This single-blind randomized clinical trial was conducted to assess the effect of a Large language model (LLM) on physicians' diagnostic reasoning compared with conventional resources.
We recruited 50 physicians with expertise in family medicine, internal medicine, or emergency medicine. Participants were randomized to either access the LLM in addition to conventional diagnostic resources or conventional resources only and allocated 60 minutes to review up to 6 clinical vignettes.
Results showed that the availability of an LLM to physicians as a diagnostic aid did not significantly improve clinical reasoning compared with conventional resources. On the other hand, the LLM alone demonstrated higher performance than both physician groups, indicating the need for technology and workforce development to realize the potential of physician-artificial intelligence collaboration in clinical practice.
【MORE】