Deng, Jiawen

Abstract RATIONALE Propofol is the first-line sedative for critically-ill, mechanically-ventilated patients, but it can increase serum triglyceride levels. Machine-learning (ML) offers a promising approach for individualized risk stratification of propofol-associated hypertriglyceridemia, enabling proactive triglyceride monitoring and sedation optimization. This study aims to develop and validate ML models to predict hypertriglyceridemia risks in critically-ill patients receiving propofol. METHODS We analyzed retrospective data from adult ICU patients on mechanical ventilation receiving continuous propofol infusion for ≥24 hours across four Mayo Clinic sites from May 2018 to June 2023. The primary outcome was hypertriglyceridemia, defined as serum triglycerides >400 mg/dL within 10 days of starting propofol. Ten-fold cross-validation and leave-one-site-out nested cross-validation (LOSO-CV) were used for model tuning and external validation of our modeling process, respectively. Feature selection was conducted through a union of Boruta and least absolute shrinkage and selection operator (LASSO). While COVID status was a strong predictor of hypertriglyceridemia, we concurrently developed non-COVID models to ensure future relevance in non-pandemic settings. Six ML algorithms (logistic regression, support vector machines, random forests, LightGBM, XGBoost, and multilayer perceptrons) were tuned using Bayesian optimization to minimize cross-entropy loss. Classification thresholds were set to target sensitivity ≥80%. Model performance was evaluated using AUC-ROC, Brier score, sensitivity, and specificity. Models with the highest Youden's Index were designated the best-performing model. Model explainability was assessed using permutation importance and SHapley Additive exPlanations (SHAP). RESULTS We included 3922 eligible patients with triglyceride measurements. Of these, 3042 patients were COVID-negative and used for non-COVID modeling. The best-performing non-COVID models achieved an average AUC-ROC of 0.69 (95% confidence interval [CI] 0.68-0.70), Brier score of 0.12 (95% CI 0.09-0.14), sensitivity of 0.79 (95% CI 0.75-0.83), and specificity of 0.48 (95% CI 0.44-0.52) during LOSO-CV. The best-performing models that included COVID status achieved an average AUC-ROC of 0.71 (95% CI 0.70-0.72), Brier score of 0.13 (95% CI 0.10-0.16), sensitivity of 0.78 (95% CI 0.71-0.84), and specificity of 0.51 (95% CI 0.45 to 0.56) during LOSO-CV. The permutation importance results of the final non-COVID model are shown in the figure. CONCLUSION We have developed sensitive ML models for predicting hypertriglyceridemia risks in critically-ill patients receiving propofol. Although developed during the COVID-19 pandemic, the non-COVID models are more likely to have future relevance, and they have similar performance as models including COVID status. These models will be integrated into a web-based clinical calculator and undergo further validation in prospective studies.

ABSTRACT Ventricular arrhythmias (VA), including ventricular tachycardia and fibrillation, are critical cardiac conditions that are often managed by catheter ablation among those unresponsive to pharmacologic therapy. The choice of anesthesia and sedation regimens for VA ablations may impact arrhythmia inducibility and hemodynamic stability, which can affect procedural success and complication rates. This systematic review and meta-analysis aimed to compare the efficacy and safety of sedation versus general anesthesia (GA) among patients undergoing VA ablation. The review was prospectively registered on PROSPERO (CRD42023441553). Database searches were conducted across five major databases from inception to March 9, 2024 to identify randomized trials or observational studies including adult patients undergoing ablations for VA. Screening and data extraction were completed in duplicate. Risk-of-bias assessments were conducted using ROBINS-I as all included studies were observational, and the quality of evidence was evaluated using the GRADE framework. Six observational studies (N = 16,435) were included. No significant differences were found between sedation and GA for total procedure time (MD: −14.16 minutes; 95%CI: −38.61 to 10.29 minutes), arrhythmia non-inducibility (RR: 0.73; 95% CI: 0.33–1.58), acute ablation success (RR: 1.06; 95% CI: 0.65–1.71), or procedural complications (RR: 0.72; 95% CI: 0.28–1.85). However, sedation was associated with significantly lower intraprocedural hemodynamic instability (RR: 0.28; 95% CI: 0.12–0.70). These findings indicate that while sedation and GA have comparable outcomes, sedation may be associated with less hemodynamic instability during VA ablation. However, more high-quality studies are needed to confirm these results.

Introduction Propofol is a widely used sedative-hypnotic agent for critically ill patients requiring invasive mechanical ventilation (IMV). Despite its clinical benefits, propofol is associated with increased risks of hypertriglyceridemia. Early identification of patients at risk for propofol-associated hypertriglyceridemia is crucial for optimising sedation strategies and preventing adverse outcomes. Machine-learning (ML) models offer a promising approach for predicting individualised patient risks of propofol-associated hypertriglyceridemia. Methods and analysis We propose the development of an ML model aimed at predicting the risk of propofol-associated hypertriglyceridemia in ICU patients receiving IMV. The study will use retrospective data from four Mayo Clinic sites. Nested cross validation (CV) will be employed, with a tenfold inner CV loop for model tuning and selection as well as an outer loop using leave-one-site-out CV for external validation. Feature selection will be conducted using Boruta and least absolute shrinkage and selection operator-penalised logistic regression. Data preprocessing steps include missing data imputation, feature scaling and dimensionality reduction techniques. Six ML algorithms will be tuned and evaluated. Bayesian optimisation will be used for hyperparameter selection. Global model explainability will be assessed using permutation importance, and local model explainability will be assessed using SHapley Additive exPlanations. Ethics and dissemination The proposed ML model aims to provide a reliable and interpretable tool for clinicians to predict the risk of propofol-associated hypertriglyceridemia in ICU patients. The final model will be deployed in a web-based clinical risk calculator. The model development process and performance measures obtained during nested CV will be described in a study publication to be disseminated in a peer-reviewed journal. The proposed study has received ethics approval from the Mayo Clinic Institutional Review Board (IRB #23–0 07 416).

