Development and Validation of a Model to Predict Acute Kidney Injury Following Wasp Stings: A Multicenter Cohort Study

BackgroundAcute kidney injury (AKI) following wasp stings is a serious and common health hazard, however the early prediction remains challenging. The study aimed to establish a model to predict AKI following wasp stings and validate it.MethodsIn the multicenter prospective cohort study, 508 patients with wasp stings from Jul 2015 to Dec 2019 were randomly divided into the training set (n = 381) and validation set (n = 127) for internal and external validation. A model that based on the multivariable logistic regression analysis was utilized to predict the probability of AKI following wasp stings by a predictive formula and a nomogram. The performances of the model were assessed by using the area under the curve (AUC) and accuracy (ACC) of the receiver operating characteristic curve. The calibration curves were utilized for estimating the consistency between the actual observed outcome and the nomogram predicted AKI probability. Decision curve analysis (DCA) demonstrated the net benefit associated with the use of the nomogram-derived probability for the prediction of AKI following wasp stings.Results Number of stings, hemoglobin (HB) < 110 g/dl, total bilirubin (TBI) > 34 mg/dl, alanine transaminase (ALT) > 40 U/L and activated partial thromboplastin time (APTT) > 47 s were demonstrated as the independent risk factors for AKI following wasp stings (all P value < 0.05) and were incorporated into the model. The performances of the model were validated (AUC = 0.912, ACC = 0.869 and AUC = 0.936, ACC = 0.898 in the training set and validation set respectively). The predictive formula and nomogram of the model could be utilized to predict the AKI following wasp stings, which having sufficient accuracies, good predictive capabilities and good net benefits.ConclusionIn conclusion, we proved that number of stings, HB < 110 g/dl, TBI > 34 mg/dl, ALT > 40 U/L and APTT > 47 s were independence risk factors for AKI following wasp stings. The predictive formula and the individual nomogram of the model might serve as promising predictive tools to assess the probability of the AKI following wasp stings.