Predicting the Clinical Status of Human Breast Cancer Using Gene Expression Profiles
Abstract
Prognostic and predictive factors are indispensable tools in the treatment of patients with neoplastic disease. For the most part, such factors rely on a few specific cell surface, histological, or gross pathologic features. Gene expression assays have the potential to supplement what were previously a few distinct features with many thousands of features. At the same time, it is essential for adequate clinical decision-making that the statistical metholdologies used to link gene expression patterns with prognosis or response to therapy be at once robust and formally address the uncertainties inherent in predictive modeling. We have developed Bayesian regression models that provide predictive capability based on gene expression data derived from DNA microarray analysis of a series of primary breast cancer samples. These patterns have the capacity to discriminate breast tumors on the basis of estrogen receptor (ER) status, and also on the basic categorized lymph node status. Importantly, we assess the utility and validity of such models in predicting status of tumors in cross-validation determinations. The practical value of such approaches relies on the ability not only to assess relative probabilities of clinical outcomes for future samples, but also to provide an honest assessment of the uncertainties associated with such predictive classifications based on the selection of gene subsets for each validation analysis. That latter point is of critical importance in the ability to apply these methodologies to clinical assessment of tumor phenotype.
Authors
Mike West, Carrie Blanchette, Holly Dressman, Erich Huang, Seiichi Ishida, Rainer Spang, Harry Zuzan, Jeffrey R. Marks, Joseph R. Nevins
Contact
- Mike West (mw@stat.duke.edu)
- Joseph Nevins (j.nevins@duke.edu)