Modeling the Novel Coronavirus Disease (COVID-19) as Hidden Markov Chains

Open Access

Year : 2022 | Volume : | Issue : 2 | Page : 27-35
By

1. Udoh N.E.

1. Professor, Department of Statistics, University of Lagos, Lagos, Nigeria
2. Research Scholar, Department of Statistics, University of Lagos, Lagos, Nigeria

Abstract

The Hidden Markov Model has over the years been an appropriate method for modeling diseases such as HIV AIDS, heart failure, and so on. With the ongoing pandemic affecting Nigeria by being responsible for 2,745 death cases out of 207,616 confirmed cases as of October 10, 2021, the need to study an important parameter of COVID-19, the case fatality rate by building a model and estimating the case fatality rate of COVID-19 in Nigeria using Lagos State as case study via hidden Markov approach arose. This study built the transition and emission probabilities of cases of COVID-19 and developed a hidden Markov Model for understanding the trend of the virus. The relevant data were gathered from the website of NCDC (Nigeria Centre for Disease Control). The Forward Algorithm, Baum–Welch, and Viterbi Algorithm were used to implement and proffer answers to the study. The result shows that the estimate case fatality rate of COVID-19 in Lagos State between the periods under study was 4.35%. The likelihood of transitioning from a state of being infected to that of recovery is 25% and the probability of transitioning from a state of being infected to death 50% and the probability of still being infected is 25%. The result of the analysis can be valuable to Governments to design the required interventions in a controlled manner.

Keywords: Markov model, Hidden Markov Model, COVID-19, case fatality rate, HIV, AIDS

How to cite this article: Nkemnole E.B., Udoh N.E. Modeling the Novel Coronavirus Disease (COVID-19) as Hidden Markov Chains rrjs 2022; 11:27-35
How to cite this URL: Nkemnole E.B., Udoh N.E. Modeling the Novel Coronavirus Disease (COVID-19) as Hidden Markov Chains rrjs 2022 {cited 2022 Sep 17};11:27-35. Available from: https://journals.stmjournals.com/rrjs/article=2022/view=92379

References

1. Oshunluyi, Esther. Providing Hypertension Education for African Immigrants at a Southern California Congregation During the COVID-19 Pandemic. (2021).
2. Liu, Yang. Estimating the case fatality rate for COVID-19: a Markov model application. Available at SSRN 3558612 (2020).
3. Zhao, Qianwen, et al. Lymphopenia is associated with severe coronavirus disease 2019 (COVID-19) infections: A systemic review and meta-analysis. International journal of infectious diseases 96 (2020): 131–135.
4. Sarkodie, Samuel Asumadu, and Phebe Asantewaa Owusu. Investigating the cases of novel coronavirus disease (COVID-19) in China using dynamic statistical techniques. Heliyon 6.4 (2020): e03747.
5. Suleiman, Ahmad Abubakar, et al. Estimation of the case fatality rate of COVID-19 epidemiological data in Nigeria using statistical regression analysis. Biosafety and Health 3.1 (2021): 4–7.
6. Kim, Byungwon, et al. Estimation of the case fatality rate based on stratification for the COVID-19 outbreak. PloS ONE 16.2 (2021): e0246921.
7. Robert, Christian P., and Wu Changye. Markov Chain Monte Carlo methods, a survey with some frequent misunderstandings. arXiv preprint arXiv:2001.06249 (2020).
8. Shiferaw, Yegnanew A. Regime shifts in the COVID-19 case fatality rate dynamics: A Markov-switching autoregressive model analysis. Chaos, Solitons & Fractals: X 6 (2021): 100059.
9. Sato, Renato Cesar, and Désirée Moraes Zouain. Modelos de Markov aplicados a saúde. Einstein (São Paulo) 8 (2010): 376–379.
10. Hassan, Zubaida, Muhammad Jawad Hashim, and Gulfaraz Khan. Population risk factors for COVID-19 deaths in Nigeria at sub-national level. The Pan African Medical Journal 35. Suppl 2 (2020).
11. Romeu, Jorge Luis. A markov chain model for COVID-19 survival analysis. PhD, Syracuse University. https://www. researchgate. net/profile/Jorge–Romeu (2020).
12. Laverty, William Henry, et al. “”An Examination of COVID-19 Occurrence in Canada Using Hidden Markov Modelling (January 31, 2020, to May 17, 2020). (2020).
13. Dempster, Arthur P., Nan M. Laird, and Donald B. Rubin. Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc Series B Stat Methodol 39.1 (1977): 1–22.
14. Rabiner, Lawrence R. A tutorial on hidden Markov Models and selected applications in speech recognition. Proceedings of the IEEE 77.2 (1989): 257–286.
15. Ghani, Azra C., et al. Methods for estimating the case fatality ratio for a novel, emerging infectious disease. Am J Epidemiol 162.5 (2005): 479–486.
16. Kawamoto, Ryouhei, et al. Hidden Markov Model for analyzing time-series health checkup data. MEDINFO 2013. IOS Press, 2013. 491–495.
17. Komariah, Kokoy Siti, and Bong-Kee Sin. Health State Modeling and Prediction based on Hidden Markov Models. 2019 Eleventh International Conference on Ubiquitous and Future Networks (ICUFN). IEEE, 2019.
18. Li, Qun, et al. Early transmission dynamics in Wuhan, China, of novel coronavirus–infected pneumonia. New England journal of medicine (2020).
19. World Health Organization. Estimating mortality from COVID-19: scientific brief, 4 August 2020. No. WHO/2019-nCoV/Sci_Brief/Mortality/2020.1. World Health Organization, 2020.

Regular Issue Open Access Article

Research & Reviews : Journal of Statistics

ISSN: 2278–2273
 Volume 11 Issue 2 Received August 22, 2022 Accepted September 3, 2022 Published September 17, 2022