Bioinformatics · 2006 · 360 citations · 28 references
ComputingBiostatisticsOncologyBayesian BiostatisticsBayesian Data AnalysisClinical Decision SupportBayesian StatisticsTumor ClassificationBayesian Data IntegrationBayesian NetworksBreast Cancer PrognosisCancer Prognostic ModelingDecision Support IntegrationDecision Support System IntegrationMicroarray AnalysisNetwork-based Prognostics
Clinical data such as patient history, laboratory tests, and ultrasound parameters are routinely underused in cancer management despite being the foundation of daily clinical decision support. The authors propose a Bayesian network strategy to integrate clinical and microarray data on an equal footing. The Bayesian network model integrates multiple data sources, performs automatic feature selection via the Markov Blanket, and allows exploration of model structure and parameters. Partial integration of the data yielded an independent test set AUC of 0.845, surpassing commonly used prognostic indices. Contact: olivier.gevaert@esat.kuleuven.be.
Abstract Motivation: Clinical data, such as patient history, laboratory analysis, ultrasound parameters—which are the basis of day-to-day clinical decision support—are often underused to guide the clinical management of cancer in the presence of microarray data. We propose a strategy based on Bayesian networks to treat clinical and microarray data on an equal footing. The main advantage of this probabilistic model is that it allows to integrate these data sources in several ways and that it allows to investigate and understand the model structure and parameters. Furthermore using the concept of a Markov Blanket we can identify all the variables that shield off the class variable from the influence of the remaining network. Therefore Bayesian networks automatically perform feature selection by identifying the (in)dependency relationships with the class variable. Results: We evaluated three methods for integrating clinical and microarray data: decision integration, partial integration and full integration and used them to classify publicly available data on breast cancer patients into a poor and a good prognosis group. The partial integration method is most promising and has an independent test set area under the ROC curve of 0.845. After choosing an operating point the classification performance is better than frequently used indices. Contact: olivier.gevaert@esat.kuleuven.be
28
Todd R. Golub, Donna K. Slonim, Pablo Tamayo et al. · Science · 1999 · 11.6K citations
A Gene-Expression Signature as a Predictor of Survival in Breast Cancer
Marc J. van de Vijver, Yudong D. He, Laura van ‘t Veer et al. · New England Journal of Medicine · 2002 · 6.5K citations · Full text
Medicine, Bioinformatics, Oncology +17
Missing value estimation methods for DNA microarrays
Olga G. Troyanskaya, Michael Cantor, Gavin Sherlock et al. · Bioinformatics · 2001 · 4.3K citations · Full text