May ChatGPT be a tool producing medical information for common inflammatory bowel disease patients’ questions?

Abstract

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.

Introduction

The Chat Generative Pre-trained Transformer (ChatGPT) (www.chat.openai.com) is an artificial intelligence (AI)-based conversational large language model (LLM) chatbot system developed by OpenAI (San Francisco, CA, United States) and released in November 2022[1]. ChatGPT sparked a vigorous debate in the scientific community regarding the application of AI in the scientific literature (e.g., in the writing of scientific articles) by bringing the spotlight to bear on the scientific reliability and accuracy that such a system could offer[2,3].

ChatGPT has also been called upon as a possible bot to answer patients’ questions regarding their diseases, offering, in some cases, the potential for this purpose[4,5]. In gastroenterology, the possible application of ChatGPT is still highly pioneering, little explored, and far from being codified. There has been an interest in ChatGPT in the gastroenterology community, especially in the possibility of being able to answer clinical questions posed by patients and research questions. Concerning the latter, Lahat et al[6], for example, expressed some potential of LLMs in the genesis of research questions, although there is a great need to improve their novelty. Yeo et al[7], on the other hand, showed promising results of ChatGPT in answering clinical questions about liver cirrhosis. Similar results have recently been reported regarding colonoscopy-related medical information (MI)[8].

In inflammatory bowel disease (IBD), medical communication with the patient is crucial, as these diseases affect the patient to three hundred and sixty degrees by directly affecting their quality of life. IBDs are chronic, relapsing-remitting diseases with a particularly complex and multifactorial pathogenesis, mainly including Crohn’s disease (CD) and ulcerative colitis (UC). Therefore, patients must undergo periodic medical check-ups, diagnostic tests, and courses of treatment, often for a lifetime[9,10].

Consequently, in today’s context of widely available technology, patients often access information technology resources to obtain information for managing their IBD. The Internet is a prime tool for this purpose because it offers the patient a considerable window of resources, including social media[11,12] and ChatGPT. Patients often consult these resources independently to conduct targeted research for their concerns, but the physician is often integrated into this process through telehealth tools[13]. This analysis aimed to review the scientific validity of AI-generated outputs provided by ChatGPT regarding the genesis of MI regarding ten questions raised by patients with IBD.

Read more on ChatGPT as a tool producing medical information on IBD

Gravina AG, Pellegrino R, Cipullo M, Palladino G, Imperio G, Ventura A, Auletta S, Ciamarra P, Federico A. May ChatGPT be a tool producing medical information for common inflammatory bowel disease patients’ questions? An evidence-controlled analysis. World J Gastroenterol 2024; 30(1): 17-33, URL: https://www.wjgnet.com/1007-9327/full/v30/i1/17.htm, DOI: https://dx.doi.org/10.3748/wjg.v30.i1.17