摘要
目的探索以血管性高危因素构建的机器学习模型早期预测血管性认知障碍的预测性能。方法2020年4月至9月,收集本院住院患者及陪护人员70例的人口学资料、血管性高危因素,行蒙特利尔认知评估量表(MoCA)评估,根据评估结果将受试者分为正常组、血管性轻度认知障碍(VaMCI)组和痴呆组;单因素方差分析筛选组间存在显著性差异的血管性高危因素,采用支持向量机(SVM)和极限学习机(ELM)构建预测模型;采用接受者操作特征曲线比较两种模型的预测性能。结果根据MoCA评估结果,正常组32例,VaMCI组23例,痴呆组15例;三组间收缩压、空腹血糖、总胆固醇、低密度脂蛋白、血尿酸有显著性差异(F>3.318,P<0.05);SVM模型预测VaMCI的曲线下面积最高,为0.911(P<0.01),SVM模型优于ELM模型。结论基于血管性高危因素构建的SVM预测模型优于ELM模型。
Objective To explore the predictive performance of machine learning model based on vascular risk factors in early pre‐diction of vascular cognitive impairment.Methods From April to September,2020,70 subjects were enrolled and collected information of the demographics and vascular risk factors.They were assessed with Montreal Cognitive Assessment(MoCA),and then divided into normal group,vascular mild cognitive impairment(VaMCI)group and dementia group.The differences of vascu‐lar risk factors among the three groups were detected with one-way ANOVA,and the significant factors were se‐lected to establish predictive models with support vector machine(SVM)and extreme learning machine(ELM).The predictive performance of two models was compared with Receiver Operating Characteristic Curve.Results There were 32 cases in the normal group,23 in VaMCI group and 15 in dementia group.Systolic blood pressure,fasting blood glucose,total cholesterol,low density lipoprotein and blood uric acid were significantly different among the three groups(F>3.318,P<0.05).The area under curve was the most(0.911)in SVM model predict‐ing for VaMCI(P<0.01),and the predictive efficacy was better for SVM model.Conclusion SVM predictive model based on vascular risk factors may be more effective for predicting VaMCI.
作者
张倩
卞敏洁
何琴
黄东锋
ZHANG Qian;BIAN Min-jie;HE Qin;HUANG Dong-feng(Department of Rehabilitation Medicine,the Seventh Affiliated Hospital,Sun Yat-sen University,Shenzhen,Guang‐dong 518000,China;Guangdong Engineering and Technology Research Center for Rehabilitation Medicine and Translation,Guangzhou,Guangdong 510000,China)
出处
《中国康复理论与实践》
CSCD
北大核心
2021年第9期1072-1077,共6页
Chinese Journal of Rehabilitation Theory and Practice
基金
中山大学临床医学研究5010计划项目(No.2014001)。
关键词
血管性认知障碍
支持向量机
极限学习机
机器学习
预测模型
vascular cognitive impairment
support vector machines
extreme learning machines
machine learning
predictive model
