J Appl Biomed 18:26-32, 2020 | DOI: 10.32725/jab.2020.004

A decision support system for the prediction of mortality in patients with acute kidney injury admitted in intensive care unit

Selda Kayaalti^1,*, Ömer Kayaalti², Bekir Hakan Aksebzeci³

¹ Develi Hatice-Muammer Kocatürk Public Hospital, Department of Anesthesiology and Reanimation, Develi, Kayseri, Turkey

² Kayseri University, Develi Hüseyin Şahin Vocational College, Department of Computer Technologies, Kayseri, Turkey

³ Abdullah Gül University, Faculty of Engineering, Department of Biomedical Engineering, Kayseri, Turkey

Intensive care unit (ICU) is a very special unit of a hospital, where healthcare professionals provide treatment and, later, close follow-up to the patients. It is crucial to estimate mortality in ICU patients from many viewpoints. The purpose of this study is to classify the status of patients with acute kidney injury (AKI) in ICU as early mortality, late mortality, and survival by the application of Classification and Regression Trees (CART) algorithm to the patients' attributes such as blood urea nitrogen, creatinine, serum and urine neutrophil gelatinase-associated lipocalin (NGAL), alkaline phosphatase, lactate dehydrogenase (LDH), gamma-glutamyl transferase, laboratory electrolytes, blood gas, mean arterial pressure, central venous pressure and demographic details of patients. This study was conducted 50 patients with AKI who were followed up in the ICU. The study also aims to determine the significance of relationship between the attributes used in the prediction of mortality in CART and patients' status by employing the Kruskal-Wallis H test. The classification accuracy, sensitivity, and specificity of CART for the tested attributes for the prediction of early mortality, late mortality, and survival of patients were 90.00%, 83.33%, and 91.67%, respectively. The values of both urine NGAL and LDH on day 7 showed a considerable difference according to the patients' status after being examined by the Kruskal-Wallis H test.

Keywords: Acute kidney injury; Classification and regression trees; Lactate dehydrogenase; Mortality prediction; Neutrophil gelatinase-associated lipocalin

Conflicts of interest:

The authors have no conflict of interests to declare.

Received: November 6, 2018; Revised: November 25, 2019; Accepted: February 19, 2020; Prepublished online: February 28, 2020; Published: March 1, 2020  Show citation