Abstract

Causal mediation analysis aims to investigate the underlying mechanism

of how an exposure exerts its effects on the outcome mediated by intermediate variables. However, existing methods for causal mediation analysis in the context of

survival models are primarily focused on estimating average causal effects and are

difficult to apply to precision medicine. Recently, machine learning has emerged

as a promising tool for precisely estimating individualized causal effects without

assuming specific model forms. This study proposes a novel method, conditional

generative adversarial network (CGAN)-based individualized causal mediation analysis with survival outcomes (CGAN-ICMA-SO), to infer individualized causal effects

with survival outcomes based on the CGAN framework. We show that the estimated

distribution of the proposed inferential conditional generator converges to the true

conditional distribution under mild conditions. Our numerical experiments indicate

that CGAN-ICMA-SO surpasses five other state-of-the-art methods. Applying the

proposed method to an Alzheimer’s disease (AD) Neuroimaging Initiative dataset

reveals the individualized direct and indirect effects of the APOE-ε4 allele on time

to AD onset.

Information

Preprint No.SS-2024-0188
Manuscript IDSS-2024-0188
Complete AuthorsCheng Huan, Xinyuan Song, Hongwei Yuan
Corresponding AuthorsXinyuan Song
Emailsxysong@sta.cuhk.edu.hk

