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

Safoora Yousefi, Fatemeh Amrollahi, Mohamed Amgad, Chengliang Dong, Joshua E. Lewis, Congzheng Song, David A. Gutman, Sameer H. Halani, Jose Enrique Velazquez Vega, Daniel J. Brat, Lee A.D. Cooper*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

129 Scopus citations


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.

Original languageEnglish (US)
Article number11707
JournalScientific Reports
Issue number1
StatePublished - Dec 1 2017

ASJC Scopus subject areas

  • General


Dive into the research topics of 'Predicting clinical outcomes from large scale cancer genomic profiles with deep survival models'. Together they form a unique fingerprint.

Cite this