阿尔茨海默病的影响因素及其预测模型构建  

Influencing Factors and Prediction Model Construction of Alzheimer Disease

作　　者：吴天晨[1] 杨卉 梁艳[1] WU Tianchen;YANG Hui;LIANG Yan(Department of Neurology,Nanjing Hospital of T.C.M,Nanjing 210001,China;School of Nursing,Nanjing University of Chinese Medicine,Nanjing 210023,China)

机构地区：[1]江苏省南京市中医院脑病科,210001 [2]江苏省南京市南京中医药大学护理学院,210023

出　　处：《实用心脑肺血管病杂志》2023年第9期50-55,共6页Practical Journal of Cardiac Cerebral Pneumal and Vascular Disease

基　　金：国家自然科学基金资助项目(81904112);江苏省自然科学基金项目(BK20190136);南京市中医药青年人才计划(ZYQ20047)。

摘　　要：目的探讨阿尔茨海默病(AD)的影响因素并构建其预测模型。方法选取2019年1月至2021年1月就诊于南京市中医院的61例AD患者作为AD组,另选取同期于该院体检中心进行体检的健康者122例作为健康组。比较两组基线资料。采用LASSO回归和多因素Logistic回归分析探讨AD的影响因素并构建其预测模型。采用ROC曲线评估预测模型对AD的预测价值。结果两组性别、年龄、载脂蛋白E(ApoE)基因分型、TC、载脂蛋白B、游离三碘甲状腺原氨酸(FT_(3))、总甲状腺素(TT_(4))比较,差异有统计学意义(P<0.05)。LASSO回归分析结果显示,性别、年龄、ApoE基因分型、FT_(3)、总三碘甲状腺原氨酸(TT_(3))是5个系数不为零的因子。多因素Logistic回归分析结果显示,性别、年龄、ApoE基因分型、TT3是AD的独立影响因素(P<0.05)。根据上述影响因素构建的预测模型如下:P=e^(x)/(1+e^(x)),其中x=-5.170+1.267×男性+0.058×年龄+2.389×ApoE3(ε3/ε3、ε2/ε4)+4.572×ApoE4(ε3/ε4、ε4/ε4)-2.059×TT_(3)。ROC曲线分析结果显示,预测模型预测AD发生的AUC为0.885[95%CI(0.832,0.938)]。结论性别、年龄、ApoE基因分型、TT_(3)是AD的影响因素,而根据上述影响因素构建的预测模型对AD具有一定预测能力。Objective To explore the influencing factors of Alzheimer disease(AD)and construct its prediction model.Methods A total of 61 patients with AD who were admitted to Nanjing Hospital of T.C.M from January 2019 to January 2021 were selected as AD group,and 122 healthy subjects who underwent physical examination in the physical examination center of the same hospital during the same period were selected as healthy group.The baseline data were compared between the two groups.LASSO regression and multivariate Logistic regression analysis was used to investigate the influencing factors of AD and to construct its prediction model.ROC curve was used to evaluate the predictive value of prediction model for AD.Results There were significant differences in gender,age,apolipoprotein E(ApoE)genotype,TC,apolipoprotein B,free triiodothyronine(FT3)and total thyroxine(TT_(4))between the two groups(P<0.05).LASSO regression analysis showed that gender,age,ApoE genotype,FT_(3) and TT_(3) were 5 factors with non-zero coefficients.Multivariate Logistic regression analysis showed that gender,age,ApoE genotype,and TT_(3) were the independently influencing factors of AD(P<0.05).The prediction model constructed according to the above influencing factors was as follows:P=e^(x)/(1+e^(x)),where x=-5.170+1.267×male+0.058×age+2.389×ApoE3(ε3/ε3,ε2/ε4)+4.572×ApoE4(ε3/ε4,ε4/ε4)-2.059×TT3.ROC curve analysis showed that the AUC of prediction model for predicting AD was 0.885[95%CI(0.832,0.938)].Conclusion Gender,age,ApoE genotype,and TT3 are the influencing factors of AD,and the prediction model constructed according to the above influencing factors has a certain ability to predict AD.

关 键 词：阿尔茨海默病 影响因素分析 预测模型 

分 类 号：R745.7[医药卫生—神经病学与精神病学]