Performance and risks of ChatGPT used in drug information: an exploratory real-world analysis.

Benedict MorathUte ChiriacElena JaszkowskiCarolin DeißHannah NürnbergKatrin HörthTorsten Hoppe-TichyKim Green

Published in: European journal of hospital pharmacy : science and practice (2023)

In a real-world sample of 50 drug-related questions, ChatGPT answered the majority of questions wrong or partly wrong. The use of artificial intelligence applications in drug information is not possible as long as barriers like wrong content, missing references and reproducibility remain.

Keyphrases

artificial intelligence
machine learning
big data
deep learning
adverse drug
healthcare
health information
drug induced
social media
electronic health record