Assessing ChatGPT's Responses to Otolaryngology Patient Questions.

Jonathan M CarninoWilliam R PellegriniMegan WillisMichael B CohenMarianella Paz-LansbergElizabeth M DavisGregory A GrilloneJessica R Levi

Published in: The Annals of otology, rhinology, and laryngology (2024)

While ChatGPT exhibits promise in addressing otolaryngology patient questions, this study demonstrates its limitations, particularly in accuracy and comprehensiveness. The identification of potentially dangerous responses underscores the need for a cautious approach to AI in medical advice. Responsible integration of AI into healthcare necessitates thorough assessments of model performance and ethical considerations for patient safety.

Keyphrases

patient safety
healthcare
case report
artificial intelligence
quality improvement
big data
social media
health information