International Journal of

ADVANCED AND APPLIED SCIENCES

EISSN: 2313-3724, Print ISSN: 2313-626X

Frequency: 12
line decor
  
line decor

 Volume 11, Issue 1 (January 2024), Pages: 20-31

----------------------------------------------

 Original Research Paper

Forecasting the incidence of dengue fever in Malaysia: A comparative analysis of seasonal ARIMA, dynamic harmonic regression, and neural network models

 Author(s): 

 Nurakmal Ahmad Mustaffa 1, *, Siti Mariam Zahari 2, Nor Alia Farhana 2, Noryanti Nasir 2, Aishah Hani Azil 3

 Affiliation(s):

 1School of Quantitative Sciences, College of Arts and Sciences, Universiti Utara Malaysia, Sintok, Malaysia
 2School of Mathematical Sciences, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam, Malaysia
 3Department of Parasitology and Medical Entomology, Faculty of Medicine, Universiti Kebangsaan Malaysia, Cheras, Malaysia

 Full text

  Full Text - PDF

 * Corresponding Author. 

  Corresponding author's ORCID profile: https://orcid.org/0000-0001-6495-301X

 Digital Object Identifier (DOI)

 https://doi.org/10.21833/ijaas.2024.01.003

 Abstract

Currently, no vaccines or specific treatments are available to treat or prevent the increasing incidence of dengue worldwide. Therefore, an accurate prediction model is needed to support the anti-dengue control strategy. The primary objective of this study is to develop the most accurate model to predict future dengue cases in the Malaysian environment. This study uses secondary data collected from the weekly reports of the Ministry of Health Malaysia (MOH) website over six years, from 2017 to 2022. Three forecasting techniques, including seasonal autoregressive integrated moving average (SARIMA), dynamic harmonic regression (DHR), and neural network autoregressive model (NNAR), were first fitted to the estimation part of the data. First, several SARIMA models were run, and the best seasonal model identified was SARIMA (0, 1, 2) (1, 1, 1)52. The best DHR model was obtained with a Fourier term of 2, as this corresponds to the lowest Akaike Information Criteria (AIC) value. The NNAR (9, 1, 6)52 was considered the best choice among the NNAR models due to its superior performance in terms of the lowest error measures. The comparison among the three techniques revealed that the DHR model was the best due to its lowest MAPE and RMSE values. Thus, the DHR model was used to generate future forecasts of weekly dengue cases in Malaysia until 2023. The results showed that the model predicted more than a thousand dengue cases around weeks 27 to 32. The results showed an increase in dengue cases after the end of the monsoon season, which lasted about five months. This technique is proving to be valuable for health administrators in improving preparedness.

 © 2023 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords

 SARIMA, Dynamic harmonic regression, Neural network autoregressive, Forecasting, Dengue

 Article history

 Received 7 August 2023, Received in revised form 11 December 2023, Accepted 18 December 2023

 Acknowledgment 

This research was supported by the Ministry of Higher Education (MOHE) of Malaysia through the Fundamental Research Grant Scheme (FRGS/1/2022/SS0/UiTM/02/20).

 Compliance with ethical standards

 Conflict of interest: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

 Citation:

 Mustaffa NA, Zahari SM, Farhana NA, Nasir N, and Azil AH (2024). Forecasting the incidence of dengue fever in Malaysia: A comparative analysis of seasonal ARIMA, dynamic harmonic regression, and neural network models. International Journal of Advanced and Applied Sciences, 11(1): 20-31

 Permanent Link to this page

 Figures

 Fig. 1 Fig. 2 Fig. 3 Fig. 4 Fig. 5 

 Tables

 Table 1 Table 2 Table 3 Table 4 Table 5 Table 6 Table 7 

----------------------------------------------   

 References (45)

