Modeling and Forecasting TB Incidence in Bolivia Using the Multilayer Perceptron Neural Network
Abstract
In this paper, the ANN approach was applied to analyze TB incidence in
Bolivia. The employed annual data covers the period 2000-2018 and the
out-of-sample period ranges over the period 2019-2023. The residuals and
forecast evaluation criteria (Error, MSE and MAE) of the applied model indicate
that the model is stable in forecasting TB incidence in Bolivia. The results of
the study indicate that TB incidence in the country will continue on a downward
trend although it will remain high around 106 cases/100 000/year over the
period 2019-2023. The government is encouraged to intensify TB surveillance and
control programs amongst other measures.
Country : Zimbabwe
1 Dr. Smartson. P. NYONI2 Thabani NYONI
ZICHIRe Project, University of Zimbabwe, Harare, Zimbabwe
Department of Economics, University of Zimbabwe, Harare, Zimbabwe
Box GEP, Jenkins G. Time Series
Analysis, Forecasting and Control. San Francisco, CA: Holden-Day, 1970
Dheda, K., Barry, C. E., &
Maartens, G. (2016). Tuberculosis, Lancet, 387 (10024): 1211 – 1226.
Jain A, et al. Hybrid neural
network models for hydrologic time series forecasting. Applied Soft Computing
2007; 7: 585–592.
K. W. WANG, C. DENG, J. P. LI, Y.
Y. ZHANG, X. Y. LIAND M. C. WU*Hybrid methodology for tuberculosis incidence
time-series forecasting based on ARIMA and a NAR neural networkEpidemiol.
Infect. (2017), 145, 1118–1129.
Kaushik AC &Sahi. S (2018).
Artificial neural network-based model for orphan GPCRs.Neural.Comput.Appl.
29,985-992
Li K, et al. Daily temperature
change in relation to the risk of childhood bacillary dysentery among different
age groups and sexes in a temperate city in China. Public Health 2015.
Li Q, et al. Application of an
autoregressive integrated moving average model for predicting the incidence of
hemorrhagic fever with renal syndrome. American Journal of Tropical Medicine
and Hygiene 2012; 87: 364–370.
Nyoni S. P &Nyoni T (2019).
Forecasting TB notifications at Silobela District Hospital, Zimbabwe.IJARIIE
5(6)2395-4396.
Nyoni S. P &Nyoni T (2019).
Forecasting TB notifications at Silobela District Hospital, Zimbabwe.IJARIIE
5(6)2395-4396.
Nyoni S. P &Nyoni T (2019).
Forecasting TB notifications at Zengeza clinic, Zimbabwe. Online at
https://mpra.ub.uni-muenchen.de/97331/ MPRA Paper No. 97331, posted 02 Dec 2019
10:13 UTC
Nyoni S. P &Nyoni T (2019).
Forecasting TB notifications at Zengeza clinic, Zimbabwe. Online at
https://mpra.ub.uni-muenchen.de/97331/ MPRA Paper No. 97331, posted 02 Dec 2019
10:13 UTC
Tabaszewski M, et al. Using a set
of GM (1,1) models to predict values of diagnostic symptoms. Mechanical Systems
and Signal Processing 2015; 52: 416–425.
Taskaya-Temizel T, et al. A
comparative study of autoregressive neural network hybrids. Neural Networks
2005; 18: 781–789.
World Health Organization. Global
TB report 2015. Geneva: World Health Organization, 2015. (http://www.
who.int/tb/publications/global report/en/)
Yang W, et al. Comparison of
filtering methods for the modeling and retrospective forecasting of influenza
epidemics. PLoS Computational Biology 2014; 10.
Yu L, et al. Application of a new
hybrid model with seasonal auto-regressive integrated moving average (ARIMA)
and nonlinear auto-regressive neural network (NARNN) in forecasting incidence
cases of HFMD in Shenzhen, China. PLoS ONE 2014; 9: e98241.
Zhang X, et al. Applications and
comparisons of four time series models in epidemiological surveillance data.
PLoS ONE 2014; 9: e88075.