Abstract Rationale Propofol is one of the first-line sedative-hypnotic agents for critically ill adults requiring mechanical ventilation. Although propofol can elevate triglyceride levels, and the latter is a risk factor for pancreatitis, the association between propofol and acute pancreatitis is unclear. Objectives We sought to determine the clinical impact and potential associations between propofol infusion, hypertriglyceridemia, and acute pancreatitis. Methods This is an observational multicenter study of adults (⩾18 yr old) who were admitted to an intensive care unit, who required mechanical ventilation and received continuous propofol infusion for at least 24 hours. The primary outcomes were the frequency of hypertriglyceridemia (>400 mg/dl) and acute pancreatitis. Further analyses were done to determine the clinical impact of elevated triglyceride levels (i.e., sedation changes) and risk factors for pancreatitis development. Results Of 11,828 patients included, 33.2% (n = 3,922) had triglyceride levels measured, of whom 21.7% (n = 851) had hypertriglyceridemia at 4.5 days (SD = 6.8) after propofol initiation. Of those still requiring sedation, 70.4% (n = 576/818) received alternative sedatives after developing hypertriglyceridemia. Pancreatitis occurred in 1.2% of patients (n = 47/3,922) and was more frequent in those with hypertriglyceridemia (3.2%, 27/851; vs. 0.7%, 20/3,071; P < 0.001). After adjustment for potential confounding variables, each 100 mg/dl increase in triglyceride levels was associated with an 11% increase in risk of pancreatitis. Propofol dose was not associated with pancreatitis development. Conclusions Acute pancreatitis is uncommon in patients receiving propofol infusion, and it occurs over a wide range of triglyceride levels, indicating a multifactorial pathophysiology. Hypertriglyceridemia frequently prompts the use of alternative sedatives. Further study is needed to determine how to best monitor and treat hypertriglyceridemia in critically ill patients receiving propofol infusion.

Objective: To assess the efficacy and safety of corticosteroids for the management of pediatric sepsis and septic shock. Data Sources: Ovid MEDLINE, Ovid Embase, CENTRAL, Web of Science (Core Collection) and China National Knowledge Infrastructure were systematically searched up to September 2023. Preprint servers, clinical trial registries and the reference sections of previous reviews were hand-searched. Study Selection: Randomized controlled trials that enrolled pediatric sepsis, septic shock or systemic inflammatory response syndrome patients, compared the use of corticosteroid regimens against standard sepsis care and reported eligible outcomes were included. Title/abstract and full-text screening were conducted in-duplicate. Data Extraction: Eligible articles were extracted using a standardized form in-duplicate. Outcomes extracted include mortality incidence, hospital and pediatric intensive care unit length of stay, duration of shock, incidence of adverse events and serious adverse events and incidence of corticosteroid-related adverse events. The risk of bias was assessed using the Revised Cochrane Risk of Bias Tool for Assessing Randomized Trials. Data Synthesis: Random-effects meta-analyses were conducted, and the quality of evidence was assessed using the Grading of Recommendations, Assessment, Development and Evaluations approach. Sixteen randomized controlled trials (N = 973) were included. Corticosteroid use may be associated with reduced mortality risks (risk ratio: 0.65, 95% CI: 0.50–0.85), shorter length of hospital stay (MD: −3.76 days, 95% CI: −6.66 to −0.86), and shorter pediatric intensive care unit length of stay (MD −2.34 days, 95% CI: −3.14 to −1.53 days). Corticosteroid use may be associated with gastrointestinal bleeding but not a higher risk of secondary infection. No studies reported on serious adverse events. All findings were based on low to very low quality of evidence. Conclusions: While corticosteroids show promise for managing pediatric sepsis and septic shock, the question of how to select the best candidate and the most optimal regimen remains unanswered. Future trials need to focus on assessing corticosteroid-related adverse events and stratifying patient inclusion by sepsis subphenotypes.

AbstractThis systematic review and meta‐analysis of randomised controlled trials (RCTs) aimed to evaluate the efficacy, safety, and tolerability of fluvoxamine for the outpatient management of COVID‐19. We conducted this review in accordance with the PRISMA 2020 guidelines. Literature searches were conducted in MEDLINE, EMBASE, International Pharmaceutical Abstracts, CINAHL, Web of Science, and CENTRAL up to 14 September 2023. Outcomes included incidence of hospitalisation, healthcare utilization (emergency room visits and/or hospitalisation), mortality, supplemental oxygen and mechanical ventilation requirements, serious adverse events (SAEs) and non‐adherence. Fluvoxamine 100 mg twice a day was associated with reductions in the risk of hospitalisation (risk ratio [RR] 0.75, 95% confidence interval [CI] 0.58–0.97; I 2 = 0%) and reductions in the risk of healthcare utilization (RR 0.68, 95% CI 0.53–0.86; I 2 = 0%). While no increased SAEs were observed, fluvoxamine 100 mg twice a day was associated with higher treatment non‐adherence compared to placebo (RR 1.61, 95% CI 1.22–2.14; I 2 = 53%). In subgroup analyses, fluvoxamine reduced healthcare utilization in outpatients with BMI ≥30 kg/m2, but not in those with lower BMIs. While fluvoxamine offers potential benefits in reducing healthcare utilization, its efficacy may be most pronounced in high‐risk patient populations. The observed non‐adherence rates highlight the need for better patient education and counselling. Future investigations should reassess trial endpoints to include outcomes relating to post‐COVID sequelaes. Registration: This review was prospectively registered on PROSPERO (CRD42023463829).