  1. Abas N, Shamsuddin RM, and Halim SA (2018). Modelling and prediction of dengue cases at two progressive regions in Malaysia. Journal of Fundamental and Applied Sciences, 10(3S): 319-324.   [Google Scholar]
  2. Aguiar M, Anam V, Blyuss KB, Estadilla CD, Guerrero BV, Knopoff D, Kooi BW, Srivastav AK, Steindorf V, and Stollenwerk N (2022). Mathematical models for dengue fever epidemiology: A 10-year systematic review. Physics of Life Reviews, 40: 65-92. https://doi.org/10.1016/j.plrev.2022.02.001   [Google Scholar] PMid:35219611 PMCid:PMC8845267
  3. Anggraeni W, Nurmasari R, Riksakomara E, Samopa F, and Wibowo RP (2017). Modified regression approach for predicting number of dengue fever incidents in Malang Indonesia. Procedia Computer Science, 124: 142-150. https://doi.org/10.1016/j.procs.2017.12.140   [Google Scholar]
  4. Aziz A and Aziz A (2021). Dengue cases prediction using machine learning approach. IRASD Journal of Computer Science and Information Technology, 2(1): 13-25. https://doi.org/10.52131/jcsit.2021.0201.0007   [Google Scholar]
  5. Azmawati MN, Aniza I, and Munawar ALI (2013). Evaluation of communication for behavioral impact (COMBI) program in dengue prevention: A qualitative and quantitative study in Selangor, Malaysia. Iranian Journal of Public Health, 42(5): 538-539.   [Google Scholar]
  6. Bhatt S, Gething PW, Brady OJ, Messina JP, Farlow AW, Moyes CL, and Hay SI (2013). The global distribution and burden of dengue. Nature, 496(7446): 504-507. https://doi.org/10.1038/nature12060   [Google Scholar] PMid:23563266 PMCid:PMC3651993
  7. Box GE and Pierce DA (1970). Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. Journal of the American Statistical Association, 65(332): 1509-1526. https://doi.org/10.1080/01621459.1970.10481180   [Google Scholar]
  8. Box GEP, Jenkins GM, and Reinsel GG (1994). Time series analysis: Forecasting and control. 3rd Edition, Prentice Hall, Englewood Cliff, USA.   [Google Scholar]
  9. Butterworth MK, Morin CW, and Comrie AC (2017). An analysis of the potential impact of climate change on dengue transmission in the southeastern United States. Environmental Health Perspectives, 125(4): 579-585. https://doi.org/10.1289/EHP218   [Google Scholar] PMid:27713106 PMCid:PMC5381975
  10. Chakraborty T, Chattopadhyay S, and Ghosh I (2019). Forecasting dengue epidemics using a hybrid methodology. Physica A: Statistical Mechanics and its Applications, 527: 121266. https://doi.org/10.1016/j.physa.2019.121266   [Google Scholar]
  11. Elhassan FAM, Qurashi MAE, and Elhafian MH (2020). Spatial statistic of reproduction of dengue fever mosquitoes transmitter phenomenon in the university municipality Jeddah Province Saudi Arabia during 2018. International Journal of Advanced and Applied Sciences, 7(11): 58-66. https://doi.org/10.21833/ijaas.2020.11.006   [Google Scholar]
  12. Ewing DA, Purse BV, Cobbold CA, and White SM (2021). A novel approach for predicting risk of vector-borne disease establishment in marginal temperate environments under climate change: West Nile virus in the UK. Journal of the Royal Society Interface, 18(178): 20210049. https://doi.org/10.1098/rsif.2021.0049   [Google Scholar] PMid:34034529 PMCid:PMC8150030
  13. Fried LP, Bentley ME, Buekens P, Burke DS, Frenk JJ, Klag MJ, and Spencer HC (2010). Global health is public health. The Lancet, 375(9714): 535-537. https://doi.org/10.1016/S0140-6736(10)60203-6   [Google Scholar] PMid:20159277
  14. Gubler DJ (2006). Dengue/dengue haemorrhagic fever: History and current status. In: Bock G and Goode J (Eds.), New treatment strategies for dengue and other flaviviral diseases: Novartis foundation symposium: 3-22. Volume 277, John Wiley and Sons, Ltd., Chichester, UK. https://doi.org/10.1002/0470058005.ch2   [Google Scholar] PMid:17319151
  15. Hamdan NI and Kilicman A (2021). The development of a deterministic dengue epidemic model with the influence of temperature: A case study in Malaysia. Applied Mathematical Modelling, 90: 547-567. https://doi.org/10.1016/j.apm.2020.08.069   [Google Scholar]
