Radiotherapy can cause short- and long-term bladder and bowel toxicities, with corresponding quality of life (QoL) detriments, in up to 60% of prostate cancer patients. This study focuses on improving radiation treatment planning with innovative combination of novel datasets and new advances in data science and artificial intelligence. We will use deep learning techniques developed by our research group to predict clinician-rated toxicity and patient-reported outcomes (PROs) using dosiomics (i.e., a recently-developed methodology to create very high-resolution three-dimensional maps of radiation dosage) and radiomics (i.e. imaging of novel tumor features such as shape and texture, that may affect radiation outcomes). We will develop and validate our prediction algorithms using detailed, existing retrospective datasets from 1,948 prostate cancer patients treated with radiation at Moffitt and 794 treated at the VA, respectively. To date, we have built and refined our retrospective data query and we are currently creating the Moffitt radiotherapy QoL database.