Prospects for the use of artificial intelligence to predict the spread of tuberculosis infection in the WHO European Region

Abstract

Objective — to analyze the prospects of using artificial intelligence and neural networks to create a geospa­tial model of TB transmission and forecast its spread in the WHO European Region using available analytical databases.
 Materials and methods. The research was carried out for the period October 2022 — March 2023. Digital access to the following full-text and abstract databases was used as the main source of research: the EBSCO Information Base Package, the world’s largest single abstract and scientific metric platform Scopus, the freely accessible search system Google Scholar, MEDLINE with Full Text, Dyna Med Plus, EBSCO eBooks Clinical Collection, the abstract and scientific metric database of scientific publications of the Thomson Reuters Web of Science Core Collection WoS, statistical data from the Ministry of Health of Ukraine and the Public Health Center, SCIE, SSCI, the online database of the National Scientific Medical Library of Ukraine, AHCI.
 Results and discussion. Migration processes in Europe still remain a global trend and create difficulties for countries that receive migrants. Adverse living conditions, close contact, poor nutrition, mental and physical stress are what refugees and migrants face. The combination of these risk factors and insufficient access to health services increases the vulnerability of refugees to TB infection. In addition, a delay in diagnosis leads to poor treatment outcomes and continued transmission of the infection to other people.The optimal way to predict the spread of TB infection in European cities, where a significant number of migrants from Ukraine arrived, is to create a mathematical model using the analytical technology of neural networks and artificial intelligence. By analyzing a large amount of data, artificial intelligence can quickly and efficiently identify connections between various factors and predict the future development of the epidemic. For example, artificial intelligence can analyze data on the incidence of TB in different regions of the world, as well as data on the number of patients with other diseases that can affect the human immune system, and make a forecast about the development of the epidemic in the future.
 Conclusions. Today, the creation of a mathematical model and the development of a simulator program for the geospatial functioning of the city and the interaction of people during the day are relevant. Understanding the natural history of TB among recently arrived migrants is important as we consider how best to implement TB control in such populations.