Uma análise multivariada dos custos previdenciários de acidentes e doenças ocupacionais

Liandra dos Santos Jesus; Eliél Batistão Freitas; Marcelo Coelho Ciorlia; Guilherme Neto Ferrari; Edwin Vladimir Cardoza Galdamez; Gislaine Camila Lapasini Leal; Paulo César Ossani

doi:10.47456/bjpe.v12i2.51575

Autores

Liandra dos Santos Jesus Federal University of Santa Catarina Autor
Eliél Batistão Freitas State University of Maringá Autor
Marcelo Coelho Ciorlia State University of Maringá Autor
Guilherme Ferrari Universidade Estadual de Maringá Autor https://orcid.org/0000-0001-6198-2616
Edwin Vladimir Cardoza Galdamez State University of Maringá Autor https://orcid.org/0000-0002-1763-9332
Gislaine Camila Lapasini Leal State University of Maringá Autor https://orcid.org/0000-0001-8599-0776
Paulo César Ossani State University of Maringá Autor

DOI:

https://doi.org/10.47456/bjpe.v12i2.51575

Palavras-chave:

Clustering, multivariate analysis, occupational health, occupational safety, social security

Resumo

The objective of this study is to identify and characterize patterns in granting social security benefits related to occupational accidents and diseases in Brazil. A quantitative approach was adopted, analyzing a comprehensive dataset of 185,238 occupational accident benefits granted by the INSS between 2019 and 2020. The methodology combined hierarchical and non-hierarchical clustering techniques to identify distinct beneficiary groups, followed by Multiple Correspondence Analysis (MCA) to explore associations among categorical variables. The results revealed three clusters with distinct profiles regarding injury types, wage levels, and demographic characteristics. Cluster 1 is characterized by repetitive strain and manual injuries among low-wage workers; Cluster 2 features musculoskeletal and psychological disorders in higher-wage groups; and traumatic injuries among the lowest wage earners dominate Cluster 3. The MCA highlighted cohesive and isolated associations among benefit types, diseases, and geographic regions. This research provides a robust, data-driven profile of the social security costs of occupational accidents in Brazil, offering valuable insights for policymakers and OSH professionals. The identification of distinct risk groups and the mapping of associated factors support the development of more targeted and equitable prevention and compensation policies.

Downloads

Os dados de download ainda não estão disponíveis.

Biografia do Autor

Liandra dos Santos Jesus, Federal University of Santa Catarina

Master in Production Engineering and currently a Ph.D. candidate at the Federal University of Santa Catarina (UFSC). https://orcid.org/0000-0002-1066-1326
Eliél Batistão Freitas, State University of Maringá

Data Scientist, Statistics B. Sc., Department of Statistics, State University of Maringá. https://orcid.org/0009-0002-2825-737X
Marcelo Coelho Ciorlia, State University of Maringá

Statistician, Statistics B. Sc., Department of Statistics, State University of Maringá. https://orcid.org/0009-0008-0212-2702
Guilherme Ferrari, Universidade Estadual de Maringá

Production Engineer, M. Sc. Production Engineering, Teacher at Department of Production Engineer, State University of Maringá. https://orcid.org/0000-0001-6198-2616
Edwin Vladimir Cardoza Galdamez, State University of Maringá

Production Engineering PhD. Professor in the Production Engineering Department and in the postgraduate programs in Production Engineering and Accounting Sciences at State University of Maringá. https://orcid.org/0000-0002-1763-9332
Gislaine Camila Lapasini Leal, State University of Maringá

Electrical engineering and industrial computing PhD. Professor in the Production Engineering Department and in the postgraduate programs in Computer Science and Production at State University of Maringá. https://orcid.org/0000-0001-8599-0776
Paulo César Ossani, State University of Maringá

Statistics and Agricultural Experimentation PhD. Professor in the Department of Statistics, State University of Maringá. https://orcid.org/0000-0002-6617-8085

Referências

Bolsoni, L. C. (2024). Análise da disparidade salarial entre gêneros no Brasil: uma abordagem estatística [Master's Thesis]. Instituto de Ciências Matemáticas e de Computação. Universidade de São Paulo, USP. https://doi.org/10.11606/d.55.2024.tde-17032025-192127

Botelho, L. H. F., Abrantes, L. A., Ferreira, M. A. M., & Costa, T. de M. T. da. (2018). Análise de fatores influentes na relação entre contribuições e benefícios previdenciários. Revista de Ciências da Administração, 1(3), 23-39. https://doi.org/10.5007/2175-8077.2018v20n52p23

Botelho, L. H. F. & Costa, T. D. M. T. da. (2020). Análise financeira da seguridade e previdência social no Brasil em tempos de reformas fiscais. Revista Catarinense da Ciência Contábil, 19(1), 2922. https://doi.org/10.16930/2237-766220202922

