Data reduction using a discrete wavelet transform in discriminant analysis of very high dimensionality data

被引：60

作者：

Qu, YS

Adam, BL

Thornquist, M

Potter, JD

Thompson, ML

Yasui, Y

Davis, J

Schellhammer, PF

Cazares, L

Clements, MA

Wright, GL

Feng, ZD

机构：

[1] Fred Hutchinson Canc Res Ctr, Canc Prevent Res Program, Seattle, WA 98104 USA

[2] Eastern Virginia Med Sch, Dept Microbiol & Mol Cell Biol & Urol, Norfolk, VA 23501 USA

[3] Virginia Prostate Cencer, Norfolk, VA USA

[4] Univ Washington, Dept Biostat, Seattle, WA 98195 USA

来源：

BIOMETRICS | 2003年 / 59卷 / 01期

关键词：

area under the ROC curve; divergence; fisher discriminant analysis; Kullback-Leibler information; Mahalanobis distance; principal components analysis;

D O I：

10.1111/1541-0420.00017

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

We present a method of data reduction using a wavelet transform in discriminant analysis when the number of variables is much greater than the number of observations. The method is illustrated with a prostate cancer study, where the sample size is 248, and the number of variables is 48,538 (generated using the ProteinChip technology). Using a discrete wavelet transform, the 48,538 data points are represented by 1271 wavelet coefficients. Information criteria identified 11 of the 1271 wavelet coefficients with the highest discriminatory power. The linear classifier with the 11 wavelet coefficients detected prostate cancer in a separate test set with a sensitivity of 97% and specificity of 100%.

引用

页码：143 / 151

页数：9

共 24 条

[1]

ALDROUBI A, 1996, WAVELETS MED BIOL

[2]

[Anonymous], 1989, MULTIVARIATE CALIBRA

[3] Application of wavelet transforms to experimental spectra: Smoothing, denoising, and data set compression [J].