Deconstructing the diagnostic reasoning of human versus artificial intelligence

Artificial intelligence (AI) is often presented as the future of medical practice. The concept of AI was developed in the 1950s and has been defined as “the use of a computer to model intelligent behaviour with minimal human intervention.” 1 It is an alternative to human intelligence, particularly as a replacement for the diagnostic skill of physicians. For several years, the scientific literature and lay media have commented that nonhuman intelligence could equal or even exceed human intelligence in diagnostic tasks.2 Human intelligence is evident in the concept of clinical reasoning, 3 which has been defined as “the internal mental processes that a physician uses when approaching clinical situations.”4 This central component of physicians’ competence, once honed, allows them to make diagnoses.3 In medicine, clinical reasoning is often understood from the perspective of cognitive psychology’s information process theory.4 Artificial intelligence may refer to several different methods. Most AI diagnostics are based on machine learning algorithms that are “intelligent” enough to handle difficult and complex problems; algorithms rely on human intelligence for their creation.5 Recently, substantial progress has been made in this field through the resurgence of neural networks — a family of methods of machine learning — and particularly deep neural networks.6 Herein, we focus mainly on machine learning (specifically deep neural networks). We analyze the differences in the ways humans and AI approach diagnostic reasoning to argue that human reasoning will not become obsolete in medical diagnosis.