Machine Learning for Regional Tuberculosis Analysis in Ukraine: Regression Modeling and Clustering

Regional tuberculosis (TB) surveillance requires analytical tools that distinguish outcome definitions, preserve temporal ordering, and characterize geographic heterogeneity. This study developed an information system integrating regression modeling and regional clustering for Ukrainian surveillance indicators. The primary predictive outcome was the quarterly regional count of patients whose multidrug-resistant or rifampicin-resistant TB (MDR/RR-TB) diagnosis was laboratory confirmed for the first time during the reporting quarter. Predictive performance was evaluated using rolling-origin one-quarter-ahead temporal validation, with Random Forest, k-nearest-neighbor regression, Gradient Boosting, a voting ensemble, and simple operational benchmarks compared on the same temporally held-out observations. Several leading approaches showed similar predictive performance, and paired region-level tests did not establish statistically significant superiority of a single model after correction for multiple comparisons. K-means clustering was used as a descriptive representation of regional heterogeneity; the selected three-group representation was stable for the illustrative 2021 analysis, although internal validation criteria did not uniquely identify three clusters as optimal. The study provides a reproducible workflow for temporally validated comparison of recorded surveillance counts together with descriptive regional grouping rather than a new learning algorithm or a causal model of TB transmission.