Artificial intelligence in oncology

Medical decisions can rely on a very large number of parameters, but it is traditionally considered that our cognitive capacity can only integrate up to five factors in order to take a decision. Oncologists will need to combine vast amount of clinical, biological, and imaging data to achieve state-of-the-art treatments. Data science and artificial intelligence (AI) will have an important role in the generation of models to predict outcome and guide treatments. A new paradigm of data-driven decision-making, reusing routine health-care data to provide decision support is emerging. This chapter explores the studies published in imaging, medical and radiation oncology and explains the technical challenges that need to be addressed before AI can be routinely used to treat cancer patients.