肺癌病人术前静脉血栓栓塞症风险预测模型的构建

Construction of risk prediction model of preoperative venous thromboembolism in lung cancer patients

目的:构建肺癌病人术前静脉血栓栓塞症风险预测模型。方法:选择2017年1月—2019年12月在某三级甲等肿瘤专科医院术前发生静脉血栓栓塞症(VTE)的47例肺癌病人作为病例组,同年度入住同一科室且术前未发生VTE的病人94例为对照组。对两组病人的一般资料、疾病史和实验室检查等信息进行回顾性分析,筛选出危险因素,采用Logistic回归分析构建风险预测模型并对其进行简化。结果:Logistic回归分析结果显示,年龄、D-二聚体、同型半胱氨酸(Hcy)和纤维蛋白原(FIB)浓度4个因素进入模型,Logistic回归方程为:Logit(P)=-3.350+2.790×年龄+2.188×FIB+1.659×Hcy+1.616×D-二聚体。对模型进一步简化评分规则,其对应的受试者工作特征曲线下面积为0.880(P<0.001)。结论:构建的肺癌病人术前静脉血栓栓塞症风险预测模型可以对肺癌病人术前VTE发生风险的预测起到一定的辅助作用,但还需多中心、大样本试验进一步验证和完善。

Objective:To construct the risk prediction model of preoperative venous thromboembolism in lung cancer patients.Methods:From January 2017 to December 2019,a total of 47 lung cancer patients who developed venous thromboembolism(VTE)before surgery in a tertiary grade A tumor specialist hospital were selected as the case group,while 94 patients in the same year were selected as the control group.The general information,disease history and laboratory examinations of the two groups of patients were retrospectively analyzed,and risk factors were screened out.Logistic regression analysis was used to construct and simplify the risk prediction model.Results:Logistic regression analysis showed that age,D-dimer,homocysteine and fibrinogen concentrations entered the model.The logistic regression equation was Logit(P)=-3.350+2.790 age+2.188 fibrinogen+1.659 homocysteine+1.616 D-dimer.The scoring rules were further simplified for the model,and the corresponding area under the receiver operating characteristic curve was 0.880(P<0.001).Conclusions:The constructed risk prediction model of preoperative venous thromboembolism in lung cancer patients can play certain auxiliary role in predicting the risk of preoperative VTE in lung cancer patients,but it needs to be further verified and improved by multi-center and large-sample experiments.