Deep Neural Network for Cure Fraction Survival Analysis Using Pseudo Values
Abstract
Abstract
Background:
The hidden assumption in most of survival analysis models is the occurrence of the event of interest for all study units. The violation of this assumption occurs in several situations. For example, in medicine, some patients may never have cancer, and some may never face Alzheimer. Ignoring such information and analyzing the data with traditional survival models may lead to misleading results. Analyzing long term survivals can be performed using both traditional and neural networks. There has been an increasing interest in modeling lifetime data using neural network. However, for long-term survivors only one neural network was introduced to estimate the uncured proportion together with the EM algorithm to account for the latency part. Neural network in survival analysis requires special cost function to account for censoring.
Methods: In this paper, we extend the neural network using pseudo values to analyze cure fraction model. It neither requires the use of special cost function nor the EM algorithm.
Results: The network is applied on both synthetic and Melanoma real datasets to evaluate its performance. We compared the results using goodness of fit methods in both datasets with cox proportional model using EM algorithm.
Conclusion: The proposed neural network has the flexibility of analyzing data without parametric assumption or special cost function. Also, it has the advantage of analyzing the data without the need of EM algorithm. Comparing the results with cox proportional model using EM algorithm, the proposed neural network performed better.
2. Boag, J., W. Maximum likelihood estimates of patients cured by cancer therapy. Journal of the Royal Statistical Society. Series B. 1949; 11(1): 15-53.
3. Farewell, V., T. The use of mixture models for the analysis of survival data with long-term survivors. Biometrics. 1982; 38: 1041-1046.
4. Yamaguchi, K. Accelerated failure time regression models with a regression model of surviving fraction: an application to the analysis of "permanent employment" in Japan. Journal of the American Statistical Association. 1992; 87(418): 284-292.
5. Yu, B., Tiwari, R., C., Cronin, K., A. and Feuer, E. J. Cure fraction estimation from the mixture cure models for grouped survival data. Statistics In Medicine. 2004; 23: 1733- 1747.
6. Kannan, N., Kundu, D., Nair, P. and Tripathi, R., C. The generalized exponential cure rate model with covariates. Journal of Applied Statistics. 2010; 37(10): 1625-1636.
7. Martinez, E., Z., Achcar, J., A., Jacome, A., A. and Santos, J., S. Mixture and non-mixture cure fraction models based on the generalized modified Weibull distribution with an application on gastric cancer data. Computer Methods And Programs In Biomedicine. 2013, 112(3); 343-355.
8. Swain, P., K., Grover, G. and Goel, K. Mixture and non mixture cure fraction models based on generalized gompertz distribution under Bayesian approach. Tatra Mountains Mathematical Publication. 2016; 66: 11-135.
9. Omer, M., Abu Bakar, M., Adam, M. and Mustafa, M. Cure models with exponentiated Weibull exponential distribution for the analysis of melanoma patients. Mathematics. 2020; 8(11), 1926; https://doi.org/10.3390/ math8111926.
10. Kuk, A., Y.,C. and Chen, C. A mixture model combining logistic regression with proportional hazards regression. Biometrica. 1992; 79(3), 531-541.
11. Peng, Y. and Dear, K., B., G. A nonparametric mixture model for cure rate estimation. Biometrics. 2000; 56, 237- 243.
12. Sy, P. G. and Taylor, J., M., G. Estimation in a Cox proportional hazards cure model. Biometrics. 2000; 56, 227- 236.
13. Othus, M., Li, Y. and Tiwari, R. C. A class of semiparametric mixture cure survival models With dependent censoring. Journal of the American Statistical Association. 2009; 104 (487), 1241- 1250.
14. Xu, J. and Peng, Y. Nonparametric cure rate estimation with covariates. The Canadian Journal of Statistics; 2014; 42(1), 1-17
15. Faraggi, D., and Simon, R. A neural network model for survival data. Statistics in Medicine. 1995; 14: 73-82.
16. Katzman, J., Shaham, U., Cloninger, A., Bates, J., Jiang, T. and Kluger,'Y. Deep Survival: A Deep Cox Proportional Hazards Network. Stat. 2016, 1050 (2), 1–10; https:// doi.org/10.1186/s12874-018-0482-1. 17. Zhu, X., Yao, J and Huang, J. Deep Convolutional Neural Network for Survival Analysis with Pathological Images. IEEE International Conference on Bioinformatics and Biomedicine. 2016: DOI: 10.1109/ BIBM.2016.7822579.
18. Zhu,X., Yao, J., Zhu, F. and Huang, H. WSISA: Making Survival Prediction from Whole Slide Histopathological Images. IEEE Conference on Computer Vision and Pattern Recognition. 2017: DOI: 10.1109/ CVPR.2017.725.
19. Pawley, M. DeepWeibull: a deep learning approach to parametric survival analysis. M.Sc. Thesis, Departement of Mathematics, Imperial College London. 2020.
20. Zhao, L. and Feng, D. Deep Neural Networks for Survival Analysis Using Pseudo Values. IEEE Journal of Biomedical and health informatics. 2020; 24(11), 3308 - 3314.
21. Xie, Y. and Yu, Z. Mixture cure rate models with neural network estimated nonparametric components. Computational Statistics. 2021; 36, 2467-2489.
22. Su, C., Chiou, S., H., Lin, F. and Platt, R., W. Analysis of survival data with cure fraction and variable selection: A pseudo observations approach. Statistical Methods in Medical Research. 2022; 31(11), 2037- 2053.
23. Andersen, P., K., Klein, J., P. and Rosthoj, S. Generalized linear models for correlated pseudo- observations with applications to multi-state models. Biometrika. 2003; 90(1), 15-27.
24. Klein, J., P., Logan, B., Harhoff, M. and Andersen, P., K. Analyzing survival curves at a fixed point in time. Statistics in Medicine. 2007; 26, 4505- 4519.
25. Andrei, A. and Murray, S. Regression models for the mean of the quality-of-life adjusted restricted survival time using pseudo observations. Biometrics. 2007; 63, 398- 404.
26. Nicolaie, M., A., Houwelingen, J., C.V., Witte, T. M., D. and Putter, H. Dynamic pseudo-observations: A robust approach to dynamic prediction in competing risks. Biometrics. 2013; 69, 1043- 1052.
27. Sabathe ́, C., Andersen, P., K., Helmer, C., Gerds, T., A., Jacqmin-Gadda, H. and Joly, P. Regression analysis in an illness-death model with interval-censored data: A pseudo value approach. Statistical Methods in Medical Research. 2019; 29(3), 752- 764.
28. Su, C., Platt, R., W. and Plante, J. Causal inference for recurrent event data using pseudo-observations. Biostatistics. 2020; 23(1), 189- 206.
29. Andersen, P., K. and Perme, M., P (2010). Pseudo-observations in survival analysis. Statistical Methods in Medical Research. 2010; 19, 71- 99.
30. Håvard Kvamme and Ørnulf Borgan (2023). The Brier Score under Administrative Censoring: Problems and Solutions. Journal of Machine Learning Research.2023; 24(2): 1- 26.
31. Kirkwood, j., M., Strawderman, M., H., Ernstoff, M., S., Smith, T., J., Borden, E., C. and Blum, R., H. (1996). Interferon alfa 2b adjuvant therapy of high-risk resected cutaneous melanoma: the eastern cooperative oncology group trial EST 1684. Journal of Clinical Oncology. 1996; 14(1), 7-17
| Files | ||
| Issue | Vol 10 No 4 (2024): . | |
| Section | Articles | |
| Keywords | ||
| Cure fraction Deep learning Neural Network Pseudo Values. | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
