Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress 2023 EHA Congress 2023 ASCO Annual Meeting
Clinical Collections
Advances in Alzheimer’s

At a glance: The ONWARDS insulin icodec trials

A round-up of the ONWARDS phase 3 clinical trials evaluating the novel weekly insulin icodec in people with diabetes.
ADVANCED SEARCH
Log in
Top
BMC Medical Research Methodology
Published in: BMC Medical Research Methodology 1/2018

Open Access 01-12-2018 | Research article

DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network

Authors: Jared L. Katzman, Uri Shaham, Alexander Cloninger, Jonathan Bates, Tingting Jiang, Yuval Kluger

Published in: BMC Medical Research Methodology | Issue 1/2018

Login to get access

Abstract

Background

Medical practitioners use survival models to explore and understand the relationships between patients’ covariates (e.g. clinical and genetic features) and the effectiveness of various treatment options. Standard survival models like the linear Cox proportional hazards model require extensive feature engineering or prior medical knowledge to model treatment interaction at an individual level. While nonlinear survival methods, such as neural networks and survival forests, can inherently model these high-level interaction terms, they have yet to be shown as effective treatment recommender systems.

Methods

We introduce DeepSurv, a Cox proportional hazards deep neural network and state-of-the-art survival method for modeling interactions between a patient’s covariates and treatment effectiveness in order to provide personalized treatment recommendations.

Results

We perform a number of experiments training DeepSurv on simulated and real survival data. We demonstrate that DeepSurv performs as well as or better than other state-of-the-art survival models and validate that DeepSurv successfully models increasingly complex relationships between a patient’s covariates and their risk of failure. We then show how DeepSurv models the relationship between a patient’s features and effectiveness of different treatment options to show how DeepSurv can be used to provide individual treatment recommendations. Finally, we train DeepSurv on real clinical studies to demonstrate how it’s personalized treatment recommendations would increase the survival time of a set of patients.

