Skip to main content
SpringerLink
Log in

A Federated Cox Model with Non-proportional Hazards

  • Chapter
  • First Online:
Multimodal AI in Healthcare

Part of the book series: Studies in Computational Intelligence ((SCI,volume 1060))

Abstract

Recent research has shown the potential for neural networks to improve upon classical survival models such as the Cox model, which is widely used in clinical practice. Neural networks, however, typically rely on data that are centrally available, whereas healthcare data are frequently held in secure silos. We present a federated Cox model that accommodates this data setting and also relaxes the proportional hazards assumption, allowing time-varying covariate effects. In this latter respect, our model does not require explicit specification of the time-varying effects, reducing upfront organisational costs compared to previous works. We experiment with publicly available clinical datasets and demonstrate that the federated model is able to perform as well as a standard model.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 199.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    For source code, see https://github.com/dkaizhang/federated-survival.

References

  1. Andreux, M., Manoel, A., Menuet, R., Saillard, C., & Simpson, C. (2020). Federated survival analysis with discrete-time cox models (pp. 1–21).

    Google Scholar 

  2. Antolini, L., Boracchi, P., & Biganzoli, E. (2005). A time-dependent discrimination index for survival data. Statistics in Medicine, 24(24), 3927–3944. https://doi.org/10.1002/sim.2427

    Article  MathSciNet  Google Scholar 

  3. Bellera, C. A., MacGrogan, G., Debled, M., De Lara, C. T., Brouste, V., & Mathoulin-Pélissier, S. (2010). Variables with time-varying effects and the Cox model: Some statistical concepts illustrated with a prognostic factor study in breast cancer. BMC Medical Research Methodology, 10. https://doi.org/10.1186/1471-2288-10-20

  4. Bello, G. A., Dawes, T. J., Duan, J., Biffi, C., de Marvao, A., Howard, L. S., Gibbs, J. S. R., Wilkins, M. R., Cook, S. A., Rueckert, D., & O’Regan, D. P. (2019). Deep-learning cardiac motion analysis for human survival prediction. Nature Machine Intelligence, 1(2), 95–104. https://doi.org/10.1038/s42256-019-0019-2

    Article  Google Scholar 

  5. Coradini, D., Daidone, M. G., Boracchi, P., Biganzoli, E., Oriana, S., Bresciani, G., Pellizzaro, C., Tomasic, G., Di Fronzo, G., & Marubini, E. (2000). Time-dependent relevance of steroid receptors in breast cancer. Journal of Clinical Oncology, 18(14), 2702–2709. https://doi.org/10.1200/JCO.2000.18.14.2702

    Article  Google Scholar 

  6. Cox, D. R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society. Series B (Methodological), 34(2), 187–202. https://doi.org/10.1111/j.2517-6161.1972.tb00899.x, https://www.jstor.org/stable/2985181

  7. Craig, E., Zhong, C., & Tibshirani, R. (2021). Survival stacking: Casting survival analysis as a classification problem (pp. 1–17). arXiv:abs/2107.13480

  8. Dai, W., Jiang, X., Bonomi, L., Li, Y., Xiong, H., & Ohno-Machado, L. (2020). VERTICOX: Vertically distributed cox proportional hazards model using the alternating direction method of multipliers. IEEE Transactions on Knowledge and Data Engineering, 4347(c), 1. https://doi.org/10.1109/tkde.2020.2989301

  9. Faraggi, D., & Simon, R. (1995). A neural network model for survival data. Statistics in Medicine, 14(1), 73–82. https://doi.org/10.1002/sim.4780140108

    Article  Google Scholar 

  10. Gensheimer, M. F., Narasimhan, B. (2019). A scalable discrete-time survival model for neural networks. PeerJ, 1–19. https://doi.org/10.7717/peerj.6257

  11. Gore, S. M., Pocock, S. J., & Kerr, G. R. (1984). Regression models and non-proportional hazards in the analysis of breast cancer survival author. Journal of the Royal Statistical Society. Series C (Applied Statistics), 33(2), 176–195.

    Google Scholar 

  12. Graf, E., Schmoor, C., Sauerbrei, W., & Schumacher, M. (1999). Assessment and comparison of prognostic classification schemes for survival data. Statistics in Medicine, 18(17–18), 2529–2545. https://doi.org/10.1002/(sici)1097-0258(19990915/30)18:17/18<2529::aid-sim274>3.0.co;2-5

    Article  Google Scholar 

  13. Katzman, J. L., Shaham, U., Cloninger, A., Bates, J., Jiang, T., & Kluger, Y. (2018). DeepSurv: Personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Medical Research Methodology, 18(1), 1–11. https://doi.org/10.1186/s12874-018-0482-1

    Article  Google Scholar 

  14. Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G., & King, D. (2019). Key challenges for delivering clinical impact with artificial intelligence. BMC Medicine, 17(1), 1–9. https://doi.org/10.1186/s12916-019-1426-2

    Article  Google Scholar 

  15. Kvamme, H., & Borgan, O. (2019). Continuous and discrete-time survival prediction with neural networks.

    Google Scholar 

  16. Kvamme, H., Borgan, O., & Scheel, I. (2019). Time-to-event prediction with neural networks and cox regression. Journal of Machine Learning Research, 20, 1–30.

