Systematic analysis of challenge-driven improvements in molecular prognostic models for breast cancer.

Sci Transl Med 2013 Apr;5(181):181re1

Sage Bionetworks, 1100 Fairview Avenue North, MS: M1-C108, Seattle, WA 98109, USA.

Although molecular prognostics in breast cancer are among the most successful examples of translating genomic analysis to clinical applications, optimal approaches to breast cancer clinical risk prediction remain controversial. The Sage Bionetworks-DREAM Breast Cancer Prognosis Challenge (BCC) is a crowdsourced research study for breast cancer prognostic modeling using genome-scale data. The BCC provided a community of data analysts with a common platform for data access and blinded evaluation of model accuracy in predicting breast cancer survival on the basis of gene expression data, copy number data, and clinical covariates. This approach offered the opportunity to assess whether a crowdsourced community Challenge would generate models of breast cancer prognosis commensurate with or exceeding current best-in-class approaches. The BCC comprised multiple rounds of blinded evaluations on held-out portions of data on 1981 patients, resulting in more than 1400 models submitted as open source code. Participants then retrained their models on the full data set of 1981 samples and submitted up to five models for validation in a newly generated data set of 184 breast cancer patients. Analysis of the BCC results suggests that the best-performing modeling strategy outperformed previously reported methods in blinded evaluations; model performance was consistent across several independent evaluations; and aggregating community-developed models achieved performance on par with the best-performing individual models.

Download full-text PDF

Source
http://dx.doi.org/10.1126/scitranslmed.3006112DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3897241PMC
April 2013
47 Reads

Publication Analysis

Top Keywords

breast cancer
32
data
8
models breast
8
cancer
8
data set
8
blinded evaluations
8
breast
8
cancer prognosis
8
models
7
approaches bcc
4
bcc comprised
4
comprised multiple
4
best-in-class approaches
4
current best-in-class
4
commensurate exceeding
4
exceeding current
4
multiple rounds
4
models submitted
4
evaluations held-out
4
held-out portions
4

References

(Supplied by CrossRef)

International journal of cancer. Journal international du cancer 2013

Perou et al.
Nature; Physical Science (London) 2000

Sorlie et al.
PNAS 2001

van de Vijver et al.
New England Journal of Medicine 2002

New England Journal of Medicine 2004

van 't Veer et al.
Nature; Physical Science (London) 2002

Rutgers et al.
European journal of cancer (Oxford, England : 1990) 2011

Cardoso et al.
2007

Sparano et al.
Clinical breast cancer 2006

Annals of Internal Medicine 2008

Journal of Clinical Oncology 2005

Similar Publications