Advertisement

CRESA: A Deep Learning Approach to Competing Risks, Recurrent Event Survival Analysis

  • Garima GuptaEmail author
  • Vishal Sunder
  • Ranjitha Prasad
  • Gautam Shroff
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11440)

Abstract

Survival analysis refers to a gamut of statistical techniques developed to infer the survival time from time-to-event data. In particular, we are interested in recurrent event survival analysis in the presence of one or more competing risks in each recurrent time-step, in order to obtain the probabilistic relationship between the input covariates and the distribution of event times. Since traditional survival analysis techniques suffer from drawbacks due to strong parametric model constraints and constant hazard based assumptions, we propose a modern deep learning based flexible probabilistic framework for cause-specific recurrent survival analysis. In single-risk scenarios, we propose an LSTM-based model where the time-steps represent the recurrent events for each participant whose covariates may be static or time-varying. To cater to multi-risk scenarios, we build on the single-risk LSTM model and introduce a cumulative incidence curve approach to handle the multiple competing risks using a joint distribution over the event times and each of the competing risks over multiple time-steps and term the proposed novel architecture as CRESA. We use the concordance index per risk and the maximum absolute error in every time-step as the metrics of performance. We demonstrate a superior predictive performance of the proposed approach (single and multiple risk scenarios) as compared to traditional model-based approaches, and deep learning based approaches for synthetic and state-of-the-art public datasets.

Keywords

Recurrent neural networks Competing risks Hazard function Deep learning LSTM Cox models Frailty 

References

  1. 1.
    Alaa, A.M., van der Schaar, M.: Deep multi-task Gaussian processes for survival analysis with competing risks. In: 30th Conference on Neural Information Processing Systems (2017)Google Scholar
  2. 2.
    Andersen, P.K., Gill, R.D.: Cox’s regression model for counting processes: a large sample study. Ann. Stat. 10, 1100–1120 (1982)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Cox, D.R.: Analysis of Survival Data. Routledge, London (2018)CrossRefGoogle Scholar
  4. 4.
    Doksum, K.A., Hbyland, A.: Models for variable-stress accelerated life testing experiments based on wener processes and the inverse gaussian distribution. Technometrics 34(1), 74–82 (1992)CrossRefGoogle Scholar
  5. 5.
    Faraggi, D., Simon, R.: A neural network model for survival data. Stat. Med. 14(1), 73–82 (1995)CrossRefGoogle Scholar
  6. 6.
    Fine, J.P., Gray, R.J.: A proportional hazards model for the subdistribution of a competing risk. J. Am. Stat. Assoc. 94(446), 496–509 (1999)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Gray, R.J.: A class of K-sample tests for comparing the cumulative incidence of a competing risk. Ann. Stat. 16, 1141–1154 (1988)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  9. 9.
    Ishwaran, H., Kogalur, U.B., Blackstone, E.H., Lauer, M.S., et al.: Random survival forests. Ann. Appl. Stat. 2(3), 841–860 (2008)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3, 160035 (2016)CrossRefGoogle Scholar
  11. 11.
    Kaplan, E.L., Meier, P.: Nonparametric estimation from incomplete observations. J. Am. Stat. Assoc. 53, 457–481 (1958)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Katzman, J.L., Shaham, U., Cloninger, A., et al.: DeepSurv: personalized treatment recommender system using a cox proportional hazards deep neural network. BMC Med. Res. Methodol. 18(1), 24 (2018)CrossRefGoogle Scholar
  13. 13.
    Kleinbaum, D.G., Klein, M.: Survival Analysis, vol. 3. Springer, New York (2010).  https://doi.org/10.1007/978-1-4419-6646-9CrossRefzbMATHGoogle Scholar
  14. 14.
    Lee, C., Zame, W.R., Yoon, J., van der Schaar, M.: Deephit: a deep learning approach to survival analysis with competing risks (2018)Google Scholar
  15. 15.
    Lee, M.L.T., Whitmore, G.: Proportional hazards and threshold regression: their theoretical and practical connections. Lifetime Data Anal. 16(2), 196–214 (2010)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Liao, L., Ahn, H.i.: Combining deep learning and survival analysis for asset health management. Int. J. Prognostics Health Manage. (2016)Google Scholar
  17. 17.
    Longini, I.M., Clark, W.S., Byers, R.H., Ward, J.W., Darrow, W.W., et al.: Statistical analysis of the stages of HIV infection using a Markov model. Stat. Med. 8, 831–843 (1989)CrossRefGoogle Scholar
  18. 18.
    Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts (2016)Google Scholar
  19. 19.
    Luck, M., Sylvain, T., Cardinal, H., Lodi, A., Bengio, Y.: Deep learning for patient-specific kidney graft survival analysis. arXiv preprint arXiv:1705.10245 (2017)
  20. 20.
    Lunn, M., McNeil, D.: Applying cox regression to competing risks. Biometrics 51, 524–532 (1995)CrossRefGoogle Scholar
  21. 21.
    Meira-Machado, L., de Uña-Álvarez, J., Cadarso-Suárez, C., Andersen, P.K.: Multi-state models for the analysis of time-to-event data. Stat. Methods Med. Res. 18(2), 195–222 (2009)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Ranganath, R., Perotte, A., Elhadad, N., Blei, D.: Deep survival analysis. arXiv preprint arXiv:1608.02158 (2016)
  23. 23.
    Rondeau, V., Mazroui, Y., Gonzalez, J.R.: Frailtypack: an R package for the analysis of correlated survival data with frailty models using penalized likelihood estimation or parametrical estimation. J. Stat. Softw. 47(4), 1–28 (2012)CrossRefGoogle Scholar
  24. 24.
    Wang, M.C., Chang, S.H.: Nonparametric estimation of a recurrent survival function. J. Am. Stat. Assoc. 94(445), 146–153 (1999)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Wang, P., Li, Y., Reddy, C.K.: Machine learning for survival analysis: a survey. arXiv preprint arXiv:1708.04649 (2017)
  26. 26.
    Wei, L.J., Lin, D.Y., Weissfeld, L.: Regression analysis of multivariate incomplete failure time data by modeling marginal distributions. J. Am. Stat. Assoc. 84, 1065–1073 (1989)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Zhu, X., Yao, J., Huang, J.: Deep convolutional neural network for survival analysis with pathological images. In: Bioinformatics and Biomedicine (BIBM), pp. 544–547. IEEE (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Garima Gupta
    • 1
    Email author
  • Vishal Sunder
    • 1
  • Ranjitha Prasad
    • 1
  • Gautam Shroff
    • 1
  1. 1.TCS Research LabNew DelhiIndia

Personalised recommendations