ChatENT: Augmented Large Language Model for Expert Knowledge Retrieval in Otolaryngology - Head and Neck Surgery

Background The recent surge in popularity of Large Language Models (LLMs), such as ChatGPT, has showcased their proficiency in medical examinations and potential contributions to medical education. However, LLMs possess inherent limitations, including inconsistent accuracy, specific prompting requirements, and the risk of generating harmful hallucinations. A domain-specific, fine-tuned model would address these limitations effectively. Methods OHNS-relevant data was systematically gathered from open-access internet sources and indexed into a database. We leveraged Retrieval-Augmented Language Modeling (RALM) to recall this information and used it for pre-training, which was then integrated into ChatGPT 4·0, creating a OHNS specific knowledge Q&A platform known as ChatENT. Findings ChatENT showed enhanced performance in the analysis and interpretation of OHNS information, outperforming ChatGPT 4.0 in both the Canadian Royal College OHNS sample examination questions challenge and the US board practice questions challenge, with a 58.4% and 26·0% error reduction, respectively. ChatENT generated fewer hallucinations and demonstrated greater consistency. Interpretation To the best of our knowledge, ChatENT is the first specialty-specific LLM in the medical field. It appears to have considerable promise in areas such as medical education, patient education, and clinical decision support. The fine-tuned model has demonstrated the capacity to overcome the limitations of existing LLMs, thereby signaling a future of more precise, safe, and user-friendly applications in the realm of OHNS. Funding The authors received no financial support for the research, authorship, and/or publication of this project. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This study did not receive any funding ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors