Abstract / Summary
Abstract Objectives Acute kidney injury (AKI) represents a major complication of vancomycin administration, leading to high rates of mortality and treatment failure. This study aimed to construct a risk scoring system for one-year mortality in vancomycin-associated acute kidney injury. Methods Patients diagnosed as vancomycin associated acute kidney injury in the Medical Information Mart for Intensive Care IV (MIMIC-IV) (version 2.0) database, were identified for analysis. Using all-subsets regression and multivariate Cox regression analysis, we identified potential predictors of one-year mortality in vancomycin-associated acute kidney injury and developed a risk score by plotting nomogram. Results 12946 patients were included in the analysis; 9064 and 3882 patients in the training and validation set were randomly divided at a 7:3 ratio, respectively. The predictive factors identified by all-subsets regression and Cox regression analysis were age, BMI, BUN, respiratory rate, infection, AKI stage 2 and 3 and cancer. With the incorporation of these factors, our model had well-fitted calibration curves and achieved good C-indexes of 0.755（95%CI：0.747，0.763）and 0.749（95%CI：0.738，0.761）in predicting one-year survive rate in the training and validation set, respectively. Conclusions The established model in this study is a simplified score system, which provides a robust tool for the prediction of one-year survive rate in AKI patients after receiving vancomycin treatment.