Artificial intelligence and medicine have a longstanding and proficuous relationship. In the present work we develop a brief assessment of this relationship with specific focus on machine learning, in which we highlight some critical points which may hinder the use of machine learning techniques for clinical diagnosis and therapy advice in practice. We then suggest a conceptual framework to build successful systems to aid clinical diagnosis and therapy advice, grounded on a novel concept we have coined drifting domains. We focus on oncology to build our arguments, as this area of medicine furnishes strong evidence for the critical points we take into account here.
Highlights:• The relationship between Artificial Intelligence and Medicine is reviewed, highlighting the reasons why few research projects in this field are brought to medical practice.• Focusing on supervised learning applied to diagnosis and therapy plan in oncology, we discuss possible means to overcome this issue.• We present how existing results related to sample complexity in machine learning can be brought to this context to become guidelines to structure and explore results of clinical trials.