ASSESSING THE CONTRIBUTION OF CONTAINMENT MEASURES, VACCINATION COVERAGE AND MOBILITY IN THE EVOLUTION OF DEATHS FROM COVID-19 IN BRAZIL
DOI:
https://doi.org/10.12957/cadest.2024.84973Palavras-chave:
COVID-19, XGBoost, Shapley Values, InterpretabilityResumo
This work proposes a method to rank the contribution of containment measures, vaccination coverage and mobility to contain the evolution of the COVID-19 pandemic in different states of Brazil. The proposed method applies the automatic learning of regression models using decision trees through the XGBoost algorithm. To interpret it globally, the SHapley Additive exPlanations (SHAP) was used, which is an algorithm based on Shapley's cooperative game theory to quantify the contribution of the analyzed characteristics to the evolution of the target variable (deaths). The evaluation results of the method indicated its efficiency to quantify the contribution of each variable in a robust way. It reveals that the percentages of vaccine coverage of the first and second dose, in addition to the closure of schools, were the measures that had the greatest contribution to the evolution of the number of deaths from COVID-19. The weighting of the variables can help the responsible actors in the elaboration of public policies to minimize the socioeconomic effects in their regions. Since, in countries with great social inequality, the use of only a few more efficient measures would be less harmful than a lockdown, as it would be extremely harmful to the quality of life of these poorer populations.
Downloads
Referências
ALGABA, E.; FRAGNELLI, V.; SÁNCHEZ-SORIANO, J. (Ed.). Handbook of the Shapley Value. CRC Press, 2019.
AKTAY, A. et al. Google COVID-19 community mobility reports: anonymization process description, 2022. Disponível em: https://arxiv.org/abs/2004.04145. Acessado em: 20/05/24.
ANTUNES, B. B. de P. et al. Progressão dos casos confirmados de COVID-19 após implantação de medidas de controle. Revista Brasileira de Terapia Intensiva, v. 32, p. 213-223, 2020.
CHAI, T.; DRAXLER, R. R. Root mean square error (RMSE) or mean absolute error (MAE)–Arguments against avoiding RMSE in the literature. Geoscientific model development, v. 7, n. 3, p. 1247-1250, 2014.
CHEMAITELLY, H. et al. Eficácia da vacina mRNA-1273 COVID-19 contra B. 1.1. 7 e B. 1.351 variantes e doença grave de COVID-19 no Catar. Medicina da Natureza, v. 27, n. 9, pág. 1614-1621, 2021.
CHEN, T. et al. Xgboost: extreme gradient boosting. R Package version 0.4-2, v. 1, n. 4, p. 1-4, 2015.
CHEN, T.; GUESTRIN, C. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. p. 785-794, 2016.
CHEW, A. W. Z.; ZHANG, L. Data-driven multiscale modelling and analysis of COVID-19 spatiotemporal evolution using explainable AI. Sustainable Cities and Society, v. 80, p. 103772, 2022.
CUCINOTTA, D.; VANELLI, M. WHO declares COVID-19 a pandemic. Acta Bio Medica: Atenei Parmensis, v. 91, n. 1, p. 157, 2020.
DAGAN, N. et al. BNT162b2 mRNA Covid-19 vaccine in a nationwide mass vaccination setting. New England Journal of Medicine, v. 384, n. 15, p. 1412-1423, 2021.
DE CASTRO-NUNES, P.; DA ROCHA RIBEIRO, G. Equidade e vulnerabilidade em saúde no acesso às vacinas contra a COVID-19. Revista Panamericana de Salud Pública, v. 46, p. e31, 2023.
DONG, E.; DU, H.; GARDNER, L. An interactive web-based dashboard to track COVID-19 in real time. The Lancet infectious Diseases, v. 20, n. 5, p. 533-534, 2020.
FLAXMAN, S. et al. Estimating the effects of non-pharmaceutical interventions on COVID-19 in Europe. Nature, v. 584, n. 7820, p. 257-261, 2020.
FLEURY, S.; FAVA, V. M. D. Vacina contra Covid-19: arena da disputa federativa brasileira. Saúde em Debate, v. 46, p. 248-264, 2022.
GALINDO, E. P.; SILVA, S. P.; PEDREIRA JUNIOR, J. U. Impactos fatais da COVID-19 nos trabalhadores brasileiros. Repositório do Conhecimento do IPEA. v. 27. 2022. Disponível em: https://repositorio.ipea.gov.br/bitstream/11058/11084/2/NT_27_Dirur_Impactos_fatais.pdf. Acessado em: 25/05/24.
HALE, T. et al. Oxford COVID-19 government response tracker (OxCGRT). Last updated, v. 8, p. 30, 2021.
