Developing classifiers for the detection of cancer using multi-analytes Article

Tarca, AL, Draghici, S, Romero, R. (2009). Developing classifiers for the detection of cancer using multi-analytes . Methods in molecular biology (Clifton, N.J.), 520 259-272. 10.1007/978-1-60327-811-9_19

cited authors

  • Tarca, AL; Draghici, S; Romero, R

abstract

  • The development of a successful classifier from multiple predictors (analytes) is a multistage process complicated typically by the paucity of the data samples when compared to the number of available predictors. Choosing an adequate validation strategy is key for drawing sound conclusions about the usefulness of the classifier. Other important decisions have to be made regarding the type of prediction model to be used and training algorithm, as well as the way in which the markers are selected. This chapter describes the principles of the classifier development and underlines the most common pitfalls. A simulated dataset is used to illustrate the main concepts involved in supervised classification. © 2009 Humana Press, a part of Springer Science+Business Media, LLC.

authors

publication date

  • December 1, 2009

published in

Digital Object Identifier (DOI)

start page

  • 259

end page

  • 272

volume

  • 520