ArticleBMC gastroenterology2025
Evaluation of the effectiveness of ChatGPT in supporting the management of autoimmune hepatitis effectiveness of ChatGPT in autoimmune hepatitis.
Article in BMC gastroenterology, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
BACKGROUND/
aimThis study aims to explore ChatGPT's ability to provide comprehensive information on AIH, its potential role in supporting the diagnostic and therapeutic processes for the disease and its broader implications for the use of artificial intelligence in healthcare. MATERIALS AND
methodsA total of 45 questions were designed and organized into 3 groups, each consisting of 15 questions (Group 1, Group 2, Group 3). The questions were categorized based on diffuculty, with Group 1 being the easiest and Group 3 the most challenging. Additionally, 5 case-based questions were formulated and ChatGPT was asked to provide diagnoses for these cases. All questions were re-asked after 14 days to evaluate the short-term stability and consistency of the artificial intelligence responses.
resultsThere was no statistically significant difference in the responses provided by ChatGPT initially (p = 0.328). However, when the questions were re-asked after 14 days, a significant difference was observed between the groups in terms of accuracy and completeness (p = 0.045 and p = 0.015, respectively). This difference was primarily due to the lower accuracy level in the responses for group 3 questions. Furthermore, when comparing ChatGPT's responses at 2-week intervals, a statistically significant improvement was noted, except for the completeness score of group 3 questions and the case-based questions.
conclusionOur findings suggest that ChatGPT may play a greater role in patient education and in supporting physicians in disease management. Future studies that test AI-generated responses from multiple perspectives and involve more centers could provide clearer guidance on this topic.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.