2011
Lack of sufficiently strong informative features limits the potential of gene expression analysis as predictive tool for many clinical classification problems
Hess KR, Wei C, Qi Y, Iwamoto T, Symmans WF, Pusztai L. Lack of sufficiently strong informative features limits the potential of gene expression analysis as predictive tool for many clinical classification problems. BMC Bioinformatics 2011, 12: 463. PMID: 22132775, PMCID: PMC3245512, DOI: 10.1186/1471-2105-12-463.Peer-Reviewed Original ResearchConceptsPrediction problemCurrent statistical methodsClinical prediction problemsReal data setsMonte Carlo cross validationStatistical methodsData setsAccurate modelPerturbedInformative featuresPrediction modelCancer data setsPredictor performanceGene expression dataProblemBreast cancer data setsClassification problemSuch featuresMean expression valuesSet
2010
Effect of training-sample size and classification difficulty on the accuracy of genomic predictors
Popovici V, Chen W, Gallas B, Hatzis C, Shi W, Samuelson FW, Nikolsky Y, Tsyganova M, Ishkin A, Nikolskaya T, Hess KR, Valero V, Booser D, Delorenzi M, Hortobagyi GN, Shi L, Symmans WF, Pusztai L. Effect of training-sample size and classification difficulty on the accuracy of genomic predictors. Breast Cancer Research 2010, 12: r5. PMID: 20064235, PMCID: PMC2880423, DOI: 10.1186/bcr2468.Peer-Reviewed Original Research