Using artificial intelligence to analyze violence against women in São Paulo
DOI:
https://doi.org/10.11606/s1518-8787.2026060007099Keywords:
Violence Against Women, Data Mining, Artificial Intelligence, Data ScienceAbstract
OBJECTIVE: To propose the Health Research Standard Process for Artificial Intelligence framework, adapted from the Cross-Industry Standard Process for Data Mining approach, and apply it using time series and artificial intelligence techniques to analyze data from the Sistema de Informação de Agravos de Notificação (SINAN – Notifiable Diseases Information System) on violence against women in São Paulo, exploring sociodemographic, spatial, and predictive dimensions. METHODS: The methodology was adapted to health research, replacing the original Business Understanding stage with Research Understanding by incorporating essential technical-scientific elements. We analyzed 80,148 reports of violence against women aged between 20 and 59 living in the city of São Paulo between 2013 and 2023. The analyses included descriptive statistics, calculation of prevalence ratios, decomposition and predictive modeling of time series capturing trends and seasonality, and geospatial analysis of notifications. RESULTS: We observed temporal patterns and sociodemographic characteristics of the victims, with increasing trends in reports of physical, psychological, and sexual violence after 2015 and seasonal behavior. Among the associations, there was a 32% increase in the prevalence of sexual violence when the aggressor was under the influence of alcohol and a 2.47 times greater risk of sexual violence among pregnant women. The geospatial distribution revealed concentrations of notifications in peripheral areas of the municipality, such as the south, east, and central zones. Predictive modeling indicated that the upward trend will persist over the next 24 months, with estimated rates reaching up to 12 cases per 100,000 inhabitants. CONCLUSION: The applicability of the Health Research Standard Process for Artificial Intelligence was effective as a model for data analysis and the development of predictive algorithms in public health. It was possible to propose a replicable methodological matrix for future research and evidence-based interventions.
References
1. World Health Organization. Violence against women prevalence estimates 2018: global, regional and national prevalence estimates for intimate partner violence against women and global and regional prevalence estimates for non-partner sexual violence against women. Geneva: World Health Organization; 2021.
2. Fórum Brasileiro de Segurança Pública. Anuário brasileiro de segurança pública 2023. Vol. 17. São Paulo: Fórum Brasileiro de Segurança Pública.; 2023.
3. Instituto DataSenado. Pesquisa nacional sobre violência doméstica e familiar contra a mulher – 2023. Brasília: Senado Federal; 2023 [citado 2025 mar 28]. Disponível em: https://www12. senado.leg.br/institucional/datasenado/pesquisa-violencia-domestica-e-familiar-2023
4. Ministério dos Direitos Humanos e da Cidadania (BR). Balanço Ligue 180: violência doméstica e familiar é a mais recorrente. Brasília: Ministério dos Direitos Humanos e da Cidadania; 2022 [citado 2025 mar 28]. Disponível em: https://www.gov.br/mdh/pt-br/assuntos/ noticias/2020-2/junho/balanco-ligue-180-violencia-domestica-e-familiar-e-a-mais-recorrente
5. Ministério da Saúde (BR). Boletim epidemiológico: Saúde da mulher brasileira: uma perspectiva integrada entre vigilância e atenção à saúde. Brasília: Ministério da Saúde; 2023 [citado 2025 mar 28]. Disponível em: https://www.gov.br/saude/pt-br/centrais-deconteudo/publicacoes/boletins/epidemiologicos/especiais/2023/saude-da-mulher-brasileira-umaperspectiva-integrada-entre-vigilancia-e-atencao-a-saude-numero-especial-mar.2023/view
6. Mascarenhas MDM, Tomaz GR, Meneses GMSD, Rodrigues MTP, Pereira VODM, Corassa RB. Análise das notificações de violência por parceiro íntimo contra mulheres, Brasil, 2011-2017. Rev Bras Epidemiol. 2020;23(suppl.1):e200007. https://doi.org/10.1590/1980-549720200007.supl.1
7. Codeco C, Coelho F, Cruz O, Oliveira S, Castro T, Bastos L. Infodengue: a nowcasting system for the surveillance of arboviruses in Brazil. Rev Epidemiol Sante Publique. 2018;66(suppl.5):S386. https://doi.org/10.1016/j.respe.2018.05.408
8. Villela DAM, Gomes MFC. O impacto da disponibilidade de dados e informação oportuna para a vigilância epidemiológica. Cad Saúde Pública. 2022;38(7):e115122. https://doi.org/10.1590/0102-311xpt115122
9. Delpino FM, Figueiredo LM, Costa ÂK, Carreno I, Silva LN, Flores AD et al. Emergency department use and Artificial Intelligence in Pelotas: design and baseline results. Rev Bras Epidemiol. 2023;26:e230021. https://doi.org/10.1590/1980-549720230021
10. Morales HMP, Guedes M, Silva JS, Massuda A. COVID-19 in Brazil: preliminary analysis of response supported by artificial intelligence in municipalities. Front Digit Health. 2021;3:648585. https://doi.org/10.3389/fdgth.2021.648585
11. Chapman P. CRISP-DM 1.0: step-by-step data mining guide. Chicago: SPSS Inc.; 2000 [citado 2025 mar 10]. Disponível em: https://api.semanticscholar.org/CorpusID:59777418
12. Stephanie EMA, Ruiz LGB, Vila MA, Pegalajar MC. Study of violence against women and its characteristics through the application of text mining techniques. Int J Data Sci Anal. 2024;18(1):35-48. https://doi.org/10.1007/s41060-023-00448-y
13. Costa CADS, Tsunoda DF. Análise de dados de violência doméstica contra a mulher. Res Soc Dev. 2023;12(1):e20112139561. https://doi.org/10.33448/rsd-v12i1.39561
14. Shimaoka AM, Lopes LR, Silva Junior AC, Bandiera-Paiva P. Health data preparation framework for unsupervised models (HealthDataPrep): a study with Alzheimer’s disease mortality data from Brazil. Int J Health Manag Rev. 2025;11(1):29. https://doi.org/10.47172/ijhmreview.v11i1.407
15. Areco KN, Konstantyner T, Bandiera-Paiva P, Balda RCX, Costa-Nobre DT, Sanudo A et al. Operational challenges in the use of structured secondary data for health research. Front Public Health. 2021;9:642163. https://doi.org/10.3389/fpubh.2021.642163
16. Shimaoka AM, Ferreira RC, Goldman A. The evolution of CRISP-DM for data science: methods, processes and frameworks. SBC Rev Comput Sci. 2024;4(1):28-43. https://doi.org/10.5753/reviews.2024.3757
17. Ferraz VCDAB, Ferezin VV, Knoch M, Durovni B, Saraceni V, Lahdo V et al. Epidemiological data monitoring dashboards as a surveillance and healthcare management strategy. Ciênc Saúde Coletiva. 2024;29(11):e04142024. https://doi.org/10.1590/1413-812320242911.04142024en
