随机森林模型和logistic回归模型在维持性血液透析患者动静脉内瘘失功预测中的应用效果比较

Application of random forest model and logistic regression model in predicting arteriovenous fistula dysfunction in maintenance hemodialysis patients

目的比较随机森林模型和logistic回归模型在维持性血液透析患者动静脉内瘘(AVF)失功预测中的应用效果。方法以2017年5月至2020年11月在温州市某中西医结合医院血液净化中心进行维持性血液透析的588名患者为研究对象,应用随机森林算法、logistic回归分析构建AVF失功模型,用受试者工作特征曲线评价2种模型的预测效能。结果随机森林模型显示老年营养风险指数、碱性磷酸酶、年龄、血小板计数、红细胞比容、钙磷乘积、C反应蛋白、凝血酶原时间、性别、甘油三酯是对AVF失功预测有重要影响的变量。随机森林预测模型的AUC为0.911(95%CI:0.857~0.964,P<0.001),logistic回归预测模型的AUC为0.755(95%CI:0.649~0.862,P<0.001)。随机森林预测模型的AUC大于logistic回归预测模型的AUC(Z=2.600,P=0.009)。多因素logistic回归分析显示年龄(OR=1.035,95%CI:1.017~1.054)、吸烟史(OR=2.543,95%CI:1.457~4.439)、糖尿病史(OR=3.194,95%CI:1.891~5.396)、较高钙磷乘积(OR=1.023,95%CI:1.007~1.039)及透析中低血压(OR=2.393,95%CI:1.064~5.379)是血透患者AVF失功发生的危险因素,营养风险指数升高(OR=0.855,95%CI:0.820~0.891)是血透患者AVF失功发生的保护因素。结论随机森林模型相较于logistic回归模型对AVF失功发生预测效果较好,但logistic回归可直观地解释结果,两者可互为补充。

Objective To compare the performance of random forest model and the logistic regression model in the prediction of arteriovenous fistula(AVF)failure in maintenance hemodialysis patients.Methods Totally 588 patients with maintenance hemodialysis in the Blood Purification Center of Wenzhou Integrated Traditional Chinese and Western Medicine Hospital from May 2017 to November 2020 were enrolled in this study.The random forest algorithm as well as logistic regression analysis were separately applied to construct arteriovenous fistula dysfunction models,and the receiver operating characteristic curve was used to evaluate the predictive efficacy of the 2 models.Results The random forest model showed that geriatric nutritional risk index,alkaline phosphatase,age,platelet count,hematocrit,calcium phosphate product,C-reactive protein,prothrombin time,gender,and triglycerides were variables that had a significant impact on the prediction of the dysfunction of AVF.The AUC of the random forest prediction model was 0.911(95%CI:0.857-0.964,P<0.001)and that of the logistic regression prediction model was 0.755(95%CI:0.649-0.862,P<0.001).The AUC of the random forest prediction model via Z-test was greater than that of the logistic regression prediction model(Z=2.600,P=0.009).Multivariate logistic regression analysis showed that age(OR=1.035,95%CI:1.017-1.054),smoking history(OR=2.543,95%CI:1.457-4.439),diabetes mellitus(OR=3.194,95%CI 1.891-5.396),higher calcium phosphorus product(OR=1.023,95%CI:1.007-1.039),and intradialytic hypotension(OR=2.393,95%CI:1.064-5.379)were independent risk factors for the development of AVF dysfunction in maintenance hemodialysis patients,while higher geriatric nutritional risk index(OR=0.855,95%CI:0.820-0.891)was an independent protective factor for the development of AVF dysfunction.Conclusion Compared with logistic regression model,random forest model has better prediction effect on AVF dysfunction,while logistic regression can intuitively explain the results,and the two can complement each other.