MODELING OF THE SPREAD OF TUBERCULOSIS BY REGIONS IN UKRAINE

Context. Modelling the spread of tuberculosis in Ukraine is particularly relevant due to the increasing number of cases, especially in 2023. Objective. The aim of this study is to solve modeling tasks by applying modern machine learning methods and data analysis to build predictive models of tuberculosis spread at the regional level. Method. To model the spread of tuberculosis at the regional level in Ukraine, it is proposed to use several approaches, such as the SIR model, cellular automata, and Random Forest. Each of these methods has its unique advantages and can provide a more detailed understanding of the dynamics of disease spread. The SIR model (Susceptible-Infectious-Recovered) is a classical epidemiological model that describes the spread of infectious diseases in a population. The model assumes three groups of the population: S (Susceptible) – susceptible to infection; I (Infectious) – infected and capable of transmitting the infection; R (Recovered) – those who have recovered and gained immunity. Cellular automata are a discrete model that uses a grid of cells to simulate spatiotemporal processes. Each cell can be in different states (e.g., healthy, infected, immune) and change its state depending on the states of neighboring cells. Random Forest is a machine learning method that uses an ensemble of decision trees for classification or regression. This method can be applied to predict the spread of tuberculosis based on a large number of input parameters. Using these methods will allow for a deep analysis and comprehensive results regarding the spread of tuberculosis at the regional level in Ukraine. This, in turn, will facilitate the development of effective strategies to combat the disease and improve public health.. Results. The results of applying the Random Forest and SIR methods were described and analyzed in detail. For Random Forest, the metrics MSE and R2 were evaluated, showing high prediction accuracy. In the case of the SIR algorithm, visual assessment of the results revealed insufficient accuracy due to model limitations. Comparing the chosen methods with other studies, a conclusion was made about the need to consider more complex algorithms to obtain more accurate results. Conclusions. Based on the research results, it can be concluded that the Random Forest method is sufficiently effective for predicting vulnerable social groups and that the SIR algorithm is less effective for modeling the spread of tuberculosis. For further research development, it is recommended to consider more complex algorithms and account for additional factors influencing the spread of the disease. Moreover, to better understand further actions to combat the disease, it is advisable to simulate the spread of tuberculosis among the population of Ukraine.