  16. Hamid SI, Ofosu-Hene ED, and Ponnusamy RR (2019). A new approach to forecast Malaysian mortality rates. International Journal of Advanced and Applied Sciences, 6(10): 53-61. https://doi.org/10.21833/ijaas.2019.10.010   [Google Scholar]
  17. Htun TP, Xiong Z, and Pang J (2021). Clinical signs and symptoms associated with WHO severe dengue classification: A systematic review and meta-analysis. Emerging Microbes and Infections, 10(1): 1116-1128. https://doi.org/10.1080/22221751.2021.1935327   [Google Scholar] PMid:34036893 PMCid:PMC8205005
  18. Hyndman RJ and Athanasopoulos G (2021). Forecasting: Principles and practice. 3rd Edition, OTexts, Melbourne, Australia.   [Google Scholar]
  19. Jabeen D, Rahim I, Iftikhar R, Rafiullah M, and Ansari M (2022). Regression modeling and correlation analysis spread of COVID-19 data for Pakistan. International Journal of Advanced and Applied Sciences, 9(3): 71-81. https://doi.org/10.21833/ijaas.2022.03.009   [Google Scholar]
  20. Johari NA, Voon K, Toh SY, Sulaiman LH, Yap IKS, and Lim PKC (2019). Sylvatic dengue virus type 4 in Aedes aegypti and Aedes albopictus mosquitoes in an urban setting in Peninsular Malaysia. PLOS Neglected Tropical Diseases, 13(11): e0007889. https://doi.org/10.1371/journal.pntd.0007889   [Google Scholar] PMid:31730672 PMCid:PMC6881067
  21. Juraphanthong W and Kesorn K (2021). Time series data enrichment using semantic information for dengue incidence forecasting. Science, Engineering and Health Studies, 15: 21050013.   [Google Scholar]
  22. Kamaruddin NIK, Said SM, Shahar HK, and Lim PY (2021). Socio-ecological determinants of dengue prevention practices: A cross-sectional study among wet market traders in a selected district in Perak, Malaysia. Asian Pacific Journal of Tropical Medicine, 14(12): 555-563. https://doi.org/10.4103/1995-7645.332810   [Google Scholar]
  23. Kaur S and Sharma S (2023). Comparative analysis of machine learning classifiers on forecasting dengue fever infection. In: Murthy KVSR, Kumar S, and Singh MK (Eds.), Recent developments in electronics and communication systems: 492–4979. IOS Press, Amsterdam, Netherlands. https://doi.org/10.3233/ATDE221302   [Google Scholar]
  24. Keshavamurthy R, Dixon S, Pazdernik KT, and Charles LE (2022). Predicting infectious disease for biopreparedness and response: A systematic review of machine learning and deep learning approaches. One Health, 15: 100439. https://doi.org/10.1016/j.onehlt.2022.100439   [Google Scholar] PMid:36277100 PMCid:PMC9582566
  25. Khashei M and Bijari M (2011). A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Applied Soft Computing, 11(2): 2664-2675. https://doi.org/10.1016/j.asoc.2010.10.015   [Google Scholar]
  26. Lazim MA (2011). Introductory business forecasting: A practical approach. 3rd Edition, UiTM Press, Shah Alam, Malaysia.   [Google Scholar]
  27. Mekparyup J and Saithanu K (2016). A new approach to detect epidemic of DHF by combining ARIMA model and adjusted Tukey’s control chart with interpretation rules. Interventional Medicine and Applied Science, 8(3): 118-120. https://doi.org/10.1556/1646.8.2016.3.6   [Google Scholar] PMid:28203393 PMCid:PMC5283758
  28. Messina JP, Brady OJ, Scott TW, Zou C, Pigott DM, Duda KA, and Hay SI (2014). Global spread of dengue virus types: Mapping the 70 year history. Trends in Microbiology, 22(3): 138-146. https://doi.org/10.1016/j.tim.2013.12.011   [Google Scholar] PMid:24468533 PMCid:PMC3946041
  29. Moffat IU and Akpan EA (2017). Time series modeling of the interaction between deterministic and stochastic trends. International Journal of Advanced and Applied Sciences, 4(9): 96-100. https://doi.org/10.21833/ijaas.2017.09.012   [Google Scholar]
  30. Naumova EN, Jagai JS, Matyas B, DeMaria A, MacNeill IB, and Griffiths JK (2007). Seasonality in six enterically transmitted diseases and ambient temperature. Epidemiology and Infection, 135(2): 281-292. https://doi.org/10.1017/S0950268806006698   [Google Scholar] PMid:17291363 PMCid:PMC2870561
