Objective To establish a risk prediction model for postoperative venous thromboembolism(VTE)in patients with gynecological tumors,and to validate the predictive efficacy of the established model.Methods A total of 420 patients with gynecological tumors who underwent surgical treatment at the Second Affiliated Hospital of Guangzhou University of Traditional Chinese Medicine from September 2021 to November 2023 were selected as the research subjects.The 420 patients were divided into modeling group(n=280)and validation group(n=140)according to a ratio of 2∶1.The patients in the modeling group were divided into VTE group(n=42)and non-VTE group(n=238)based on whether they developed VTE after surgery.Univariate and multivariate logistic regression analyses were made to identify the factors related to the occurrence of VTE in patients,and a nomogram model for VTE risk prediction was constructed.Calibration curve,receiver operating characteristic(ROC)curve,and decision curve were used for internal and external validation to evaluate the predictive performance of the nomogram model.Results The univariate analysis results showed that age,body mass index,smoking,previous history of VTE,Caprini score,clinical stage,operation time,and postoperative bed rest time were associated with the occurrence of VTE in patients after surgery(P＜0.05).The multivariate logistic regression analysis results showed that high body mass index,previous history of VTE,Caprini score of 3-4 points and ≥5 points,clinical stage Ⅳ,operation time ≥ 2 hours,and postoperative bed rest time ≥3 days were independent risk factors for VTE in patients with gynecological tumors after surgery(P＜0.05).The calibration curve of the nomogram risk prediction model constructed based on independent risk factors of VTE showed good consistency between the predicted incidence and the actual incidenceof VTE.The ROC curve showed that the area under the curve(AUC)of ROC of the constructed nomogram prediction model was 0.839(95％confidence interval:0.770-0.909),indicating good discrimination.The validation of the model based on the validation set data showed that the AUC of the constructed model for predicting VTE in gynecological tumor patients after surgery was 0.857(95％confidence interval:0.777-0.938),indicating good discrimination.The decision curve showed that the constructed prediction model had good clinical net benefit when the threshold was between 0.18 and 0.80.Conclusion The factors that contribute to the occurrence of VTE in patients with gynecological tumors after surgery include high body mass index,previous history of VTE,Caprini score of 3-4 points and ≥5 points,clinical stage Ⅳ,operation time of ≥2 hours,and postoperative bed rest time of ≥3 days.The nomogram model constructed based on the above risk factors has good predictive performance and clinical applicability.