Prescriptive temporal modeling approach using climate variables to forecast dengue incidence in Córdoba, Colombia

Ever Medina; Myladis R Cogollo; Gilberto González-Parra; Ever Medina; Myladis R Cogollo; Gilberto González-Parra

doi:10.3934/mbe.2024341

Mathematical Biosciences and Engineering

2024, Volume 21, Issue 12: 7760-7782. doi: 10.3934/mbe.2024341

Previous Article Next Article

Research article

Prescriptive temporal modeling approach using climate variables to forecast dengue incidence in Córdoba, Colombia

1.
Departamento de Matematicas y Estadistica, Universidad de Cordoba, Monteria 230002, Colombia
2.
Department of Mathematics, New Mexico Tech, New Mexico 87801, USA

Received: 27 August 2024 Revised: 16 November 2024 Accepted: 22 November 2024 Published: 06 December 2024

We present a modeling strategy to forecast the incidence rate of dengue in the department of Córdoba, Colombia, thereby considering the effect of climate variables. A Seasonal Autoregressive Integrated Moving Average model with exogenous variables (SARIMAX) model is fitted under a cross-validation approach, and we examine the effect of the exogenous variables on the performance of the model. This study uses data of dengue cases, precipitation, and relative humidity reported from years 2007 to 2021. We consider three configurations of sizes training set-test set: 182-13,189-6, and 192-3. The results support the theory of the relationship between precipitation, relative humidity, and dengue incidence rate. We find that the performance of the models improves when the time series models are previously adjusted for each of the exogenous variables, and their forecasts are used to determine the future values of the dengue incidence rate. Additionally, we find that the configurations 189-6 and 192-3 present the most consistent results with regard to the model's performance in the training and test data sets.
- Dengue,
- climate variables,
- time series,
- incidence rate,
- SARIMAX,
- exogenous variables
Citation: Ever Medina, Myladis R Cogollo, Gilberto González-Parra. Prescriptive temporal modeling approach using climate variables to forecast dengue incidence in Córdoba, Colombia[J]. Mathematical Biosciences and Engineering, 2024, 21(12): 7760-7782. doi: 10.3934/mbe.2024341

Related Papers:

Abstract

We present a modeling strategy to forecast the incidence rate of dengue in the department of Córdoba, Colombia, thereby considering the effect of climate variables. A Seasonal Autoregressive Integrated Moving Average model with exogenous variables (SARIMAX) model is fitted under a cross-validation approach, and we examine the effect of the exogenous variables on the performance of the model. This study uses data of dengue cases, precipitation, and relative humidity reported from years 2007 to 2021. We consider three configurations of sizes training set-test set: 182-13,189-6, and 192-3. The results support the theory of the relationship between precipitation, relative humidity, and dengue incidence rate. We find that the performance of the models improves when the time series models are previously adjusted for each of the exogenous variables, and their forecasts are used to determine the future values of the dengue incidence rate. Additionally, we find that the configurations 189-6 and 192-3 present the most consistent results with regard to the model's performance in the training and test data sets.

References

[1]	World Health Organization, Dengue guias para el diagnóstico, tratamiento, prevención y control: nueva edición, 2009. https://apps.who.int/iris/handle/10665/44504
[2]	Pan American Health Organization, Dengue, 2022. https://www.paho.org/en/topics/dengue
[3]	K. Fatima, N. I. Syed, Dengvaxia controversy: impact on vaccine hesitancy, J. Glob. Health, 8 (2018). https://doi.org/10.7189/jogh.08-020312 doi: 10.7189/jogh.08-020312
[4]	A. C. Jaramillo, Infecciones por arbovirus, Rev. MVZ Córdoba, 5 (2000), 51–56.
[5]	M. F. Suárez, M. J. Nelson, Registro de altitud del aedes aegypti en Colombia, Biomédica, 1 (1981), 1–225.
[6]	J. C. Castrillón, J. C. Castaño, S. Urcuqui, Dengue en Colombia: diez años de evolución, Rev. chilena de infectología, 32 (2015), 142–149.
[7]	B. Castillo, J. Castillo, M. Salas, El dengue y su incidencia en la salud de niños y adolescentes frente a la economía colombiana, Rev. Med. - Facultad de Ciencias de la Salud - Programa de Medicina, 14 (2015), 38–44.
[8]	A. M. Sánchez, Análisis de la respuesta del estado colombiano frente al fenómeno de la niña 2010–2011 : el caso de Santa Lucía, Technical report, 2014.
[9]	V. N. Valencia, Y. Díaz, J. M. Pascale, M. F. Boni, J. E. Sanchez-Galan, Assessing the effect of climate variables on the incidence of dengue cases in the metropolitan region of panama city, Int. J. Environ. Res. Public Health, 18 (2021), 12108. https://doi.org/10.3390/ijerph182212108 doi: 10.3390/ijerph182212108
[10]	G. Box, G. Jenkins, G, Reinsel, G. Ljung, Time Series Analysis Forecasting and Control, John Wiley & Sons, Inc, 5th edition, 2016.
[11]	Z. Li, H. Gurgel, L. Xu, L. Yang, J. Dong, Improving dengue forecasts by using geospatial big data analysis in google earth engine and the historical dengue information-aided long short term memory modeling, Biology, 11 (2022), 169. https://doi.org/10.3390/biology11020169 doi: 10.3390/biology11020169
[12]	C. M. Benedum, K. M. Shea, H. E. Jenkins, L. Y. Kim, N. Markuzon, Weekly dengue forecasts in Iquitos, Peru; San Juan, Puerto Rico; and Singapore, PLOS Neglect. Trop. D., 14 (2020), e0008710. https://doi.org/10.1371/journal.pntd.0008710 doi: 10.1371/journal.pntd.0008710
[13]	R. Bomfim, S. Pei, J. Shaman, T. Yamana, H. A. Makse, J. S. Andrade, et al., Predicting dengue outbreaks at neighbourhood level using human mobility in urban areas, J.Roy. Soc. I., 17 (2020), 20200691. https://doi.org/10.1371/journal.pntd.0008710 doi: 10.1371/journal.pntd.0008710
[14]	S. Polwiang, The time series seasonal patterns of dengue fever and associated weather variables in Bangkok (2003-2017), BMC Infect. Dis., 20 (2020), 208. https://doi.org/10.1186/s12879-020-4902-6 doi: 10.1186/s12879-020-4902-6
[15]	L. Thiruchelvam, S. C. Dass, V. S. Asirvadam, H. Daud, B. S. Gill, Determine neighboring region spatial effect on dengue cases using ensemble Arima models, Sci. Rep., 11 (2021), 5873. https://doi.org/10.1038/s41598-021-84176-y doi: 10.1038/s41598-021-84176-y
[16]	F. Cortes, C. M. T. Martelli, R. X. Arraes de Alencar, U. Ramos, J. Bosco, O. Gongalves, et al., Time series analysis of dengue surveillance data in two brazilian cities, Acta Trop., 182 (2018), 190–197. https://doi.org/10.1016/j.actatropica.2018.03.006 doi: 10.1016/j.actatropica.2018.03.006
[17]	T. Chakraborty, S. Chattopadhyay, I. Ghosh, Forecasting dengue epidemics using a hybrid methodology, Phys. A, 527 (2019), 121266. https://doi.org/10.1016/j.physa.2019.121266 doi: 10.1016/j.physa.2019.121266
[18]	N. Zhao, K. Charland, M. Carabali, E. O. Nsoesie, M. Maheu-Giroux, E. Rees, et al., Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia, PLOS Neglect. Trop. D., 14 (2020), e0008056. https://doi.org/10.1371/journal.pntd.0008056 doi: 10.1371/journal.pntd.0008056
[19]	L. López, A. Pulecio, G. Marcillo, Dengue cases in Colombia: Mathematical forecasts for 2018–2022, MEDICC Rev., 21 (2019), 38–45.
[20]	A. L. Buczak, B. Baugher, L. J. Moniz, T. Bagley, S. M. Babin, E. Guven, Ensemble method for dengue prediction, PLOS ONE, 13 (2018), e0189988. https://doi.org/10.1371/journal.pone.0189988 doi: 10.1371/journal.pone.0189988
[21]	A. F. B. Gabriel, A. P. Alencar, S. G. E. K. Miraglia, Dengue outbreaks: unpredictable incidence time series, Epidemiol. Infect., 147 (2019), e116. https://doi.org/10.1017/S0950268819000311 doi: 10.1017/S0950268819000311
[22]	V. J. Jayaraj, R. Avoi, N. Gopalakrishnan, D. B. Raja, Y. Umasa, Developing a dengue prediction model based on climate in Tawau, Malaysia, Acta Trop., 197 (2019), 105055. https://doi.org/10.1016/j.actatropica.2019.105055 doi: 10.1016/j.actatropica.2019.105055
[23]	W. Liang, A. Hu, P. Hu, J. Zhu, Y. Wang, Estimating the tuberculosis incidence using a SARIMAX-NNARX hybrid model by integrating meteorological factors in Qinghai Province, China, Int. J. Biometeorol., 67 (2023), 55–65. https://doi.org/10.1007/s00484-022-02385-0 doi: 10.1007/s00484-022-02385-0
[24]	P. Manigandan, M. D. S. Alam, M. Alharthi, U. Khan, K. Alagirisamy, D. Pachiyappan, et al., Forecasting natural gas production and consumption in United States-Evidence from SARIMA and SARIMAX models, Energies, 14 (2021), 6021. https://doi.org/10.3390/en14196021 doi: 10.3390/en14196021
[25]	M. J. Llop, A. Gómez, P. Llop, M. S. López, G. V. Müller, Prediction of leptospirosis outbreaks by hydroclimatic covariates: a comparative study of statistical models, Int. J. Biometeorol., 66 (2022), 2529–2540. https://doi.org/10.1007/s00484-022-02378-z doi: 10.1007/s00484-022-02378-z
[26]	M. R. Cogollo, G. González-Parra, A. J. Arenas, Modeling and forecasting cases of RSV using artificial neural networks, Mathematics, 9 (2021), 2958. https://doi.org/10.3390/math9222958 doi: 10.3390/math9222958
[27]	G. González-Parra, J. F. Querales, D. Aranda, Predicción de la epidemia del virus sincitial respiratorio en Bogotá, DC, utilizando variables climatológicas, Biomédica, 36 (2016), 378–389. https://doi.org/10.7705/biomedica.v36i3.2763 doi: 10.7705/biomedica.v36i3.2763
[28]	N. B. D. Campos, M. H. F. Morais, A. P. R. Ceolin, M. C. M. Cunha, R. R. Nicolino, O. L.Schultes, et al., Twenty-two years of dengue fever (1996-2017): an epidemiological study in a Brazilian city, Int. J. Env. Health Res., 31 (2021), 315–324. https://doi.org/10.1080/09603123.2019.1656801 doi: 10.1080/09603123.2019.1656801
[29]	R. Chumpu, N. Khamsemanan, C. Nattee, The association between dengue incidences and provincial-level weather variables in Thailand from 2001 to 2014, Plos One, 14 (2019), e0226945. https://doi.org/10.1371/journal.pone.0226945 doi: 10.1371/journal.pone.0226945
[30]	F. J. Colón-González, C. Fezzi, I. R. Lake, P. R. Hunter, The effects of weather and climate change on dengue, PLoS Neglect. Trop. Dis., 7 (2013), e2503. https://doi.org/10.1371/journal.pntd.0002503 doi: 10.1371/journal.pntd.0002503
[31]	Y. L. Hii, H. Zhu, N. Ng, L. C. Ng, J. Rocklöv, Forecast of dengue incidence using temperature and rainfall, PLoS Neglect. Trop. Dis., 6(2012), e1908. https://doi.org/10.1371/journal.pntd.0001908 doi: 10.1371/journal.pntd.0001908
[32]	W. A. Abualamah, N. A. Akbar, H. S. Banni, M. A. Bafail, Forecasting the morbidity and mortality of dengue fever in KSA: A time series analysis (2006–2016), J. Taibah Univ. Med. Sci., 16 (2021), 448–455. https://doi.org/10.1016/j.jtumed.2021.02.007 doi: 10.1016/j.jtumed.2021.02.007
[33]	N. Mohammed, M. Z. Rahman, Forecasting dengue incidence in Bangladesh using seasonal ARIMA model, a time series analysis, in International Conference on Machine Intelligence and Emerging Technologies, (2022), 589–598. https://doi.org/10.1007/978-3-031-34622-4-47
[34]	M. Panja, T. Chakraborty, S. S. Nadim, I. Ghosh, U. Kumar, N. Liu, An ensemble neural network approach to forecast Dengue outbreak based on climatic condition, Chaos, Solitons & Fractals, 167 (2023), 113124. https://doi.org/10.1016/j.chaos.2023.113124 doi: 10.1016/j.chaos.2023.113124
[35]	M. Tejaswi, V. Supritha, S. Thangam, Early prediction of dengue cases using time series model, in 2023 IEEE 8th International Conference for Convergence in Technology (I2CT), (2023), 1–6. https://doi.org/10.1109/I2CT57861.2023.10126405
[36]	L. A. Barboza, S. W. Chou-Chen, P. Vásquez, Y. E. García, J. G. Calvo, H. G. Hidalgo, et al., Assessing dengue fever risk in Costa Rica by using climate variables and machine learning techniques, PLOS Neglect. Trop. Dis., 17 (2023), e0011047. https://doi.org/10.1371/journal.pntd.0011047 doi: 10.1371/journal.pntd.0011047
[37]	E. Dantas, M. Tosin, A. Cunha Jr, Calibration of a SEIR–SEI epidemic model to describe the Zika virus outbreak in Brazil, Appl. Math. Comput., 338 (2018), 249–259. https://doi.org/10.1016/j.amc.2018.06.024 doi: 10.1016/j.amc.2018.06.024
[38]	J. A. Gutierrez, K. Laneri, J. P. Aparicio, G.J. Sibona, Meteorological indicators of dengue epidemics in non-endemic Northwest Argentina, Infect. Dis. Mod., 7 (2022), 823–834. https://doi.org/10.1016/j.idm.2022.10.004 doi: 10.1016/j.idm.2022.10.004
[39]	S. S. Md-Sani, J. Md-Noor, W. H. Han, S. P. Gan, N. S. Rani, H. L. Tan, et al., Prediction of mortality in severe dengue cases, BMC Infect. Dis., 18 (2018), 1–9. https://doi.org/10.1186/s12879-018-3141-6 doi: 10.1186/s12879-018-3141-6
[40]	K. C. Poh, L. F. Chaves, M. Reyna-Nava, C. M. Roberts, C. Fredregill, R. Bueno Jr, et al., The influence of weather and weather variability on mosquito abundance and infection with West Nile virus in Harris County, Texas, USA, Sci. Total Environ., 675 (2019), 260–272. https://doi.org/10.1016/j.scitotenv.2019.04.109 doi: 10.1016/j.scitotenv.2019.04.109
[41]	C. C. D. Silva, C. L. D. Lima, A. C. G. D. Silva, G. Machado Magalhães Moreno, A. Musah, A. Aldosery, et al., Forecasting Dengue, Chikungunya and Zika cases in Recife, Brazil: a spatio-temporal approach based on climate conditions, health notifications and machine learning, Res., Soc. Dev., 10 (2021), e452101220804. https://doi.org/10.33448/rsd-v10i12.20804 doi: 10.33448/rsd-v10i12.20804
[42]	B. V. Vishwas A. Patel, Hands-on Time Series Analysis with Python, Apress, 2020. https://doi.org/10.1007/978-1-4842-5992-4
[43]	K. Taegon, J. Minseok, C. J. Hyun, J. Sung-Kwan, Short-term residential load forecasting using 2-step sarimax, J. Elec. Eng. Tech., 17 (2022), 751–758. https://doi.org/10.1007/s42835-021-00917-z doi: 10.1007/s42835-021-00917-z
[44]	R Core Team, R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing, Vienna, Austria, 2023.
[45]	J. Breitung P. H. Franses, On Phillips–Perron-type tests for seasonal unit roots, Economet. Theor., 14 (1998), 200–221. https://doi.org/10.1017/S0266466698142032 doi: 10.1017/S0266466698142032
[46]	A. Kagalwala, kpsstest: A command that implements the Kwiatkowski, Phillips, Schmidt, and Shin test with sample-specific critical values and reports p-values, Stata J., 22 (2022), 269–292. https://doi.org/10.1177/1536867X221106371 doi: 10.1177/1536867X221106371
[47]	E. Kosicka, E. Kozłowski, D. Mazurkiewicz, The use of stationary tests for analysis of monitored residual processes, Eksploatacja i Niezawodność, 17 (2015), 604–609. http://dx.doi.org/10.17531/ein.2015.4.17 doi: 10.17531/ein.2015.4.17
[48]	S. Panigrahi, R. M. Pattanayak, P. K. Sethy, S. K. Behera, Forecasting of sunspot time series using a hybridization of arima, ets and svm methods, Sol. Phys., 296 (2021), 1–19. https://doi.org/10.1007/s11207-020-01757-2 doi: 10.1007/s11207-020-01757-2
[49]	H. Hewamalage, K. Ackermann, C. Bergmeir, Forecast evaluation for data scientists: common pitfalls and best practices, Data Min. Knowl. Discovery, 37 (2023), 788–832. https://doi.org/10.1007/s10618-022-00894-5 doi: 10.1007/s10618-022-00894-5
[50]	R. Hyndman, G, Athanasopoulos, Forecasting: Principles and Practice, OTexts, 2 edition, 2018.
[51]	K. M. Lem, The STL-ARIMA approach for seasonal time series forecast: a preliminary study, in the 19th IMT-GT International Conference on Mathematics, Statistics and Their Applications (ICMSA 2024), 67 (2024), 01008. https://doi.org/10.1051/itmconf/20246701008
[52]	J. M. González, V. Pakrashi, B. Ghosh, An overview of performance evaluation metrics for short-term statistical wind power forecasting, Renew. Sust. Energ. Rev., 138 (2021), 110515. https://doi.org/10.1016/j.rser.2020.110515 doi: 10.1016/j.rser.2020.110515
[53]	S. Engmann, D. Cousineau, Comparing distributions: the two-sample Anderson-Darling test as an alternative to the Kolmogorov-Smirnoff test, J, Appl. Quant. Methods, 6 (2011), 1–18.
[54]	U. Knief, W. Forstmeier, Violating the normality assumption may be the lesser of two evils, Beh. Res. Meth., 53 (2021), 2576–2590. https://doi.org/10.3758/s13428-021-01587-5 doi: 10.3758/s13428-021-01587-5
[55]	C. L. Lima, A. C. da Silva, G. M. Moreno, C. Cordeiro da Silva, A. Musah, A. Aldosery, et al., Temporal and spatiotemporal arboviruses forecasting by machine learning: A systematic review, Front. Pub. Health, 10 (2022), 900077. https://doi.org/10.3389/fpubh.2022.900077 doi: 10.3389/fpubh.2022.900077
[56]	N. A. M. H. Abdullah, N. C. Dom, S. A. Salleh, H. Salim, N. Precha, The association between dengue case and climate: A systematic review and meta-analysis, One Health, 15 (2022), 100452. https://doi.org/10.1016/j.onehlt.2022.100452 doi: 10.1016/j.onehlt.2022.100452

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)