Large language models in perioperative medicine—applications and future prospects: a narrative review
Bibliographic record
Abstract
PURPOSE: Large language models (LLMs) are a subset of artificial intelligence (AI) and linguistics designed to help computers understand and analyze human language. Clinical applications of LLMs have recently been recognised for their potential enhanced analytic capacity. Availability and performance of LLMs are expected to increase substantially over time with a significant impact on patient care and health care provider workflow. Despite increasing recognition of LLMs, insights on the utilities, associated benefits and limitations are scarce among perioperative clinicians. In this narrative review, we delve into the functionalities and prospects of existing LLMs and their clinical application in perioperative medicine. Furthermore, we summarize challenges and constraints that must be addressed to fully realize the potential of LLMs. SOURCE: We searched MEDLINE, Google Scholar, and PubMed® databases for articles referencing LLMs in perioperative care. PRINCIPAL FINDINGS: We found that in the perioperative setting (from surgical diagnosis to discharge postoperatively), LLMs have the potential to improve the efficiency and accuracy of health care delivery by extracting and summarizing clinical data, making recommendations on the basis of these findings, as well as addressing patient queries. Moreover, LLMs can be used for clinical decision-making support, surveillance tools, predictive modelling, and enhancement of medical research and education. CONCLUSIONS: The integration of LLMs into perioperative medicine presents a significant opportunity to enhance patient care, clinical decision-making, and operational efficiency. These models can streamline processes, provide personalized patient education, and offer robust decision support. Nevertheless, their clinical implementation requires addressing several key challenges, including managing hallucinations, ensuring data security, and mitigating inherent biases. If these challenges are met, LLMs can revolutionize perioperative practice, improving both patient outcomes and clinician workflow.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.006 | 0.006 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".