Published online Jan 7, 2024. doi: 10.3748/wjg.v30.i1.17
Peer-review started: November 4, 2023
First decision: November 30, 2023
Revised: December 7, 2023
Accepted: December 28, 2023
Article in press: December 28, 2023
Published online: January 7, 2024
Processing time: 63 Days and 5.1 Hours
Artificial intelligence is increasingly entering everyday healthcare. Large language model (LLM) systems such as Chat Generative Pre-trained Transformer (ChatGPT) have become potentially accessible to everyone, including patients with inflammatory bowel diseases (IBD). However, significant ethical issues and pitfalls exist in innovative LLM tools. The hype generated by such systems may lead to unweighted patient trust in these systems. Therefore, it is necessary to understand whether LLMs (trendy ones, such as ChatGPT) can produce plausible medical information (MI) for patients. This review examined ChatGPT’s potential to provide MI regarding questions commonly addressed by patients with IBD to their gastroenterologists. From the review of the outputs provided by ChatGPT, this tool showed some attractive potential while having significant limitations in updating and detailing information and providing inaccurate information in some cases. Further studies and refinement of the ChatGPT, possibly aligning the outputs with the leading medical evidence provided by reliable databases, are needed.
Core Tip: Patients with inflammatory bowel disease (IBD) increasingly access information resources online to receive information about disease management. Emerging artificial intelligence (AI) systems such as Chat Generative Pre-trained Transformer (ChatGPT) are taking hold in the daily reality of many patients with IBD. Through them, patients can potentially understand these systems as reliable or substitutes for medical consultation, especially for issues about reluctantly talking to their gastroenterologist. This review, examining ChatGPT’s outputs to common questions from patients with IBD, outlined how, while this AI system can provide some medical information, there are some limitations related to poor updating and the risk of inaccuracies that push for its cautious use.