References

  1. Abrevaya, J., Y.-C. Hsu, and R. P. Lieli (2015). Estimating conditional average treatment effects. Journal of Business & Economic Statistics 33(4), 485–505.
  2. Albert, J. M. and W. Wang (2015). Sensitivity analyses for parametric causal mediation effect estimation. Biostatistics 16(2), 339–351.
  3. Bica, I., J. Jordon, and M. van der Schaar (2020). Estimating the effects of continuous-valued interventions using generative adversarial networks. Advances in Neural Information Processing Systems 33, 16434–16445.
  4. Blacker, D., J. Haines, L. Rodes, H. Terwedow, R. Go, L. Harrell, R. Perry, S. Bassett, G. Chase,
  5. D. Meyers, et al. (1997). Apoe-4 and age at onset of alzheimer’s disease: the nimh genetics initiative. Neurology 48(1), 139–147.
  6. Chapfuwa, P., S. Assaad, S. Zeng, M. J. Pencina, L. Carin, and R. Henao (2021). Enabling counterfactual survival analysis with balanced representations. In Proceedings of the Conference on Health, Inference, and Learning, pp. 133–145.
  7. Chapfuwa, P., C. Tao, C. Li, C. Page, B. Goldstein, L. C. Duke, and R. Henao (2018). Adversarial time-to-event modeling. In International Conference on Machine Learning, pp. 735–744. PMLR.
  8. Chen, P., W. Dong, X. Lu, U. Kaymak, K. He, and Z. Huang (2019). Deep representation learning for individualized treatment effect estimation using electronic health records. Journal of Biomedical Informatics 100, 103303.
  9. Chipman, H. A., E. I. George, and R. E. McCulloch (2010). BART: Bayesian additive regression trees. The Annals of Applied Statistics 4(1), 266–298.
  10. Chu, J., W. Dong, J. Wang, K. He, and Z. Huang (2020). Treatment effect prediction with adversarial deep learning using electronic health records. BMC Medical Informatics and Decision Making 20(4), 1–14.
  11. Cox, D. R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society: Series B (Methodological) 34(2), 187–202.
  12. Cui, Y., M. R. Kosorok, E. Sverdrup, S. Wager, and R. Zhu (2023). Estimating heterogeneous treatment effects with right-censored data via causal survival forests. Journal of the Royal Statistical Society Series B: Statistical Methodology 85(2), 179–211.
  13. Curth, A., C. Lee, and M. van der Schaar (2021). Survite: Learning heterogeneous treatment effects from time-to-event data. Advances in Neural Information Processing Systems 34, 26740–26753.
  14. Dyachenko, T. L. and G. M. Allenby (2018). Bayesian analysis of heterogeneous mediation. Georgetown McDonough School of Business Research Paper (2600140).
  15. Ge, Q., X. Huang, S. Fang, S. Guo, Y. Liu, W. Lin, and M. Xiong (2020). Conditional generative adversarial networks for individualized treatment effect estimation and treatment selection.
  16. Hayes, A. F. (2015). An index and test of linear moderated mediation. Multivariate Behavioral Research 50(1), 1–22.
  17. Hayfield, T. and J. S. Racine (2008). Nonparametric econometrics: The np package. Journal of Statistical Software 27, 1–32.
  18. Henderson, N. C., T. A. Louis, G. L. Rosner, and R. Varadhan (2020). Individualized treatment effects with censored data via fully nonparametric bayesian accelerated failure time models. Biostatistics 21(1), 50–68.
  19. Huan, C., X. Song, and H. Yuan (2024). Individualized causal mediation analysis with continuous treatment using conditional generative adversarial networks. Statistics and Computing 34(170), 1–21.
  20. Huang, Y.-T. and H.-I. Yang (2017). Causal mediation analysis of survival outcome with multiple mediators. Epidemiology (Cambridge, Mass.) 28(3), 370–378.
  21. Imai, K., L. Keele, and D. Tingley (2010). A general approach to causal mediation analysis. Psychological Methods 15(4), 309–334.
  22. Imai, K. and T. Yamamoto (2013). Identification and sensitivity analysis for multiple causal mechanisms: Revisiting evidence from framing experiments. Political Analysis 21(2), 141– 171.
  23. Imbens, G. W. and D. B. Rubin (2015). Causal Inference in Statistics, Social, and Biomedical Sciences. Cambridge University Press.
  24. Ishwaran, H., U. B. Kogalur, E. H. Blackstone, and M. S. Lauer (2008). Random Survival Forests. The Annals of Applied Statistics 2(3), 841–860.
  25. Jesson, A., S. Mindermann, Y. Gal, and U. Shalit (2021). Quantifying ignorance in individual-level causal-effect estimates under hidden confounding. In International Conference on Machine Learning, pp. 4829–4838. PMLR.
  26. Jin, Y., Z. Ren, and E. J. Cand`es (2023). Sensitivity analysis of individual treatment effects: A robust conformal inference approach. Proceedings of the National Academy of Sciences 120(6), e2214889120.
  27. Knaus, M. C. (2022). Double machine learning-based programme evaluation under unconfoundedness. The Econometrics Journal 25(3), 602–627.
  28. Knaus, M. C., M. Lechner, and A. Strittmatter (2021). Machine learning estimation of heterogeneous causal effects: Empirical monte carlo evidence. The Econometrics Journal 24(1), 134–161.
