Acute Kidney Injury (AKI) occurs frequently in critically ill patients. AKI is associated with increased morbidity and mortality, and a high financial cost. The Kidney Disease/Improving Global Outcomes (KDIGO) working group has defined and classified AKI in three stages of increasing severity, according to serum creatinine levels and urine output. Although no effective treatment currently exists that could attenuate the course of AKI, early prediction of AKI to detect the patients at risk could be a first step in the discovery and assessment of new therapies. For that purpose, we propose an AKI predictor for patients admitted to an intensive care unit (ICU). Using routinely available patient characteristics, the AKI predictor is able to predict if an adult patient will develop any stage of AKI (as defined by the KDIGO serum creatinine criteria) during the first week of ICU stay.
The AKI predictor is based on extensive statistical retrospective analysis of data from a large number of adult ICU patients. The database of the large prospective multicenter randomized EPaNIC clinical trial1 was used to build and validate the predictive models. In this study, 4640 patients were randomized to receive either early or late parenteral nutrition. The models were constructed using Random Forests, a data mining technique. They have good discrimination and are well calibrated in this large cohort of patients.
Three models have been developed according to the timing of availability of clinical information of a critically ill patient in an ICU: a baseline model using only demographic data and data known before ICU admission; an admission model that adds data available upon ICU admission; and a day 1 model that, in addition, uses data available on the first day in ICU. This way, the risk of developing AKI can be estimated before ICU admission, at ICU admission, and after the first 1-24 hours in the ICU.
The parameters used by the models are believed to be available in most ICU patients throughout the world. In addition the models are sparse and use a relatively low amount of attributes. Nevertheless, because they have been developed and validated in the EPaNIC database, the performance and validity of the model in datasets from other centers might be different from the performance in the original EPaNIC dataset. The presented models are a work in progress, and can be further validated and recalibrated using more multicenter data. The models requires prospective external validation.
Marine Flechet graduated in Engineering Sciences with a master in Biomedical Engineering from the University of Liège, Belgium and the EPFL, Switzerland. She was the recipient of the best master’s thesis in Biomedical Engineering award and the best master’s thesis in Engineering award.
Marine Flechet is currently pursuing a PhD in the Department & Laboratory of Intensive Care Medicine at the KU Leuven, Belgium. She focuses on developing clinical prediction models to the patient bedside.
Fabian Güiza graduated in Engineering with a master in Electronics from Bogotá, Colombia and a master in Artificial Intelligence from the KU Leuven, Belgium. He is currently a project leader of the research group at the Department & Laboratory of Intensive Care Medicine at the KU Leuven.
His research interest is the use of artificial intelligence, image processing, data mining and machine learning to analyze medical data, specifically ICU related data.
Miet Schetz is a staff member at the Department & Laboratory of Intensive Care Medicine at the KU Leuven, Belgium and an Associate Professor of the Faculty of Medicine of the KU Leuven.
The major track of Prof. Miet Schetz focuses on Acute Kidney Injury (AKI) and its treatment by extracorporeal techniques. She is a member of the international KDIGO working group, and one of the authors of the KDIGO criteria to define AKI. She is the AKI Section editor for the journal “Intensive Care Medicine”.
Medical doctor specialized in Anesthesiology, in Intensive Care Medicine, in Biostatistics and in Endocrinology, Greet Van den Berghe is head of the Department & Laboratory of Intensive Care Medicine at the KU Leuven, Belgium. She was awarded the FWO Excellence Prize, in recognition of her scientific career.
Greet Van den Berghe is also full Professor of Medicine at the KU Leuven. She is a member of the Belgian Royal Academy of Medicine, a member of the German National Academy of Sciences – Leopoldina, and a fellow of the Royal College of Physicians of Edinburgh. Her research interest focuses on endocrinology of critical illness.
Medical doctor specialized in Anesthesiology and in Intensive Care Medicine, Geert Meyfroidt is currently associate professor of the Faculty of Medicine of the KULeuven and is Deputy Head of Clinic at the Department & Laboratory of Intensive Care Medicine at the UZ Leuven. He is a member of the board of the Belgian Society of Intensive Care Medicine (SIZ).
His research interests are data mining and predictive modelling on data from critically ill patients, with a particular interest in intracranial pressure, cerebrovascular autoregulation, and cerebral oximetry in brain injured patients and critically ill children.
Our group combines a research laboratory with a large intensive care unit (65 beds, over 2500 patients each year), both located on the Health Sciences Campus of Gasthuisberg in Leuven, Belgium. This unique setting allows a very fast and effective interaction among clinicians and basic researchers within the research team, allowing research from “bed to bench and from bench to bed”.