An Explainability Study Associated with Fluid Creep Administration During the First 24 Hours of ICU Admission

Intravenous fluid therapy is one of the most common interventions for hospitalised patients admitted to intensive care. In particular, patients may be subject to a progressive and dangerous accumulation of fluids. In this context, we can define Fluid Creep (FC) as those fluids used to dilute drugs and nutritions and to maintain catheter patency. This single-center, retrospective study was carried out on the MargheritaTre database and included 4786 patients with an average of 1606 ml (1 quartile 849-3 quartile 2000) of FC in the first 24 hours of intensive care unit admission. The objective of this analysis is to identify variables significantly associated with FC, initially by means of a linear model and subsequently by means of a classification model aimed at identifying patients at risk of receiving high FC using explainable artificial intelligence (AI) techniques. After comparing the performance of seven machine learning models, logistic regression was found to be the model with the best accuracy on the test set of 0.76. Therefore, the SHAP (SHapley Additive exPlanations) algorithm was applied to conduct an explainable AI analysis, with the aim of interpreting the behaviour of the model and determining the most relevant variables in classifying the risk of high FC.