  29. Martinussen, T., S. Vansteelandt, M. Gerster, and J. v. B. Hjelmborg (2011). Estimation of direct effects for survival data by using the aalen additive hazards model. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 73(5), 773–788.
  30. Oprescu, M., J. Dorn, M. Ghoummaid, A. Jesson, N. Kallus, and U. Shalit (2023). B-learner: Quasi-oracle bounds on heterogeneous causal effects under hidden confounding. In International Conference on Machine Learning, pp. 26599–26618. PMLR.
  31. Park, S. and D. Kaplan (2015). Bayesian causal mediation analysis for group randomized designs with homogeneous and heterogeneous effects: Simulation and case study. Multivariate
  32. Preacher, K. J., D. D. Rucker, and A. F. Hayes (2007). Addressing moderated mediation hypotheses: Theory, methods, and prescriptions. Multivariate Behavioral Research 42(1), 185–227.
  33. Qin, X. and G. Hong (2017). A weighting method for assessing between-site heterogeneity in causal mediation mechanism. Journal of Educational and Behavioral Statistics 42(3), 308–340.
  34. Qin, X. and L. Wang (2024). Causal moderated mediation analysis: Methods and software. Behavior Research Methods 56(3), 1314–1334.
  35. Roussotte, F. F., B. A. Gutman, S. K. Madsen, J. B. Colby, K. L. Narr, P. M. Thompson, A. D.
  36. N. I. (ADNI, et al. (2014). The apolipoprotein e epsilon 4 allele is associated with ventricular expansion rate and surface morphology in dementia and normal aging. Neurobiology of Aging 35(6), 1309–1317.
  37. Royston, P. and M. K. Parmar (2011). The use of restricted mean survival time to estimate the treatment effect in randomized clinical trials when the proportional hazards assumption is in doubt. Statistics in Medicine 30(19), 2409–2421.
  38. Rubin, D. B. (2005). Causal inference using potential outcomes: Design, modeling, decisions. Journal of the American Statistical Association 100(469), 322–331.
  39. Shen, J., L. Wang, S. Daignault, D. E. Spratt, T. M. Morgan, and J. M. Taylor (2018). Estimating the optimal personalized treatment strategy based on selected variables to prolong survival via random survival forest with weighted bootstrap. Journal of Biopharmaceutical Statistics 28(2), 362–381.
  40. Sparapani, R. A., B. R. Logan, R. E. McCulloch, and P. W. Laud (2016). Nonparametric survival 2753.
  41. Sun, R., X. Zhou, and X. Song (2021). Bayesian causal mediation analysis with latent mediators and survival outcome. Structural Equation Modeling: A Multidisciplinary Journal 28(5), 778–790.
  42. Tang, M.-X., Y. Stern, K. Marder, K. Bell, B. Gurland, R. Lantigua, H. Andrews, L. Feng,
  43. B. Tycko, and R. Mayeux (1998). The apoe-ϵ4 allele and the risk of alzheimer disease among african americans, whites, and hispanics. Jama 279(10), 751–755.
  44. Thompson, P. M., K. M. Hayashi, G. I. De Zubicaray, A. L. Janke, S. E. Rose, J. Semple, M. S.
  45. Hong, D. H. Herman, D. Gravano, D. M. Doddrell, et al. (2004). Mapping hippocampal and ventricular change in alzheimer disease. Neuroimage 22(4), 1754–1766.
  46. VanderWeele, T. and S. Vansteelandt (2014). Mediation analysis with multiple mediators. Epidemiologic Methods 2(1), 95–115.
  47. VanderWeele, T. J. (2011). Causal mediation analysis with survival data. Epidemiology 22(4), 582–585.
  48. VanderWeele, T. J. and P. Ding (2017). Sensitivity analysis in observational research: introducing the e-value. Annals of Internal Medicine 167(4), 268–274.
  49. Wei, L.-J. (1992). The accelerated failure time model: a useful alternative to the cox regression model in survival analysis. Statistics in Medicine 11(14-15), 1871–1879.
  50. Xu, S., L. Liu, and Z. Liu (2022). Deepmed: Semiparametric causal mediation analysis with debiased deep learning. Advances in Neural Information Processing Systems 35, 28238–28251.
  51. Xue, F., X. Tang, G. Kim, K. C. Koenen, C. L. Martin, S. Galea, D. Wildman, M. Uddin, and
  52. A. Qu (2022). Heterogeneous mediation analysis on epigenomic ptsd and traumatic stress in a predominantly african american cohort. Journal of the American Statistical Association 117(540), 1669–1683.
  53. Yin, M., C. Shi, Y. Wang, and D. M. Blei (2024). Conformal sensitivity analysis for individual treatment effects. Journal of the American Statistical Association 119(545), 122–135.
  54. Yoon, J., J. Jordon, and M. Van Der Schaar (2018). Ganite: Estimation of individualized treatment effects using generative adversarial nets. In International Conference on Learning Representations, pp. 1–22.
  55. Zhou, X. and X. Song (2021). Mediation analysis for mixture cox proportional hazards cure models. Statistical Methods in Medical Research 30(6), 1554–1572. Cheng Huan

Acknowledgments

This research is fully supported by GRF grant (No. 14303622) of HKSAR.

Supplementary Materials

The online supplementary material contains the theoretical proofs, other technical details, and parts of numerical results.

Supplementary materials are available for download.