    MathSciNet  MATH  Google Scholar 

  17. Li, H., Boimel, P., Janopaul-Naylor, J., Zhong, H., Xiao, Y., Ben-Josef, E., & Fan, Y. (2019). Deep convolutional neural networks for imaging data based survival analysis of rectal cancer (pp. 1–4).

    Google Scholar 

  18. Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018). Federated optimization in heterogeneous networks. arxiv:abs/1812.06127

  19. Lu, C. L., Wang, S., Ji, Z., Wu, Y., Xiong, L., Jiang, X., & Ohno-Machado, L. (2015). WebDISCO: A web service for distributed cox model learning without patient-level data sharing. Journal of the American Medical Informatics Association, 22(6), 1212–1219. https://doi.org/10.1093/jamia/ocv083

    Article  Google Scholar 

  20. Luck, M., Sylvain, T., Cardinal, H., Lodi, A., & Bengio, Y. (2017). Deep learning for patient-specific kidney graft survival analysis (Nips 2017). arxiv:abs/1705.10245

  21. McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Agüera y Arcas, B. (2017). Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017 (Vol. 54).

    Google Scholar 

  22. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Köpf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., & Chintala, S. (2019). PyTorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, 32(NeurIPS).

    Google Scholar 

  23. Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., Ourselin, S., Sheller, M., Summers, R. M., Trask, A., Xu, D., Baust, M., & Cardoso, M. J. (2020). The future of digital health with federated learning. NPJ Digital Medicine, 3(1), 1–7. https://doi.org/10.1038/s41746-020-00323-1

  24. Wang, P., Li, Y., & Reddy, C. K. (2019). Machine learning for survival analysis: A survey. ACM Computing Surveys, 51(6). https://doi.org/10.1145/3214306

  25. Wiens, J., Saria, S., Sendak, M., Ghassemi, M., Liu, V. X., Doshi-Velez, F., Jung, K., Heller, K., Kale, D., Saeed, M., Ossorio, P. N., Thadaney-Israni, S., & Goldenberg, A. (2019). Do no harm: A roadmap for responsible machine learning for health care. Nature Medicine, 25(September). https://doi.org/10.1038/s41591-019-0548-6

  26. Yang, L., Beliard, C., & Rossi, D.: Heterogeneous data-aware federated learning (1).

    Google Scholar 

  27. Zhu, X., Yao, J., & Huang, J. (2017). Deep convolutional neural network for survival analysis with pathological images. In Proceedings—2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016 (Vol. 2, pp. 544–547). https://doi.org/10.1109/BIBM.2016.7822579

  28. Zhu, X., Yao, J., Zhu, F., & Huang, J. (2017). WSISA: Making survival prediction from whole slide histopathological images. In Proceedings—30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 (pp. 6855–6863). https://doi.org/10.1109/CVPR.2017.725

Download references

Acknowledgements

This work was supported by the UKRI CDT in AI for Healthcare http://ai4health.io (Grant No. EP/S023283/1).

Author information

Authors and Affiliations

  1. Imperial College London, SW7 2BX, London, UK

    D. Kai Zhang

  2. Imperial College London, SW7 2BX, London, UK

    Francesca Toni

  3. Imperial College London, SW7 2BX, London, UK

    Matthew Williams

Authors
  1. D. Kai Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Francesca Toni
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Matthew Williams
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to D. Kai Zhang .

Editor information

Editors and Affiliations

  1. Oak-Ridge National Laboratory (ORNL), Center for Biomedical Informatics, The University of Tennessee Health Science Center (UTHSC), Memphis, TN, USA

    Arash Shaban-Nejad

  2. School of Nursing, University of Minnesota, Minneapolis, MN, USA

    Martin Michalowski

  3. Research Center, IBM Almaden, San Jose, CA, USA

    Simone Bianco

Appendix A Additional Figures

Appendix A Additional Figures

See Figs. 4, 5, 6.

Fig. 4
figure 4

Discretisation and interpolation

Full size image
Fig. 5
figure 5

Two sets of survival estimates with correct ranking (green above blue) but poor calibration given under-/overestimation of true survival curves

Full size image
Fig. 6
figure 6

Kaplan-Meier estimates with 95% confidence interval

Full size image

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Zhang, D.K., Toni, F., Williams, M. (2023). A Federated Cox Model with Non-proportional Hazards. In: Shaban-Nejad, A., Michalowski, M., Bianco, S. (eds) Multimodal AI in Healthcare. Studies in Computational Intelligence, vol 1060. Springer, Cham. https://doi.org/10.1007/978-3-031-14771-5_12

Download citation

Publish with us

Policies and ethics

Search

Navigation