Objective To construct a risk prediction model for central venous catheter-associated deep venous thrombosis(CADVT) in children with congenital heart disease after surgery,and to verify the prediction effect of the model. Methods A total of 234 children hospitalized in the cardiac care unit of a tertiary first-class pediatric hospital in Zhejiang Province from January to November 2021 were conveniently selected as the model building subjects. According to whether CADVT occurred,they were divided into a CADVT group(53 cases) and a non-CADVT group(181 cases). Logistic regression analysis was used to establish the risk prediction model. Hosmer-Lemeshow test was used to determine the goodness of fit of the model. The receiver operator characteristic curve (ROC) was used to test the prediction effect of the model,and a nomogram model was drawn. 60 children with congenital heart disease after surgery in the same hospital from December 2021 to February 2022 were selected as the validation group,and Hosmer-Lemeshow test and ROC curve were used for external verification of the model. Results The incidence of CADVT in children with congenital heart disease after surgery was 22.65%. Intubation duration(OR=1.172),D-dimer concentration(OR=1.169),fibrinogen concentration(OR=3.888),days of sedation(OR=1.538),using of vasoconstrictor(OR=3.554) and pediatric critical illness score(OR=3.308) were its risk factors(P<0.05). The Hosmer-Lemeshow test showed that χ2=4.456,P=0.814,the area under the ROC curve was 0.957(95%CI:0.930~0.984),the optimal critical value was 0.813,the sensitivity was 0.962,and the specificity was 0.851. In the external validation,the sensitivity,specificity and accuracy of the model were 0.857,0.870,86.67%,respectively. Conclusion The risk prediction model constructed in this study has good effects,which can provide a reference for clinical evaluation of the risk of CADVT in children with congenital heart disease after surgery.