Analysis of the Influence of Various Factors on the Prevalence of Tuberculosis in Ukraine

Abstract

A medical approach to the analysis of socio-economic, medical and demographic factors affecting the prevalence of tuberculosis in Ukraine is insufficient for timely prognosing the prospects for the development of the tuberculosis epidemic and developing an appropriate plan to address its challenges. Objective — to analyse influence of various factors on tuberculosis prevalence in Ukrainian population. Materials and methods. For the analysis, data were collected over the past sixteen years, covering all regions of Ukraine, including information on the number of specialized hospitals, the number of fluoroscopic examinations per 100,000 people, vaccination data, the number of Mycobacterium tuberculosis excretors, the prevalence among urban and rural residents, and the percentage of different demographic groups (workers, health care workers, students, pupils, retirees, the unemployed, homeless people, released prisoners, private sector workers). Results and discussion. The analysis, conducted through the Stacking model, enables the identification of crucial variables that significantly influence the prevalence of tuberculosis. Evaluating the significance of each element in the model enables a deeper comprehension of morbidity dynamics and the optimization of intervention strategies. The creation and validation of machine learning models such as linear regression, random forests, and adaptive boosting have enabled accurate predictions of tuberculosis prevalence. The use of 5-fold cross-validation increased the reliability of the predictions, ensuring stability and accuracy across different demographic groups. Conclusions. The application of artificial intelligence in analyzing socioeconomic, medical, and demographic data has facilitated the identification of key factors influencing the prevalence of tuberculosis in Ukraine. Specifically, the analysis has verified the substantial effects of the quantity of specialized hospitals, the rate of fluoroscopic examinations, and the frequency of bacterial excretion on the prevalence rates.