Acute Kidney Injury After Cardiac Surgery

This study aimed to develop and validate a machine learning (ML) prediction model of acute kidney injury (AKI) for use in AKI surveillance and management. 15,880 patients aged 18 and above who underwent cardiac surgery between 2017 and 2018 were included in the study. 70% of the observations were randomly selected for training and the remaining 30% for testing. The demographics, comorbidities, laboratory examination parameters, and operation details were used to construct a prediction model for AKI by logistic regression and eXtreme gradient boosting (Xgboost). The discrimination of each model was assessed on the test cohort by the area under the receiver operator characteristic (AUROC) curve, while calibration was performed by the calibration plot. The results showed that Xgboost had a better performance than logistic regression in predicting AKI.