Large language models and their current use in perioperative medicine: a scoping review protocol

This review aims to map existing evidence on the applications of large language models (LLMs) in perioperative care, including the types of technologies employed, the clinical tasks they support, and the evidence gaps that may influence their future adoption.

The perioperative period-encompassing care from surgical planning through postoperative recovery-is complex and time-sensitive, requiring rapid, accurate, and context-specific decision-making to optimize patient outcomes. LLMs offer new opportunities to streamline workflows, enhance clinical decision support, and personalize patient education. However, their implementation also raises concerns, including risks of error, ethical challenges, and biases inherent in training data. A systematic overview of current applications is needed to guide safe and effective integration of LLMs into perioperative care.

This review will include studies of any design, including randomized and non-randomized trials, case reports, and letters presenting primary data on the use of LLMs in perioperative contexts. Eligible settings span the perioperative continuum, from preoperative assessment and surgical planning to intraoperative support, discharge, and recovery.

This review will adhere to the JBI methodology for scoping reviews. A peer-reviewed search strategy will be used in the databases MEDLINE (Ovid), Embase (Ovid), EBM Reviews (Ovid), and Scopus. Two reviewers will independently identify eligible studies at title and abstract stage and then screen for full texts. Information on study details will be charted in duplicate onto standardized data collection forms. Results will be presented using descriptive summaries, frequency tables, and visual plots that highlight the extent of evidence and remaining gaps.

OSF https://osf.io/a3tkw/.