基于LASSO回归下维持性血液透析患者认知功能减退的预测模型构建分析  

Construction of predictive model for cognitive decline in maintenance hemodialysis patients based on LASSO regression

作　　者：樊伟[1] 闻萍[2] 邵丽娜[1] 崔英[1] 张瑾[1] FAN Wei;WEN Ping;SHAO Li-na;CUI Ying;ZHANG Jin(Department of Nephrology,YixinPeoples Hospital of Jiangsu Province,Wuxi 214200,China;Department of Nephrology,The Second Affliliated Hospital of Nanjing Medical University,Nanjing 210003,China)

机构地区：[1]江苏省无锡市宜兴市人民医院肾内科,无锡214200 [2]南京医科大学第二附属医院肾内科,南京210003

出　　处：《中国血液净化》2023年第4期259-263,共5页Chinese Journal of Blood Purification

摘　　要：目的 构建基于LASSO回归下维持性血液透析(maintenance hemodialysis,MHD)患者认知功能减退的预测模型。方法 前瞻性纳入2016年3月~2021年3月于宜兴市人民医院接受MHD治疗的100例患者。采用蒙特利尔认知评估量表(Montreal cognitive assessment,MoCA)将患者分为认知功能障碍(cognitive impairment,CI)组(MocA<26分)、非CI组(MocA≥26分)。收集一般资料及临床资料,用LASSO回归筛选具有非0系数的MHD患者发生CI相关特征因素,构建LASSO-Logistics回归模型,绘制受试者工作特征曲线(ROC)评估模型效能。并选取71例MHD患者的资料行外部验证。结果 最终CI组、非CI组各有62例、38例患者。CI组患者年龄(t=3.164,P=0.002)、透析龄(t=2.915,P=0.004)、高敏C反应蛋白(hs-CRP;t=3.257,P=0.002)、三酰甘油(t=2.235,P=0.028)、总胆固醇(t=2.461,P=0.016)及合并糖尿病(χ^(2)=3.950,P=0.047)高于非CI组,CI组血清白蛋白(t=4.254,P<0.001)、血清钙(t=4.018,P<0.001)及MoCA评分(t=10.646,P<0.001)低于非CI组MHD患者。LASSO回归筛选上述因素,代入Logistics回归分析显示年龄(OR=1.135,95%CI:1.041~1.238,P=0.004)、透析龄(OR=1.138,95%CI:1.012~1.279,P=0.031)、hs-CRP(OR=2.394,95%CI:1.158~4.950,P=2.394)、血清白蛋白(OR=0.759,95%CI:0.593~0.971,P=0.028)是MHD患者发生CI的危险因素。LASSO-Logistics回归模型预测MHD患者CI发生的曲线下面积(AUC)为0.892(95%CI:0.813~0.945)。外部验证显示:AUC为0.899(95%CI:0.0.804~0.958),Youden指数J为0.713。结论 年龄、透析龄、hs-CRP、低白蛋白与MHD患者发生CI显著相关,构建的预测模型能够较好的预测这类人群发生CI。Objective To construct a predictive model based on LASSO regression for maintenance hemodialysis(MHD)patients with cognitive decline.Methods 100 patients treated with MHD in Yixing People's Hospital from March 2016 to March 2021 were prospectively included.The patients were classified into a cognitive impairment(CI)group(MocA<26)and a non-CI group(MocA≥26)using the Montreal cognitive assessment(MocA)scale.General and clinical data were collected.Characteristic factors related to CI in MHD patients with non-zero coefficients were screened by LASSO regression.Lasso-Logistics regression model was constructed and receiver operating characteristic curve(ROC)was drawn to evaluate the model effectiveness.Data rows of 71 MHD patients were selected for external verification.Results There were 62 patients in CI group and 38 patients in non-CI group,respectively.LASSO regression showed that age,dialysis vintage,diabetes mellitus(OR=1.673,95%CI:0.150~18.661,P=0.676),higher sensitive C-reactive protein(hs-CRP),triglyceride,total cholesterol,serum albumin and serum calcium were significantly correlated with the occurrence of CI in MHD patients.Logistic regression analysis showed that age(OR=1.135,95%CI:1.041~1.238,P=0.004),dialysis vintage(OR=1.138,95%CI:1.012~1.279,P=0.031),hs-CRP(OR=2.394,95%CI:1.158~4.950,P=2.394),serum albumin(OR=0.759,95%CI:0.593~0.971,P=0.028)were risk factors for CI in MHD patients.Lasso-logistics regression model predicted that the AUC of CI occurrence in MHD patients was 0.892(95%CI:0.813~0.945).External verification showed that the area under the curve(AUC)was 0.899(95%CI:0.0.804~0.958),and the Youden index J was 0.713.Conclusion Age,dialysis vintage,hs-CRP and lower albumin were significantly correlated with the incidence of CI in MHD patients,and the established prediction model could better predict the incidence of CI in MHD patients.

关 键 词：LASSO回归 维持性血液透析 认知功能 预测模型 

分 类 号：R459.5[医药卫生—治疗学]