Identifying Acute Kidney Injury Trajectory Phenotypes Associated with Hospital Mortality

Acute kidney injury (AKI) is a complex systemic syndrome associated with high morbidity and mortality and risk for the subsequent development of kidney and non-kidney complications. Nearly 50% of patients in the intensive care unit (ICU) experience AKI. AKI severity is a key metric for evaluating patients risk of hospital mortality. Current AKI serum creatinine (SCr) stratification is based on absolute changes in Serum Creatinine (SCr) and the maximal increase relative to the patients baseline value. However, such characterization does not include either the progression or duration of AKI, both of which are associated with adverse outcomes. In this article, by leveraging a large volume of SCr temporal variabilities within the first 7 days of ICU stay, we propose a novel model called Trajectory of Acute Kidney Injury (TAKI) for the identification of AKI trajectory subtypes. Experimental results demonstrate that TAKI is a feasible method of AKI subtyping and superior to the current AKI KDIGO definition for the association with hospital mortality in this subset of critically ill patients.