Open Access Research article

Using logistic regression to improve the prognostic value of microarray gene expression data sets: application to early-stage squamous cell carcinoma of the lung and triple negative breast carcinoma

David W Mount1, Charles W Putnam2, Sara M Centouri3, Ann M Manziello1, Ritu Pandey1, Linda L Garland4 and Jesse D Martinez5*

Author Affiliations

1 Bioinformatics Shared Service, Arizona Health Sciences Center, The University of Arizona, Tucson, Arizona 85735, USA

2 Department of Surgery, Arizona Health Sciences Center, The University of Arizona, Tucson, Arizona 85735, USA

3 Arizona Comprehensive Cancer Center, The University of Arizona, Tucson, Arizona 85735, USA

4 Department of Medicine, Arizona Health Sciences Center, The University of Arizona, Tucson, Arizona 85735, USA

5 Department of Cellular and Molecular Medicine, Arizona Health Sciences Center, The University of Arizona, Tucson, Arizona 85735, USA

For all author emails, please log on.

BMC Medical Genomics 2014, 7:33  doi:10.1186/1755-8794-7-33

Published: 10 June 2014

Abstract

Background

Numerous microarray-based prognostic gene expression signatures of primary neoplasms have been published but often with little concurrence between studies, thus limiting their clinical utility. We describe a methodology using logistic regression, which circumvents limitations of conventional Kaplan Meier analysis. We applied this approach to a thrice-analyzed and published squamous cell carcinoma (SQCC) of the lung data set, with the objective of identifying gene expressions predictive of early death versus long survival in early-stage disease. A similar analysis was applied to a data set of triple negative breast carcinoma cases, which present similar clinical challenges.

Methods

Important to our approach is the selection of homogenous patient groups for comparison. In the lung study, we selected two groups (including only stages I and II), equal in size, of earliest deaths and longest survivors. Genes varying at least four-fold were tested by logistic regression for accuracy of prediction (area under a ROC plot). The gene list was refined by applying two sliding-window analyses and by validations using a leaveā€“one-out approach and model building with validation subsets. In the breast study, a similar logistic regression analysis was used after selecting appropriate cases for comparison.

Results

A total of 8594 variable genes were tested for accuracy in predicting earliest deaths versus longest survivors in SQCC. After applying the two sliding window and the leave-one-out analyses, 24 prognostic genes were identified; most of them were B-cell related. When the same data set of stage I and II cases was analyzed using a conventional Kaplan Meier (KM) approach, we identified fewer immune-related genes among the most statistically significant hits; when stage III cases were included, most of the prognostic genes were missed. Interestingly, logistic regression analysis of the breast cancer data set identified many immune-related genes predictive of clinical outcome.

Conclusions

Stratification of cases based on clinical data, careful selection of two groups for comparison, and the application of logistic regression analysis substantially improved predictive accuracy in comparison to conventional KM approaches. B cell-related genes dominated the list of prognostic genes in early stage SQCC of the lung and triple negative breast cancer.