Analysis of patterns in mammography reports of the Unified Health System using machine learning with aggregated data
DOI:
https://doi.org/10.59681/2175-4411.v18.2026.1606Keywords:
Mammography, Machine Learning, Observational StudyAbstract
Objective: To apply data science methods to aggregated information from the Cancer Information System (SISCAN) and the Department of Informatics of the Unified Health System to identify demographic patterns and estimate the risk of abnormal mammography reports in the Unified Health System between 2013 and 2025. Methods: Observational study using public, aggregated, and anonymized data. Demographic profiles were grouped using the K-Means algorithm, and the risk of abnormal reports, defined as categories 4, 5, or 6 of the Breast Imaging Reporting and Data System (BI-RADS), was estimated using Random Forest. Validation included silhouette index, cross-validation, statistical tests, and predictive metrics. Results: Aggregated SISCAN tables organized by age group, race/ethnicity, education level, and BI-RADS categories were analyzed. Six clusters were identified, with higher proportional risk among Indigenous populations, individuals without formal education, and those in the youngest and oldest age groups. Groups with higher examination volumes showed lower proportional risk but a high absolute burden of abnormal reports. Conclusion: The results indicate demographic heterogeneity in the distribution of abnormal mammography reports within the Unified Health System and reinforce the potential of computational methods applied to aggregated data to support public policies for breast cancer screening.
Downloads
References
1. Ministério da Saúde (BR). Carta dos direitos dos usuários da saúde. 3. ed. Brasília: Ministério da Saúde; 2011. [citado 2026 out 15]. Disponível em: https://bvsms.saude.gov.br/bvs/publicacoes/cartas_direitos_usuarios_saude_3ed.pdf
2. Migowski A, Silva GAE, Dias MBK, Diz MDPE, Sant'Ana DR, Nadanovsky P. Diretrizes para detecção precoce do câncer de mama no Brasil. II - Novas recomendações nacionais, principais evidências e controvérsias. Cad Saude Publica. 2018;34(6):e00074817. doi: https://doi.org/10.1590/0102-311X00074817
3. D'Orsi CJ, Sickles EA, Mendelson EB, Morris EA. ACR BI-RADS atlas: breast imaging reporting and data system. 5th ed. Reston (VA): American College of Radiology; 2013.
4. Instituto Nacional de Câncer José Alencar Gomes da Silva (INCA). Manual do Sistema de Informação do Câncer (Siscan): módulos 1, 2, 3 e 4. Rio de Janeiro: INCA; 2021. [citado 2026 out 15]. Disponível em: https://www.inca.gov.br/publicacoes/manuais/manual-do-sistema-de-informacao-do-cancer-siscan-modulos-1-2-3-e-4
5. Dias MBK, Assis M, Santos ROMD, Ribeiro CM, Migowski A, Tomazelli JG. Adequação da oferta de procedimentos para a detecção precoce do câncer de mama no Sistema Único de Saúde: um estudo transversal, Brasil e regiões, 2019. Cad Saude Publica. 2024;40(5):e00139723. doi: https://doi.org/10.1590/0102-311XPT139723
6. Santos YM, Campos MJR, Miranda AHFSB, Holanda JRC. Câncer de mama no Brasil: epidemiologia e correlação com a mamografia, de 2014 a 2024. Cuad Educ Desarro. 2024;16(13):e6735. doi: https://doi.org/10.55905/cuadv16n13-012
7. Farias KFFL, Santos AAP, Santos M, Moraes MM, Cavalcante KOR, Moreira AS. Análise Epidemiológica das Mamografias Realizadas em Alagoas no Período 2018-2022. Rev Cienc Med Biol. 2024;23(2):265-72. doi: https://doi.org/10.9771/cmbio.v23i2.56813
8. Pereira ALV, Lucas EM, Vieira JM, Silva PLF, Bertoloni CRS. Epidemiologia do câncer de mama em Patos de Minas. Res Soc Dev. 2024;13(12):e210131247936. doi: https://doi.org/10.33448/rsd-v13i12.47936
9. Pal Choudhury P, Wilcox AN, Brook MN, Zhang Y, Ahearn T, Orr N, et al. Comparative Validation of Breast Cancer Risk Prediction Models and Projections for Future Risk Stratification. J Natl Cancer Inst. 2020;112(3):278-85. doi: https://doi.org/10.1093/jnci/djz113
10. Breiman L. Random Forests. Mach Learn. 2001;45(1):5-32. doi: https://doi.org/10.1023/A:1010933404324
11. Jain AK. Data clustering: 50 years beyond K-means. Pattern Recognit Lett. 2010;31(8):651-66. doi: https://doi.org/10.1016/j.patrec.2009.09.011
12. Chapman P, Clinton J, Kerber R, Khabaza T, Reinartz T, Shearer C, et al. CRISP-DM 1.0: step-by-step data mining guide. Chicago: SPSS Inc.; 2000.
