Machine learning and cancer survival: analysis of the Registro Hospitalar de Câncer do Estado de São Paulo

Authors

  • Fernando Henrique de Albuquerque Maia University of São Paulo image/svg+xml
  • Lucas Buk Cardoso Instituto Mauá de Tecnologia image/svg+xml
  • Simone Aldrey Angelo University of São Paulo image/svg+xml
  • Yasmin Pacheco Gil Bonilha Instituto Mauá de Tecnologia image/svg+xml
  • Adeylson Guimarães Ribeiro Fundação Oncocentro de São Paulo. São Paulo, SP, Brasil
  • Maria Paula Curado A.C. Camargo Cancer Center. Grupo de Epidemiologia e Estatística em Câncer. São Paulo, SP, Brasil
  • Gisele Aparecida Fernandes A.C. Camargo Cancer Center. Grupo de Epidemiologia e Estatística em Câncer. São Paulo, SP, Brasil
  • Alexandre Dias Porto Chiavegatto Filho University of São Paulo image/svg+xml
  • Vanderlei Cunha Parro Instituto Mauá de Tecnologia image/svg+xml
  • Tatiana Natasha Toporcov University of São Paulo image/svg+xml

DOI:

https://doi.org/10.11606/s1518-8787.2026060007389

Keywords:

Neoplasms, Survival Analysis, Machine Learning

Abstract

OBJECTIVE: To compare the performance of different Survival Machine Learning (SML) algorithms in predicting the survival of cancer patients. METHODS: Data from the Registro Hospitalar de Câncer do Estado de São Paulo (São Paulo State Cancer Registry Hospital) were used, covering the five most incident types of cancer (breast, prostate, lung, colorectal and cervix). Six algorithms were evaluated: Gradient Boosting Survival (GBS), Random Survival Forest (RSF), Support Vector Machine Survival  (SVM-Survival), XGBoost Cox, XGBoost Accelerated Failure Time (AFT), and LightGBM. Performance was measured by the Concordance Index (C-Index), C-Index IPCW and  Integrated Brier Score (IBS) metrics. RESULTS: The XGBoost AFT model showed the best C-Index results for breast (0.7845), lung (0.7368), colorectal (0.7618), and cervix (0.7726), while GBS was superior for prostate (0.7574). Clinical staging was consistently the most important variable, according to the  explainability analysis. CONCLUSION: The SML algorithms showed good predictive performance, regardless of cancer type, sample size and censoring proportion. These models show potential for subsidizing cancer planning and supporting strategic decisions in the organization of cancer care networks.

Downloads

Download data is not yet available.

References

1. Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024;74(3):229-63. https://doi.org/10.3322/caac.21834

2. Kleinbaum DG, Klein M. Survival analysis: a self-learning text. 3a ed. New York: Springer; 2012. (Statistics for biology and health).

3. Bustamante-Teixeira MT, Faerstein E, Latorre MR. Técnicas de análise de sobrevida. Cad Saude Publica. 2024;18:579–94. https://doi.org/10.1590/S0102-311X2002000300003

4. Kourou K, Exarchos TP, Exarchos TP, Exarchos K, Exarchos KP, Karamouzis MV, et al. Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J. 2015;13:8–17. https://doi.org/10.1016/j.csbj.2014.11.005

5. Tizi W, Berrado A. Machine learning for survival analysis in cancer research: a comparative study. Sci Afr. 2023;21:e01880. https://doi.org/10.1016/j.sciaf.2023.e01880

6. Cardoso LB, Parro VC, Peres SV, Curado MP, Fernandes GA, Wünsch Filho V, et al. Machine learning for predicting survival of colorectal cancer patients. Sci Rep. 2023 Jun 1;13(1):8916. https://doi.org/10.1038/s41598-023-35649-9

7. Silva GFS, Duarte LS, Shirassu MM, Peres SV, Moraes MA, Chiavegatto Filho A. Machine learning for longitudinal mortality risk prediction in patients with malignant neoplasm in São Paulo, Brazil. Artif Intell Life Sci. 2023;3:100061. https://doi.org/10.1016/j.ailsci.2023.100061

8. Cardoso LB, Angelo SA, Bonilha YPG, Maia F, Ribeiro AG, Curado MP et al. Methodology for comparing machine learning algorithms for survival analysis. arXiv; 2025. [citado 2025 out 29]. Disponível em: https://arxiv.org/abs/2510.24473. doi: 10.48550/ARXIV.2510.24473.

9. Fundação Oncocentro de São Paulo. Banco de dados do RHC. São Paulo: FOSP; 2024 [citado 2024 jul 20]. Disponível em: https://fosp.saude.sp.gov.br/fosp/diretoria-adjunta-deinformacao-e-epidemiologia/rhc-registro-hospitalar-de-cancer/banco-de-dados-do-rhc/

10. Harrell FE, Califf RM, Pryor DB, Lee KL, Rosati RA. Evaluating the yield of medical tests. JAMA. 1982;247(18):2543-6.

