Purpose
We aimed to evaluate the performance of ChatGPT within the context of IBD, which is expected to become an increasingly significant health issue in the future. Additionally, the objective of the study was to assess whether ChatGPT serves as a reliable and useful resource for both patients and healthcare professionals.
Methods
For this study, specific 20 questions were identified for the two main components of IBD, which are Crohn's Disease (CD) and Ulcerative Colitis (UC). All the questions for each disease were divided into two categories, directed towards patients and healthcare professionals. The responses were evaluated with seven-point Likert-type reliability and usefulness scales.
Results
The highest scores in both reliability and usefulness were obtained from professional sources (mean 5.00 ± SD 1.21 and mean 5.15 ± SD 1.08, respectively). The ranking in terms of reliability and usefulness, respectively, was as follows: CD (mean 4.70 ± SD 1.26 and mean 4.75 ± SD 1.06) questions, and then UC (mean 4.40 ± SD 1.21 and mean 4.55 ± SD 1.31) questions. The reliability scores of the answers for the professionals were significantly higher than those for the patients (Both raters, p = o.o32).
Conclusion
Despite its realism and usability in IBD diseases, ChatGPT still has some deficiencies and errors. The rectification of ChatGPT's deficiencies and its improvement by developers with more detailed and up-to-date information could make it an important source of information for both patients and medical professionals.