Conclusions

The predictive and modeling capabilities of DeepSurv will enable medical researchers to use deep neural networks as a tool in their exploration, understanding, and prediction of the effects of a patient’s characteristics on their risk of failure.
Literature
1.
2.
Royston P, Altman DG. External validation of a cox prognostic model: principles and methods. BMC Med Res Methodol. 2013; 13(1):1.CrossRef
3.
Bair E, Tibshirani R. Semi-supervised methods to predict patient survival from gene expression data. PLoS Biol. 2004; 2(4):108.CrossRef
4.
Cheng W-Y, Yang T-HO, Anastassiou D. Development of a prognostic model for breast cancer survival in an open challenge environment. Sci Total Environ. 2013; 5(181):181–5018150.
5.
6.
Liestbl K, Andersen PK, Andersen U. Survival analysis and neural nets. Stat Med. 1994; 13(12):1189–200.CrossRef
7.
Street WN. A neural network model for prognostic prediction In: Kaufmann M, editor. Proceedings of the Fifteenth International Conference on Machine Learning. San Francisco: 1998. p. 540–46.
8.
Jerez JM, Franco L, Alba E, Llombart-Cussac A, Lluch A, Ribelles N, Munárriz B, Martín M. Improvement of breast cancer relapse prediction in high risk intervals using artificial neural networks. Breast Cancer Res Treat. 2005; 94(3):265–72. https://​doi.​org/​10.​1007/​s10549-005-9013-y.
9.
Biganzoli E, Boracchi P, Mariani L, Marubini E. Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. Stat Med. 1998; 17(10):1169–86.CrossRefPubMed
10.
11.
Sargent DJ. Comparison of artificial neural networks with other statistical approaches. Cancer. 2001; 91(S8):1636–42.CrossRefPubMed
12.
Xiang A, Lapuerta P, Ryutov A, Buckley J, Azen S. Comparison of the performance of neural network methods and cox regression for censored survival data. Comput Stat Data Anal. 2000; 34(2):243–57.CrossRef
13.
Mariani L, Coradini D, Biganzoli E, Boracchi P, Marubini E, Pilotti S, Salvadori B, Silvestrini R, Veronesi U, Zucali R, et al. Prognostic factors for metachronous contralateral breast cancer: a comparison of the linear cox regression model and its artificial neural network extension. Breast Cancer Res Treat. 1997; 44(2):167–78.CrossRefPubMed
14.
Therneau T, Grambsch PM. Modeling Survival Data : Extending the Cox Model. New York: Springer; 2000.CrossRef
15.
Ishwaran H, Kogalur UB. Random survival forests for r. R News. 2007; 7(2):25–31.
16.
Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS. Random survival forests. Ann Appl Statist. 2008; 2(3):841–60.CrossRef
17.
Ranganath R, Perotte A, Elhadad N, Blei D. Deep survival analysis In: Doshi-Velez F, Fackler J, Kale D, Wallace B, Weins J, editors. Proceedings of the 1st Machine Learning for Healthcare Conference. Proceedings of Machine Learning Research, vol 56. Northeastern University, Boston, MA, USA: PMLR: 2016. p. 101–14. http://​proceedings.​mlr.​press/​v56/​Ranganath16.​html.
18.
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014; 15(1):1929–58.
19.
Klambauer G, Unterthiner T, Mayr A, Hochreiter S. Self-normalizing neural networks. In: Advances in Neural Information Processing Systems: 2017. p. 972–81. arXiv preprint. 1706.​02515.
20.
21.
Nesterov Y. Gradient methods for minimizing composite functions. Math Program. 2013; 140(1):125–61.CrossRef
22.
Senior A, Heigold G, Ranzato M, Yang K. An empirical study of learning rates in deep neural networks for speech recognition. In: Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE: 2013. p. 6724–8.
23.
Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res. 2012; 13(1):281–305.
24.
Harrell FE, Lee KL, Califf RM, Pryor DB, Rosati RA. Regression modeling strategies for improved prognostic prediction. Stat Med. 1984; 3(2):143–52.CrossRefPubMed
25.
Efron B, Tibshirani RJ. An Introduction to the Bootstrap. New York: Chapman & Hall; 1993.CrossRef
26.
27.
Hosmer DW, Lemeshow S, May S. Applied Survival Analysis: Regression Modeling of Time to Event Data. 2nd ed. New York: Wiley-Interscience; 2008.CrossRef
28.
Knaus WA, Harrell FE, Lynn J, Goldman L, Phillips RS, Connors AF, Dawson NV, Fulkerson WJ, Califf RM, Desbiens N, et al. The support prognostic model: objective estimates of survival for seriously ill hospitalized adults. Ann Intern Med. 1995; 122(3):191–203.CrossRefPubMed
29.
Curtis C, Shah SP, Chin S-F, Turashvili G, Rueda OM, Dunning MJ, Speed D, Lynch AG, Samarajiwa S, Yuan Y, et al. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature. 2012; 486(7403):346–52.PubMedPubMedCentral
30.
Lakhanpal R, Sestak I, Shadbolt B, Bennett GM, Brown M, Phillips T, Zhang Y, Bullman A, Rezo A. Ihc4 score plus clinical treatment score predicts locoregional recurrence in early breast cancer. The Breast. 2016; 29:147–52.CrossRefPubMed
31.
Foekens JA, Peters HA, Look MP, Portengen H, Schmitt M, Kramer MD, Brünner N, Jänicke F, Meijer-van Gelder ME, Henzen-Logmans SC, et al. The urokinase system of plasminogen activation and prognosis in 2780 breast cancer patients. Cancer Res. 2000; 60(3):636–43.PubMed
32.
Schumacher M, Bastert G, Bojar H, Huebner K, Olschewski M, Sauerbrei W, Schmoor C, Beyerle C, Neumann R, Rauschecker H. Randomized 2 x 2 trial evaluating hormonal treatment and the duration of chemotherapy in node-positive breast cancer patients. german breast cancer study group. J Clin Oncol. 1994; 12(10):2086–93.CrossRefPubMed
33.
Altman DG, Royston P. What do we mean by validating a prognostic model?Stat Med. 2000; 19(4):453–73.CrossRefPubMed
34.
35.
Sobol IM. Uniformly distributed sequences with an additional uniform property. USSR Comput Math Math Phys. 1976; 16(5):236–42.CrossRef
36.
Metadata
Title
DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network
Authors
Jared L. Katzman
Uri Shaham
Alexander Cloninger
Jonathan Bates
Tingting Jiang
Yuval Kluger
Publication date
01-12-2018
Publisher
BioMed Central
Published in
BMC Medical Research Methodology / Issue 1/2018
Electronic ISSN: 1471-2288
DOI
https://doi.org/10.1186/s12874-018-0482-1

Other articles of this Issue 1/2018

BMC Medical Research Methodology 1/2018 Go to the issue

Research article

Simulation shows undesirable results for competing risks analysis with time-dependent covariates for clinical outcomes

Research article

Lasso regularization for left-censored Gaussian outcome and high-dimensional predictors

Research article

Access to primary care for socio-economically disadvantaged older people in rural areas: exploring realist theory using structural equation modelling in a linked dataset

Research article

Multistate recursively imputed survival trees for time-to-event data analysis: an application to AIDS and mortality post-HIV infection data

Research article

The patient experience with treatment and self-management (PETS) questionnaire: translation and cultural adaption of the Norwegian version

Research article

A comparison of estimators from self-controlled case series, case-crossover design, and sequence symmetry analysis for pharmacoepidemiological studies