Using machine learning to assess efficiency of tuberculosis service

Abstract

The purpose of the study was to assess the impact of the availability of TB care on the TB epidemic process. Processing and analysis were performed using methods of machine learning: cluster analysis, linear regression analysis and autoregressive models. It is shown that clusters with the severe epidemic situation are characterized by low staff availability in all its indicators and vice versa. The staff availability of TB care is the most important factor affecting the TB process.