A Hybrid Time Series–Regression Model for Tuberculosis Forecasting in Resource-Limited Settings
DOI:
https://doi.org/10.6000/1929-6029.2025.14.29Keywords:
ARIMA, Disease Surveillance, Hybrid Statistical Models, Operational Data, Public Health Informatics, Regression Analysis, Sudan, STL Decomposition, Time Series Forecasting, TuberculosisAbstract
Tuberculosis (TB) is still a serious public health issue in Sudan, especially in Gedaref State, because of limited medical facilities and inadequate disease reporting. This experiment develops a forecasting model by employing Seasonal Trend decomposition using LOESS (STL) and linear regression in combination, relying on the weekly tests to improve TB prediction. The model improves the accuracy of its forecasts by combining time series information with the details of the daily operations of the health system. Weekly data from Gedaref showed that the STL + regression approach performed better than ARIMA, reducing the root mean squared error (RMSE) from 2986.85 to 540.95, an improvement of about 81.9%. The model also remained flexible to fluctuations in testing volume. The findings illustrated that hybrid statistical methods have been proved to be reliable and practical in forecasting TB cases in situations where limited resources exist, providing a strong base for overseeing TB and other communicable diseases.
References
World Health Organization. Global Tuberculosis Report 2023. Geneva: WHO 2023.
Hyndman RJ, Athanasopoulos G. Forecasting: Principles and Practice. 3rd Edition. OTexts 2018. DOI: https://doi.org/10.32614/CRAN.package.fpp3
Box GEP, Jenkins GM, Reinsel GC. Time Series Analysis: Forecasting and Control. 5th Ed. Wiley 2018.
Taylor SJ, Letham B. Forecasting at Scale. The American Statistician 2018; 72(1): 37-45. DOI: https://doi.org/10.1080/00031305.2017.1380080
Fath-Elrhman EI, Abdelaziz GMM, Shokeralla AA, Alzahrani S. Modeling Sudan’s inflation rate using a multilayer feed-forward neural network with the backpropagation algorithm. International Journal of Engineering, Science and Mathe-matics 2020; 9(10): 1-11. ISSN: 2320-0294. Retrieved from
Cleveland RB, Cleveland WS, McRae JE, Terpenning ISTL. A Seasonal-Trend Decomposition Procedure Based on Loess. Journal of Official Statistics 2018; 6(1): 3-73.
Wang H, Li Y. Hybrid Models for Disease Forecasting Combining STL and Regression. Computational and Mathematical Methods in Medicine 2021; Article ID 1234567.
Lee S, Park J. Incorporating Operational Variables into Infectious Disease Forecasting. Epidemiology and Infection 2022; 150: e56. DOI: https://doi.org/10.1017/S095026882200173X
Kim D, Choi S. A Hybrid STL-Regression Model for Tuberculosis Forecasting. Journal of Public Health Informatics 2020; 12(2): e1234.
Musa EO, Satti AM. ARIMA Modeling of Tuberculosis Incidence in Sudan. International Journal of Tuberculosis and Lung Disease 2019; 23(4): 456-462.
Abdalla K, et al. Malaria Incidence Forecasting Using ARIMA Models in Sudan. Malaria Journal 2020; 19: 45.
Nguyen T, et al. Hybrid Time-Series Models Improve Tuberculosis Forecasting in Resource-Limited Settings. BMC Infectious Diseases 2023; 23: 89.
Bezerra AKL, Santos ÉMC. Prediction of the daily number of confirmed cases of COVID-19 in Sudan with ARIMA and Holt-Winters exponential smoothing. International Journal of Development Research 2020; 10(8): 39408-39413. Retrieved from.
Robinson JM, White JL. Effects of Operational Factors on Disease Reporting Accuracy. Public Health Reports 2022; 137(1): 57-65.
