Add to Favourites
To login click here
This study analyzed ChatGPT responses on 100 urologic patient case studies and evaluated the appropriateness compared to responses from a board-certified urologist. The findings revealed that only 52% of all chatbot responses were considered appropriate, indicating that only one out of every two individuals interacting with ChatGPT regarding urologic concerns will receive a response that aligns with a urologist’s response. Additionally, the study found a discrepancy in the appropriateness of responses between males and females, as well as a higher readability score among responses on emergency urology patients.
