腹腔镜前列腺癌根治术后患者静脉血栓栓塞症风险预测模型的构建  

Construction of a risk prediction model for venous thromboembolism in patients after laparoscopic radical prostatectomy

作　　者：马香爱[1] 何有华[2] 俞英[3] 吴洁[1] MA Xiang’ai;HE Youhua;YU Ying;WU Jie(Operating Room,the Second Affiliated Hospital&Yuying Children’s Hospital of Wenzhou Medical University,Wenzhou 325027,China;Department of Urology,the Second Affiliated Hospital&Yuying Children’s Hospital of Wenzhou Medical University,Wenzhou 325027,China;Operating Room,the First Affiliated Hospital of Wenzhou Medical University,Wenzhou 325015,China)

机构地区：[1]温州医科大学附属第二医院育英儿童医院手术室,浙江温州325027 [2]温州医科大学附属第二医院育英儿童医院泌尿外科,浙江温州325027 [3]温州医科大学附属第一医院手术室,浙江温州325015

出　　处：《温州医科大学学报》2025年第2期112-120,共9页Journal of Wenzhou Medical University

基　　金：温州市基础性科研项目(Y2023594)。

摘　　要：目的:构建腹腔镜前列腺癌根治术后患者发生静脉血栓栓塞症(VTE)的风险预测模型。方法:收集2020年1月至2023年12月在温州医科大学附属第二医院育英儿童医院住院治疗的306例腹腔镜前列腺癌根治术后患者数据作为训练集;收集2023年9月至2023年12月在温州医科大学附属第一医院住院治疗的98例同类型患者作为验证集。采用LASSO-Logistic回归分析筛选风险因素,并构建列线图预测模型。应用Hosmer-Lemeshow检验判断模型拟合优度,使用ROC曲线评价模型预测效能,绘制校准曲线评价模型的校准度。结果:BMI≥24 kg/m^(2)、VTE史、手术时间、术中出血量、术后D-二聚体和术后卧床时间是VTE风险因素(P<0.05)。根据以上6个因素联合Caprini评分构建的预测模型Hosmer-Lemeshow检验显示χ^(2)=8.029,P=0.431。训练集和验证集的AUC分别为0.906(95%CI=0.854~0.959)和AUC为0.974(95%CI=0.926~1.000),准确率分别为86.6%和98.0%。校准曲线显示训练集与验证集中的模型校准度较高。结论:该模型预测效果良好,可为临床评估腹腔镜前列腺癌根治术后患者VTE风险提供参考。Objective:To construct a risk prediction model for venous thromboembolism(VTE)in patients after laparoscopic radical prostatectomy.Methods:The data of 306 patients after laparoscopic radical prostatectomy hospitalized in the Second Affiliated Hospital&Yuying Children’s Hospital of Wenzhou Medical University from January 2020 to December 2023 were collected as the training set;98 patients of the same type hospitalized in the First Affiliated Hospital of Wenzhou Medical University from September 2023 to December 2023 were collected as the validation set.Cross-sectional LASSO-Logistic regression analysis was used to screen risk factors and construct a nomogram prediction model.Hosmer-Lemeshow test was applied to determine the model’s goodness of fit.ROC curves to evaluate the predictive efficacy of the model and calibration curves to evaluate the calibration of the model.Results:BMI≥24 kg/m^(2),history of VTE,operative time,intraoperative bleeding,postoperative D-dimer,and postoperative bed rest time were the risk factors for VTE(P<0.05).Hosmer-Lemeshow test of the prediction model constructed based on the above 6 factors combined with Caprini scores showedχ^(2)=8.029,P=0.431.The AUCs of the training and validation sets were 0.906(95%CI=0.854-0.959)and 0.974(95%CI=0.926-1.000),with accuracies of 86.6%and 98.0%,respectively.The calibration curves showed that the model was well calibrated in the training and validation sets.Conclusion:The model demonstrates a good predictive performance which provides reference for assessing VTE risk in patients after laparoscopic radical prostatectomy in clinical practice.

关 键 词：前列腺癌 静脉血栓栓塞症 腹腔镜 风险预测模型 外科护理学 

分 类 号：R737.2[医药卫生—肿瘤]