Abstract: Objective:To investigate factors associated with mitral valve calcification (MVC) in maintenance dialysis patients and to construct a multidimensional risk discrimination model. Methods:A total of 1642 maintenance dialysis patients from four dialysis centers in Jiangsu Province,China,between January 2020 and June 2023 were included. Skeletal muscle density (SMD) was measured using multidetector spiral computed tomography.The least absolute shrinkage and selection operator (Lasso) regression was applied to identify independent factors associated with MVC,which were then incorporated into a multivariable logistic regression to develop a risk discrimination model and a visualized nomogram. The incremental value of SMD was assessed.Model performance was evaluated using receiver operating characteristic (ROC) curves,calibration plots,Hosmer-Lemeshow goodness-of-fit test,decision curve analysis (DCA),net reclassification improvement (NRI),and integrated discrimination improvement (IDI).Stratified analyses were performed to verify model robustness. Results:MVC was present in 289 patients (17.60%) and absent in 1353 patients (82.40%).Lasso and multivariable logistic regression analyses showed that age,dialysis vintage,alkaline phosphatase (ALP),and parathyroid hormone (PTH) were positively associated with MVC,whereas SMD,lymphocyte-to-monocyte ratio (LMR),and apolipoprotein A1 (ApoA1) were negatively associated.Incorporation of SMD into the model slightly increased the area under the ROC curve (training set:0.780vs0.772,P=0.267; validation set:0.739vs0.731,P=0.513) and significantly improved both IDI (0.024) and NRI (0.316).No significant interaction effects were identified in stratified analyses. Conclusion:The nomogram-based risk discrimination model incorporating SMD,age,dialysis vintage,ALP,PTH,LMR,and ApoA1 demonstrated good discriminative ability for MVC occurrence in maintenance dialysis patients.This model may facilitate early identification of high-risk patients and guide timely intervention.