A comprehensive sensitivity analysis of microarray breast cancer classification under feature variability |
| |
Authors: | Herman MJ Sontrop Perry D Moerland René van den Ham Marcel JT Reinders Wim FJ Verhaegh |
| |
Institution: | (1) Molecular Diagnostics Department, Philips Research, High Tech Campus 12a, 5656 AE Eindhoven, the Netherlands;(2) Bioinformatics Laboratory, Department of Clinical Epidemiology, Biostatistics and Bioinformatics, Academic Medical Center, Meibergdreef 9, 1100, AZ, Amsterdam, the Netherlands;(3) Biomolecular Engineering Department, Philips Research, High Tech Campus 11, 5656, AE, Eindhoven, the Netherlands;(4) Delft Bioinformatics Lab, Delft University of Technology, Mekelweg 4, 2628, CD, Delft, the Netherlands |
| |
Abstract: | Background Large discrepancies in signature composition and outcome concordance have been observed between different microarray breast
cancer expression profiling studies. This is often ascribed to differences in array platform as well as biological variability.
We conjecture that other reasons for the observed discrepancies are the measurement error associated with each feature and
the choice of preprocessing method. Microarray data are known to be subject to technical variation and the confidence intervals
around individual point estimates of expression levels can be wide. Furthermore, the estimated expression values also vary
depending on the selected preprocessing scheme. In microarray breast cancer classification studies, however, these two forms
of feature variability are almost always ignored and hence their exact role is unclear. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|