Advertisement

RNN-SURV: A Deep Recurrent Model for Survival Analysis

  • Eleonora GiunchigliaEmail author
  • Anton Nemchenko
  • Mihaela van der Schaar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11141)

Abstract

Current medical practice is driven by clinical guidelines which are designed for the “average” patient. Deep learning is enabling medicine to become personalized to the patient at hand. In this paper we present a new recurrent neural network model for personalized survival analysis called rnn-surv. Our model is able to exploit censored data to compute both the risk score and the survival function of each patient. At each time step, the network takes as input the features characterizing the patient and the identifier of the time step, creates an embedding, and outputs the value of the survival function in that time step. Finally, the values of the survival function are linearly combined to compute the unique risk score. Thanks to the model structure and the training designed to exploit two loss functions, our model gets better concordance index (C-index) than the state of the art approaches.

References

  1. 1.
    Aalen, O.: A Model for nonparametric regression analysis of counting processes. In: Klonecki, W., Kozek, A., Rosiński, J. (eds.) Mathematical Statistics and Probability Theory. LNS, vol. 2, pp. 1–25. Springer, New York (1980).  https://doi.org/10.1007/978-1-4615-7397-5_1CrossRefGoogle Scholar
  2. 2.
    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. 17, 1169–1186 (1998)CrossRefGoogle Scholar
  3. 3.
    Breslow, N.E., Chatterjee, N.: Design and analysis of two-phase studies with binary outcome applied to Wilm’s tumour prognosis. Appl. Stat. 48, 457–468 (1999)zbMATHGoogle Scholar
  4. 4.
    Buckley, J., James, I.: Linear regression with censored data. Biometrika 66(3), 429–436 (1979)CrossRefGoogle Scholar
  5. 5.
    Cox, D.R.: Partial likelihood. Biometrika 62(2), 269 (1975)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Dezfouli, H.N.: Improving gastric cancer outcome prediction using time-point artificial neural networks models. Cancer Inform. 16, 117693511668606 (2017)CrossRefGoogle Scholar
  7. 7.
    Faraggi, D., Simon, R.: A neural network model for survival data. Stat. Med. 14(1), 73–82 (1995)CrossRefGoogle Scholar
  8. 8.
    Gal, Y., Ghahramani, Z.: A theoretically grounded application of dropout in recurrent neural networks. In: 29th NIPS, pp. 1019–1027 (2016)Google Scholar
  9. 9.
    Harrell, F.J., Califf, R., Pryor, D., Lee, K., Rosati, R.: Evaluating the yield of medical tests. JAMA 247(18), 2543–2546 (1982)CrossRefGoogle Scholar
  10. 10.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997).  https://doi.org/10.1162/neco.1997.9.8.1735CrossRefGoogle Scholar
  11. 11.
    Ishwaran, H., Kogalur, U.B., Blackstone, E.H., Lauer, M.S.: Random survival forests. Ann. Appl. Stat. 2, 841–860 (2008)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Kaplan, E.L., Meier, P.: Non parametric estimation from incomplete observations. J. Am. Stat. Assoc. 53, 457–481 (1958)CrossRefGoogle Scholar
  13. 13.
    Katzman, J., Shaham, U., Cloninger, A., Bates, J., Jiang, T., Kluger, Y.: Deep survival: a deep cox proportional hazards network. CoRR (2016)Google Scholar
  14. 14.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs/1412.6980 (2014). http://arxiv.org/abs/1412.6980
  15. 15.
    Klein, J.P., Moeschberger, M.L.: Survival Analysis Techniques for Censored and Truncated Data, 2nd edn. Springer, New York (2003)zbMATHGoogle Scholar
  16. 16.
    Kyle, R., et al.: Use of monclonal serum immunoglobulin free light chains to predict overall survival in the general population. N. Engl. J. Med. 354, 1362–1369 (2006)CrossRefGoogle Scholar
  17. 17.
    Li, Y., Wang, J., Ye, J., Reddy, C.K.: A multi-task learning formulation for survival analysis. In: 22nd ACM SIGKDD, KDD 2016, pp. 1715–1724. ACM, New York (2016)Google Scholar
  18. 18.
    Liestbl, K., Andersen, P.K., Andersen, U.: Survival analysis and neural nets. Stat. Med. 13(12), 1189–1200 (1994)CrossRefGoogle Scholar
  19. 19.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: 27th ICML, pp. 807–814 (2010)Google Scholar
  20. 20.
    Prechelt, L.: Early stopping—but when? In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 53–67. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-35289-8_5CrossRefGoogle Scholar
  21. 21.
    Shivaswamy, P.K., Chu, W., Jansche, M.: A support vector approach to censored targets. In: Proceedings of 7th IEEE ICDM, ICDM 2007, pp. 655–660. IEEE Computer Society (2007).  https://doi.org/10.1109/ICDM.2007.93
  22. 22.
    Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  23. 23.
    Steck, H., Krishnapuram, B., Dehing-oberije, C., Lambin, P., Raykar, V.C.: On ranking in survival analysis: bounds on the concordance index. In: Platt, J.C., Koller, D., Singer, Y., Roweis, S.T. (eds.) 20th NIPS, pp. 1209–1216. Curran Associates Inc., New York (2008)Google Scholar
  24. 24.
    Van Buuren, S., Oudshoorn, K.: Flexible mutlivariate imputation by MICE. TNO, Leiden (1999)Google Scholar
  25. 25.
    Venables, W.N., Ripley, B.D.: Modern Applied Statistics with S. Springer, Heidelberg (2002).  https://doi.org/10.1007/978-0-387-21706-2CrossRefzbMATHGoogle Scholar
  26. 26.
    Yu, C.N., Greiner, R., Lin, H.C., Baracos, V.: Learning patient-specific cancer survival distributions as a sequence of dependent regressors. In: Shawe-Taylor, J., Zemel, R.S., Bartlett, P.L., Pereira, F., Weinberger, K.Q. (eds.) 24th NIPS, pp. 1845–1853. Curran Associates Inc., New York (2011)Google Scholar
  27. 27.
    Zhang, J., Chen, L., Vanasse, A., Courteau, J., Wang, S.: Survival prediction by an integrated learning criterion on intermittently varying healthcare data. In: 30th AAAI, AAAI 2016, pp. 72–78. AAAI Press (2016)Google Scholar
  28. 28.
    Zhu, X., Yao, J., Huang, J.: Deep convolutional neural network for survival analysis with pathological images. In: IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016, Shenzhen, China, pp. 544–547 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Eleonora Giunchiglia
    • 1
    Email author
  • Anton Nemchenko
    • 2
  • Mihaela van der Schaar
    • 2
    • 3
    • 4
  1. 1.DIBRISUniversità di GenovaGenovaItaly
  2. 2.Department of Electrical and Computer EngineeringUCLALos AngelesUSA
  3. 3.Department of Engineering ScienceUniversity of OxfordOxfordUK
  4. 4.Alan Turing InstituteLondonUK

Personalised recommendations