Objective This study aims to construct a prediction model based on the Naive Bayes classifier to predict the risk of acute kidney injury (AKI) in asphyxiated neonates in the early stage. Methods The subjects were 79 asphyxiated neonates born and treated at Hospital from September 2022 to December 2024. By collecting clinical data, measuring renal tissue oxygen saturation (RrSO 2 ), and detecting relevant biomarkers, and by combining SMOTE oversampling technique and Recursive Feature Elimination Cross-validation (RFECV) algorithm, six key variables (Cystatin-C, RrSO 2 , oliguria, lactate, β 2 -microglobulin, and creatinine) were selected to build the prediction model. Interpretable machine learning methods were used to explain the established model, and a nomogram for calculating the disease probability of the research subjects was plotted. Results The model achieved an accuracy of 0.929, sensitivity of 0.889, and specificity of 1.000 on the training set; on the testing set, it achieved an accuracy of 0.826, sensitivity of 0.846, and specificity of 0.800. Conclusions The study shows that this model can provide a reliable reference for the early assessment of AKI risk in clinical practice, thus helping improve the prognosis of asphyxiated neonates. Future research needs to expand the sample size and conduct multicenter validation to further optimize the model.
Zhang et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: