〔Abstract〕 ObjectiveTo analyze the risk factors for long-term cardiovascular events in patients undergoing long-term peritoneal dialysis (PD), and to construct and validate a visual nomogram prediction model based on multiple parameters. MethodsA prospective cohort study was conducted, consecutively enrolling 248 maintenance PD patients (dialysis duration ≥ 3 months). Demographic characteristics, clinical indicators, laboratory parameters, and echocardiographic indices (including left ventricular ejection fraction [LVEF], E/e' ratio, etc.) were collected. The composite endpoint was defined as the occurrence of cardiovascular events or cardiovascular death, with non-cardiovascular death as the competing risk and loss to follow-up or the end of follow-up as censoring events. Fine-Gray competing risks model was used to screen independent predictors, based on which a nomogram model was constructed. Internal validation was performed using the Bootstrap method (1 000 resamplings), and the concordance index (C-index) and time-dependent receiver operating characteristic (time-dependent ROC) curve were calculated to evaluate the model performance. Results With a median follow-up of 29 months (interquartile range: 24–35 months), 88 patients (35.48%) reached the composite endpoint, including 80 cases of cardiovascular events and 8 cases of cardiovascular death, and 4 patients died of non-cardiovascular causes. Multivariate Fine-Gray analysis revealed that age, diabetes mellitus, hemoglobin (HGB) level and E/e' ratio were independent influencing factors of the composite endpoint. Specifically, each 1-year increase in age was associated with a 3.0% increase in the risk of the composite endpoint ( HR=1.030 , P=0.006); patients with diabetes mellitus had a 167.9% higher risk compared with non-diabetic patients ( HR=2.679, P=0.007); each 1g/L increase in HGB level contributed to a 1.5% reduction in the risk ( HR=0.985, P=0.003); and each 0.1 increase in E/e' ratio led to a 7.2% increase in the risk ( HR=1.072, P=0.045). The nomogram model had a C-index of 0.76 (95% CI0.698–0.820), and the AUC of the time-dependent ROC curve reached 0.849 (95% CI0.761–0.938) at 23 months of follow-up. Conclusion Increased age, complicated with diabetes mellitus, decreased HGB, and elevated E/e' ratio are independent risk factors of long-term occurrence of cardiovascular events and cardiovascular death in patients undergoing long-term PD. The nomogram model constructed based on the above variables has good predictive value and clinical applicability, which can provide a reference for cardiovascular risk stratification and individualized intervention in long-term PD patients.