Time series models for neonatal mortality rate forecasting
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1348Keywords:
Primary Health Care, Health Policy, Data ScienceAbstract
Objective: The present work aims to evaluate parametric and non-parametric time series models for forecasting the neonatal mortality rate in medium-sized Brazilian municipalities. Method: The models were training using historical data from 2010 to 2022 and evaluated in terms of performance metrics and predictions values. Results: According to the results, the time series of the neonatal mortality rate has stationary and seasonal profile. Among the algorithms considered, the Seasonal Autoregressive Integrated Moving Average model was able to capture the pattern of the time series and make predictions with greater precision. However, residual autocorrelation was confirmed, which could lead to biased results. Conclusion: From the analysis of the results, the importance of evaluating both parametric and non-parametric models to provide information on information on forecasting neonatal mortality that could be used to evaluate and discuss Brazilian Public Health policies.
References
Garcia LP, Schneider IJC, Oliveira C de, Traebert E, Traebert J. What is the impact of national public expenditure and its allocation on neonatal and child mortality? A machine learning analysis. BMC Public Health. 2023; 23(1):793.
Kale PL, Fonseca SC. Mortalidade neonatal específica por idade e fatores associados na coorte de nascidos vivos em 2021, no estado do Rio de Janeiro, Brasil. Revista Brasileira de Epidemiologia. 2022 ;25:e220038.
Vieira C, Arato B, Fernandes L, et al. Association of the Previne Brasil Program in prenatal care and maternal-child mortality. 2024. BMC Public Health. Preprint.
Soyiri IN, Reidpath DD. An overview of health forecasting. Environ Health Prev Med. 2013; 18(1):1.
Yang Y, Cao Z, Zhao P, Zeng DD, Zhang Q, Luo Y. Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study. Journal of Safety Science and Resilience. 2021;2(3):146–156.
Morgenstern JD, Buajitti E, O’Neill M, et al. Predicting population health with machine learning: a scoping review. BMJ Open 2020;10(10):e037860.
Tomov L, Chervenkov L, Miteva DG, Batselova H, Velikova T. Applications of time series analysis in epidemiology: Literature review and our experience during COVID-19 pandemic. World J Clin Cases. 2023 ;11(29):6974.
He S, Zhang H, Liu X, et al. Under-5, infant, and neonatal mortality trends and causes of death, 1991-2022: Findings from death surveillance in Xicheng district of Beijing, China. Prev Med Rep. 2023; 36.
Ferreira HNC, Capistrano GN, Morais TNB, et al. Screening and hospitalization of breast and cervical cancer in Brazil from 2010 to 2022: A time-series study. PLoS One. 2023; 18(10).
Parmezan ARS, Souza VMA, Batista GEAPA. Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model. Inf Sci. 2019; 484:302–337.
Cao H, Wang J, Li Y, et al. Trend analysis of mortality rates and causes of death in children under 5 years old in Beijing, China from 1992 to 2015 and forecast of mortality into the future: An entire population-based epidemiological study. BMJ Open 2017;7(9).
Rajia S, Sabiruzzaman M, Islam MK, Hossain MG, Lestrel PE. Trends and future of maternal and child health in Bangladesh. PLoS One 2019;14(3).
Zhang R, Song H, Chen Q, Wang Y, Wang S, Li Y. Comparison of ARIMA and LSTM for prediction of hemorrhagic fever at different time scales in China. PLoS One 2022;17.
Calvo MCM, Lacerda JT de, Colussi CF, Schneider IJC, Rocha TAH. Estratificação de municípios brasileiros para avaliação de desempenho em saúde. Epidemiologia e Serviços de Saúde. 2016; 25(4):767–776.
Silveira AG, Mattos VLD, Nakamura LR, Amaral MC, Konrath AC, Bornia AC. Análise do Valor p Determinado pela Estatística τ na Aplicação do Teste de Dickey-Fuller Aumentado. Trends in Computational and Applied. 2022; 23(2):283–298.
Joosery B, Deepa G. Comparative analysis of time-series forecasting algorithms for stock price prediction [Homepage on the Internet]. In: Proceedings of the 1st International Conference on Advanced Information Science and System. New York, NY, USA: ACM, 2019; p. 1–6.
Taslim DG, Murwantara IM. A Comparative Study of ARIMA and LSTM in Forecasting Time Series Data. In: 2022 9th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE). IEEE, 2022; p. 231–235.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
