Search

A systematic review and meta-analysis was conducted to assess the performance of ChatGPT, an artificial intelligence language model, in medical examinations. The study analyzed 19 articles that reported ChatGPT's performance in various medical fields, such as plastic surgery, anesthesia, and diabetes. The overall performance of ChatGPT ranged from 40% to 100%, with a mean performance of 61.1%. The study suggests that ChatGPT has the potential to be a useful educational tool in medical education, but caution should be exercised in its use for examination preparation. Future research is needed to explore the role of AI chatbots in medical education. [Extracted from the article]