Development and Validation of a Web-based Prediction Model for Acute Kidney Injury after surgery

Background and objectives Acute kidney injury after surgery is associated with high mortality and morbidity. The purpose of this study is to develop and validate a risk prediction tool for the occurrence of postoperative acute kidney injury requiring renal replacement therapy. Design, setting, participants, measurements This retrospective cohort study had 2,299,502 surgical patients over 2015-2017 from the American College of Surgeons National Surgical Quality Improvement Program Database (ACS-NSQIP). Eleven predictors were selected for the predictive model: age, history of congestive heart failure, diabetes, ascites, emergency surgery, preoperative serum creatinine, hematocrit, sodium, preoperative sepsis, preoperative acute renal failure and surgery type. The predictive model was trained using 2015-2016 data (n=1,487,724) and further tested using 2017 data (n=811,778). A risk model was developed using multivariate logistic regression and machine learning methods. Main outcomes The primary outcome was postoperative 30-day acute kidney injury requiring renal replacement therapy(AKI-D) Results The unadjusted 30-day postoperative mortality rate associated with AKI-D was 37.5%. The renal risk prediction model had high AUC (area under the receiver operating characteristic curve, training cohort: 0.89, test cohort: 0.90) for postoperative AKI-D. Conclusions This model provides a clinically useful bedside predictive tool for postoperative acute kidney injury requiring dialysis.