Innovative regression model-based decision support tool for optimizing radiotherapy techniques in thoracic esophageal cancer

Abstract

BackgroundModern radiotherapy exemplified by intensity-modulated radiation therapy (IMRT) and volumetric modulated arc therapy (VMAT), has transformed esophageal cancer treatment. Facing challenges in treating thoracic esophageal cancer near vital organs, this study introduces a regression model-based decision support tool for the optimal selection of radiotherapy techniques.MethodsWe enrolled 106 patients diagnosed with locally advanced thoracic esophageal cancer in this study and designed individualized IMRT and VMAT radiotherapy plans for each patient. Detailed dosimetric analysis was performed to evaluate the differences in dose distribution between the two radiotherapy techniques across various thoracic regions. Single-factor and multifactorial logistic regression analyses were employed to establish predictive models (P1 and P2) and factors such as TLV/PTV ratio. These models were used to predict the compliance and potential advantages of IMRT and VMAT plans. External validation was performed in a validation group of 30 patients.ResultsUsing predictive models, we developed a data-driven decision support tool. For upper thoracic cases, VMAT plans were recommended; for middle/lower thoracic cases, the tool guided VMAT/IMRT choices based on TLV/PTV ratio. Models P1 and P2 assessed IMRT and VMAT compliance. In validation, the tool showed high specificity (90.91%) and sensitivity (78.95%), differentiating IMRT and VMAT plans. Balanced performance in compliance assessment demonstrated tool reliability.ConclusionIn summary, our regression model-based decision support tool provides practical guidance for selecting optimal radiotherapy techniques for thoracic esophageal cancer patients. Despite a limited sample size, the tool demonstrates potential clinical benefits, alleviating manual planning burdens and ensuring precise, individualized treatment decisions for patients.