Format

Send to

Choose Destination
Sci Rep. 2017 Sep 15;7(1):11707. doi: 10.1038/s41598-017-11817-6.

Predicting clinical outcomes from large scale cancer genomic profiles with deep survival models.

Author information

1
Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, 30322, USA.
2
Department of Biostatistics, Mailman School of Public Health, Columbia University, New York, NY, 10032, USA.
3
Department of Biomedical Engineering, Georgia Institute of Technology/Emory University School of Medicine, Atlanta, GA, 30322, USA.
4
Department of Computer Science, Cornell University, Ithaca, NY, 14850, USA.
5
Department of Neurology, Emory University School of Medicine, Atlanta, GA, 30322, USA.
6
Emory University School of Medicine, Atlanta, GA, 30322, USA.
7
Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA, 30322, USA.
8
Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA.
9
Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, 30322, USA. lee.cooper@emory.edu.
10
Department of Biomedical Engineering, Georgia Institute of Technology/Emory University School of Medicine, Atlanta, GA, 30322, USA. lee.cooper@emory.edu.
11
Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA. lee.cooper@emory.edu.

Abstract

Translating the vast data generated by genomic platforms into accurate predictions of clinical outcomes is a fundamental challenge in genomic medicine. Many prediction methods face limitations in learning from the high-dimensional profiles generated by these platforms, and rely on experts to hand-select a small number of features for training prediction models. In this paper, we demonstrate how deep learning and Bayesian optimization methods that have been remarkably successful in general high-dimensional prediction tasks can be adapted to the problem of predicting cancer outcomes. We perform an extensive comparison of Bayesian optimized deep survival models and other state of the art machine learning methods for survival analysis, and describe a framework for interpreting deep survival models using a risk backpropagation technique. Finally, we illustrate that deep survival models can successfully transfer information across diseases to improve prognostic accuracy. We provide an open-source software implementation of this framework called SurvivalNet that enables automatic training, evaluation and interpretation of deep survival models.

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center