13. Rousseeuw PJ. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math. 1987;20:53-65. doi: https://doi.org/10.1016/0377-0427(87)90125-7
14. Razali NM, Wah YB. Power comparisons of Shapiro-Wilk, Kolmogorov-Smirnov, Lilliefors and Anderson-Darling tests. J Stat Model Anal. 2011;2(1):21-33. [citado 2025 jun]. Disponível em: https://jsma.um.edu.my/index.php/jsma/article/view/3647
15. Arlot S, Celisse A. A survey of cross-validation procedures for model selection. Stat Surv. 2010;4:40-79. doi: https://doi.org/10.1214/09-SS054
16. Han J, Kamber M, Pei J. Cluster Analysis. In: Han J, Kamber M, Pei J. Data mining: concepts and techniques. 3rd ed. Waltham (MA): Morgan Kaufmann; 2012. p. 443-95. doi: https://doi.org/10.1016/B978-0-12-381479-1.00010-1
17. Wongvibulsin S, Wu KC, Zeger SL. Clinical risk prediction with random forests for survival, longitudinal, and multivariate (RF-SLAM) data analysis. BMC Med Res Methodol. 2020;20(1):1. doi: https://doi.org/10.1186/s12874-019-0863-0
18. Abdi H, Williams LJ. Principal component analysis. Wiley Interdiscip Rev Comput Stat. 2010;2(4):433-59. doi: https://doi.org/10.1002/wics.101
19. Humaira H, Rasyidah R. Determining the appropiate cluster number using elbow method for K-means algorithm. In: Proceedings of the 2nd Workshop on Multidisciplinary and Applications (WMA 2018); 2018 jan 24-25; Padang, Indonesia. [s.l.]: EAI; 2020. doi: https://doi.org/10.4108/eai.24-1-2018.2292388
20. Shutaywi M, Kachouie NN. Silhouette analysis for performance evaluation in machine learning with applications to clustering. Entropy. 2021;23(6):759. doi: https://doi.org/10.3390/e23060759
21. Kim TK. Understanding one-way ANOVA using conceptual figures. Korean J Anesthesiol. 2017;70(1):22-6. doi: https://doi.org/10.4097/kjae.2017.70.1.22
22. Bradley AP. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit. 1997;30(7):1145-59. doi: https://doi.org/10.1016/S0031-3203(96)00142-2
23. Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One. 2015;10(3):e0118432. doi: https://doi.org/10.1371/journal.pone.0118432
24. Instituto Nacional de Câncer José Alencar Gomes da Silva (INCA). Parâmetros técnicos para detecção precoce do câncer de mama. Rio de Janeiro: INCA; 2023. [citado 2026 out 15]. Disponível em: https://ninho.inca.gov.br/jspui/handle/123456789/17258
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rebeca Lameira de Rezende, Roni Rodrigues, Claudia Aparecida Martins, Raphael de Souza Rosa Gomes, Anderson Castro Soares de Oliveira

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