Exploiting Machine Learning Technologies to Study the Compound Effects of Serum Creatinine and Electrolytes on the Risk of Acute Kidney Injury in Intensive Care Units

Abstract

Assessing the risk of acute kidney injury (AKI) has been a challenging issue for clinicians in an intensive care unit (ICU) as AKI could lead to many complications and even fatality. However, several early signs of AKI are non-specific and the current clinical practice monitors only the level of serum creatinine and the volume of urine output. Therefore, it is of great medical merit to identify all possible risk factors of AKI. In recent years, a number of studies have reported the associations between several serum electrolytes and AKI. Nevertheless, the compound effects of serum creatinine, blood urea nitrogen (BUN), and clinically relevant serum electrolytes have not been comprehensively investigated. Accordingly, we initiated this study aiming to develop machine learning models that not only illustrate how these factors interact with each other but also provide new insights for developing new clinical practices to assess AKI risk. Our analyses reveal that among the factors investigated the levels of serum creatinine, chloride, and magnesium are the major risk factors associated with the development of AKI in ICUs.