The role of Artificial Intelligence in Celiac disease support: analyzing ChatGPT's effectiveness for healthcare providers and patients

Authors : Yunus Halil Polat, Rasim Eren Cankurtaran

Pages : 326-330

Doi:10.38053/acmj.1649283

View : 53 | Download : 83

Publication Date : 2025-05-30

Article Type : Research Paper

Abstract :Aims: Celiac disease is a significant autoimmune disorder that affects a substantial portion of the population, necessitating accurate and reliable information for effective management. Despite its importance, there are currently no studies assessing the performance of Artificial Intelligence (AI) language models, such as ChatGPT, in providing information on this condition. This study aims to evaluates the reliability and usefulness of ChatGPT\\\'s responses to frequently asked questions regarding celiac disease, thereby filling a critical gap in understanding the capabilities of AI in this important healthcare context. Methods: A total of 20 questions (10 for patients/caregivers and 10 for healthcare professionals) were prepared based on the most frequently searched queries about celiac disease using Google Trends. Responses generated by ChatGPT and scored by two independent Likert raters. Results: The analysis revealed strong inter-rater reliability, with Cronbach’s alpha values of α=0.839 for reliability and α=0.753 for usefulness, indicating robust agreement between raters. Notably, the highest reliability and usefulness scores for the patient and caregiver group were associated with questions on symptoms, the celiac disease diet, and gluten-free products. For the healthcare professionals group, key topics included diagnosis, pathological classification, and celiac disease comorbidities. Importantly, no significant differences were found between raters in the evaluation of reliability (p=0.939) and usefulness (p=0.102). Conclusion: This study demonstrates that AI-based language models like ChatGPT can serve as reliable and useful resources for both patients and healthcare professionals seeking information about celiac disease. While the model excelled in addressing commonly discussed topics, it revealed limitations in handling complex issues, emphasizing the need for ongoing refinement of AI tools. These findings support the integration of AI in healthcare communication, highlighting its potential to enhance access to crucial health information while underscoring the importance of continual improvement to meet diverse user needs.
Keywords : Celiac disease, chatGBT, artificial intelligence

ORIGINAL ARTICLE URL