DOI: http://dx.doi.org/10.18203/2394-6040.ijcmph20160620

Forecasting the trend in cases of Ebola virus disease in West African countries using auto regressive integrated moving average models

Manikandan M., Velavan A., Zile Singh, Anil J. Purty, Joy Bazroy, Senthamarai Kannan

Abstract


Background: Ebola Virus Disease (EVD), formerly known as Ebola haemorrhagic fever, is a severe, often fatal illness in humans. The current outbreak in West African countries like Guinea, Liberia and Sierra Leone is one of the largest in the history. Hence, to forecast the trend in a number of cases of EVD reported in these Countries a univariate time series model was used.

Methods:We adopted an Auto Regressive Integrated Moving Average (ARIMA) models on the data collected between March 2014 to December 2014 and verified it using the data available between Jan 2015 to June 2015. The same has been used to predict the number of cases till December 2016 without any additional intervention.

Results: The results also showed an increasing trend in the actual and forecasted numbers of EVD cases. The appropriate ARIMA (1, 1, 0) model was selected based on Bayesian Information Criteria (BIC) values.

Conclusions:Hence, to prevent the disease from getting established as an endemic in these countries, additional interventions with an increase in the intensity of existing interventions and support of the international community along with WHO is essential to stop the epidemic.


Keywords


Univariate time series, Ebola, ARIMA, BIC, Forecasting

Full Text:

PDF

References


Ebola situation report. Geneva. World Health Organization. Available from http://apps.who.int/ ebola/ebola-situation-reports. Accessed on 15th November 2015.

Bhatnagar S, Lal V, Gupta SD, Gupta OP. Forecasting Incidence of Dengue in Rajasthan, Using Time Series Analyses. Indian Journal of Public Health. 2012;56(4):281-5.

Widerström M, Omberg M, Ferm M, Pettersson AK, Eriksson MR, Eckerdal I, et al. Autoregressive Integrated Moving Average (ARIMA) Modelling of Time Series of Local Telephone Triage Data for Syndromic Surveillance. Online Journal of Public Health Informatics. 2014;6(1):e18.

Wangdi K, Asivanon PS, Silawan T, Lawpoolsri S, White NJ, Kaewkungwal J. Development of temporal modelling for forecasting and prediction of malaria infection susing time-series and ARIMAX analyses: A casestudy in endemic districts of Bhutan.Malaria Journal. 2010;9:251.

Prabakaran C, Sivapragasam C. Forecasting Areas and Production of Rice in India using ARIMA model, International Journal of Farm Sciences. 2014;4(1):99-106.

Zhang PG. Time series forecasting using a hybrid ARIMA and neural network models. Neurocomputing. 2003;50:159-75.

Promprou S, Jaroensutasinee M, Jaroensutasinee K. Forecasting Dengue Hemorrhagic Fever Cases in Southern Thailand using ARIMA Models, Dengue Bulletin. 2006;30:99-106.

Box G, Pierce DA. Distribution of residual autocorrelations in autoregressive- integrated Moving average time-series models. J Am Stat Ass. 1970;65:1509-26.

Box GEP, Jenkins GM. Time Series Analysis: Forecasting and Control, 2nd ed. San Francisco: Holden-Day. 1976:575.