9种结合式机器学习算法在肿瘤早期诊断中的准确性比较研究  

A Comparative Study on the Accuracy of Nine Combined Machine Learning Algorithms in Early Diagnosis of Tumor

作　　者：冯利 岳小飞 FENG Li;YUE Xiaofei(College of Medicine,The Open University of China,Beijing 100039,China;Department of Pharmacy,Beijing Rehabilitation Hospital,Beijing 100144,China)

机构地区：[1]国家开放大学医药学院,北京100039 [2]北京康复医院药剂科,北京100144

出　　处：《医学信息学杂志》2022年第5期25-29,共5页Journal of Medical Informatics

摘　　要：提出应用偏最小二乘法与线性判别分析、K-最近邻法、决策树等组成9种结合式分类器,分析幼年转基因肿瘤小鼠及正常对照组小鼠的血清蛋白质组数据集,阐述原理与方法,比较各结合式分类器的分类准确率。The paper proposes nine combined classifiers,including Partial Least Squares(PLS),Linear Discriminant Analysis(LDA),K-Nearest Neighbor(KNN) method,Decision Tree(DT),etc.,which are used to analyze the serum proteome data sets of young transgenic tumor mice and normal control mice.It expounds the principle and method,and compares the classification accuracy of the combined classifiers.

关 键 词：机器学习 早期诊断 肿瘤 高维数据 

分 类 号：R-058[医药卫生]