Predicting clinical outcomes from large scale cancer genomic profiles with deep survival models
| Autor: | Lee Ad Cooper, Congzheng Song, Fatemeh Amrollahi, Mohamed Amgad, Sameer H. Halani, Safoora Yousefi, José E. Velázquez Vega, David A. Gutman, Daniel J. Brat, Joshua E. Lewis, Chengliang Dong |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
0301 basic medicine
Survival Computer science Bayesian probability Datasets as Topic lcsh:Medicine Machine learning computer.software_genre Article 03 medical and health sciences Bayes' theorem 0302 clinical medicine Deep Learning Neoplasms Humans Medicine lcsh:Science Survival analysis 030304 developmental biology 0303 health sciences Multidisciplinary Artificial neural network business.industry Scale (chemistry) Deep learning Bayesian optimization lcsh:R Cancer Bayes Theorem Genomics medicine.disease Prognosis Backpropagation 3. Good health Treatment Outcome 030104 developmental biology 030220 oncology & carcinogenesis lcsh:Q Neural Networks Computer Data mining Artificial intelligence business computer Software Predictive modelling |
| Zdroj: | Scientific Reports, Vol 7, Iss 1, Pp 1-11 (2017) Scientific Reports |
| ISSN: | 2045-2322 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |