Malaria remains a major public health challenge necessitating accurate predictive models to inform effective intervention strategies in Sierra Leone. This study compares the performance of Holt-Winters’ Exponential Smoothing, Harmonic, and Artificial Neural Network (ANN) models using data from January 2018 to December 2023, incorporating both historical case records from Sierra Leone’s Health Management Information System (HMIS) and meteorological variables including humidity, precipitation, and temperature. The ANN model demonstrated superior performance, achieving a Mean Absolute Percentage Error (MAPE) of 4.74% before including climatic variables. This was further reduced to 3.9% with the inclusion of climatic variables, outperforming traditional models like Holt-Winters and Harmonic, which yielded MAPEs of 22.53% and 17.90% respectively. The ANN’s success is attributed to its ability to capture complex, non-linear relationships in the data, particularly when enhanced with relevant climatic variables. Using the optimized ANN model, we forecasted malaria cases for the next 24 months, predicting a steady increase from January 2024 to December 2025, with seasonal peaks. This study underscores the potential of machine learning approaches, particularly ANNs, in epidemiological modelling and highlights the importance of integrating environmental factors into malaria prediction models, recommending the ANN model for informing more targeted and efficient malaria control strategies to improve public health outcomes in Sierra Leone and similar settings.
References
[1]
Autino, B., Noris, A. and Russo, R. (2012) Epidemiology of Malaria in Endemic Areas. Mediterranean Journal of Hematology and Infectious Diseases, 4, e2012060.
[2]
Abeku, T.A., de Vlas, S.J. and Borsboom, G. (2002) Forecasting Malaria Incidence from Historical Morbidity Patterns in Epidemic-Prone Areas of Ethiopia: A Simple Seasonal Adjustment Method Performs Best. Tropical Medicine & International Health, 7, 851-857. https://doi.org/10.1046/j.1365-3156.2002.00924.x
[3]
World Health Organization (2020) World Malaria Report 2020. World Health Organization. https://www.who.int/publications/i/item/9789240015791
[4]
Gething, P.W., Smith, D.L. and Patil, A.P. (2010) Climate Change and the Global Malaria Recession. Nature, 465, 342-345. https://doi.org/10.1038/nature09098
[5]
Tonnang, H.E.Z., Kangalawe, R.Y.M. and Yanda, P.Z. (2010) Predicting and Mapping Malaria Under Climate Change Scenarios: The Potential Redistribution of Malaria Vectors in Africa. Malaria Journal, 9, 1-10. https://doi.org/10.1186/1475-2875-9-111
[6]
Mordecai, E.A., Ryan, S.J. and Caldwell, J.M. (2020) Climate Change Could Shift Disease Burden from Malaria to Arboviruses in Africa. The Lancet Planetary Health, 4, e416-e423. https://doi.org/10.1016/S2542-5196(20)30178-9
[7]
Ryan, S.J., Lippi, C.A. and Zermoglio, F. (2020) Shifting Transmission Risk for Malaria in Africa with Climate Change: A Framework for Planning and Intervention. Malaria Journal, 19, 1-14. https://doi.org/10.1186/s12936-020-03224-6
[8]
Patz, J.A., Campbell-Lendrum, D. and Holloway, T. (2005) Impact of Regional Climate Change on Human Health. Nature, 438, 310-317. https://doi.org/10.1038/nature04188
[9]
Lafferty, K.D. (2009) The Ecology of Climate Change and Infectious Diseases. Ecology, 90, 888-900. https://doi.org/10.1890/08-0079.1
[10]
Grover-Kopec, E.K., Blumenthal, M.B. and Ceccato, P. (2006) Web-Based Climate Information Resources for Malaria Control in Africa. Malaria Journal, 5, 1-9. https://doi.org/10.1186/1475-2875-5-38
[11]
Anwar, M.Y., Lewnard, J.A. and Parikh, S. (2016) Time Series Analysis of Malaria in Afghanistan: Using ARIMA Models to Predict Future Trends in Incidence. Malaria Journal, 15, 1-10. https://doi.org/10.1186/s12936-016-1602-1
[12]
Anokye, R., Acheampong, E. and Owusu, I. (2018) Time Series Analysis of Malaria in Kumasi: Using ARIMA Models to Forecast Future Incidence. Cogent Social Sciences, 4, Article 1461544. https://doi.org/10.1080/23311886.2018.1461544
[13]
Zinszer, K., Verma, A.D. and Charland, K. (2012) A Scoping Review of Malaria Forecasting: Past Work and Future Directions. BMJ Open, 2, e001992. https://doi.org/10.1136/bmjopen-2012-001992
[14]
Wangdi, K., Singhasivanon, P. and Silawan, T. (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. Malaria Journal, 9, 1-9. https://doi.org/10.1186/1475-2875-9-251
[15]
Zhang, X., Zhang, T. and Young, A.A. (2014) Applications and Comparisons of Four Time Series Models in Epidemiological Surveillance Data. PLOS ONE, 9, e88075. https://doi.org/10.1371/journal.pone.0088075
[16]
Kumar, P., Vatsa, R. and Sarthi, P.P. (2020) Modeling an Association between Malaria Cases and Climate Variables for Keonjhar District of Odisha, India: A Bayesian Approach. Journal of Parasitic Diseases, 44, 319-331. https://doi.org/10.1007/s12639-020-01210-y
[17]
Liatsis, P., Foka, A. and Goulermas, J.Y. (2007) Adaptive Polynomial Neural Networks for Times Series Forecasting. ELMAR 2007, Zadar, 12-14 September 2007, 35-39. https://doi.org/10.1109/ELMAR.2007.4418795
[18]
National Malaria Control Programme (2021) Sierra Leone Malaria Indicator Survey 2021, NMCP, SSL, CRS, and Utica International. Freetown, Sierra Leone.
