Machine learning e sobrevida em câncer: análise do Registro Hospitalar de Câncer de São Paulo
DOI:
https://doi.org/10.11606/s15188787.2026060007389Palavras-chave:
Neoplasias, Análise de Sobrevida, Aprendizado de MáquinaResumo
OBJETIVO: Comparar o desempenho de diferentes algoritmos de Survival Machine Learning (SML) na predição da sobrevida de pacientes com câncer. MÉTODOS: Utilizaram-se dados do Registro Hospitalar de Câncer do Estado de São Paulo, contemplando os cinco tipos de câncer mais incidentes (mama, próstata, pulmão, colorretal e colo do útero). Foram avaliados seis algoritmos: Gradient Boosting Survival (GBS), Random Survival Forest (RSF), Support Vector Machine Survival (SVM-Survival), XGBoost Cox, XGBoost Accelerated Failure Time (AFT) e LightGBM. O desempenho foi medido pelas métricas Concordance Index (C-Index), C-Index IPCW e Integrated Brier Score (IBS). RESULTADOS: O modelo XGBoost AFT apresentou os melhores resultados de C-Index para mama (0,7845), pulmão (0,7368), colorretal (0,7618) e colo do útero (0,7726), enquanto o GBS foi superior para próstata (0,7574). O estadiamento clínico foi consistentemente a variável mais importante, segundo a análise de explicabilidade. CONCLUSÃO: Os algoritmos de SML demonstraram bom desempenho preditivo, independentemente do tipo de câncer, do tamanho amostral e da proporção de censura. Esses modelos mostram potencial para subsidiar o planejamento oncológico e apoiar decisões estratégicas na organização das redes de atenção ao câncer.
Referências
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
Publicado
Edição
Seção
Licença
Direitos autorais (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
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
Como Citar
Dados de financiamento
-
Fundação de Amparo à Pesquisa do Estado de São Paulo
Números do Financiamento 2021/11794-4;2025/00444-3
