· · · Repository hosted by TU Delft Library



Home · About · Disclaimer ·
   Options
 
Type:
Year:

Subtype specific breast cancer event prediction

Attachments

These file attachments have been under embargo and were made available to the public after the embargo was lifted on 9 January 2011.

Author: Sontrop, H.M.J. · Verhaegh, W.F.J. · Van den Ham, R. · Reinders, M.J.T. (Univ. Delft) · Moerland, P. (AMC Amsterdam)
Type:Conference paper
Date:2010-11-10
Embargo lifted:2011-01-09
Publisher: IEEE
Institution: Philips Research
Source:GENSIPS 2010: 9th IEEE International Workshop Genomic Signal Processing and Statistics, 10-12 November 2010, Cold Spring Harbor Laboratory, NY, USA
Identifier: MS 31.797
Keywords: breast cancer · classification · clinical decision support · microarrays · outcome prediction · subtype
Rights: (c) IEEE

Abstract

We investigate the potential to enhance breast cancer event predictors by exploiting subtype information. We do this with a two-stage approach that first determines a sample's subtype using a recent module-driven approach, and secondly constructs a subtype-specific predictor to predict a metastasis event within five years. Our methodology is validated on a large compendium of microarray breast cancer datasets,including 43 replicate array pairs for assessing subtyping stability. Note that stratifying by subtype strongly reduces the training set sizes available to construct the individual predictors, which may decrease performance. Besides sample size, other factors likeunequal class distributions and differences in the number of samplesper subtype, easily obscure a fair comparison between subtype-specific predictors constructed on different subtypes, but also between subtype specific and subtype a-specific predictors. Therefore, we constructed a completely balanced experimental design, in which none ofthe above factors play a role and show that subtype-specific eventpredictors clearly outperform predictors that do not take subtype information into account.

Content Viewer