Diagnosis is an especially tantalizing application for generative AI: Even when given tough cases that might stump doctors, the large language model GPT-4 has solved them surprisingly well.
But a new study points out that accuracy isn’t everything — and shows exactly why health care leaders already rushing to deploy GPT-4 should slow down and proceed with caution. When the tool was asked to drum up likely diagnoses, or come up with a patient case study, it in some cases produced problematic, biased results.
“GPT-4, being trained off of our own textual communication, shows the same — or maybe even more exaggerated — racial and sex biases as humans,” said Adam Rodman, a clinical reasoning researcher who co-directs the iMED Initiative at Beth Israel Deaconess Medical Center and was not involved in the research.
About the Author Reprints
Exciting news! STAT has moved its comment section to our subscriber-only app, STAT+ Connect. Subscribe to STAT+ today to join the conversation or join us on Twitter, Facebook, LinkedIn, and Threads. Let's stay connected!
To submit a correction request, please visit our Contact Us page.