Analysis of Socio-environmental and Behavioral Factors in the Identification of Obsessive-Compulsive Disorder: An Approach Using Data from the 2019 Brazilian Health Survey

• Anna Puga Campos Rodrigues Pontifical Catholic University of Minas Gerais
• Luis Enrique Zárate Galvez Pontifical Catholic University of Minas Gerais

DOI: https://doi.org/10.5753/sbbd.2024.241105

Abstract

Obsessive-Compulsive Disorder (OCD) is a mental distress characterized by the presence of obsessions and compulsions that significantly affect individuals’ lives, as described in the DSM-5 manual. This work explores the analysis of OCD using data from the 2019 National Health Survey (PNS), addressing socio-environmental and behavioral aspects. Using the Explainable Boosting Machine (EBM) algorithm and a Decision Tree, the study identifies relevant variables for the classification of OCD, demonstrating the influence of socio-environmental factors in the identification of the disorder. Results indicate improvements in the models’ metrics with the inclusion of these variables, as well as agreement with other results in the literature.

Keywords: Obsessive-Compulsive Disorder, Data Mining and Analytics, OCD, EBM, Decision Tree, Data-centric applications

References

Association, A. P. (2013). Manual Diagnóstico e Estatístico de Transtornos Mentais. Artmed, 5 edition.

Azeredo, C. M., Cotta, R. M. M., Schott, M., Maia, T. d. M., and Marques, E. S. (2007). Avaliação das condições de habitação e saneamento: a importância da visita domiciliar no contexto do programa de saúde da família. Ciência Saúde Coletiva, 12(3):743–753.

Bang, L., Kristensen, U. B., Wisting, L., Stedal, K., Garte, M., Minde, , and Rø, (2020). Presence of eating disorder symptoms in patients with obsessive-compulsive disorder. BMC Psychiatry, 20(1):36.

Brander, G., Pérez-Vigil, A., Larsson, H., and Mataix-Cols, D. (2016). Systematic review of environmental risk factors for obsessive-compulsive disorder: A proposed roadmap from association to causation. Neuroscience Biobehavioral Reviews, 65:36–62. Epub 2016 Mar 21.

Buss, P. M. and Pellegrini Filho, A. (2007). A saúde e seus determinantes sociais. Physis: Revista de Saúde Coletiva, 17(1):77–93.

Cazzolato, M., Rodrigues, L., Ribeiro, M., Gutierrez, M., Jr., C. T., and Traina, A. (2021). Similarity search and correlation-based exploratory analysis in ehrs: A case study with covid-19 databases. In Anais do XXXVI Simpósio Brasileiro de Bancos de Dados, pages 25–36, Porto Alegre, RS, Brasil. SBC.

Hu, X., Liu, Q., Li, B., Tang, W., Sun, H., Li, F., Yang, Y., Gong, Q., and Huang, X. (2016). Multivariate pattern analysis of obsessive–compulsive disorder using structural neuroanatomy. European Neuropsychopharmacology, 26(2):246–254.

Højgaard, D. R., Arildskov, T. W., Skarphedinsson, G., and et al. (2023). Do autistic traits predict outcome of cognitive behavioral therapy in pediatric obsessive-compulsive disorder? Research on Child and Adolescent Psychopathology, 51:1083–1095.

Instituto Brasileiro de Geografia e Estatística (IBGE) (2020). Pesquisa nacional de saúde 2019. [link] t=resultados. Acesso em: 2024-07-15.

KNIME (2023). Decision tree learner (3.6.0). [link]. Accessed: 2024-07-12.

Montevecchi, A. and Zárate, L. E. (2014). Pictorea: Um método para descoberta de conhecimento em bancos de dados convencionais. Novas Edições Acadêmicas. Published by Lucky’s Textbooks, Dallas, TX, U.S.A.

Pasternak, S. (2016). Habitação e saúde. Estudos Avançados, 30(86):51–66.

Sabrina Boger, Thomas Ehring, G. B. and Werner, G. G. (2020). Impact of childhood mal-treatment on obsessive-compulsive disorder symptom severity and treatment outcome. European Journal of Psychotraumatology, 11(1):1753942.

Segalàs, C., Labad, J., Salvat-Pujol, N., Real, E., Alonso, P., Bertolín, S., Jiménez-Murcia, S., Soriano-Mas, C., Monasterio, C., Menchón, J. M., and Soria, V. (2021). Sleep disturbances in obsessive-compulsive disorder: influence of depression symptoms and trait anxiety. BMC Psychiatry, 21(1):42.

Souza, V., Nobre, J., and Becker, K. (2020). Characterization of anxiety, depression, and their comorbidity from texts of social networks. In Anais do XXXV Simpósio Brasileiro de Bancos de Dados, pages 121–132, Porto Alegre, RS, Brasil. SBC.

The InterpretML Contributors (2023). Explainable boosting machine. Accessed: 2024-05-23.

Zarate, L., Petrocchi, B., Maia, C. D., Felix, C., and Gomes, M. P. (2023). Capto - a method for understanding problem domains for data science projects. Concilium.