Machine-learning techniques for building a diagnostic model for very mild dementia.
Machine-learning techniques for building a diagnostic model for very mild dementia.
复制标题
DOI：
10.1016/j.neuroimage.2010.03.084
复制
发表时间：
2010-08-01
期刊：
影响因子：
5.7
通讯作者：
Herskovits, Edward H.
中科院分区：
文献类型：
--
作者：
Chen, Rong;Herskovits, Edward H.
许多研究人员试图构建诊断模型，以区分患有非常轻度痴呆（VMD）的个体和健康老年人，基于结构磁共振（MR）图像。这些模型，在大多数情况下，是基于判别分析或逻辑回归，很少有报告的替代方法。为了确定不同方法的相对优势，分析结构MR数据，以区分VMD患者和正常老年对照组，我们评估了七种不同的分类方法，每种方法都用于从83名受试者（33名VMD和50名对照）的训练数据集生成诊断模型。然后，我们使用从30名受试者（13名VMD和17名对照）获得的独立数据集评估每个诊断模型。我们发现，这七种诊断模型之间存在显着的性能差异。相对于由判别分析和逻辑回归生成的诊断模型，当从所有图谱结构生成诊断模型时，由其他高性能诊断模型生成算法生成的诊断模型表现出增加的泛化能力。
Many researchers have sought to construct diagnostic models to differentiate individuals with very mild dementia (VMD) from healthy elderly people, based on structural magnetic-resonance (MR) images. These models have, for the most part, been based on discriminant analysis or logistic regression, with few reports of alternative approaches. To determine the relative strengths of different approaches to analyzing structural MR data to distinguish people with VMD from normal elderly control subjects, we evaluated seven different classification approaches, each of which we used to generate a diagnostic model from a training data set acquired from 83 subjects (33 VMD and 50 control). We then evaluated each diagnostic model using an independent data set acquired from 30 subjects (13 VMD and 17 control). We found that there were significant performance differences across these seven diagnostic models. Relative to the diagnostic models generated by discriminant analysis and logistic regression, the diagnostic models generated by other high-performance diagnostic-model–generation algorithms manifested increased generalizability when diagnostic models were generated from all atlas structures.
登录
查看更多内容
影响因子：
8.9
作者：
Huang, J;Ling, CX
通讯作者：
Ling, CX
影响因子：
14.5
作者：
Kloeppel, Stefan;Stonnington, Cynthia M.;Chu, Carlton;Draganski, Bogdan;Scahill, Rachael I.;Rohrer, Jonathan D.;Fox, Nick C.;Jack, Clifford R., Jr.;Ashburner, John;Frackowiak, Richard S. J.
通讯作者：
Frackowiak, Richard S. J.
影响因子：
--
作者：
Burns, JM;Church, JA;Buckner, RL
通讯作者：
Buckner, RL
影响因子：
7.5
作者：
Friedman, N;Geiger, D;Goldszmidt, M
通讯作者：
Goldszmidt, M
影响因子：
4.2
作者：
Convit, A;DeLeon, MJ;George, A
通讯作者：
George, A