Modeling and Forecasting TB Incidence in Tanzania: The Artificial Neural Network Approach
Abstract
In this research article, the ANN approach was applied to analyze TB
incidence in Tanzania. The employed annual data covers the period January
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
Tanzania. The results of the study indicate that TB incidence will sharply rise
from 239 cases/100 000 /year in 2019 to 456 cases/100 000/year in 2020 and then
decline sharply to around 239 cases per 100 000/year in 2023. In order to
contribute meaningfully to the national control strategy of a TB-free Tanzania,
the government should, among other things, intensify TB surveillance and
control programs.
Country : Zimbabwe
1 Dr. Smartson. P. NYONI2 Thabani NYONI
ZICHIRe Project, University of Zimbabwe, Harare, Zimbabwe
Department of Economics, University of Zimbabwe, Harare, Zimbabwe
Anwar MY, Lewnard JA, Parikh S
& Pitzer VE (2016). Time series analysis of malaria in Afghanistan: using
ARIMA models to predict future trends in incidence. Malar J.;15(1):566.
doi:10.1186/s12936-016-1602-1
Briet OJ., Amerasinghe PH., &Vounatsou
P (2013). Generalized seasonal autoregressive integrated moving average models
for count data with application to malaria time series with low case numbers.
PLoS One;8(6): e65761. doi: 10.1371/journal.pone.0065761
Briet OJ., Vounatsou P., Gunawardena
DM., Galappaththy GN &Amerasinghe PH (2008). Models for short term malaria
prediction in Sri Lanka. Malar J;7(1):76. doi:10.1186/1475-2875-7-129
G.E.P. Box, G. Jenkins, “Time
Series Analysis, Forecasting and Control”, Holden-Day, San Francisco, CA, 1970.
Li XX., Wang LX., & Zhang H
(2013). Seasonal variations in notification of active tuberculosis cases in
China, 2005–2012. PLoS One;8 (7): e68102. doi: 10.1371/journal.pone.0068102
N ‘Gattia AK., Coulibaly D &
Nzussouo NT (2016). Effects of climatological parameters in modeling and
forecasting seasonal influenza transmission in Abidjan, Cote d ‘Ivoire. BMC
Public Health;16(1):972. doi:10.1186/s12889-016-3503-1
Permanasari AE., Rambli DR., &
Dominic PD. Performance of univariate forecasting on seasonal diseases: the
case of tuberculosis. Adv Exp Med Biol;696(696):171–179.
doi:10.1007/978-1-44197046-6_17
Ramirez AP., Buitrago JI., Gonzalez
JP., Morales AH & Carrasquilla G (2014). Frequency and tendency of malaria
in Colombia, 1990 to 2011: a descriptive study. Malar J;13(1):202.
doi:10.1186/14752875-13-202
Wangdi K., Singhasivanon P.,
Silawan T., Lawpoolsri S., White NJ &Kaewkungwal J (2010). Development of
temporal modelling for forecasting and prediction of malaria infections using
time-series and ARIMAX analyses: a case study in endemic districts of Bhutan.
Malar J. 2010; 9(1): 251. doi:10.1186/1475-2875-9-251
Wubuli A., Li Y & Xue F (2017).
Seasonality of active tuberculosis notification from 2005 to 2014 in Xinjiang,
China. PLoS One;12(7): e0180226. doi: 10.1371/journal.pone.0180226
Zhang GP, “Time series forecasting
using a hybrid ARIMA and neural network model”, Neurocomputing 50 (2003),
pages: 159–175.
