Session Item

In this presentation we will first discuss the definition of big data in the context of medicine and oncology. We will explain how Big Data can be leveraged to better personalize treatments: which medical data can be harvested and used? How granular and structured the data should be? What is an ontology and why are they essential for data mining? What is a clinical data warehouse and what are the main platforms available for research? We will then describe the methods used to explore large data sets, with a focus on machine learning. We will highlight the existing methods available to automate treatments (from contouring to dosimetry) and to predict the outcome of a disease. Finally, we will talk about the limits and risks of these new methods. If therapeutic decisions are entirely derived from existing data, what are the implications for the practice and evolution of medicine? Will the radiation oncology professionnals have any actual decision to make in the future? Just like in The Matrix, what will be our role in a world where free will is an illusion and everything can be predicted with high accuracy?