[19]
U.S. President’s Malaria Initiative (2024) Sierra Leone FY 2024 Country Malaria Profile—Final, U.S. Agency for International Development (USAID). https://www.pmi.gov/where-we-work/sierra-leone/
[20]
Okunlola, O.A. and Oyeyemi, O.T. (2019) Spatio-Temporal Analysis of Association between Incidence of Malaria and Environmental Predictors of Malaria Transmission in Nigeria. Scientific Reports, 9, Article No. 17500. https://doi.org/10.1038/s41598-019-53814-x
[21]
Okiring, J., Routledge, I., Esptein, A., et al. (2021) Associations between Environmental Covariates and Malaria Incidence in High Transmission Settings of Uganda: A Distributed Non-Linear Lagged Ecological Analysis. BMC Public Health, 21, Article 1962. https://doi.org/10.1186/s12889-021-11949-5
[22]
Gaudart, J., Touré, O. and Dessay, N. (2009) Modelling Malaria Incidence with Environmental Dependency in a Locality of Sudanese Savannah Area, Mali. Malaria Journal, 8, 1-12. https://doi.org/10.1186/1475-2875-8-61
[23]
Oyebode, O.J. (2013) Solid Waste Management for Sustainable Development and Public Health: A Case Study of Lagos State in Nigeria. Universal Journal of Public Health, 1, 33-39. https://doi.org/10.13189/ujph.2013.010301
[24]
Kafando, P., Segda, B.G., Nzihou, J.F. and Koulidiati, J. (2013) Environmental Impacts of Waste Management Deficiencies and Health Issues: A Case Study in the City of Kaya, Burkina Faso. Journal of Environmental Protection, 4, 1080-1087. https://doi.org/10.4236/jep.2013.410124
[25]
Mohamed, J., Mohamed, A.I. and Daud, E.I. (2022) Evaluation of Prediction Models for the Malaria Incidence in Marodijeh Region, Somaliland. Journal of Parasitic Diseases, 46, 395-408. https://doi.org/10.1007/s12639-021-01458-y
[26]
da Cunha, G.B., Luitgards-Moura, J.F. and Naves, E.L.M. (2010) Use of an Artificial Neural Network to Predict the Incidence of Malaria in the City of Canta, State of Roraima. Revista da Sociedade Brasileira de Medicina Tropical, 43, 567-570. https://doi.org/10.1590/S0037-86822010000500019
[27]
Mansaray, A.S., Barrie, A. and Jabati, E.B.M. (2021) Utilizing Geospatial Tools to Assign Unique Identifiers to Water Bodies in a Low-Income Country. Journal of Water Resource and Protection, 13, 236-253. https://doi.org/10.4236/jwarp.2021.133014
[28]
Nicol, D.S.W.H., Fyfe, C. and Sesay, S.M. (1999) Sierra Leone. Encyclopedia Britannica, Inc.
[29]
Weather Atlas (2024) Weather Atlas: Climate Data for 2024, Weather Atlas. https://www.weather-atlas.com
[30]
World Bank (2019) World Bank Country and Lending Groups—Country Classifications. The World Bank Group. https://datahelpdesk.worldbank.org/knowledgebase/articles/906519-world-bank-country-and-lending-groups
[31]
Wadsworth, R., Jalloh, A. and Lebbie, A. (2019) Changes in Rainfall in Sierra Leone: 1981-2018. Climate, 7, Article 144. https://doi.org/10.3390/cli7120144
[32]
Roser, M., Ritchie, H. and Ortiz-Ospina, E. (2020) Burden of Disease. Our World in Data. https://ourworldindata.org/burden-of-disease
[33]
Rismala, R., Liong, T.H. and Ardiyanti, A. (2013) Prediction of Malaria Incidence in Banggai Regency Using Evolving Neural Network. 2013 International Conference on Technology, Informatics, Management, Engineering and Environment, Bandung, 23-26 June 2013, 89-94. https://doi.org/10.1109/TIME-E.2013.6611970
[34]
Ooi, C.H., Bujang, M.A. and Bakar, T.M.I.T.A. (2017) Over Two Decades of Plasmodium Knowlesi Infections in Sarawak: Trend and Forecast. Acta Tropica, 176, 83-90. https://doi.org/10.1016/j.actatropica.2017.07.027
[35]
Menda, D.M., Nawa, M. and Zimba, R.K. (2021) Forecasting Confirmed Malaria Cases in Northwestern Province of Zambia: A Time Series Analysis Using 2014-2020 Routine Data. Advances in Public Health, 2021, Article ID: 6522352. https://doi.org/10.1155/2021/6522352
[36]
Bi, P., Tong, S. and Donald, K. (2003) Climatic Variables and Transmission of Malaria: A 12-Year Data Analysis in Shuchen County, China. Public Health Reports, 118, 65-71. https://doi.org/10.1016/S0033-3549(04)50218-2
[37]
Kipruto, E.K., Ochieng, A.O. and Anyona, D.N. (2017) Effect of Climatic Variability on Malaria Trends in Baringo County, Kenya. Malaria Journal, 16, 1-11. https://doi.org/10.1186/s12936-017-1848-2
[38]
Kumar, A., Bansal, H. and Jaiswal, A. (2023) Early Disease Prediction Using ML. International Journal of Advanced Engineering and Nano Technology, 11, 123-134. https://doi.org/10.35940/ijaent.I9694.11101123
[39]
Taylor, M.A., Bennett, C.L. and Schoen, M.W. (2021) Advances in Artificial Neural Networks as a Disease Prediction Tool. Journal of Cancer Research and Therapeutics, 9, 1-11. https://doi.org/10.14312/2052-4994.2021-1
