Development of a Risk Prediction Model for Sepsis-Related Delirium Based on Multiple Machine Learning Approaches and an Online Calculator
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background
Sepsis-associated delirium (SAD) occurs due to disruptions in neurotransmission linked to inflammatory responses from infections. It poses significant challenges in clinical management and is associated with poor outcomes. Survivors often experience long-term cognitive and behavioral issues that impact their quality of life and place a burden on their families. This study aims to create and validate an interpretable machine learning algorithm for predicting SAD. We will also develop an online web calculator based on this model to assist in assessing the risk of SAD onset in clinical settings.
Methods
This study is a retrospective analysis utilizing data from 16120 patients in the Medical Information Mart for Intensive Care IV database. To manage imbalanced data, we applied the SMOTE method. Feature selection was conducted using Multivariate Logistic Regression, Lasso regression, and the Boruta algorithm. We developed predictive models using eight machine learning algorithms and selected the best one for validation. The SHapley Additive exPlanations (SHAP) method was used for visualization and interpretation, enhancing the clinical understanding of the model, alongside the creation of an online web calculator.
Results
We combined three feature selection methods to identify 17 key features for our machine learning prediction model. The Gradient Boosting Machine showed strong calibration and excellent predictive performance in the internal validation set. The SHAP feature importance ranking revealed five critical risk factors for predicting outcomes: Glasgow Coma Scale, ICU Day, Chloride, Sodium, and Sequential Organ Failure Assessment. Based on this optimal model, we successfully developed an online web calculator.
Conclusion
We developed a machine learning predictive model for SAD that showed strong performance and clinical utility in accurately predicting SAD. Additionally, we created a user-friendly web calculator to help healthcare professionals identify SAD early, allowing for timely treatment adjustments and improved patient outcomes.