Brasil. (1991). Lei 8.213, de 24 de julho de 1991. Recovered from https://www.planalto.gov.br/ccivil_03/leis/l8213cons.htm

Brasil. (2011). Lei 12.527, de 18 de novembro de 2011. Recovered from https://www.planalto.gov.br/ccivil_03/_ato2011-2014/2011/lei/l12527.htm

Brasil. (2016). Decreto 8.777, de 11 de maio de 2016. Recovered from https://legislacao.presidencia.gov.br/atos/?tipo=DEC&numero=8777&ano=2016&ato=c90ATSq1EeZpWT24e

Brasil. (2020). Boletim Estatístico da Previdência Social, BEPS (p. 58). Secretaria da Previdência. Recovered from https://www.gov.br/previdencia/pt-br/assuntos/previdencia-social/copy_of_arquivos/beps122020_final-1.pdf

Brasil. (2025). SMARTLAB. Observatório digital de saúde e segurança no trabalho. Ministério Público do Trabalho. Recovered from https://smartlabbr.org/sst

Cabello, A. F. T., Martínez-Rojas, M., Carrillo-Castrillo, J. A., & Rubio-Romero, J. C. (2021). Occupational accident analysis according to professionals of different construction phases using association rules. Safety Science, 144, 105457. https://doi.org/10.1016/j.ssci.2021.105457

Eyerkaufer, M. L., Bonfante, E. A., Dallabona, L. F., & Fabre, V. V. (2019). Simulador de custos para gestão de riscos de acidentes de trabalho. Revista Catarinense da Ciência Contábil, 18, 1-16. https://doi.org/10.16930/2237-766220192753

Fernandes, F. T. (2021). Machine learning em saúde e segurança do trabalhador: perspectivas, desafios e aplicações [Doctorade Thesis]. Faculdade de Saúde Pública. Universidade de São Paulo, USP. https://doi.org/10.11606/t.6.2021.tde-27012022-140548

Ferrari, G. N., Ossani, P. C., de Souza, R. C. T., Leal, G. C. L., & Galdamez, E. V. C. (2023). Impact of rising temperatures on occupational accidents in Brazil in the period 2006 to 2019: a multiple correspondence analysis. Safety Science, 161, 106078. https://doi.org/10.1016/j.ssci.2023.106078

Gouveia, A. G. P., Horsth, T. A., & Faroni, W. (2017). Análise quantílica dos fatores de influência na arrecadação do regime geral de previdência social em Minas Gerais. Revista Brasileira de Políticas Públicas e Internacionais, 2(2), 135-151. https://doi.org/10.22478/ufpb.2525-5584.2017v2n2.35243

Hämäläinen, P., Takala, J., & Kiat, T. B. (2017). Global estimates of occupational accidents and work-related illnesses 2017 (p. 21). WHS Institute. Recovered from https://www.icohweb.org/site/images/news/pdf/Report%20Global%20Estimates%20of%20Occupational%20Accidents%20and%20Work-related%20Illnesses%202017%20rev1.pdf

Hartigan, J. A. & Wong, M. A. (1979). Algorithm AS 136: a K-Means clustering algorithm. Applied Statistics, 28(1), 100. https://doi.org/10.2307/2346830

Health and Safety Execute - HSE. (2020). Costs to Britain of workplace fatalities and self-reported injuries and ill health, 2018/2019. Health and Safety Execute. Recovered from https://www.hse.gov.uk/statistics/

International Labour Organization - ILO. (2020). Quick guide on sources and uses of statistics on occupational safety and health (p. 58). Recovered from https://www.ilo.org/sites/default/files/wcmsp5/groups/public/%40dgreports/%40stat/documents/publication/wcms_759401.pdf

Kakhki, F. D., Freeman, S. A., & Mosher, G. A. (2019). Evaluating machine learning performance in predicting injury severity in agribusiness industries. Safety Science, 117, 257-262. https://doi.org/10.1016/j.ssci.2019.04.026

Leigh, J. P. (2011). Economic burden of occupational injury and illness in the United States. Milbank Quarterly, 89(4), 728-772. https://doi.org/10.1111/j.1468-0009.2011.00648.x

Madalozzo, R & Artes, R. (2017). Escolhas profissionais e impactos no diferencial salarial entre homens e mulheres. Cadernos de Pesquisa, 47(163), 202–221. https://doi.org/10.1590/198053143666

Menegon, L. da S., Menegon, F. A., & Kupek, E. (2021). Mortalidade por acidentes de trabalho no Brasil: análise de tendência temporal, 2006-2015. Revista Brasileira de Saúde Ocupacional, 46(e8). https://doi.org/10.1590/2317-6369000025219

Ossani, P. C. & Cirillo, M. A. (2025). Multivariate analysis [R package MVar version 2.2.7]. R-Project.org. Recovered from https://cran.r-project.org/package=MVar

