AUTHOR=Gao Zejun , Ge Jinlin , Xu Ruoshi , Chen Xiaoyan , Cai Zhenzhai 

TITLE=Potential application of ChatGPT in Helicobacter pylori disease relevant queries

JOURNAL=Frontiers in Medicine

VOLUME=11

YEAR=2024

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2024.1489117

DOI=10.3389/fmed.2024.1489117

ISSN=2296-858X

ABSTRACT=<sec id="sec1"><title>Background</title><p>Advances in artificial intelligence are gradually transforming various fields, but its applicability among ordinary people is unknown. This study aims to explore the ability of a large language model to address <italic>Helicobacter pylori</italic> related questions.</p></sec><sec id="sec2"><title>Methods</title><p>We created several prompts on the basis of guidelines and the clinical concerns of patients. The capacity of ChatGPT on <italic>Helicobacter pylori</italic> queries was evaluated by experts. Ordinary people assessed the applicability.</p></sec><sec id="sec3"><title>Results</title><p>The responses to each prompt in ChatGPT-4 were good in terms of response length and repeatability. There was good agreement in each dimension (Fleiss’ kappa ranged from 0.302 to 0.690, <italic>p</italic> &lt; 0.05). The accuracy, completeness, usefulness, comprehension and satisfaction scores of the experts were generally high. Rated usefulness and comprehension among ordinary people were significantly lower than expert, while medical students gave a relatively positive evaluation.</p></sec><sec id="sec4"><title>Conclusion</title><p>ChatGPT-4 performs well in resolving <italic>Helicobacter pylori</italic> related questions. Large language models may become an excellent tool for medical students in the future, but still requires further research and validation.</p></sec>