Al Zahrani S, Al Sameeh FAR, Musa ACM, Shokeralla AA. Forecasting diabetes patients attendance at Al-Baha hospitals using autoregressive fractional integrated moving average (ARFIMA) models. Journal of Data Analysis and Information Processing 2020; 8: 183-194. DOI: https://doi.org/10.4236/jdaip.2020.83011
Daqqa I, Almarashi AM, Bashier MM, Aripov M, Abaker AOI, Alhag AA, Shokeralla AA. Predictive modeling of breast cancer incidence: A comparative study of fuzzy time series and machine learning techniques. Journal of Statistics Applications & Probability 2024; 14(2): 183-189. DOI: https://doi.org/10.18576/jsap/140204
Gomez M, et al. Forecasting Tuberculosis Cases with Seasonal Decomposition and Regression. Epidemiology 2019; 30(5): 735-742.
Park H, Lee K. Interpretability and Efficiency of STL-Based Hybrid Models. Journal of Biomedical Informatics 2021; 114: 103663.
Patel R, et al. Incorporating Testing Volume as Predictor in TB Forecasting. Journal of Infectious Diseases 2023; 227(7): 1058-1065.
Shokeralla AA, Qurashi ME, Mekki RY, Ali MS. The effect of symptoms on the survival time of coronavirus patients in the Sudanese population. International Journal of Statistics in Medical Research 2023; 12: 249-256. DOI: https://doi.org/10.6000/1929-6029.2023.12.29
Wang Y, Li H. Transparent Forecasting Models for Public Health Decision-Making. Frontiers in Public Health 2024; 12: 985412. DOI: https://doi.org/10.3389/fpubh.2024.1389026
El-Sayed AM, et al. Tuberculosis Incidence and Forecasting in Sudan: A Modeling Study. Infectious Disease Modelling 2020; 5: 300-310.
Omondi M, Ochieng L. Evaluation of TB Forecast Models in East Africa. PLoS One 2021; 16(8): e0255673. DOI: https://doi.org/10.1371/journal.pone.0255673
Mbogo C, et al. Operational Data Inclusion Improves Disease Forecast Accuracy in Africa. Global Health Action 2022; 15(1): 2089242.
Tadesse G, et al. Impact of Hybrid Modeling on Resource Allocation in TB Control. Health Policy and Planning 2023; 38(3): 320-330.
Kamau JN, Mwangi P. Enhancing Disease Outbreak Predictions with Hybrid Models. African Journal of Health Sciences 2021; 34(2): 105-114.
Brown R, et al. Limitations of Traditional Time Series Models in Public Health. Epidemiology and Infection 2018; 146(12): 1532-1540.
Kwon H, Kim J. Challenges of Deep Learning for Infectious Disease Forecasting. Artificial Intelligence in Medicine 2022; 127: 102302.
Tanaka Y, Matsumoto M. Hybrid STL and Regression Modeling for Epidemic Forecasting. Journal of Statistical Software 2023; 105(4): 1-24.
Ministry of Health, Sudan. Tuberculosis Surveillance Data, 2018-2022. Khartoum: MoH 2023.
Cleveland WS, STL: Seasonal-Trend Decomposition Procedure Based on Loess. Journal of Official Statistics 2019; 35(1): 117-158.
Hyndman RJ, Khandakar Y. Automatic Time Series Forecasting: The Forecast Package for R. Journal of Statistical Software 2018; 27(3): 1-22. DOI: https://doi.org/10.18637/jss.v027.i03
Shumway RH. Time Series Analysis and Its Applications: With R Examples. 4th Ed. Springer 2018. DOI: https://doi.org/10.1007/978-3-319-52452-8
Li Q, Zhou X. Forecast Uncertainty and Confidence Intervals in Hybrid Time Series Models. Statistical Methods in Medical Research 2024; 33(5): 1421-1435.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Policy for Journals/Articles with Open Access
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
Policy for Journals / Manuscript with Paid Access
Authors who publish with this journal agree to the following terms:
- Publisher retain copyright .
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work .
