiotherapy techniques in the pelvis JOURNAL=Frontiers in Physics VOLUME=Volume 11 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2023.1217275 DOI=10.3389/fphy.2023.1217275 ISSN=2296-424X ABSTRACT=Background and objectives: Various machine learning(ML)-based models have demonstrated potential as virtual quality assurance tools, being capable of accurately predicting the dose verification results of IMRT or VMAT plans, thereby providing safe and efficient treatment guarantee for patients.However, there has been no research yet that simultaneously integrates different intensity-modulated radiation therapy techniques to predict gamma pass rate(GPR) and explain the model. Methods: Retrospective analysis of the 3D dosimetric verification results based on measurements with GPR criteria of 3%/2 mm and 10% dose threshold of 409 pelvic IMRT and VMAT plans was carried. Radiomic features were extracted from the dose files, from which the XGBoost algorithm based on Shapley additive explanations(SHAP) values was used to select the optimal feature subset as the input for the prediction model. The study employed four different ML algorithms, including random forest(RF), adaptive boosting(AdaBoost), extreme gradient boosting(XGBoost), and light gradient boosting machine(LightGBM) to construct predictive models. Sensitivity, specificity, F1 score, and AUC value were calculated to evaluate the classification performance of these models. The SHAP values were utilized to perform a related interpretive analysis on the best-performing model.The sensitivities and specificities of the RF, AdaBoost, XGBoost, and LightGBM models were 0.96, 0.82, 0.93, and 0.89, and 0.38, 0.54, 0.62, and 0.62, respectively. The F1 scores and area under the curve(AUC) values were 0.86, 0.81, 0.88, and 0.86, and 0.81, 0.77, 0.85, and 0.83, respectively. The explanation of the model output based on SHAP values can provide a reference basis for medical physicist when adjusting the plan, thereby improving the efficiency and quality of treatment plans. Conclusion: It is feasible to use a ML method based on radiomics to establish a GPR classification prediction model for IMRT and VMAT plans in the pelvis. The XGBoost model performs better in classification than the other three tree-based ensemble models, and global explanations and single-sample explanations of the model output through SHAP values may offer reference for medical physicists to provide high-quality plans, promoting the clinical application and implementation of GPR prediction models, and providing safe and efficient personalized QA management for patients.