Abstract:Aim To investigate the incremental predictive value of the atherogenic index of plasma (AIP) for atherosclerotic cardiovascular disease (ASCVD) events in patients with hyperuricemia. Methods This dual-center retrospective study included patients with hyperuricemia who were hospitalized between January 2018 and December 2019.The primary outcome was the first occurrence of ASCVD events during follow-up. Data from the First Affiliated Hospital of Guangxi Medical University were used for model development and internal validation, whereas data from Nanning First People's Hospital were used for external validation. Least absolute shrinkage and selection operator (LASSO) regression was used to select baseline predictors. Logistic regression models with and without AIP were constructed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), integrated discrimination improvement (IDI), net reclassification improvement (NRI), Brier score, decision curve analysis (DCA), and Shapley additive explanations (SHAP) analysis. Results The modeling dataset included 633 patients, of whom 267 experienced ASCVD events. The external validation dataset included 132 patients, of whom 40 experienced ASCVD events. LASSO regression selected eight baseline predictors:age, glycated hemoglobin A1c (HbA1c), hypertension, creatinine, diabetes, smoking history, sex, and systolic blood pressure. After the addition of AIP, the AUC in the internal test set increased from 0.809 to 0.838, and the Brier score decreased from 0.173 to 0.158, with an IDI of 0.041 (P=0.008) and an NRI of 0.158 (P=0.005). In the external validation set, the AUC increased from 0.810 to 0.858, and the Brier score decreased from 0.162 to 0.140, with an IDI of 0.061 (P=0.018) and an NRI of 0.283 (P<0.001). Decision curve analysis and SHAP analysis indicated that AIP improved the clinical net benefit of the model and demonstrated relatively high feature importance. Conclusions AIP improves the predictive performance for ASCVD events in patients with hyperuricemia beyond traditional clinical risk factors. It may serve as a potential supplementary marker for risk stratification in this population.