AI in Medicine News ・ ⚠️ Safety, errors and bias

Medical chatbots resist unnecessary tests, but waver where doctors disagree

Bioengineer.org · 10/21 03:28 UTC

Six large language models rarely discouraged medically indicated care. They became less consistent when recommending unnecessary tests in areas where clinical experts themselves disagree.

Read the original (Bioengineer.org)

See it in the digest → ・ See this issue →