Clinical-Radiomics Nomogram for Risk Prediction of Esophageal Fistula in Patients with Esophageal Squamous Cell Carcinoma Treated by IMRT or VMAT

Abstract

This study aimed to analyze the predictive factors of esophageal fistula (EF) in patients with esophageal squamous cell carcinoma (ESCC) receiving intensity-modulated radiotherapy (IMRT) or Volumetric Modulated Arc Therapy (VMAT), and to establish a prediction model for risk prediction of EF. A total of 479 patients with ESCC treated with IMRT or VMAT from 2013 to 2020 in Xijing hospital were retrospectively analyzed. A total of 43 patients with EF and 129 patients without EF were included in the analysis by 1:3 propensity score matching (time of diagnosis, gender). The clinical risk factors associated with EF were obtained based on univariate logistic regression analysis. Radiomic features were extracted and selected from pre-treatment contrast-enhance computed tomography (CT) to construct radiomic signature. The clinical-radiomics nomogram was constructed based on multivariate stepwise logistic regression. The classification performance of the model was evaluated based on 100 times of 5-fold cross validation. The median OS of the 172 patients included in the analysis was 27.8 months (range 1.3-104.9m), and the median OS of EF patients was lower than that of non-EF patients with 13.1 months (range 1.3-65.3m) vs 49.4 months (range 4.0-104.9m, p<0.001). A total of 1158 radiomics features were extracted and 8 radiomics features were finally selected. The area under the receiver operating characteristic curve (AUC) value of radiomic signature calculated by selected features for predicting EF was 0.794, and it also had the prognostic ability of OS risk stratification (median OS:17.6vs 46.6m, p<0.001). Multivariate analysis showed that the tumor length, tumor volume, T stage, lymphocyte rate and grade 4 esophagus stenosis were related to EF, and the AUC value of clinical nomogram for predicting EF was 0.849. The clinical-radiomics nomogram had the best performance in predicting EF with an AUC value of 0.896. The clinical-radiomics nomogram can predict the risk of EF in ESCC patients, and be helpful for individualized treatment of esophageal cancer.