This project designs a novel approach for adaptive radiotherapy treatment of head and neck cancer. Statistical and computational methods are applied to Big Data, collected from cohorts of patients, to tailor precise treatment for a new patient who has similar characteristics to a specific cohort. This award supports initiation of a collaborative research project between four complementary domains: clinical, image analysis and visualization, high-dimensional data management, and statistical learning. The empirically-derived treatment rules developed in this project have the potential to improve the standard of care.
The project defines novel reinforcement learning techniques which account for multidimensional outcomes and patient preferences. The project extends the state of the art by taking into account both spatial data (such as medical images) and nonspatial data (such as demographics and toxicity) in the development of the treatment rules. The approach further takes into account the patient's preference with regard to side effects. The methods developed may be used to derive optimal treatment strategies across not only a variety of cancer diagnoses, but other chronic conditions that require making multiple decisions that must weigh the tradeoffs between efficacy and toxicity, including mental health disorders, substance abuse diseases, and diabetes. This award is supported by the National Institutes of Health Big Data to Knowledge (BD2K) Initiative in partnership with the National Science Foundation Division of Mathematical Sciences.
