Construction and validation of a risk prediction model for acute kidney injury in patients after cardiac arrest

Abstract

Objective Identifying patients at high risk for cardiac arrest-associated acute kidney injury (CA-AKI) helps in early preventive interventions. This study aimed to establish and validate a high-risk nomogram for CA-AKI. Methods In this retrospective dataset, 339 patients after cardiac arrest (CA) were enrolled and randomized into a training or testing dataset. The Student’s t-test, non-parametric Mann-Whitney U test, or χ2 test was used to compare differences between the two groups. Optimal predictors of CA-AKI were determined using the Least Absolute Shrinkage and Selection Operator (LASSO). A nomogram was developed to predict the early onset of CA-AKI. The performance of the nomogram was assessed using metrics such as area under the curve (AUC), calibration curves, decision curve analysis (DCA), and clinical impact curve (CIC). Results In total, 150 patients (44.2%) were diagnosed with CA-AKI. Four independent risk predictors were identified and integrated into the nomogram: chronic kidney disease, albumin level, shock, and heart rate. Receiver operating characteristic (ROC) analyses showed that the nomogram had a good discrimination performance for CA-AKI in the training dataset 0.774 (95%CI, 0.715–0.833) and testing dataset 0.763 (95%CI, 0.670–0.856). The AUC values for the two groups were calculated and compared using the Hanley-McNeil test. No statistically significant differences were observed between the groups. The calibration curve demonstrated good agreement between the predicted outcome and actual observations. Good clinical usefulness was identified using DCA and CIC. Conclusion An easy-to-use nomogram for predicting CA-AKI was established and validated, and the prediction efficiency of the clinical model has reasonable clinical practicability.