MOBILE INTELLIGENT AGENTS FOR PREDICTING THE SPREAD OF TUBERCULOSIS ON A SMALL SCALE

Abstract

The article presents a study focused on the development and analysis of
a tuberculosis spread model in enclosed spaces using moving cellular automata based on principles of
information technology and artificial intelligence. The proposed approach accounts for the mobility of
infected agents, spatial characteristics of the environment, ventilation conditions, and the stochastic nature
of Mycobacterium tuberculosis transmission. The model incorporates four cell states (healthy, latent, active,
dead) with probabilistic transition rules reflecting real epidemiological processes. Numerical experiments
were conducted across three environments—open area, office space, and trench—simulating diverse agent
interaction conditions. Results revealed that spatial geometry significantly impacts disease dynamics: in
enclosed spaces, the peak proportion of active cases reaches 6%, compared to 2.3% in open areas. The
active phase duration varies from 400 days in trenches to 650 days in offices, with the latent case proportion
in enclosed settings peaking at 42.6%. Model validation confirmed its alignment with real data, where one
infected individual infects 10–15 others. The findings highlight the model’s potential for predicting
tuberculosis outbreaks in Ukraine and designing preventive measures, such as ventilation optimization or
quarantine strategies.
Keywords: tuberculosis, moving cellular automata, artificial intelligence, intelligent agents,
information technology, modeling

References
1. Статистика захворюваності на ТБ в Україні. Центр громадського здоров'я. URL:
https://phc.org.ua/kontrol-zakhvoryuvan/tuberkuloz/statistika-z-tb.
2. World Health Organization. Latent tuberculosis infection. Updated and consolidated
guidelines for programmatic management. 2018.
3. Сем’янів І. О., Тодоріко Л. Д., Виклюк Я. І., Невінський Д. В. Застосування
геопросторової мультиагентної системи для моделювання різних аспектів передачі
туберкульозу. INFUSION & CHEMOTHERAPY. 2024. Т.7, №1. С. 9-17. DOI:10.32902/2663-
0338-2024-1-9-17.
4. Європейський центр з профілактики та контролю захворювань. URL:
https://www.ecdc.europa.eu/en/publications-data/tuberculosis-surveillance-and-monitoring-europe2022-2020-data.
5. Vyklyuk Y., Semianiv I., Nevinskyi D., Todoriko L., Boyko N. Applying geospatial multiagent system to model various aspects of tuberculosis transmission. New Microbes and New
Infections Journal. 2024.Т.59.DOI:10.1016/j.nmni.2024.101417.
6. Butov D., Feshchenko Y., Chesov D. National survey on the impact of the war in Ukraine on
TB diagnostics and treatment services in 2022. The international journal of tuberculosis and lung
disease : the official journal of the International Union against Tuberculosis and Lung Disease. 2023.
T.27, №1. C. 86-88. DOI:10.5588/ijtld.22.0563.
7. Vyklyuk Y., Nevinskyi D., Boyko N. GEOCITY — A new dynamic-spatial model of urban
ecosystem. Journal of the Geographical Institute “Jovan Cvijić” SASA. 2023. Т.73, №2. С. 187-203.
DOI: 10.2298/IJGI2302187V.
8. Mabud T. S., Alves M. L. D., Ko A. I., Basu S., Walter K. S., Cohen T., Mathema B., Colijn
C., Lemos E., Croda J., Andrews J. R. Evaluating strategies for control of tuberculosis in prisons and
prevention of spillover into communities: An observational and modeling study from Brazil. PubMed.
2019. Т.16, №1. DOI:10.1371/journal.pmed.1002737.
9. Todoriko L.D., Andriiets O.A., Vyklyuk Y.I., Semyaniv I.O., Margineanu I., Lesnic' E.,
Nevinsky D.V., Yeremenchuk I.V. Prospects for the use of artificial intelligence to predict the spread
of tuberculosis infection in the WHO European Region. ТУБЕРКУЛЬОЗ ЛЕГЕНЕВІ ХВОРОБИ
ВІЛ-ІНФЕКЦІЯ. 2023. Т.53, №2. С. 86-92. DOI:10.30978/TB2023-2-86.
10. WHO consolidated guidelines on tuberculosis. Module 3: diagnosis – rapiddiagnostics for
tuberculosis detection . 2021.
11. Невінський Д. В., Сем’янів І. О., Виклюк Я. І. Вивчення зв'язку між туберкульозом та
соціально-економічними, медичними, демографічними чинниками в Україні. URL:
https://doi.org/10.18372/2073-4751.81.2013.
12. World Health Organization Data. 2022. URL: https://www.who.int.
13. Brauer F., Castillo–Chavez C., Feng Z. Mathematical models in epidemiology. 2019.
14. Hrizi O., Gasmi K., Ben Ltaifa I., Alshammari H., Karamti H., Krichen M., Ben Ammar L.,
Mahmood A. Tuberculosis disease diagnosis based on an optimized machine learning model. Journal
of Health Engineering. 2022. DOI: 10.1155/2022/8950243.
15. Sameera Abar, Georgios K. Theodoropoulos, Pierre Lemarinier, Gregory M.P. O’Hare. Agent
Based Modelling and Simulation tools: A review of the state-of-art software. COMPUTER SCIENCE
REVIEW JOURNAL. 2017. Т.24. С. 13-33. URL: https://doi.org/10.1016/j.cosrev.2017.03.001.