Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Gene expression–based survival prediction in lung adenocarcinoma: a multi-site, blinded validation study


Although prognostic gene expression signatures for survival in early-stage lung cancer have been proposed, for clinical application, it is critical to establish their performance across different subject populations and in different laboratories. Here we report a large, training–testing, multi-site, blinded validation study to characterize the performance of several prognostic models based on gene expression for 442 lung adenocarcinomas. The hypotheses proposed examined whether microarray measurements of gene expression either alone or combined with basic clinical covariates (stage, age, sex) could be used to predict overall survival in lung cancer subjects. Several models examined produced risk scores that substantially correlated with actual subject outcome. Most methods performed better with clinical data, supporting the combined use of clinical and molecular information when building prognostic models for early-stage lung cancer. This study also provides the largest available set of microarray data with extensive pathological and clinical annotation for lung adenocarcinomas.

This is a preview of subscription content

Access options

Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Figure 1: Classifier performance.
Figure 2: Kaplan-Meier estimates of the survivor function for method A on each validation data set for the four hypotheses.
Figure 3: Kaplan-Meier estimates of the survivor function for method A (cross-validated) on training sets UM and MSK.


  1. Jemal, A. et al. Cancer Statistics 2006. CA Cancer J. Clin. 56, 106–130 (2006).

    Article  Google Scholar 

  2. Booth, C.M. & Shepherd, F.A. Adjuvant chemotherapy for resected non-small cell lung cancer. J. Thorac. Oncol. 2, 180–187 (2006).

    Article  Google Scholar 

  3. Gandara, D.R., Wakelee, H., Calhoun, R. & Jablons, D. Adjuvant chemotherapy of stage I non-small cell lung cancer in North America. J. Thorac. Oncol. 7 (suppl. 3), S125–S127 (2007).

    Article  Google Scholar 

  4. Shepherd, F.A. et al. Erlotinib in previously treated non-small-cell lung cancer. N. Engl. J. Med. 353, 123–132 (2005).

    CAS  Article  Google Scholar 

  5. Bhattacharjee, A. et al. Classification of human lung carcinomas by mRNA expression profiling reveals distinct adenocarcinoma subclasses. Proc. Natl. Acad. Sci. USA 98, 13790–13795 (2001).

    CAS  Article  Google Scholar 

  6. Garber, M.E. et al. Diversity of gene expression in adenocarcinoma of the lung. Proc. Natl. Acad. Sci. USA 98, 13784–13789 (2001).

    CAS  Article  Google Scholar 

  7. Beer, D.G. et al. Gene-expression profiles predict survival of subjects with lung adenocarcinoma. Nat. Med. 8, 816–824 (2002).

    CAS  Article  Google Scholar 

  8. Wigle, D.A. et al. Molecular profiling of non–small cell lung cancer and correlation with disease-free survival. Cancer Res. 62, 3005–3008 (2002).

    CAS  PubMed  Google Scholar 

  9. Potti, A. et al. A genomic strategy to refine prognosis in early-stage non–small-cell lung cancer. N. Engl. J. Med. 355, 570–580 (2006).

    CAS  Article  Google Scholar 

  10. Chen, H.Y. et al. A five-gene signature and clinical outcome in non-small-cell lung cancer. N. Engl. J. Med. 356, 11–20 (2007).

    CAS  Article  Google Scholar 

  11. Lu, Y. et al. A gene expression signature predicts survival of subjects with stage I non-small cell lung cancer. PLoS Med. 12, e467 (2006).

    Article  Google Scholar 

  12. Dobbin, K.K. et al. Interlaboratory comparability study of cancer gene expression analysis using oligonucleotide microarrays. Clin. Cancer Res. 11, 565–572 (2005).

    CAS  Google Scholar 

  13. Fry, W.A., Phillips, J.L. & Menck, H.R. Ten-year survey of lung cancer treatments and survival in hospitals in the United States. Cancer 86, 1867–1876 (1999).

