Development and internal validation of a prediction model for acute kidney injury following cardiac valve replacement surgery

Abstract

BackgroundAcute kidney injury (AKI) is a common complication after cardiac surgery. This study aims to develop and validate a risk model for predicting AKI after cardiac valve replacement surgery. MethodsData from patients undergoing surgical valve replacement between January 2015 and December 2018 in our hospital were retrospectively analyzed. The subjects were randomly divided into a derivation cohort and a validation cohort at a ratio of 7:3. The primary outcome was defined as AKI within 7 days after surgery. Logistic regression analysis was conducted to select risk predictors for developing the prediction model. Receiver operator characteristic curve (ROC), calibration plot and clinical decision curve analysis (DCA) will be used to evaluate the discrimination, precision and clinical benefit of the prediction model. ResultsA total of 1159 patients were involved in this study. The prevalence of AKI following surgery was 37.0% (429/1159). Logistic regression analysis showed that age, hemoglobin, fibrinogen, serum uric acid, cystatin C, bicarbonate, and cardiopulmonary bypass time were independent risk factors associated with AKI after surgical valve replacement (all P < 0.05). The areas under the ROC curves (AUCs) in the derivation cohort and the validation cohort were 0.777 (95% CI 0.744–0.810) and 0.760 (95% CI 0.706–0.813), respectively. The calibration plots indicated excellent consistency between the prediction probability and actual probability. DCA demonstrated great clinical benefit of the prediction model. ConclusionsWe developed a prediction model for predicting AKI after cardiac valve replacement surgery that was internally validated to have good discrimination, calibration, and clinical practicability.