Risk Scoring for the Diagnosis of Acute Kidney Injury: A Novel Model Developed for Chronic Kidney Disease Patients in the Emergency Department

Abstract

Introduction: Chronic kidney disease significantly increases the risk of acute kidney injury, and delays in diagnosing acute kidney injury in emergency departments can lead to adverse clinical outcomes. This study aimed to develop a practical and effective tool for assessing the risk of acute kidney injury in patients with chronic kidney disease.

Materials and Methods: This retrospective cohort study was conducted at a state hospital over eight months in 2024, involving 1,500 patients aged 18 years and older with a confirmed diagnosis of chronic kidney disease. Data were extracted from electronic medical records, encompassing demographic, clinical, and laboratory parameters. Risk factors were analyzed using logistic regression, and significant variables were used to develop a scoring system. The model's performance was evaluated using the area under the receiver operating characteristic curve, as well as sensitivity, specificity,

Results: The developed model achieved an operating characteristic curve of 0.75, with a sensitivity of 68% and a specificity of 72%. In univariate analysis, diabetes and hypertension were significant, but not in multivariate analysis. Subgroup analysis revealed improved model performance in patients under 50 years old and those without diabetes.

Conclusion: This study presents a valuable tool for predicting the risk of acute kidney injury in patients with chronic kidney disease, thereby potentially enhancing clinical decision-making and improving patient outcomes. However, prospective studies and applications across diverse patient populations are necessary to enhance the model’s generalizability.