The Effect of Concomitant Sirolimus and Propofol Therapy on Triglyceride Concentrations in Critically Ill Patients

Development and validation of machine-learning models for predicting the risk of hypertriglyceridemia in critically ill patients receiving propofol sedation using retrospective data: a protocol

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).

Protocol for the development and validation of machine-learning models for predicting the risk of hypertriglyceridemia in critically ill patients receiving propofol sedation using retrospective data

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 optimizing sedation strategies and preventing adverse outcomes. Machine learning (ML) models offer a promising approach for predicting individualized patient risks of propofol-associated hypertriglyceridemia.

Methods and analysis

We propose the development of a ML model aimed at predicting the risk of propofol-associated hypertriglyceridemia in ICU patients receiving IMV. The study will utilize retrospective data from four Mayo Clinic sites. Nested cross-validation (CV) will be employed, with a 10-fold 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 LASSO-penalized logistic regression. Data preprocessing steps include missing data imputation, feature scaling, and dimensionality reduction techniques. Six ML algorithms will be tuned and evaluated. Bayesian optimization 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 (SHAP).

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 cross-validation 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 #23-007416).

Strengths and limitations of this study

Robust external validation using a nested cross-validation (CV) framework will help assess the generalizability of models produced from the modeling pipeline across different hospital settings.A diverse set of machine learning (ML) algorithms and advanced hyperparameter tuning techniques will be employed to identify the most optimal model configuration.Integration of feature explainability will enhance the clinical applicability of the ML models by providing transparency in predictions, which can improve clinician trust and encourage adoption.Reliance on retrospective data may introduce biases due to inconsistent or erroneous data collection, and the computational intensity of the validation approach may limit replication and future model expansion in resource-constrained settings.

The Incidence of Propofol-Induced Hypertriglyceridemia and Identification of Associated Risk Factors

Supplemental Digital Content is available in the text.

Objectives:

The objective of this study was to describe the incidence of propofol-induced hypertriglyceridemia and the risk factors associated with hypertriglyceridemia in mechanically ventilated ICU patients while receiving propofol.

Design:

This was a single-center case-control study.

Setting:

Brigham and Women’s Hospital, a tertiary academic medical center in Boston, MA.

Subjects:

Adult ICU patients who received continuous infusion propofol for at least 24 hours from May 1, 2019, to December 31, 2019, were included. Patients were excluded if they were diagnosed with acute pancreatitis upon admission or did not have any serum triglyceride levels evaluated during propofol administration.

Interventions:

None.

Measurements and Main Results:

The major outcome was the incidence and risk factors associated with the development of propofol-induced hypertriglyceridemia, defined as triglyceride level greater than or equal to 400 mg/dL. Minor outcomes included the prevalence of acute pancreatitis. A hybrid multivariate logistic regression analysis was used to evaluate the relation between individual risk factors and the dependent variable of hypertriglyceridemia. During the study period, 552 patients were evaluated for inclusion, of which 136 were included in the final analysis. A total of 38 patients (27.9%) developed hypertriglyceridemia with a median time to hypertriglyceridemia of 47 hours. The only significant independent risk factor for development of hypertriglyceridemia identified was the cumulative propofol dose (odds ratio, 1.04; 95% CI, 1.01–1.08; p = 0.016). Two of the 38 hypertriglyceridemia patients (5.3%) were diagnosed with acute pancreatitis.

Conclusions:

In our analysis, approximately one third of patients developed hypertriglyceridemia with cumulative propofol dose identified as a significant predictor of the development of hypertriglyceridemia. Despite a high incidence of hypertriglyceridemia, a significant number of patients continued propofol therapy, and a relatively low prevalence of pancreatitis was observed. Future analyses are warranted to further investigate these results.