Objective To explore the value of a combined model based on high-kilovoltage CT radiomics and clinical factors for predicting monosodium urate (MSU) crystal deposition in gouty arthritis. Methods The clinical data of 136 patients with MSU crystal deposition adjacent to joints confirmed by dual-energy CT (DECT) and 79 patients with non-MSU calcifications adjacent to joints were retrospectively analyzed. The dataset was randomly divided into a training set (n=150) and a validation set (n=65) at a ratio of 7:3 for the construction of predictive models. Radiomic features were extracted from high-kilovolt (135 kV) images, and 20 radiomic features were selected using minimum redundancy-maximum relevance and least absolute shrinkage and selection operator (LASSO) regression. Logistic regression, light gradient boosting machine (LightGBM), and support vector machine models were built based on the selected features, and the best-performing model was identified. Multivariate logistic regression analysis was used to screen for risk factors associated with MSU crystal deposition adjacent to joints. A nomogram model was then constructed by integrating radiomic features and clinical variables. The diagnostic performance of the models was evaluated by means of the receiver operating characteristics (ROC) area under the curve (AUC). Results Multivariate logistic regression analysis revealed that CT value was an independent risk factor for MSU crystal deposition adjacent to joints (P<0.001). Among the three machine-learning models, the LightGBM model demonstrated the best predictive performance and good dataset robustness. Therefore, the nomogram was constructed using the LightGBM model. The AUCs of the nomogram model for predicting MSU crystal deposition in the training and validation sets were 0.932 and 0.856, respectively, both exceeding 0.85 and significantly higher than those of the clinical model (De-long test, P<0.05). No statistically significant difference was observed between nomogram model and radiomics model (De-long test, P>0.05). Conclusions High-kilovoltage CT radiomics analysis can predict MSU crystal deposition adjacent to joints. The nomogram model and the radiomics model both demonstrate high diagnostic performance, which can provide valuable references for clinical decision-making.