18. Sampieri RH, Collado CF, Lucio MPB. Metodologia de pesquisa. 6a ed. Porto Alegre: Penso; 2023.
19. Hyndman RJ, Athanasopoulos G. Forecasting: principles and practice. 3rd ed. Melbourne: Otexts; 2021 [citado 2025 mar 28]. Disponível em: https://otexts.com/fpp3/
20. Taylor SJ, Letham B. Forecasting at scale. PeerJ Preprints. 2017;5:e3190v2. https://doi.org/10.7287/peerj.preprints.3190v2
21. Stochero L, Pinto LW. Caracterização das notificações de violência contra as mulheres que vivem em contextos rurais no Brasil, de 2011 a 2020. Rev Bras Epidemiol. 2024;27:e240059. https://doi.org/10.1590/1980-549720240059.2
22. Instituto DataSenado. Pesquisa nacional de violência contra a mulher negra. Brasília: Senado Federal; 2023 [citado 2025 mar 28]. Disponível em: https://www.senado.leg.br/institucional/ datasenado/relatorio_online/pesquisa_violencia_mulheres_negras/2024/interativo.html
23. Instituto DataSenado. Pesquisa nacional de violência contra a mulher. Brasília: Senado Federal; 2023 [citado 2025 mar 28]. Disponível em: https://www12.senado.leg.br/institucional/ datasenado/publicacaodatasenado?id=pesquisa-estadual-de-violencia-contra-a-mulher-2024
24. Ministério da Justiça e Segurança Pública (BR). Violência contra a mulher: casos de feminicídio recuam 5% em 2024. Brasília: Ministério da Justiça e Segurança Pública; 2024 [citado 2025 mar 29]. Disponível em: https://www.gov.br/mj/pt-br/assuntos/noticias/ violencia-contra-a-mulher-casos-de-feminicidio-recuam-5-em-2024
25. Koutaniemi EM, Einiö E. Seasonal variation in seeking help for domestic violence based on Google search data and Finnish police calls in 2017. Scand J Public Health. 2021;49(3):254-9. https://doi.org/10.1177/1403494819834098
26. Khurana B. New study finds holidays peak times for domestic violence injuries. Somerville: Mass General Brigham Newsroom; 2023 [citado 2025 mar 28]. Disponível em: https://www. massgeneralbrigham.org/en/about/newsroom/articles/study-finds-holidays-peak-times-domesticviolence-injuries
27. Ayala E. Analysis and prediction of violence against women [Internet]. 2022 [citado 2025 mar 28]. Disponível em: https://www.researchgate.net/ publication/361162563_Analysis_and_prediction_of_violence_against_women
28. Guo C, Wan M, Wang Y, Wang P, Tousey-Pfarrer M, Liu H et al. Associations between intimate partner violence and adverse birth outcomes during pregnancy: a systematic review and metaanalysis. Front Med. 2023;10:1140787. https://doi.org/10.3389/fmed.2023.1140787
29. Melkam M, Fente BM, Negussie YM, Asmare ZA, Asebe HA, Lemma SB et al. Impact of partner alcohol use on intimate partner violence among reproductive-age women in East Africa Demographic and Health Survey: propensity score matching. BMC Public Health. 2024;24:2365. https://doi.org/10.1186/s12889-024-19932-6
30. Sontate KV, Kamaluddin MR, Mohamed IN, Mohamed RMP, Shaikh MF, Kamal H et al. Alcohol, aggression, and violence: from public health to neuroscience. Front Psychol. 2021;12:699726. https://doi.org/10.3389/fpsyg.2021.699726
31. Coeli CM, Pinheiro RS, Carvalho MS. Neither better nor worse, simply different. Cad Saúde Pública. 2014;30(7):1363-5. https://doi.org/10.1590/0102-311XPE010714
32. Garcia KKS, Miranda CB, Sousa FN. Procedimentos para vinculação de dados da saúde: aplicações na vigilância em saúde. Epidemiol Serv Saúde. 2022;31(3):e20211272. https://doi.org/10.1590/S2237-96222022000300004
33. World Health Organization. Global strategy on digital health 2020-2025. Geneva: World Health Organization; 2021.
34. Cruz-Mendoza MC, Melendez-Armenta RA, Canul-Reich J, Muñoz-Benítez J. Machine learning applied to improve prevention of, response to, and understanding of violence against women. Informatics. 2025;12(2):40. https://doi.org/10.3390/informatics12020040
Published
Issue
Section
How to Cite
Funding data
-
Ministério da Saúde
Grant numbers TED 179/2023