11. Robins JM, Rotnitzky A, Zhao LP. Estimation of regression coefficients when some regressors are not always observed. J Am Stat Assoc. 1994;89(427):846-66. https://doi.org/10.1080/01621459.1994.10476818

12. Graf E, Schmoor C, Sauerbrei W, Schumacher M. Assessment and comparison of prognostic classification schemes for survival data. Stat Med. 1999;18(17-18):2529–45. https://doi.org/10.1002/(sici)1097-0258(19990915/30)18:17/18<2529::aid-sim274>3.0.co;2-5.

13. Akiba T, Sano S, Yanase T, Ohta T, Koyama M. Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Anchorage: ACM; 2019 [citado 2025 out 22]. P2623-31. Disponível em: https://dl.acm.org/doi/10.1145/3292500.3330701

14. Bergstra J, Bardenet R, Bengio Y, Kégl B. Algorithms for hyper-parameter optimization. In: ShaweTaylor J, Zemel R, Bartlett P, Pereira F, Weinberger KQ, editors. Advances in neural information processing systems. New York: Curran Associates, Inc.; 2011 [citado 2026 abr 22]. Disponível em: https://proceedings.neurips.cc/paper_files/paper/2011/file/86e8f7ab32cfd12577bc2619 bc635690-Paper.pdf

15. Hansen N. The CMA evolution strategy: a tutorial. arXiv; 2016. https://doi.org/10.48550/ARXIV.1604.00772.

16. Lundberg S, Lee SI. A unified approach to interpreting model predictions. arXiv; 2017. https://doi.org/10.48550/ARXIV.1705.07874

17. Breiman L. Random forests. Mach Learn. 2001;45(1):5-32. doi: 10.1023/A:1010933404324.

18. Yu W, Lu Y, Shou H, Xu H, Shi L, Geng X, et al. A 5-year survival status prognosis of nonmetastatic cervical cancer patients through machine learning algorithms. Cancer Med. 2023;12(6):6867-76. https://doi.org/10.1002/cam4.5477

19. Moncada-Torres A, van Maaren MC, Hendriks MP, Siesling S, Geleijnse G. Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival. Sci Rep. 2021;11(1):6968. https://doi.org/10.1038/s41598-021-86327-7

20. Peng ZH, Tian J, Chen B, Zhou H, Bi H, He M et al. Development of machine learning prognostic models for overall survival of prostate cancer patients with lymph node-positive. Sci Rep. 2023;13(1):18449. https://doi.org/10.1038/s41598-023-45804-x

21. Germer S, Rudolph C, Labohm L, Katalinic A, Rath N, Rausch K et al. Survival analysis for lung cancer patients: a comparison of Cox regression and machine learning models. Int J Med Inform. 2024;191:105607. https://doi.org/10.1016/j.ijmedinf.2024.105607

22. Yang XJ, Qiu H, Wang LY, Wang X. Predicting colorectal cancer survival using time-to-event machine learning: retrospective cohort study. J Med Internet Res. 2023;25:e44417. https://doi.org/10.2196/44417

23. Kolasseri AE, Venkataramana B. Comparative study of machine learning and statistical survival models for enhancing cervical cancer prognosis and risk factor assessment using SEER data. Sci Rep. 2024;14(1):22203. https://doi.org/10.1038/s41598-024-72790-5

24. Krzyziński M, Spytek M, Baniecki H, Biecek P. SurvSHAP(t): time-dependent explanations of machine learning survival models. Knowl Based Syst. 2023;262:110234. https://doi.org/10.1016/j.knosys.2022.110234

Downloads

Published

2026-06-24

Issue

Vol. 60 (2026)

Section

Original Articles

License

Copyright (c) 2026 Fernando Henrique de Albuquerque Maia, Lucas Buk Cardoso, Simone Aldrey Angelo, Yasmin Pacheco Gil Bonilha, Adeylson Guimarães Ribeiro, Maria Paula Curado, Gisele Aparecida Fernandes, Alexandre Dias Porto Chiavegatto Filho, Vanderlei Cunha Parro, Tatiana Natasha Toporcov

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Maia, F. H. de A., Cardoso, L. B., Angelo, S. A., Bonilha, Y. P. G., Ribeiro, A. G., Curado, M. P., Fernandes, G. A., Chiavegatto Filho, A. D. P., Parro, V. C., & Toporcov, T. N. (2026). Machine learning and cancer survival: analysis of the Registro Hospitalar de Câncer do Estado de São Paulo. Revista De Saúde Pública, 60, 31. https://doi.org/10.11606/s1518-8787.2026060007389

Funding data