Gene Expression Profiles for Predicting Metastasis in Breast Cancer: A Cross-Study Comparison of Classification Methods

Machine learning has increasingly been used with microarray gene expression data and for the development of classifiers using a variety of methods. However, method comparisons in cross-study datasets are very scarce. This study compares the performance of seven classification methods and the effect...

Full description

Saved in:
Bibliographic Details
Main Authors: Mark Burton, Mads Thomassen, Qihua Tan, Torben A. Kruse
Format: Article
Language:English
Published: Wiley 2012-01-01
Series:The Scientific World Journal
Online Access:http://dx.doi.org/10.1100/2012/380495
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849305073242341376
author Mark Burton
Mads Thomassen
Qihua Tan
Torben A. Kruse
author_facet Mark Burton
Mads Thomassen
Qihua Tan
Torben A. Kruse
author_sort Mark Burton
collection DOAJ
description Machine learning has increasingly been used with microarray gene expression data and for the development of classifiers using a variety of methods. However, method comparisons in cross-study datasets are very scarce. This study compares the performance of seven classification methods and the effect of voting for predicting metastasis outcome in breast cancer patients, in three situations: within the same dataset or across datasets on similar or dissimilar microarray platforms. Combining classification results from seven classifiers into one voting decision performed significantly better during internal validation as well as external validation in similar microarray platforms than the underlying classification methods. When validating between different microarray platforms, random forest, another voting-based method, proved to be the best performing method. We conclude that voting based classifiers provided an advantage with respect to classifying metastasis outcome in breast cancer patients.
format Article
id doaj-art-08e358c45fe04258a16730b1fad03f5d
institution Kabale University
issn 1537-744X
language English
publishDate 2012-01-01
publisher Wiley
record_format Article
series The Scientific World Journal
spelling doaj-art-08e358c45fe04258a16730b1fad03f5d2025-08-20T03:55:33ZengWileyThe Scientific World Journal1537-744X2012-01-01201210.1100/2012/380495380495Gene Expression Profiles for Predicting Metastasis in Breast Cancer: A Cross-Study Comparison of Classification MethodsMark Burton0Mads Thomassen1Qihua Tan2Torben A. Kruse3Research Unit of Human Genetics, Institute of Clinical Research, University of Southern Denmark, Sdr. Boulevard 29, 5000 Odense C, DenmarkResearch Unit of Human Genetics, Institute of Clinical Research, University of Southern Denmark, Sdr. Boulevard 29, 5000 Odense C, DenmarkResearch Unit of Human Genetics, Institute of Clinical Research, University of Southern Denmark, Sdr. Boulevard 29, 5000 Odense C, DenmarkResearch Unit of Human Genetics, Institute of Clinical Research, University of Southern Denmark, Sdr. Boulevard 29, 5000 Odense C, DenmarkMachine learning has increasingly been used with microarray gene expression data and for the development of classifiers using a variety of methods. However, method comparisons in cross-study datasets are very scarce. This study compares the performance of seven classification methods and the effect of voting for predicting metastasis outcome in breast cancer patients, in three situations: within the same dataset or across datasets on similar or dissimilar microarray platforms. Combining classification results from seven classifiers into one voting decision performed significantly better during internal validation as well as external validation in similar microarray platforms than the underlying classification methods. When validating between different microarray platforms, random forest, another voting-based method, proved to be the best performing method. We conclude that voting based classifiers provided an advantage with respect to classifying metastasis outcome in breast cancer patients.http://dx.doi.org/10.1100/2012/380495
spellingShingle Mark Burton
Mads Thomassen
Qihua Tan
Torben A. Kruse
Gene Expression Profiles for Predicting Metastasis in Breast Cancer: A Cross-Study Comparison of Classification Methods
The Scientific World Journal
title Gene Expression Profiles for Predicting Metastasis in Breast Cancer: A Cross-Study Comparison of Classification Methods
title_full Gene Expression Profiles for Predicting Metastasis in Breast Cancer: A Cross-Study Comparison of Classification Methods
title_fullStr Gene Expression Profiles for Predicting Metastasis in Breast Cancer: A Cross-Study Comparison of Classification Methods
title_full_unstemmed Gene Expression Profiles for Predicting Metastasis in Breast Cancer: A Cross-Study Comparison of Classification Methods
title_short Gene Expression Profiles for Predicting Metastasis in Breast Cancer: A Cross-Study Comparison of Classification Methods
title_sort gene expression profiles for predicting metastasis in breast cancer a cross study comparison of classification methods
url http://dx.doi.org/10.1100/2012/380495
work_keys_str_mv AT markburton geneexpressionprofilesforpredictingmetastasisinbreastcanceracrossstudycomparisonofclassificationmethods
AT madsthomassen geneexpressionprofilesforpredictingmetastasisinbreastcanceracrossstudycomparisonofclassificationmethods
AT qihuatan geneexpressionprofilesforpredictingmetastasisinbreastcanceracrossstudycomparisonofclassificationmethods
AT torbenakruse geneexpressionprofilesforpredictingmetastasisinbreastcanceracrossstudycomparisonofclassificationmethods