Background: Conventional machine learning (ML) models for predicting surgical outcomes have limitations in generalizability. We explored large language models (LLMs) as scalable alternatives to conventional ML models in predicting postoperative outcomes, including in-hospital 30-day mortality, intensive care unit (ICU) admission, and acute kidney injury (AKI). Methods: This study utilized the Informative Surgical Patient for Innovative Research Environment (INSPIRE) dataset (n = 80 985) from South Korea for model development and internal validation, and the Medical Informatics Operating Room Vitals and Events Repository (MOVER) dataset (n = 6265) from the United States for external validation. The study compared three different LLMs—Generative Pre-trained Transformer [GPT]-4o, Llama-3-70B, and OpenBioLLM-70B—against MLs using various prompt engineering approaches. LLMs were evaluated with different model parameter quantizations (4-bit normalized floating point vs. 16-bit brain floating point). Results: OpenBioLLM-70B was comparable to eXtreme Gradient Boosting (XGBoost) across all tasks (in-hospital 30-day mortality: area under receiver operating characteristic curve [AUROC] 0.782 [95% CI, 0.748–0.813] vs. 0.791 [95% CI, 0.753–0.825]; ICU admission: AUROC 0.595 [95% CI, 0.581–0.609] vs. 0.594 [95% CI, 0.580–0.608]; AKI: AUROC 0.830 [95% CI, 0.802–0.855] vs. 0.823 [95% CI, 0.792–0.851]) during external validation. Open-source LLMs maintained performance with 4-bit quantization, reducing computational requirements by 75%. Conclusions The findings support the versatility and efficiency of LLMs for clinical decision support through on-premises compatibility, addressing data privacy. Further validation with diverse datasets is needed to ensure their reliability and applicability across different perioperative settings.

Delirium is a common but serious complication in critically ill patients. Family visitation has been shown to reduce delirium; however, during the coronavirus disease 2019 (COVID-19) pandemic, intensive care units (ICUs) restricted regular visitation to prevent the spread of infection. This study aimed to evaluate the association between visitation policies and incidence of delirium in the ICUs. Methods: This was a retrospective before-and-after study conducted in medical and surgical ICUs at a tertiary hospital. Adult patients admitted to an ICU during one of two periods were included: before the COVID-19 pandemic (June 2017 to May 2019) with regular visitation and during the pandemic (June 2020 to May 2022) with prohibited visitation. Delirium was assessed using the Confusion Assessment Method for the ICU. The primary outcome was association between delirium incidence and visitation policy. Results: Totals of 1,566 patients from the pre-COVID-19 period and 1,404 patients from the COVID-19 period were analyzed. The incidence of delirium was higher during the COVID-19 period (48.1% vs. 38.4%, P<0.001). After adjusting for relevant variables, the restricted visitation policy during COVID-19 remained a risk factor for delirium (odds ratio, 1.37; 95% CI, 1.13–1.65; P=0.001). Conclusions: Complete restriction of ICU visitations during the COVID-19 pandemic was associated with a significant increase in delirium incidence. These findings suggest the importance of visitation policies on patient outcomes and suggest the need for alternative strategies, such as video visitation, to mitigate the adverse effects of visitation restrictions during pandemics.

With the growing interest of researchers in machine learning and artificial intelligence (AI) based on large data, their roles in medical research have become increasingly prominent. Despite the proliferation of predictive models in perioperative medicine, external validation is lacking. Open datasets, defined as publicly available datasets for research, play a crucial role by providing high-quality data, facilitating collaboration, and allowing an objective evaluation of the developed models. Among the available datasets for surgical patients, VitalDB has been the most widely used, with the Medical Informatics Operating Room Vitals and Events Repository recently launched and the Informative Surgical Patient dataset for Innovative Research Environment expected to be released soon. For critically ill patients, the available resources include the Medical Information Mart for Intensive Care, the eICU Collaborative Research Database, the Amsterdam University Medical Centers Database, and the High time Resolution ICU Dataset, with the anticipated release of the Intensive Care Network with Million Patients’ information for the AI Clinical decision support system Technology dataset. This review presents a detailed comparison of each to enrich our understanding of these open datasets for data science and AI research in perioperative medicine.