Early Cardiovascular Risk Prediction in Quilombola Afro-descendants: A Data-Driven Approach

  • J. S. L. Figuerêdo UEFS
  • R. S. Rosa UEFS
  • R. N. S. O. Boery UESB
  • J. B. Júnior UEFS
  • R. T. Calumby UEFS

Resumo


Cardiovascular diseases (CVD) are the leading cause of global mortality. People from different social groups can be affected. However, socially vulnerable groups, such as the Quilombola communities in Brazil, may have an increased risk. Recently, sample data from this population were used to predict metabolic syndrome with machine learning(ML). Although metabolic syndrome is a risk factor for CVD, directly predicting cardiovascular risk itself might be more effective for implementing preventive strategies. Therefore, this study developed and assessed ML models to estimate CVD risk, including a variable importance analysis. Most models achieved over 80% effectiveness, with logistic regression achieving the best result. Considering the variable importance analysis, sex, age and income were identified as the most important variables, along with other socioeconomic and anthropometric data.

Palavras-chave: Cardiovascular Risk Prediction, Computer aided prognosis, Quilombola, Framingham score

Referências

Bhardwaj, A. et al. Application of machine learning for cardiovascular disease risk prediction. Computational Intelligence and Neuroscience vol. 2023, 2023.

Bishop, C. M. Pattern Recognition and Machine Learning. Springer-Verlag, Berlin, Heidelberg, 2006.

Borhanuddin, B. et al. 10-year cardiovascular disease risk estimation based on lipid profile-based and bmi-based framingham risk scores across multiple sociodemographic characteristics: The malaysian cohort project. Scientific World Journal vol. 2018, pp. 2979206, 2018.

Costa, L. C. and Thuler, L. C. S. Fatores associados ao risco para doenças não transmissíveis em adultos brasileiros: estudo transversal de base populacional. Revista Brasileira de Estudos de População 29 (1): 133–145, Jan, 2012.

Dawber, T. The Framingham Study: The Epidemiology of Atherosclerotic Disease. HUP, Cambridge, 1980.

Day, T. E. and Goldlust, E. Cardiovascular disease risk profiles. American Heart Journal 160 (1): e3, 2010.

Dorigny, M. Atlas das escravidões: da Antiguidade até os nossos dias. Vozes, Petrópolis (RJ), 2017.

Li, J. P. et al. Heart disease identification method using machine learning classification in e-healthcare. IEEE Access vol. 8, pp. 107562–107582, 2020.

Lobo, L. C. Inteligência artificial e medicina. Revista Brasileira de Educação Médica 41 (2): 185–193, Apr, 2017.

Malta, D. C. et al. Estimativas do risco cardiovascular em dez anos na população brasileira: Um estudo de base populacional. Arquivos Brasileiros de Cardiologia 116 (3): 423–431, Mar, 2021.

Mozaffarian, D. et al. Heart disease and stroke statistics–2016 update: A report from the american heart association. Circulation vol. 133, pp. e38–e360, 2015.

Oshunbade, A. A. et al. Cigarette smoking, incident coronary heart disease, and coronary artery calcification in black adults: The jackson heart study. Journal of the American Heart Association 10 (7): e017320, 2021.

Rodgers, J. L. et al. Cardiovascular risks associated with gender and aging. JCDD 6 (2): 19, 2019.

Rosa, R. S. et al. Cardiovascular Risk and Factors Associated to the Health in Hypertensive African Descent People Resident in Quilombola Community. Revista Cuidarte vol. 12, 00, 2021.

SBC, SBH, and SBN. Vi diretrizes brasileiras de hipertensão. Arq Bras Cardiol 95 (1 suppl.1): 1–51, 2010.

Silva, G. et al. Cardiac arrhythmia detection in ecg signals using graph convolutional network. In Anais do XXII SBCAS. SBC, Porto Alegre, RS, Brasil, pp. 25–35, 2022.

Tanure, R. G. A. Da necessidade da implementação de políticas públicas no combate ao racismo estrutural. Boletim Científico ESMPU 20 (57): 265–284, 2021.

Torres, R. C. et al. Modelo matemático para prever probabilidade de quilombolas desenvolverem síndrome metabólica com fluxograma de atendimento de saúde. Scientia Plena 19 (8), set., 2023.

Ventura, N., , et al. An interpretable classification model for identifying individuals with attention defict hyperactivity disorder. In Anais do X KDMiLe. SBC, Porto Alegre, RS, Brasil, pp. 66–73, 2022.

World Health Organization. Cardiovascular Diseases. [link]. Accessed: 2024-03-04.

Yu, K.-H. et al. Artificial intelligence in healthcare. Nature Biomedical Engineering 2 (10): 719–731, Oct, 2018.
Publicado
17/11/2024
FIGUERÊDO, J. S. L.; ROSA, R. S.; BOERY, R. N. S. O.; B. JÚNIOR, J.; CALUMBY, R. T.. Early Cardiovascular Risk Prediction in Quilombola Afro-descendants: A Data-Driven Approach. In: SYMPOSIUM ON KNOWLEDGE DISCOVERY, MINING AND LEARNING (KDMILE), 12. , 2024, Belém/PA. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2024 . p. 129-136. ISSN 2763-8944. DOI: https://doi.org/10.5753/kdmile.2024.244746.