ABSTRACT
Integrating a large and heterogeneous amount of data is challenging. This chapter introduces the concept of big data and the specificities of this approach in the medical field. It details the opportunities of data science applied to radiation oncology as a tool for treatment planning and predictive modeling. The chapter explains the main requirements for the implementation of a precision medicine program relying on big data. Big data in radiation oncology means studying large cohorts of patients and integrating heterogeneous types of data. Using these types of data through machine learning holds great promises for identifying patterns beyond human comprehension. Radiation oncology is one of the most interesting fields of medicine for big data analytics because treatment planning and delivery data are very structured. The chapter explores the challenges data scientists face: Means of heterogeneity management and data curation, storage, and access are all mandatory before analysis can actually start.
