‘This time is different’: physician knowledge in the age of artificial intelligence

Abstract

Great diagnosticians are often portrayed as recognising rare diseases that evade the efforts of mere mortals. This makes for great TV and local legends, but does not reflect daily practice, where the most common diagnostic challenge is discriminating between common conditions like pneumonia and heart failure or appendicitis and gastroenteritis. Questions about how to train the brain to make those distinctions are central to the efforts of many clinician educators. An unresolved issue is whether the structure of knowledge (about diseases and diagnostic pathways) in the physician’s long-term memory or the clinician’s mode of cognition (intuitive or analytical thinking) is more deterministic of diagnostic success. A study1 in this issue of BMJQS sheds light on this issue, but also invites a broader question: is physician cognition still essential for this task at all? In a two-phase experiment, Mamede et al 1 asked 68 internal medicine residents to recall from memory the key clinical features of six conditions (vitamin B12 deficiency, inflammatory bowel disease, hyperthyroidism, adrenal insufficiency, appendicitis, endocarditis). Physicians were categorised as high knowledge (HK) or low knowledge (LK) based on their recall of discriminating features, which are essential to differentiate one condition from common competing diagnoses. One week later, the residents were given related clinical vignettes and asked to render a diagnosis. Half of the vignettes had a salient distracting feature (SDF), a clinical finding that may prompt the physician to suspect a condition other than the correct diagnosis. For example, a vignette of a confused patient included a family history of dementia, which was irrelevant in the face of strong evidence for vitamin B12 deficiency. The authors used the SDF as a model for activating the anchoring heuristic , which is a tendency to adhere to an early judgement triggered by a data point. Essentially, …