Applications and research trends of large language models in healthcare: A bibliometric analysis

Aim: This study aims to reveal the current scientific studies and research trends on the use of Large Language Models (LLM) in the field of health by bibliometric analysis. Material and Methods: Data were sourced from open-access clinical research articles published between 2023 and 2025, extracted from the Web of Science database. A total of 173 articles meeting the inclusion criteria were analyzed using the “Bibliometrix” R package and the “Biblioshiny” interface, focusing on publication trends, co-authorship networks, keyword co-occurrences, and thematic mapping.Results: Results revealed a substantial rise in academic interest in LLMs within healthcare, with significant contributions from researchers in the United States, China, and various European countries. Prominent keywords such as "Artificial Intelligence," "ChatGPT," and "Medical Education" indicate that LLMs are increasingly explored for educational and clinical support applications. Thematic analysis identified emerging research areas including "performance," "health disparities," and "ethical challenges." While LLMs offer considerable opportunities in healthcare, they also present notable risks like data privacy issues, misinformation, and ethical oversight gaps.Conclusion: In conclusion, this study provides a comprehensive overview of LLM applications in healthcare, highlighting key research themes and identifying gaps within the current literature.