Purpose: Recently, there has been a growing interest in using ChatGPT for various applications in Medicine. We evaluated the interest of OpenAI chatbot (GPT 4.0) for drug information activities at Toulouse Pharmacovigilance Center.
Methods: Based on a series of 50 randomly selected questions sent to our pharmacovigilance center by healthcare professionals or patients, we compared the level of responses from the chatbot GPT 4.0 with those provided by specialists in pharmacovigilance.
Results: Chatbot answers were globally not acceptable. Responses to inquiries regarding the assessment of drug causality were not consistently precise or clinically meaningful.
Conclusion: The interest of chatbot assistance needs to be confirmed or rejected through further studies conducted in other pharmacovigilance centers.
Keywords: Adverse drug reaction; ChatGPT; Drug information service; Pharmacovigilance; Safety.
© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.