DC3 -- A Diagnostic Case Challenge Collection for Clinical Decision Support

摘要: In clinical care, obtaining a correct diagnosis is the first step towards successful treatment and, ultimately, recovery. Depending on complexity of case, diagnostic phase can be lengthy and ridden with errors delays. Such have high likelihood to cause patients severe harm or even lead their death are estimated cost U.S. healthcare system several hundred billion dollars each year.To avoid errors, physicians increasingly rely decision support systems drawing from heuristics, historic cases, textbooks, guidelines scholarly biomedical literature. The evaluation such systems, however, often conducted in an ad-hoc fashion, using non-transparent methodology, proprietary data.This paper presents DC3, collection 31 extremely difficult case challenges, manually compiled solved by experts. For we present number temporally ordered physician-generated observations alongside eventually confirmed true diagnosis. We additionally provide inferred dense relevance judgments for these cases among PubMed 27 million articles.