Advisory Board December 3, 2024
According to a new study published in JAMA Network Open, doctors who used ChatGPT did not perform better when making a diagnosis compared to doctors who only used conventional resources. However, ChatGPT alone performed significantly better than both groups of doctors.
Study details and key findings
For the study, 50 physicians, which included 26 attendings and 24 residents, were given six case histories selected from a larger set of 105 real cases. These cases have been used by researchers since the 1990s but have never been published, meaning the physicians would not have seen them beforehand and OpenAI’s artificial intelligence (AI) chatbot ChatGPT could not have been trained on them.
During the study, the doctors were asked to come up...
Today's Sponsors
Today's Sponsor