Research Papers:

A multi-step classifier addressing cohort heterogeneity improves performance of prognostic biomarkers in three cancer types

Ellis Patrick _, Sarah-Jane Schramm, John T. Ormerod, Richard A. Scolyer, Graham J. Mann, Samuel Mueller and Jean Y.H. Yang

PDF  |  HTML  |  Supplementary Files  |  How to cite

Oncotarget. 2017; 8:2807-2815. https://doi.org/10.18632/oncotarget.13203

Metrics: PDF 1601 views  |   HTML 2592 views  |   ?  


Ellis Patrick1,6,7,8,10, Sarah-Jane Schramm2,3, John T. Ormerod1,9, Richard A. Scolyer4,5, Graham J. Mann2,3, Samuel Mueller1,*, Jean Y.H. Yang1,3,*

1School of Mathematics and Statistics, The University of Sydney, Sydney, Australia

2The Westmead Millennium Institute for Medical Research, The University of Sydney, Sydney, Australia

3Melanoma Institute Australia, The University of Sydney, Sydney, Australia

4Tissue Pathology and Diagnostic Oncology, Royal Prince Alfred Hospital, Sydney, Australia

5Discipline Pathology, Sydney Medical School, The University of Sydney, Sydney, Australia

6Program in Translational NeuroPsychiatric Genomics, Institute for the Neurosciences, Department of Neurology, Brigham and Women’s Hospital, Boston, MA, USA

7Harvard Medical School, Boston, MA, USA

8Program in Medical and Population Genetics, Broad Institute, Cambridge, MA, USA

9ARC Centre of Excellence for Mathematical & Statistical Frontiers

10Program in Translational NeuroPsychiatric Genomics, Institute for the Neurosciences, Department of Psychiatry, Brigham and Women’s Hospital, Boston, MA, USA

*These authors have contributed equally to this work

Correspondence to:

Jean Y.H. Yang, email: [email protected]

Keywords: biomarker, classification, cancer, pathology, prognosis

Received: March 12, 2016    Accepted: September 26, 2016    Published: November 08, 2016


Cancer research continues to highlight the extensive genetic diversity that exists both between and within tumors. This intrinsic heterogeneity poses one of the central challenges to predicting patient clinical outcome and the personalization of treatments. Despite progress in some individual tumor types, it is not yet possible to prospectively, accurately classify patients by expected survival. One hypothesis proposed to explain this is that the prognostic classifiers developed to date are insufficiently sensitive and specific; however it is also possible that patients are not equally easy to classify by any given biomarker. We demonstrate in a cohort of 45 AJCC stage III melanoma patients that clinico-pathologic biomarkers can identify those patients that are most likely to be misclassified by a molecular biomarker. The process of modelling the classifiability of patients was then replicated in a cohort of 49 stage II breast cancer patients and 53 stage III colon cancer patients. A multi-step procedure incorporating this information not only improved classification accuracy but also indicated the specific clinical attributes that had made classification problematic in each cohort. These findings show that, even when cohorts are of moderate size, including features that explain the patient-specific performance of a prognostic biomarker in a classification framework can improve the modelling and estimation of survival.

Creative Commons License All site content, except where otherwise noted, is licensed under a Creative Commons Attribution 4.0 License.
PII: 13203