中心静脉导管堵塞风险预测模型的构建及验证

Establishment and verification of the risk prediction model for central venous catheter occlusion

目的探索中心静脉导管堵塞的风险因素,构建并验证其风险预测模型。方法选择440例置入中心静脉导管的患者,根据导管置入时间按3∶1分为建模组(330例)和验证组(110例)。建模组依据是否发生导管堵塞分组,运用单因素和多因素Logistic回归分析导管堵塞的危险因素,建立中心静脉导管堵塞的风险预测模型。采用H-L检验、ROC曲线评价风险预测模型的预测效果。结果多因素Logistic回归分析结果显示,血栓史、糖尿病、D-二聚体、肠外营养是中心静脉导管堵塞的独立危险因素,其风险预测模型:Y=3×血栓史+1×糖尿病+1×D-二聚体(≥0.5 mg/L)+1×肠外营养。建模组ROC曲线下面积为0.745,H-L检验结果显示,χ^2=9.411,P=0.309。验证组ROC曲线下面积为0.750,H-L检验结果显示,χ^2=14.263,P=0.075。结论血栓史、糖尿病、D-二聚体、肠外营养是中心静脉导管堵塞的独立危险因素。本研究构建的风险预测模型具有较强的鉴别和预测效能,能为临床预防中心静脉导管堵塞提供参考。

Objective To explore the risk factors of central venous catheter(CVC)occlusion,and to establish and verify its risk prediction model.Methods A total of 440 patients with CVC were selected and divided into a modeling group(330 cases)and a validation group(110 cases)chronologically.The modeling group was classified according to whether the catheter was occluded,then the risk factors of occlusion were analyzed using univariate and multivariate logistic regression,and a risk prediction model of CVC occlusion was established.The H-L test and ROC curve were used to evaluate the prediction effect of the risk prediction model.Results Multivariate logistic regression analysis showed that,thrombosis history,diabetes,D-dimer and parenteral nutrition were independent risk factors for CVC occlusion.The risk prediction model was Y=3×thrombosis history+1×diabetes+1×D-dimer(≥0.5 mg/L)+1×parenteral nutrition.The area under the ROC curve of the modeling group was 0.745,and the H-L test result showed χ^2=9.411,P=0.309.The area under the ROC curve of the validation group was 0.750,H-L test result revealed χ^2=14.263,P=0.075.Conclusion History of thrombosis,diabetes,D-dimer,and parenteral nutrition are independent risk factors for CVC occlusion.The established risk prediction model has good identification and predictive performance,and it can provide refe-rence for clinical prevention of CVC occlusion.