基于随机森林的阿尔茨海默病患者结构能力智能评测  

Intelligent Evaluation of Structural Ability in Alzheimer′s Patients Based on Random Forest

作　　者：刘王亚 郁磊 任璐 赵娅蓉 李阳[4] 靳祯 LIU Wang-ya;YU Lei;REN Lu;ZHAO Ya-rong;LI Yang;JIN Zhen(Complex Systems Research Center,Shanxi University,Taiyuan 030006,China;Shanxi Key Laboratory of Mathematical Techniques and Big Data Analysis on Disease Control and Prevention,Shanxi University,Taiyuan 030006,China;The First Clinical Medical College,Shanxi Medical University,Taiyuan 030001,China;The First Hospital,Shanxi Medical University,Taiyuan 030001,China)

机构地区：[1]山西大学复杂系统研究所,山西太原030006 [2]山西大学疾病防控的数学技术与大数据分析山西省重点实验室,山西太原030006 [3]山西医科大学第一临床医学院,山西太原030001 [4]山西医科大学第一医院,山西太原030001

出　　处：《云南师范大学学报（自然科学版）》2020年第5期17-20,共4页Journal of Yunnan Normal University:Natural Sciences Edition

基　　金：国家自然科学基金资助项目(61803242);山西省重点研发计划资助项目(201703D421012,201803D31032);中央引导地方科技发展专项资金资助项目(YDZX20191400002563)。

摘　　要：提出了一种基于随机森林的阿尔茨海默病(AD)患者结构能力智能评测模型,并对109名患者进行了实验验证.实验结果表明,当五边形复制测试结果中五边形和交织形成的四边形的长度特征和角度特征同时作为模型输入时,模型的识别准确率可达97%以上,较好地解决了社区大样本条件下AD初期筛查医护人员不足的情况.The intelligent evaluation model based on random forest was experimentally validated with 109 patients with Alzheimer′s Disease(AD).The experimental results show that when the length and angle characteristics of the pentagons and the interlacing quadrilateral are both input into the model,the model has the highest recognition accuracy,up to more than 97%,which better solves the problem of insufficient medical staff in the initial screening of AD under the condition of large community sample.

关 键 词：阿尔茨海默症 结构能力 随机森林 自动测评 五边形复制测试 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]