  31. Nayak MSDP and Narayan KA (2019). Forecasting dengue fever incidence using ARIMA analysis. International Journal of Collaborative Research on Internal Medicine and Public Health, 11(3): 924-932.   [Google Scholar]
  32. Nazni WA, Hoffmann AA, NoorAfizah A, Cheong YL, Mancini MV, Golding N, and Sinkins SP (2019). Establishment of Wolbachia strain wAlbB in Malaysian populations of Aedes aegypti for dengue control. Current Biology, 29(24): 4241-4248. https://doi.org/10.1016/j.cub.2019.11.007   [Google Scholar] PMid:31761702 PMCid:PMC6926472
  33. Othman M, Indawati R, Suleiman AA, Qomaruddin MB, and Sokkalingam R (2022). Model forecasting development for dengue fever incidence in Surabaya City using time series analysis. Processes, 10(11): 2454. https://doi.org/10.3390/pr10112454   [Google Scholar]
  34. Patil S and Pandya S (2021). Forecasting dengue hotspots associated with variation in meteorological parameters using regression and time series models. Frontiers in Public Health, 9: 798034. https://doi.org/10.3389/fpubh.2021.798034   [Google Scholar] PMid:34900929 PMCid:PMC8661059
  35. Ramanathan K, Thenmozhi M, George S, Anandan S, Veeraraghavan B, Naumova EN, and Jeyaseelan L (2020). Assessing seasonality variation with harmonic regression: Accommodations for sharp peaks. International Journal of Environmental Research and Public Health, 17(4): 1318. https://doi.org/10.3390/ijerph17041318   [Google Scholar] PMid:32085630 PMCid:PMC7068504
  36. Roster K, Connaughton C, and Rodrigues FA (2022). Machine-learning–based forecasting of dengue fever in Brazilian cities using epidemiologic and meteorological variables. American Journal of Epidemiology, 191(10): 1803-1812. https://doi.org/10.1093/aje/kwac090   [Google Scholar] PMid:35584963
  37. Tantawichien T (2012). Dengue fever and dengue haemorrhagic fever in adolescents and adults. Paediatrics and International Child Health, 32(Sup1): 22-27. https://doi.org/10.1179/2046904712Z.00000000049   [Google Scholar] PMid:22668446 PMCid:PMC3381442
  38. Vásquez P, Sanchez F, Barboza LA, García YE, Calvo JG, Chou-Chen SW, and Mery G (2022). Mathematical and statistical models for the control of mosquito-borne diseases: The experience of Costa Rica. Revista Panamericana de Salud Pública, 46: e113. https://doi.org/10.26633/RPSP.2022.113   [Google Scholar] PMid:36060201 PMCid:PMC9426954
  39. Vaughn DW (2000). Invited commentary: Dengue lessons from Cuba. American Journal of Epidemiology, 152(9): 800-803. https://doi.org/10.1093/aje/152.9.800   [Google Scholar] PMid:11085390
  40. Wang WH, Urbina AN, Chang MR, Assavalapsakul W, Lu PL, Chen YH, and Wang SF (2020). Dengue hemorrhagic fever–A systemic literature review of current perspectives on pathogenesis, prevention and control. Journal of Microbiology, Immunology and Infection, 53(6): 963-978. https://doi.org/10.1016/j.jmii.2020.03.007   [Google Scholar] PMid:32265181
  41. Wang Y, Li Y, Ren X, and Liu X (2022). A periodic dengue model with diapause effect and control measures. Applied Mathematical Modelling, 108: 469-488. https://doi.org/10.1016/j.apm.2022.03.043   [Google Scholar]
  42. Waseem MD, Nawaz A, Rasheed U, Raza A, and Albarka MO (2023). A time series regression-based model for predicting the spread of dengue disease. In the International Conference on Robotics and Automation in Industry, IEEE, Peshawar, Pakistan: 1-6. https://doi.org/10.1109/ICRAI57502.2023.10089545   [Google Scholar] PMCid:PMC9936943
  43. Wenger JB and Naumova EN (2010). Seasonal synchronization of influenza in the United States older adult population. PLOS ONE, 5(4): e10187. https://doi.org/10.1371/journal.pone.0010187   [Google Scholar] PMid:20419169 PMCid:PMC2855366
  44. Whitehorn J and Farrar J (2011). Dengue. Clinical Medicine, 11(5): 483-487. https://doi.org/10.7861/clinmedicine.11-5-483   [Google Scholar] PMid:22034713 PMCid:PMC4954247
  45. Young PC, Pedregal DJ, and Tych W (1999). Dynamic harmonic regression. Journal of Forecasting, 18(6): 369-394. https://doi.org/10.1002/(SICI)1099-131X(199911)18:6<369::AID-FOR748>3.0.CO;2-K   [Google Scholar]