Machine-learning techniques for building a diagnostic model for very mild dementia

被引:48
作者
Chen, Rong [1 ]
Herskovits, Edward H. [1 ]
机构
[1] Univ Penn, Dept Radiol, Philadelphia, PA 19104 USA
基金
美国国家卫生研究院;
关键词
COGNITIVE IMPAIRMENT; ENTORHINAL CORTEX; CLASSIFICATION; HIPPOCAMPUS; DISEASE;
D O I
10.1016/j.neuroimage.2010.03.084
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
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 controls) 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. (C) 2010 Elsevier Inc. All rights reserved
引用
收藏
页码:234 / 244
页数:11
相关论文
共 41 条
[1]  
[Anonymous], 2005, PROCEEDING 11 ACM SI, DOI DOI 10.1145/1081870.1081875
[2]  
[Anonymous], 1990, SUPPORT VECTOR LEARN
[3]  
[Anonymous], 1993, Proceedings of the 13th International Joint Conference on Artificial Intelligence
[4]  
[Anonymous], 2000, Pattern Classification
[5]   NEUROPATHOLOGICAL STAGING OF ALZHEIMER-RELATED CHANGES [J].
BRAAK, H ;
BRAAK, E .
ACTA NEUROPATHOLOGICA, 1991, 82 (04) :239-259
[6]   White matter lesions are prevalent but differentially related with cognition in aging and early Alzheimer disease [J].
Burns, JM ;
Church, JA ;
Johnson, DK ;
Xiong, CJ ;
Marcus, D ;
Fotenos, AF ;
Snyder, AZ ;
Morris, JC ;
Buckner, RL .
ARCHIVES OF NEUROLOGY, 2005, 62 (12) :1870-1876
[7]   Network analysis of mild cognitive impairment [J].
Chen, R ;
Herskovits, EH .
NEUROIMAGE, 2006, 29 (04) :1252-1259
[8]   Specific hippocampal volume reductions in individuals at risk for Alzheimer's disease [J].
Convit, A ;
DeLeon, MJ ;
Tarshish, C ;
DeSanti, S ;
Tsui, W ;
Rusinek, H ;
George, A .
NEUROBIOLOGY OF AGING, 1997, 18 (02) :131-138
[9]  
COWELL R, 1998, P NATO ADV STUD I LE, P9
[10]   Predicting conversion to Alzheimer disease using standardized clinical information [J].
Daly, E ;
Zaitchik, D ;
Copeland, M ;
Schmahmann, J ;
Gunther, J ;
Albert, M .
ARCHIVES OF NEUROLOGY, 2000, 57 (05) :675-680