Paez, O., Uahinui, T., Genaidy, A., Karwowski, W., Sun, L., & Daraiseh, N. (2006). Estimating uninsured costs of work-related accidents, part II: an incidence-based model. Theoretical Issues in Ergonomics Science, 7(3), 247-260. https://doi.org/10.1080/14639220500090547

Perez, G. de S. (2025). Capital humano e desigualdade: um estudo sobre os salários no Distrito Federal [Professional Master's Degree in Economics]. Universidade de Brasília, Brasília. Recovered from http://repositorio.unb.br/handle/10482/52062

R Core Team. (2023). A Language and environment for statistical computing. R Foundation for Statistical Computing. R Core Team. Recovered from https://www.r-project.org/

Rajabi, F., Jahangiri, M., Alimohammadlou, M., & Kamalinia, M. (2025). Identify and classify common errors, antecedents, outcomes, and mitigation strategies in qualitative and semi-quantitative workplace safety risk management: Integrating grounded theory and systematic literature review. Safety Science, 187, 106851. https://doi.org/10.1016/j.ssci.2025.106851

Reis, B. L. dos, Rosa, A. C. F. da, Machado, A. de A., Wencel, S. L. S. S., Leal, G. C. L., Galdamez, E. V. C., & Thom de Souza, R. C. (2021). Data mining in occupational safety and health: a systematic mapping and roadmap. Production Journal, 31(e20210048). https://doi.org/10.1590/0103-6513.20210048

Rencher, A. C. & Christensen, W. F. (2012). Methods of multivariate analysis. Wiley.

Sá, A. C. M. G. N. de, Gomide, M. H. M., & Sá, A. T. N. de. (2016). Acidentes de trabalho suas repercussões legais, impactos previdenciários e importância da gestão no controle e prevenção: revisão sistemática de literatura. Revista Médica de Minas Gerais, 26(e1825). https://doi.org/10.5935/2238-3182.20160125

Sanni-Anibire, M. O., Mahmoud, A. S., Hassanain, M. A., & Salami, B. A. (2020). A risk assessment approach for enhancing construction safety performance. Safety Science, 121(2), 15-29. https://doi.org/10.1016/j.ssci.2019.08.044

Santana, V. S., Araújo-Filho, J. B., Albuquerque-Oliveira, P. R., & Barbosa-Branco, A. (2006). Acidentes de trabalho: custos previdenciários e dias de trabalho perdidos. Revista de Saúde Pública, 40(6), 1004-1012. https://doi.org/10.1590/s0034-89102006000700007

Sindeaux, R. V., de Souza, R. M. F., Júlia, A. J. V. G., Reis, B. S., Sobral, K. J. B. V., & Martins, K. R. (2025). Salários mais elevados: quem são, onde estão e o que fazem os que ocupam o topo da pirâmide salarial no norte de Minas Gerais. Revista Foco, 18(4), e8142-e8142. https://doi.org/10.54751/revistafoco.v18n4-002

Souza, N. M. de. (1990). Análise de correspondência [Undergraduate Final Projects]. Instituto de Matemática. Estatística: Bacharelado. Universidade Federal do Rio Grande do Sul. Recovered from https://lume.ufrgs.br/handle/10183/134295

Safe Work Australia - SWA. (2017). The cost of work-related injury and illness for Australian employers, workers and the community 2012-13. Safe Work Australia. Recovered from https://www.safeworkaustralia.gov.au/doc/cost-work-related-injury-and-illness-australian-employers-workers-and-community-2012-13

Tenoury, G. N. C. da S., Madalozzo, R. C., & Martins, S. R. (2021). Diferença salarial e taxa de participação no mercado de trabalho brasileiro: uma análise a partir do sexo dos indivíduos. Estudos Econômicos, 51(01), 33-72. https://doi.org/10.1590/0101-41615112grs

Tompa, E., Mofidi, A., Heuvel, S. van den, Bree, T. van, Michaelsen, F., Jung, Y., Porsch, L., Emmerik, M. van, IWH (Institute for Work & Health), TNO (The Netherlands Organisation for Applied Scientific Research), & VVA (Valdani Vicari & Associati). (2019). The value of occupational safety and health and the societal costs of work-related injuries and diseases. European Agency for Safety and Health at Work - EU-OSHA. https://doi.org/10.2802/251128

Varoquaux, G., Buitinck, L., Louppe, G., Grisel, O., Pedregosa, F., & Mueller, A. (2015). Scikit-learn machine learning without learning the machinery. GetMobile: Mobile Computing and Communications, 19(1), 29-33. https://doi.org/10.1145/2786984.2786995

Xu, D. & Tian, Y. (2015). A comprehensive survey of clustering algorithms. Annals of Data Science, 2(2), 165-193. https://doi.org/10.1007/s40745-015-0040-1

Zubaroğlu, A. & Atalay, V. (2020). Data stream clustering: a review. Artificial Intelligence Review, 54. https://doi.org/10.1007/s10462-020-09874-x