HASTIE, T.; TIBSHIRANI, R.; FRIEDMAN, J. Boosting and Additive Trees. In: The elements of statistical learning. Springer, New York, NY, p.337-384, 2009.
JARA, A. et al. Effectiveness of an inactivated SARS-CoV-2 vaccine in Chile. New England Journal of Medicine, v. 385, n. 10, p. 875-884, 2021.
KUHN, M. Building predictive models in R using the caret package. Journal of Statistical Software, v. 28, p. 1-26, 2008.
LOPEZ BERNAL, J. et al. Effectiveness of Covid-19 vaccines against the B. 1.617. 2 (Delta) variant. New England Journal of Medicine, v. 385, n. 7, p. 585-594, 2021.
LUNDBERG, S. M. et al. Explainable AI for trees: From local explanations to global understanding. 2019. Disponível em: https://arxiv.org/abs/1905.04610. Acessado em: 18/05/24.
MEHTA, P. et al. COVID-19: consider cytokine storm syndromes and immunosuppression. Lancet (London, England), v. 395, n. 10229, p. 1033, 2020.
MINISTÉRIO DA SAÚDE (BR). Sistema de Informação do Programa Nacional de Imunizações SI-PNI. 2022. Disponível em: http://pni.datasus.gov.br. Acessado em: 08/05/24
MINISTÉRIO DA SÁUDE. Portaria nº 454 de 20 de março de 2020. Declara, em todo o território nacional, o estado de transmissão comunitária do coronavírus (covid-19). Diário Oficial da União 2020; 20 mar. Disponível em: https://www.planalto.gov.br/ccivil_03/portaria/prt454-20-ms.htm#:~:text=Portaria%20n%C2%BA%20454%2D20%2Dms&text=Declara%2C%20em%20todo%20o%20territ%C3%B3rio,coronav%C3%ADrus%20(covid%2D19).&text=Considerando%20a%20necessidade%20de%20dar,Art. Acessado em 16/05/24.
MOLNAR, C. Interpretable machine learning: a guide for making black box models explainable. 2 ed. Leanpub Publisher, 2020. Disponível em: https://christophm.github.io/interpretable-ml-book. Acessado em: 24/04/24.
NATIVIDADE, M. dos S. et al. Distanciamento social e condições de vida na pandemia COVID-19 em Salvador-Bahia, Brasil. Ciência & Saúde Coletiva, v. 25, p. 3385-3392, 2020.
NISHIURA, H. et al. Closed environments facilitate secondary transmission of coronavirus disease 2019 (COVID-19). MedRxiv, p. 2020.02. 28.20029272, 2020.
ORELLANA, J. D. Y. et al. Mudanças no padrão de internações e óbitos por COVID-19 após substancial vacinação de idosos em Manaus, Amazonas, Brasil. Cadernos de Saúde Pública, v. 38, p. PT192321, 2022.
PEIXOTO, V. R.; VIEIRA, A.; AGUIAR, P.; SOUSA, P.; ABRANTES, A. Timing, Adesão e Impacto das Medidas de Contenção da COVID-19 em Portugal. Escola Nacional de Saúde Pública, 2020. Disponível em: https://www.unl.pt/sites/default/files/impacto_das_medidas_de_contencao_da_covid-19_em_portugal_3_maio_final.pdf. Acesso em: 12/05/24.
R CORE TEAM. R: A language and environment for statistical computing. 2019.
SHARMA, M. et al. Understanding the effectiveness of government interventions against the resurgence of COVID-19 in Europe. Nature communications, v. 12, n. 1, p. 1-13, 2021.
SOHRABI, C. et al. World Health Organization declares global emergency: A review of the 2019 novel coronavirus (COVID-19). International journal of surgery, v. 76, p. 71-76, 2020.
SUMMAN, A.; NANDI, A. Timing of non-pharmaceutical interventions to mitigate COVID-19 transmission and their effects on mobility: a cross-country analysis. The European Journal of Health Economics, v. 23, n. 1, p. 105-117, 2022.
THOMPSON, B. Stepwise regression and stepwise discriminant analysis need not apply here: A guidelines editorial. Educational and psychological measurement, v. 55, n. 4, p. 525-534, 1995.
ZHU, N. et al. A novel coronavirus from patients with pneumonia in China, 2019. New England Journal of Medicine, v. 382, n. 8, p. 727-733, 2020.
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Copyright (c) 2024 Paulo Henrique Couto Simões
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
Declaramos que, em caso de aceitação do artigo, os autores permanecem com os direitos autorais do artigo, concedendo a revista Cadernos do IME – Série Estatística os direitos de primeira publicação e outros direitos de publicação não exclusivos referentes ao mesmo.
