Assessing ChatGPT's capability in understanding and reporting antiretroviral therapy drug–drug interactions (ACCURATE-DDI)

Key Points

• The study aims to evaluate ChatGPT's accuracy and specificity in reporting drug-drug interactions related to antiretroviral therapy.
• Assessment of ChatGPT's generated responses regarding ARV drug interactions.
• Comparison of generated information against established medical literature.
• Evaluation of accuracy metrics based on correct versus incorrect information.
• ChatGPT displayed limited accuracy in identifying drug interactions.
• Responses often mixed accurate and inaccurate information.
• ChatGPT is not recommended as a reliable source for ARV DDI information.

Abstract