Abstract
In radiotherapy (RT) for brain tumors, patient heterogeneity masks treatment effects, complicating the prediction and mitigation of radiation-induced brain necrosis. Therefore, understanding this heterogeneity is essential for improving outcome assessments and reducing toxicity.
We developed a clinically practical pipeline to clarify the relationship between dosimetric features and outcomes by identifying key variables. We processed data from a cohort of 130 patients treated with proton therapy for brain and head and neck tumors, utilizing an expert-augmented Bayesian network to understand variable interdependencies and assess structural dependencies. Critical evaluation involved a three-level grading system for each network connection and a Markov blanket analysis to identify variables directly impacting necrosis risk. Statistical assessments included log-likelihood ratio, integrated discrimination index, net reclassification index, and receiver operating characteristic (ROC).
The analysis highlighted tumor location and proximity to critical structures such as white matter and ventricles as major determinants of necrosis risk. The majority of network connections were clinically supported, with quantitative measures confirming the significance of these variables in patient stratification (log-likelihood ratio = 12.17; P = 0.016; integrated discrimination index = 0.15; net reclassification index = 0.74). The ROC curve area was 0.66, emphasizing the discriminative value of nondosimetric variables.
Key patient variables critical to understanding brain necrosis post-RT were identified, aiding the study of dosimetric impacts and providing treatment confounders and moderators. This pipeline aims to enhance outcome assessments by revealing at-risk patients, offering a versatile tool for broader applications in RT to improve treatment personalization in different disease sites.