Development of Acute Kidney Injury Predictor Score in Intensive Care Unit Patients in Padang, Indonesia

Abstract

Objective. This study aims to develop and create a specialized acute kidney injury (AKI) predictor score for the intensive care unit (ICU) patients in Padang, Indonesia.

Patients and Methods. This study was a prospective observational study on 352 ICU patients at three specialized hospitals in Padang City; Dr. M. Djamil General Hospital, Dr. Rasidin General Hospital, and Siti Rahmah Islamic Hospital. Data regarding demographics, clinical characteristics, laboratory results, and outcomes related to AKI were gathered. The factors that predict AKI were identified using multivariate logistic regression analysis to determine independent factors. The predictor scores were created using regression coefficients and then internally confirmed.

Results. Out of a total of 352 patients, 128 individuals (36.4%) suffered from AKI. Factors that independently predict the occurrence of AKI include age over 60 years old, having a history of chronic kidney disease, having sepsis, need for vasopressors, and having creatinine level 1.3 mg/dL (IQR 1.0-1.8) upon admission to ICU. An area under the curve (AUC) of 0.85 (95% CI 0.80-0.90) indicated the strong performance of the constructed predictor score.

Conclusion. The constructed AKI predictor score a scale factor of 10, resulting in a range of 0–10 for the AKI predictor score. It demonstrates a good level of accuracy in predicting AKI in ICU patients in Padang. This score can be used by healthcare professionals to quickly identify and categorize individuals based on their risk level, facilitating timely intervention and personalized treatment.