    CAS  Article  Google Scholar 

  14. Li, C. & Wong, W.H. Model-based analysis of oligonucleotide arrays: expression index computation and outlier detection. Proc. Natl. Acad. Sci. USA 98, 31–36 (2001).

    CAS  Article  Google Scholar 

  15. Moran, C.J. et al. Rantes expression by lung adenocarcinomas is a predictor of survival in stage I subjects. Clin. Cancer Res. 8, 3803–3812 (2002).

    CAS  PubMed  Google Scholar 

  16. Stephenson, A.J. et al. Integration of gene expression profiling and clinical variables to predict prostate carcinoma recurrence after radical prostatectomy. Cancer 104, 290–298 (2005).

    CAS  Article  Google Scholar 

  17. Sotiriou, C. & Piccart, M.J. Taking gene-expression profiling to the clinic: when will molecular signatures become relevant to subject care? Nat. Rev. Cancer 7, 545–553 (2007).

    CAS  Article  Google Scholar 

  18. Gonen, M. & Heller, G. Concordance probability and discriminatory power in proportional hazards regression. Biometrika 92, 965–970 (2005).

    Article  Google Scholar 

Download references


We thank M. Orringer, A. Pickens, F. Taylor, N. Liu, D. Lau, M. Whitehead, L. Chen, L. Vargas, Y. Xiao, M. Maddaus and C. Hoang. We thank M. Heiskanen, L. Liu, D. Reeves and S. Whitley from the US National Cancer Institute Center for Bioinformatics and W. Ricker from Information Management Services for assistance with development of the lung study database and data management. We thank D. Sawyer, J.M. Askew and A. Vaughn of the Cancer and Leukemia Group B Statistical Center, Duke University for quality control of the clinical data. We thank Affymetrix for technical support. This work was supported by US National Cancer Institute grants CA84953, CA84999, CA84995, CA85052 and CA46592 and contracts 263-MQ-319735, 263-MQ-319740, 263-MQ-319746 and 263-MQ-510430 and support from the Canadian Cancer Society.

Author information

Authors and Affiliations



Writing Committee: K.S., J.M.G.T., S.A.E., M.S.T., T.J.Y., W.L.G., S.E., I.J., V.E.S., M.M., R.K., K.K.D., T.L., J.W.J. and D.G.B. Members of the Writing Committee participated in the planning, initiation, data generation, data analysis and manuscript preparation for the project.

Additional participants: T.J.G., D.E.M., A.C.C. and S.H. participated in aspects of sample collection and preparation, data generation and data analysis at the University of Michigan. C.Q.Z., D.S., F.A.S., K.D. and L.S. participated in aspects of sample collection and preparation, data generation and data analysis at the Ontario Cancer Institute. K.N., N.P., B.W., R.V., C.L.-A and T.G. participated in aspects of sample collection and preparation, data generation and data analysis at the Dana-Farber Cancer Institute and Broad Institute. M.G. assembled the clinical data at the H. Lee Moffitt Cancer Center. J.S., M.Z., V.R., M.K., A.V., N.M., W.T. and A.S. participated in aspects of sample collection and preparation, data generation and data analysis at Memorial Sloan-Kettering Cancer Center. B.C. participated in the planning and initiation of the study.

Corresponding authors

Correspondence to James W Jacobson or David G Beer.

Additional information

The consortium consists of the Writing Committee plus additional participants as detailed in the Author Contributions section.

Supplementary information

Supplementary Text and Figures

Supplementary Figs. 1 and 2 (PDF 2763 kb)

Supplementary Table 1

Supplementary Data (XLS 409 kb)

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Director's Challenge Consortium for the Molecular Classification of Lung Adenocarcinoma. Gene expression–based survival prediction in lung adenocarcinoma: a multi-site, blinded validation study. Nat Med 14, 822–827 (2008).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:

Further reading


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing