Forecasting Weekly Influenza Detections in South Africa Using SARIMA and LSTM Models
DOI:
https://doi.org/10.63158/journalisi.v8i5.1860Keywords:
Influenza surveillance, laboratory detections, FluNet, time-series forecasting, SARIMA, LSTM, public health surveillance, South AfricaAbstract
This study compares Seasonal Autoregressive Integrated Moving Average (SARIMA) and Long Short-Term Memory (LSTM) models for forecasting weekly laboratory influenza detections in South Africa using World Health Organization (WHO) FluNet surveillance data. Weekly laboratory detection counts from January 1997 to March 2026 were preprocessed, regularized, and treated for missing values, yielding 1,522 weekly observations. Data were divided chronologically into training (20 January 1997–11 May 2020; 1,217 weeks) and a fixed-holdout test period (18 May 2020–16 March 2026; 305 weeks). SARIMA incorporated a 52-week seasonal period, while LSTM used a 52-week lookback window with Min–Max scaling fitted exclusively to training data. A Seasonal Naïve model with a 52-week seasonal lag was included as a benchmark. Forecast performance was assessed using RMSE and MAE, while Diebold–Mariano (DM) test assessed differences in forecast accuracy. LSTM achieved the lowest errors, with RMSE of 9.49 and MAE of 6.31, compared with 23.58 and 15.56 for SARIMA and 29.93 and 16.02 for Seasonal Naïve, respectively. Relative to SARIMA, LSTM reduced RMSE and MAE by 59.8% and 59.4%. DM tests indicated significantly lower forecast loss for LSTM than SARIMA using MSE (DM = 6.6661, p < 0.001) and MAE (DM = 9.7569, p < 0.001). The study provides an empirical comparison of statistical and deep-learning approaches using a nearly three-decade WHO FluNet surveillance series. LSTM provided significantly more accurate forecasts than SARIMA under the fixed-holdout design. Future research should examine robustness using rolling-origin validation and multiple forecasting horizons.
Downloads
References
[1] World Health Organization, “Influenza (seasonal),” Feb. 28, 2025. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/influenza-%28seasonal%29.
[2] F. E. L. Guma, “Analysis of influenza-like illness trends in Saudi Arabia: A comparative study of statistical and deep learning techniques,” Osong Public Health Res. Perspect., vol. 16, no. 3, pp. 270–284, 2025, doi: 10.24171/j.phrp.2025.0080.
[3] S. Fiandrino, A. Bizzotto, G. Guzzetta, S. Merler, F. Baldo, E. Valdano, A.M. Urdiales, A. Bella, F. Celino, L. Zino, and A. Rizzo, “Collaborative forecasting of influenza-like illness in Italy: The Influcast experience,” Epidemics, vol. 50, Art. no. 100819, 2025, doi: 10.1016/j.epidem.2025.100819.
[4] E. O. Nsoesie, O. Oladeji, A. S. A. A. Abah, and M. L. Ndeffo-Mbah, “Forecasting influenza-like illness trends in Cameroon using Google Search Data,” Sci. Rep., vol. 11, Art. no. 6713, 2021, doi: 10.1038/s41598-021-85987-9.
[5] National Institute for Communicable Diseases, “Influenza surveillance report 2025,” 2026, [Online]. Available: https://www.nicd.ac.za/influenza-surveillance-report-2025
[6] S. O. Olukanmi, F. V. Nelwamondo, and N. I. Nwulu, “Leveraging Google search data and artificial intelligence methods for provincial-level influenza forecasting: A South African case study,” Int. J. Online Biomed. Eng. 18, no. 11 2022, doi: 10.3991/ijoe.
[7] S. B. Choi and I. Ahn, “Forecasting seasonal influenza-like illness in South Korea after 2 and 30 weeks using Google Trends and influenza data from Argentina,” PLoS ONE, vol. 15, no. 7, Art. no. e0233855, 2020, doi: 10.1371/journal.pone.0233855.
[8] S. Cho, C. H. Sohn, M. W. Jo, S.-Y. Shin, J. H. Lee, S. M. Ryoo, W. Y. Kim, and D.-W. Seo, “Correlation between national influenza surveillance data and Google Trends in South Korea,” PLoS ONE, vol. 8, no. 12, Art. no. e81422, 2013, doi: 10.1371/journal.pone.0081422.
[9] M. Kang, H. Zhong, J. He, S. Rutherford, and F. Yang, “Using Google Trends for influenza surveillance in South China,” PLoS ONE, vol. 8, no. 1, Art. no. e55205, 2013, doi: 10.1371/journal.pone.0055205.
[10] C. W. Chukwu, G. Obaido, I. D. Mienye, K. Aruleba, E. Esenogho, and C. Modisane, “Time series modeling of monkeypox incidence in Central Africa’s endemic regions,” Mach. Learn. Appl., vol. 22, Art. no. 100778, 2025, doi: 10.1016/j.mlwa.2025.100778.
[11] Y. Teng, D. Bi, G. Xie, Y. Jin, Y. Huang, B. Lin, X. An, D. Feng, and Y. Tong, “Dynamic forecasting of Zika epidemics using Google Trends,” PLoS ONE, vol. 12, no. 1, Art. no. e0165085, 2017, doi: 10.1371/journal.pone.0165085.
[12] E. G. Igwe and W. M. Olatokun, “Patterns and conversational structure of knowledge sharing on Ebola virus disease among healthcare practitioners: Observations from a pilot study,” J. Librarianship Inf. Sci., vol. 55, no. 3, pp. 836–847, 2023, doi: 10.1177/09610006221106180.
[13] C. Alicino, N. L. Bragazzi, V. Faccio, D. Amicizia, D. Panatto, R. Gasparini, G. Icardi, and A. Orsi, “Assessing Ebola-related web search behaviour: Insights and implications from an analytical study of Google Trends-based query volumes,” Infect. Dis. Poverty, vol. 4, Art. no. 54, 2015, doi: 10.1186/s40249-015-0090-9
[14] S. A. Ebiaredoh-Mienye, T. G. Swart, E. Esenogho, and I. D. Mienye, “A machine learning method with filter-based feature selection for improved prediction of chronic kidney disease,” 2022, doi: 10.3390/bioengineering9080350.
[15] M. Effenberger, A. Kronbichler, J. I. Shin, G. Mayer, H. Tilg, and P. Perco, “Association of the COVID-19 pandemic with Internet search volumes: A Google Trends analysis,” Int. J. Infect. Dis., vol. 95, pp. 192–197, 2020, doi: 10.1016/j.ijid.2020.04.033.
[16] S. M. Ayyoubzadeh, S. M. Ayyoubzadeh, H. Zahedi, M. Ahmadi, and S. R. Niakan Kalhori, “Predicting COVID-19 incidence through analysis of Google Trends data in Iran: Data mining and deep learning pilot study,” JMIR Public Health Surveill., vol. 6, no. 2, Art. no. e18828, 2020, doi: 10.2196/18828.
[17] C. Li, L. J. Chen, X. Chen, M. Zhang, C. P. Pang, and H. Chen, “Retrospective analysis of the possibility of predicting the COVID-19 outbreak from Internet searches and social media data, China, 2020,” Euro Surveill., vol. 25, no. 10, Art. no. 2000199, 2020, doi: 10.2807/1560-7917.ES.2020.25.10.2000199.
[18] X. Zhou, J. Ye, and Y. Feng, “Tuberculosis surveillance by analyzing Google Trends,” IEEE Trans. Biomed. Eng., vol. 58, no. 8, pp. 2247–2254, 2011, doi: 10.1109/TBME.2011.2132132.
[19] A. Mavragani and G. Ochoa, “Infoveillance of infectious diseases in USA: STDs, tuberculosis, and hepatitis,” J. Big Data, vol. 5, Art. no. 30, 2018, doi: 10.1186/s40537-018-0140-9.
[20] S. Chadsuthi, S. Iamsirithaworn, W. Triampo, and C. Modchang, “Modeling seasonal influenza transmission and its association with climate factors in Thailand using time-series and ARIMAX analyses,” Comput. Math. Methods Med., vol. 2015, Art. no. 436495, 2015, doi: 10.1155/2015/436495.
[21] Q. Mao, K. Zhang, W. Yan, and C. Cheng, “Forecasting the incidence of tuberculosis in China using the seasonal auto-regressive integrated moving average (SARIMA) model,” J. Infect. Public Health, vol. 11, no. 5, pp. 707–712, 2018, doi: 10.1016/j.jiph.2018.04.009.
[22] T. Xiao-Qing, Z. Zhan-Lin, G. Zheng, Y. Mahan, H. Bing-Xue, T. Tian, A. Ainiwaer, C. Zhen, G. Hailili, F. Xu-Cheng, and D. Jiang-Hong, “Forecasting influenza-like illness in Urumqi based on ARIMAX model,” Chin. J. Dis. Control Prev., vol. 22, no. 6, pp. 590–593, 2018, doi: 10.16462/J.CNKI.ZHJBKZ.2018.06.012.
[23] W. Anggraeni and L. Aristiani, “Using Google Trend data in forecasting number of dengue fever cases with ARIMAX method: Case study Surabaya, Indonesia,” in Proc. Int. Conf. Inf. Commun. Technol. Syst. (ICTS), 2016, doi: 10.1109/ICTS.2016.7910283
[24] C. Poirier, A. Lavenu, V. Bertaud, B. Campillo-Gimenez, E. Chazard, M. Cuggia, and G. Bouzillé, “Real time influenza monitoring using hospital big data in combination with machine learning methods: Comparison study,” JMIR Public Health Surveill., vol. 4, no. 4, Art. no. e11361, 2018, doi: 10.2196/11361.
[25] M. Santillana, A. T. Nguyen, M. Dredze, M. J. Paul, E. O. Nsoesie, and J. S. Brownstein, “Combining search, social media, and traditional data sources to improve influenza surveillance,” PLoS Comput. Biol., vol. 11, no. 10, Art. no. e1004513, 2015, doi: 10.1371/journal.pcbi.1004513.
[26] S. Prasanth, U. Singh, A. Kumar, V. A. Tikkiwal, and P. H. J. Chong, “Forecasting spread of COVID-19 using Google Trends: A hybrid GWO-deep learning approach,” Chaos Solitons Fractals, vol. 142, Art. no. 110336, 2021, doi: 10.1016/j.chaos.2020.110336.
[27] S. Volkova, E. Ayton, K. Porterfield, and C. D. Corley, “Forecasting influenza-like illness dynamics for military populations using neural networks and social media,” PLoS ONE, vol. 12, no. 12, Art. no. e0188941, 2017, doi: 10.1371/journal.pone.0188941.
[28] C. T. Yang Y.-A. Chen, Y.-W. Chan, C.-L. Lee, Y.-T. Tsan, W.-C. Chan, and P.-Y. Liu, “Influenza-like illness prediction using a long short-term memory deep learning model with multiple open data sources,” J. Supercomput., vol. 76, pp. 9303–9329, 2020, doi: 10.1007/s11227-020-03182-5.
[29] S. Chae, S. Kwon, and D. Lee, “Predicting infectious disease using deep learning and big data,” Int. J. Environ. Res. Public Health, vol. 15, no. 8, Art. no. 1596, 2018, doi: 10.3390/ijerph15081596.
[30] Y. T. Tsan, D. Y. Chen, P. Y. Liu, E. Kristiani, K. L. P. Nguyen, and C. T. Yang, “The prediction of influenza-like illness and respiratory disease using LSTM and ARIMA,” 2022, doi: 10.3390/ijerph19031858.
[31] D. Zhao, H. Zhang, Q. Cao, Z. Wang, S. He, M. Zhou, and R. Zhang, “The research of ARIMA, GM(1,1), and LSTM models for prediction of TB cases in China,” PLoS ONE, vol. 17, no. 2, Art. no. e0262734, 2022, doi: 10.1371/journal.pone.0262734.
[32] J. Shaman and A. Karspeck, “Forecasting seasonal outbreaks of influenza,” Proc. Natl. Acad. Sci. U.S.A., vol. 109, no. 50, pp. 20425–20430, 2012, doi: 10.1073/pnas.1208772109.
[33] M. Riaz, M. H. Sial, S. Sharif, and Q. Mehmood, “Epidemiological forecasting models using ARIMA, SARIMA, and Holt–Winter multiplicative approach for Pakistan,” Comput. Math. Methods Med., vol. 2023, Art. no. 8907610, 2023, doi: 10.1155/2023/8907610.
[34] A. Watad, S. Watad, N. Mahroum, K. Sharif, H. Amital, N.L. Bragazzi, and M. Adawi, “Forecasting the West Nile Virus in the United States: An extensive novel data streams–based time series analysis and structural equation modeling of related digital searching behavior,” JMIR Public Health Surveill., 2019, doi: 10.2196/publichealth.
[35] V. K. R. Chimmula and L. Zhang, “Time series forecasting of COVID-19 transmission in Canada using LSTM networks,” Chaos Solitons Fractals, vol. 135, Art. no. 109864, 2020, doi: 10.1016/j.chaos.2020.109864.
[36] F. E. L. Guma, “Comparative analysis of time series prediction models for visceral leishmaniasis: Based on SARIMA and LSTM,” Appl. Math. Inf. Sci., vol. 18, no. 1, pp. 125–132, 2024, doi: 10.18576/amis/180113.
[37] E. Budgell, A. L. Cohen, J. M. McAnerney, S. Walaza, S. A. Madhi, L. H. Blumberg, H. Dawood, K. Kahn, S. Tempia, and M. Venter, “Evaluation of two influenza surveillance systems in South Africa,” PLoS ONE, 2015.
[38] S. O. Olukanmi, F. V. Nelwamondo, and N. I. Nwulu, “Utilizing Google Search Data with deep learning, machine learning and time series modeling to forecast influenza-like illnesses in South Africa,” IEEE Access, vol. 9, pp. 126822–126836, 2021, doi: 10.1109/ACCESS.2021.3110972.
[39] S. O. O. and F. V. Nelwamondo, “Digital influenza surveillance: The prospects of Google Trends data for South Africa,” 2020, doi: 10.1109/icABCD49160.
[40] World Health Organization, “Global Influenza Surveillance and Response System (GISRS),” 2026. [Online]. Available: https://www.who.int/initiatives/global-influenza-surveillance-and-response-system.
[41] World Health Organization, “FluNet,” 2026. [Online]. Available: https://www.who.int/tools/flunet
[42] A. B. Suthar, J. Wang, V. Seffren, R. E. Wiegand, S. Griffing, and E. Zell, “Public health impact of COVID-19 vaccines in the US: Observational study,” BMJ, vol. 377, Art. no. e069317, 2022, doi: 10.1136/bmj-2021-069317.
[43] A. K. Dubey, A. Kumar, V. García-Díaz, A. K. Sharma, and K. Kanhaiya, “Study and analysis of SARIMA and LSTM in forecasting time series data,” Sustain. Energy Technol. Assess., vol. 47, Art. no. 101474, 2021, doi: 10.1016/j.seta.2021.101474.
[44] S. Aryal, D. Nadarajah, P. L. Rupasinghe, C. Jayawardena, and D. Kasthurirathna, “Comparative analysis of deep learning models for multi-step prediction of financial time series,” J. Comput. Sci., vol. 16, no. 10, pp. 1401–1416, 2020, doi: 10.3844/jcssp.2020.1401.1416.
[45] Z. Zhao, M. Zhai, G. Li, X. Gao, W. Song, X. Wang, H. Ren, Y. Cui, Y. Qiao, J. Ren, L. Chen, and L. Qiu, “Study on the prediction effect of a combined model of SARIMA and LSTM based on SSA for influenza in Shanxi Province, China,” BMC Infect. Dis., vol. 23, Art. no. 71, 2023, doi: 10.1186/s12879-023-08025-1.
[46] J. S. Adeyeye, and E. B. Nkemnole, "Predicting malaria incident using hybrid sarima-lstm model", International Journal of Mathematical Sciences and Optimization: Theory and Applications, 9(1), pp.59-80, 2023
[47] P. Aghelpour, B. Mohammadi, and S. M. Biazar, “Long-term monthly average temperature forecasting in some climate types of Iran, using the models SARIMA, SVR, and SVR-FA,” 2019: P. Aghelpour et al. Theoretical and applied climatology, 138(3), pp.1471-1480.
[48] R. Zhao, J. Liu, Z. Zhao, M. Zhai, H. Ren, X. Wang, Y. Li, Y. Cui, Y. Qiao, J. Ren, L. Chen, and L. Qiu, “A hybrid model for tuberculosis forecasting based on empirical mode decomposition in China,” BMC Infect. Dis., vol. 23, Art. no. 665, 2023, doi: 10.1186/s12879-023-08609-x.
[49] T. C. Mills, A Very British Affair: Six Britons and the Development of Time Series Analysis During the 20th Century. London, U.K.: Palgrave Macmillan, 2012.
[50] K. E. ArunKumar, D. V. Kalaga, C. Mohan Sai Kumar, M. Kawaji, and T. M. Brenza, “Comparative analysis of Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM) cells, autoregressive integrated moving average (ARIMA), seasonal autoregressive integrated moving average (SARIMA) for forecasting COVID-19 trends,” Alexandria Eng. J., vol. 61, no. 10, pp. 7585–7603, 2022, doi: 10.1016/j.aej.2022.01.011.
[51] J. Yang, L. Yang, G. Li, J. Du, L. Ma, T. Zhang, X. Zhang, J. Yang, L. Feng, W. Yang, and C. Wang, “Comparative study on influenza time series prediction models in a megacity from 2010 to 2019 based on SARIMA and deep learning hybrid prediction model,” 2022, doi: 10.21203/rs.
[52] A. K. L. Bezerra, and É.M.C. Santos, “Prediction of daily confirmed COVID-19 cases in Sudan with ARIMA and Holt-Winters exponential smoothing,” Int. J. Dev. Res., vol. 10, no. 8, pp. 39408–39413, 2020, doi: 10.37118/ijdr.19811.08.2020.
[53] L. Mamudu, A. Yahaya, and S. Dan’azumi, “Application of seasonal autoregressive integrated moving average (SARIMA) for flows of River Kaduna,” Nigerian J. Eng., vol. 28, no. 2, pp. 84–90, 2021.
[54] M. Othman, R. Indawati, A. A. Suleiman, M. B. Qomaruddin, and R. Sokkalingam, “Model forecasting development for dengue fever incidence in Surabaya City using time series analysis,” Processes, vol. 10, no. 11, Art. no. 2454, 2022, doi: 10.3390/pr10112454.
[55] A. H. Amshi, R. Prasad, and B. K. Sharma, “Forecasting cholera disease using SARIMA and LSTM models with discrete wavelet transform as feature selection,” J. Intell. Fuzzy Syst., vol. 45, no. 3, 2023, doi: 10.3233/JIFS-223901.
[56] A. H. Amshi and R. Prasad, “Time series analysis and forecasting of cholera disease using discrete wavelet transform and seasonal autoregressive integrated moving average model,” Sci. Afr., vol. 20, Art. no. e01652, 2023, doi: 10.1016/j.sciaf. 2023.e01652.
[57] H. Liu, C. Li, Y. Shao, X. Zhang, Z. Zhai, X. Wang, X. Qi, J. Wang, Y. Hao, Q. Wu, and M. Jiao, “Forecast of the trend in incidence of acute hemorrhagic conjunctivitis in China from 2011–2019 using the Seasonal Autoregressive Integrated Moving Average (SARIMA) and Exponential Smoothing (ETS) models,” J. Infect. Public Health, vol. 13, no. 2, pp. 287–294, 2020, doi: 10.1016/j.jiph.2019.12.008.
[58] World Health Organization, “Influenza update No. 401,” 2026, [Online]. Available: https://www.who.int/publications/m/item/influenza-update-n-401
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Author's Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
