Can ChatGPT-4o provide new systematic review ideas to oral and maxillofacial surgeons?

Abstract

ObjectiveThis study aims to evaluate the capacity of ChatGPT-4o to generate new systematic review ideas in the field of oral and maxillofacial surgery. The data obtained from this study will provide evidence-based information to oral and maxillofacial surgeons regarding the academic use of GPT-4o. Materials and methodsChatGPT-4o was asked to provide four previously unpublished systematic review ideas each for the topics of impacted third molars, dental implants, orthognathic surgery, and temporomandibular disorders. A literature search was conducted in the PubMed database to check if the ideas generated by GPT-4o had been previously published, and the search results were compared with the ideas generated by the AI. ResultsThe PubMed database search resulted in a total of 871 publications, with 37 publications found to be related to the topics generated by GPT-4o after the first and second screening. Out of the 16 publication ideas generated by GPT-4o, 9 (56.25 %) were determined to be previously unexplored according to the PubMed database search. There was no statistically significant relationship between the presence of ChatGPT's suggestions in PubMed and the subject areas of the studies. ConclusionChatGPT-4o has a high potential to be used as a valuable tool for suggesting systematic review topics in oral and maxillofacial surgery. Additionally, this tool can assist researchers not only in proposing publication ideas but also in developing the methodology of the study.