Large language models and their current use in perioperative medicine: a scoping review protocol
Bibliographic record
Abstract
OBJECTIVE: 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. INTRODUCTION: 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. ELIGIBILITY CRITERIA: 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. METHODS: 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. REVIEW REGISTRATION: OSF https://osf.io/a3tkw/.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".