APPLICATION OF HIDDEN MARKOV MODEL (HMM) FOR THE PREDICTION OF DENGUE FEVER OUTBREAK IN NIGERIA
DOI:
https://doi.org/10.60787/jnamp.vol71no.611Keywords:
Dengue fever, Hidden Markov Model, Outbreak prediction, Vector-borne diseases, NigeriaAbstract
Dengue fever remains a pressing public health concern in Nigeria, marked by recurrent outbreaks and complex transmission patterns. This study employs a Hidden Markov Model (HMM) to predict dengue fever outbreak trends by modeling the latent outbreak risk levels based on reported case data from 2014 to 2023. The model leverages the Baum-Welch algorithm for parameter estimation, while the Viterbi and Forward algorithms are used for state sequence inference and sequence probability computation, respectively. By integrating discrete observed data with probabilistic state transitions, the HMM captures the underlying dynamics of disease progression. The model's performance was evaluated using statistical measures such as precision, recall, F1-score, and accuracy, revealing its effectiveness in learning outbreak patterns and identifying potential epidemic phases. A ten-year forecast (2024–2033) was also produced, offering valuable insights for early warning systems and strategic health planning. This research highlights the utility of HMM in epidemiological modeling and reinforces its potential for guiding data-driven decision-making in infectious disease control.
Downloads
References
Adesina, A. O., Okeke, C. N., & Mohammed, Y. T. (2019). Rising prevalence of dengue in Nigeria: A wake-up call. African Journal of Health Sciences, 33(2), 134–142.
Adesola, O., Bello, K. J., & Aluko, M. O. (2024). Urbanization and dengue transmission in Nigeria: A spatial analysis. Journal of Urban Health and Epidemiology, 12(1), 44–57.
Eddy, S. R. (1996). Hidden Markov models. Current Opinion in Structural Biology, 6(3), 361–365. https://doi.org/10.1016/S0959-440X(96)80056-X
Farrington, C. P., Whitaker, H. J., & Hocine, M. N. (2013). Early detection of infectious disease outbreaks: Modelling outbreaks with hidden Markov models. Statistics in Medicine, 32(28), 5006–5021. https://doi.org/10.1002/sim.5902
George, J., & Thomas, S. (2018). Modeling of dengue fever death counts using hidden Markov models. Journal of Environmental Statistics, 8(9), 1–11.
Graves, P. N., Xu, B., & Lee, H. C. (2016). A hierarchical hidden Markov model for multi-strain infectious disease dynamics: Application to dengue fever. PLOS Computational Biology, 12(8), e1005079. https://doi.org/10.1371/journal.pcbi.1005079
Guzman, M. G., Halstead, S. B., Artsob, H., Buchy, P., Farrar, J., Gubler, D. J., & Peeling, R. W. (2016). Dengue: A continuing global threat. Nature Reviews Microbiology, 14(2), 123–131.
Hii, Y. L., Rocklöv, J., Ng, N., Tang, C. S., Pang, F. Y., & Sauerborn, R. (2012). Climate variability and increase in intensity and magnitude of dengue incidence in Singapore. Global Health Action, 5(1), 147–152. https://doi.org/10.3402/gha.v5i0.147
Koller, D., & Friedman, N. (2009). Probabilistic graphical models: Principles and techniques. MIT Press.
Nigeria Centre for Disease Control. (2023). Public health advisory on dengue fever outbreak in Sokoto State. https://ncdc.gov.ng
Okeke, I. N., & Abubakar, M. (2021). Dengue fever in Nigeria: Epidemiology, burden and future directions. Tropical Medicine & International Health, 26(5), 555–562. https://doi.org/10.1111/tmi.13561
Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257–286. https://doi.org/10.1109/5.18626
Ridwan, O. A., Favour, A. A., Ibrahim, I., Godfred, Y. S., & Mahmud, I. A. (2024). Addressing the dengue fever challenges in Nigeria: A narrative review and recommendations for control. https://doi.org/10.53854
World Health Organization. (2020). Dengue and severe dengue: Factsheet. https://www.who.int/news-room/fact-sheets/detail/dengue-and-severe-dengue
Downloads
Published
Issue
Section
License
Copyright (c) 2025 The Journals of the Nigerian Association of Mathematical Physics
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
