Abstract

Dengue fever is a mosquito-borne viral disease that has grown dramatically around the world in recent years. It is more prevalent in tropical and subtropical countries. Annually, an estimated 390 million infections occur worldwide. Several studies have shown that climate factors influence this disease. Furthermore, it was shown that the influence of climate factors on dengue incidences was expected to be visible after some lag period. Identifying the climate factors that influence the spread of dengue fever would be helpful in combatting growth of the disease. This study builds an Artificial Neural Network (ANN) model for predicting the risk status of dengue incidences based on climate factors. The climate factors, average temperature, rainfall, and average relative humidity with a time lag are used as input parameters to the ANN. The monthly dengue incidences and the data on climate factors from the city of Colombo in Sri Lanka are used for this study. The accuracy of the ANN model prediction is found to be 90%.

References

• WHO (World Health Organization): Who spreads dengue and severe dengue? https://www.who.int/denguecontrol/faq/en/index5.html, accessed 05 August 2010.
• CDC. Centers for disease control and prevention, https://www.cdc.gov/dengue/index.html, accessed 01 August 2020.
• WHO (World Health Organization) 2009: WHO Report on Global Surveillance of Epidemic-prone Infectious Diseases - Dengue and dengue hemorrhagic fever. https://www.who.int/csr/resources/publications/dengue/CSR_ISR_2000_1/en/index5.html, accessed 01 August 2020.
• Shepard, D. S., Undurraga, E.A., Hallasa, Y. A., and Stanaway, J. D. 2016. The global economic burden of dengue: a systematic analysis. Lancet Infectious Diseases, 16, 935–941
• Al-Muhandis,  N. and Hunter, P. R. 2011. The Value of Educational Messages Embedded in a Community-Based Approach to Combat Dengue Fever: A Systematic Review and Meta Regression Analysis. PLOS Neglected Tropical Diseases, 5(8): e1278. https://doi.org/10.1371/journal.pntd.0001278
• Sirisena, P.P.N.N. and Noordeen, F. 2014. Evolution of Dengue in Sri Lanka—Changes in the Virus, Vector, and Climate. Int. J. Infect. Dis., 19, 6–12
• Epidemiology Unit of Ministry of Health of Sri Lanka. Available Online: http://www.epid.gov.lk/web/
• Morin, C. W., Comrie, A. C. and Ernst, K. C. 2013. Climate and dengue transmission: evidence and implications. Environ Health Perspectives. 121, 1264–1272; http://dx.doi.org/10.1289/ehp.1306556
• Chandrakantha, L. 2019. Statistical analysis of climate factors influencing dengue incidences in Colombo, Sri Lanka: Poisson and negative binomial regression approach. Int. J. Sci. Res. Publ. 9, 133–144, doi:10.2322/IJSRP.9.02.2019.p8616
• Vu, H.H., Okumura, J., Hashizume, M., Tran, D.N. and Yamamoto, T. 2014. Regional differences in the growing incidences of dengue fever in Vietnam explained by weather variability. Trop. Med. Health. 42, 25–33. doi: 10.2149/tmh.2013-24
• Withanage, G.P., Wishwakula, S.D., Gunawardena, Y.I and Hapugoda, M.D. 2018. A Forecasting Model for Dengue Incidence in the District of Gampaha, Sri Lanka. Parasites and Vectors. 11, 262, doi:10.1186/s13071-018-2828-2.
• Breiman, L. 2001. Statistical modeling: the two cultures (with comments and a rejoinder by the author). Statistical Science.  16(3): 199–231
• Pacelli, V. and Azzollinni, M. 2011. An Artificial Neural Network Approach for Credit Risk Management, Journal of Intelligent Learning Systems and Applications, 3, 103-112
• Gupta, D. P. and Goyal, S. 2018. Credit Risk Prediction Using Artificial Neural Network Algorithm, I.J. Modern Education and Computer Science, 5, 9-16
• Rachata, N., Charoenkwan. P., Yooyativong. T., Chamnongthai . K., Lursinsap, C. and Higuchi, K. Automatic prediction system of dengue haemorrhagic-fever outbreak risk by using entropy and artificial neural network; Proceedings of the International Symposium on Communications and Information Technologies; Vientiane, Laos. 21–23 October 2008
• Aburas, H. M., Cetiner , B. G. and Sari, M. 2010. Dengue confirmed-cases prediction: A neural network model. Expert Syst. Appl.  37, 4256–4260. doi: 10.1016/j.eswa.2009.11.077
• Hwang, S., Clarite, D.S., Elijorde, F.I., Gerardo, B.D. and Byun, Y. 2016. A web-based analysis of dengue tracking and prediction using artificial neural network. Advanced Science and Technology Letters; Science & Engineering Research Support Society; Sandy Bay, TAS, Australia: 122, 160–164.
• Nishanthi, P., Perera, A. and Wijekoon, H. 2014. Prediction of dengue outbreaks in Sri Lanka using artificial neural networks. Int. J. Comput. Appl., 101, 1–5
• Ughelli, V., Lisnichuk, Y., Paciello, J., and Pane, J. 2017. Prediction of Dengue Cases in Paraguay Using Artificial Neural Networks. Int’l Conf. Health Informatics and Medical Systems – HIMS 1, 130-136
• Ong, E. and Flitman, A.1997. Using neural networks to predict binary outcomes,   IEEE International Conference on Intelligent Processing Systems (Cat. No.97TH8335), Beijing, China, 1, 427-431 doi: 10.1109/ICIPS.1997.672816.
• Bertolaccini, L., Solli, P., Pardolesi, A., and Pasini, A. 2017. An overview of the use of artificial neural networks in lung cancer research. Journal of thoracic disease, 9(4), 924–931. https://doi.org/10.21037/jtd.2017.03.157
• Maca, P., Pech. P. and Pavlasek, J. 2014. Comparing the Selected Transfer Functions and Local Optimization Methods for Neural Network Flood Runoff Forecast, Mathematical Problems in Engineering. https://doi.org/10.1155/2014/782351
• Department of Census and Statistics of Sri Lanka. http://www.statistics.gov, accessed 01 August 2020.
• Nakhapakorn, K. and Tripathi, N.K. 2005. An Information Value Based Analysis of Physical and Climatic Factors Affecting Dengue Fever and Dengue Haemorrhagic Fever Incidence. Int. J. Health Geogr. 4, doi:10.1186/1476-072X-4-13.
• Gunther, F. and Fritsch, S. 2010. neuralnet: Training of Neural Networks, The R Journal. 2(1), 30-38. https://journal.r-project.org/archive/2010/RJ-2010-006/RJ-2010-006.pdf
• Pineda, F. J. 1987. Generalization of back-propagation to recurrent neural networks. Physical review letters, 59(19), 2229.
• Nayak, S. C., Misra, B. B. and Behera, H. S. 2014. Impact of Data Normalization on Stock Index Forecasting, International Journal of Computer Information Systems and Industrial Management Applications. 6, 257-269.
• Zhang, Z. 2016. Neural networks: further insight into error functions, generalized weights and others. Annals of Translational Medicine. 4(16), 300. doi: 10.21037/atm.2016.05.37.
• Woods, K. and Bowyer, K. W. 1997. Generating ROC curves for artificial neural networks, IEEE Transactions on Medical Imaging, 16 (3), 329-337. doi: 10.1109/42.585767.