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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
Andersen, P.K., Gill, R.D.: Cox’s regression model for counting processes: a large sample study. Ann. Stat. 10, 1100–1120 (1982)
Cox, D.R.: Analysis of Survival Data. Routledge, London (2018)
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)
Faraggi, D., Simon, R.: A neural network model for survival data. Stat. Med. 14(1), 73–82 (1995)
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)
Gray, R.J.: A class of K-sample tests for comparing the cumulative incidence of a competing risk. Ann. Stat. 16, 1141–1154 (1988)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Ishwaran, H., Kogalur, U.B., Blackstone, E.H., Lauer, M.S., et al.: Random survival forests. Ann. Appl. Stat. 2(3), 841–860 (2008)
Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3, 160035 (2016)
Kaplan, E.L., Meier, P.: Nonparametric estimation from incomplete observations. J. Am. Stat. Assoc. 53, 457–481 (1958)
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)
Kleinbaum, D.G., Klein, M.: Survival Analysis, vol. 3. Springer, New York (2010). https://doi.org/10.1007/978-1-4419-6646-9
Lee, C., Zame, W.R., Yoon, J., van der Schaar, M.: Deephit: a deep learning approach to survival analysis with competing risks (2018)
Lee, M.L.T., Whitmore, G.: Proportional hazards and threshold regression: their theoretical and practical connections. Lifetime Data Anal. 16(2), 196–214 (2010)
Liao, L., Ahn, H.i.: Combining deep learning and survival analysis for asset health management. Int. J. Prognostics Health Manage. (2016)
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)
Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts (2016)
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)
Lunn, M., McNeil, D.: Applying cox regression to competing risks. Biometrics 51, 524–532 (1995)
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)
Ranganath, R., Perotte, A., Elhadad, N., Blei, D.: Deep survival analysis. arXiv preprint arXiv:1608.02158 (2016)
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)
Wang, M.C., Chang, S.H.: Nonparametric estimation of a recurrent survival function. J. Am. Stat. Assoc. 94(445), 146–153 (1999)
Wang, P., Li, Y., Reddy, C.K.: Machine learning for survival analysis: a survey. arXiv preprint arXiv:1708.04649 (2017)
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)
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gupta, G., Sunder, V., Prasad, R., Shroff, G. (2019). CRESA: A Deep Learning Approach to Competing Risks, Recurrent Event Survival Analysis. In: Yang, Q., Zhou, ZH., Gong, Z., Zhang, ML., Huang, SJ. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2019. Lecture Notes in Computer Science(), vol 11440. Springer, Cham. https://doi.org/10.1007/978-3-030-16145-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-16145-3_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-16144-6
Online ISBN: 978-3-030-16145-3
eBook Packages: Computer ScienceComputer Science (R0)