Automated clinical decision support system with deep learning dose prediction and NTCP models to evaluate treatment complications in patients with esophageal cancer

•Deep learning (DL) is used to predict the radiotherapy dose in esophageal cancer.•This study elaborates an automated tool combining DL models and NTCP models.•The automated model-based approach redirects esophageal cancer patients to PT.•The automated tool succeeds in predicting which patients should be referred to PT.