Predicting tuberculosis incidence using machine learning

Introduction. Forecasting the development of the tuberculosis (TB) epidemic is a complex task, as the epidemic process as a phenomenon is multifactorial.

Aim. To create a dynamic model for long-term forecasting of TB incidence in the Russian Federation using machine learning methods for planning and implementing evidence-based preventive measures, taking into account regional characteristics of the epidemic situation.

Materials and methods. The development of the dynamic forecast model included the selection of epidemiological, social, demographic, and economic factors with the greatest influence on the development of the TB epidemic using the Delphi expert assessment method; determination of the weight of each factor; ranking of the constituent entities of the Russian Federation by level of economic development, TB incidence, and mortality; and the creation of a mathematical model using machine learning methods. A Gaussian process was chosen as the machine learning model. The model was trained on data from 2010–2016 and validated on data from 2017–2021. The models were implemented in Python 3 using the open-source scikit-learn library and CatBoost.

Results. The model matrix consisted of indicators that have the greatest impact on the development of the TB epidemic: gross regional product, unemployment rate, life expectancy; TB incidence; the proportion of newly diagnosed pulmonary TB patients with bacterial isolation detected by sputum smear microscopy and culture, the proportion of primary multidrug-resistant TB cases, and the number of TB-related deaths during the first year of observation. The resulting dynamic model of TB incidence using machine learning methods has high predictive ability (R2 = 0.78).

Conclusions. The dynamic model for predicting TB incidence has high predictive capabilities regardless of the level of economic development of a constituent entity of the Russian Federation and can serve as the basis for developing individualized algorithms for selecting measures to optimize the detection, treatment, and prevention of TB.

1. Khalfin RA, Madyanova VV, Stolbov AP, Efimova AO, Kachkova OE. Design of patient-centered health care system in the digital transformation of health care. Health Care Standardization Problems. 2019;(11-12):50–57. (In Russ.) https://doi.org/10.26347/1607-2502201911-12050-057.

2. Suchkov SV, Stavitskaya NV, Notkins A, Lopukhin YuM, Bunz F, Belov YuV et al. Introduction to predictive, preventive and personalized medicine: past experience and future reality. Tuberculosis and Lung Diseases. 2014;91(7):77–89. (In Russ.) Available at: https://www.tibl-journal.com/jour/article/view/109.

3. Yakovlev AA. On the Role of Global and Regional Factors in the Development of the Epidemic Process of Anthroponotic Infections. Epidemiologiya i Vaktsinoprofilaktika. 2020;19(6):86–100. (In Russ.) https://doi.org/10.31631/2073-3046-2020-19-6-86-100.

4. Meshkov IO, Revyakina OV, Krasnov VA, Shvarts YaSh, Petrenko TI. Methods of multidimensional statistic processing of data applied to find regularities in the course of tuberculosis in Siberian and Fareastern federal districts. Tuberculosis and Lung Diseases. 2018;96(6):30–37. (In Russ.) https://doi.org/10.21292/2075-1230-2018-96-6-30-37.

5. Kreps TV. Interdisciplinary approach in research and teaching: advantages and challenges of application. Scientific Bulletin of the Southern Institute of Management. 2019;(1):115–120. (In Russ.) Available at: https://www.elibrary.ru/zdbern.

6. Rogulin RS. Using data analytics and machine learning techniques to forecast and plan demand, to optimize inventory levels, reduce stockouts, and improve customer satisfaction. Theoretical Economics. 2023;(8):35–53. (In Russ.) Available at: https://theoreticaleconomy.ru/ru/nauka/article/ 81582/view.

7. Avilov KK, Romanyukha AA, Belilovsky EM, Borisov SE. Comparison of Modeling Schemes for Natural Course of Pulmonary Tuberculosis. Mathematical Biology and Bioinformatics. 2019;14(2):570–587. (In Russ.) https://doi.org/10.17537/2019.14.570.

8. Nian SC, Fang YC, Huang MS. In-mold and Machine Sensing and Feature Extraction for Optimized IC-tray Manufacturing. Polymers. 2019;11(8):1348. https://doi.org/10.3390/polym11081348.

9. Bruzda J. Demand forecasting under fill rate constrains – The case of reorder points. Int J Forecast. 2020;36(4):1342–1361. https://doi.org/10.1016/j.ijforecast.2020.01.007.

10. Zhukov GA, Mikhailus VE, Osadchaya AV. The use of neural networks and machine learning in forecasting economic processes. Industrial Economy. 2025;(4):18–24. (In Russ.) Available at: https://elibrary.ru/dpaafr.

11. Avilov KK, Romanyukha AA. Mathematical modeling of tuberculosis propagation and patient detection. Autom Remote Control. 2007;68:1604–1617. https://doi.org/10.1134/S0005117907090159.

12. Bekembayeva GS, Khauadamova GT. Mathematical modeling in epidemiology of tuberculosis of juvenile population in RK. Medicine and Ecology. 2009;(1):31–36. (In Russ.) Available at: https://cyberleninka.ru/article/n/matematicheskoe-modelirovanie-v-epidemiologii-tuberkuleza-detskopodrostkovogo-naseleniya-v-rk.

13. Khantaeva NS, Mikhalevich IM, Kulesh DV. Analysis and prediction of epidemiological indices of tuberculosis on the basis of multidimensional methods. Bulletin of the East Siberian Scientific Center SBRAMS. 2011;(2):184–189. (In Russ.) Available at: https://elibrary.ru/oigqdh.

14. Kuzin AA, Glushakov RI, Parfenov SA, Sapozhnikov KV, Lazarev AA. Development of an artificial intelligence system for the forecasting of infectious diseases. Fundamental and Clinical Medicine. 2023;8(3):143–154. (In Russ.) https://doi.org/10.23946/2500-0764-2023-8-3-143-154.

15. Cherniaev IA, Tsvetkov AI, Chugaev YuP, Chernavin PF. Forecasting trends in the tuberculosis epidemic situation using a simulation dynamic model. Ural Medical Journal. 2023;22(5):58–65. (In Russ.) https://doi.org/10.52420/ 2071-5943-2023-22-5-58-65.

16. Kosova AA, Chalapa VI, Kovtun OP. Methods for modellind and forecasting dynamics of infectious diseases. Ural Medical Journal. 2023;22(4):102–112. (In Russ.) https://doi.org/10.52420/2071-5943-2023-22-4-102-112.

17. Krivorotko OI, Andornaya DV, Kabanikhin SI. Sensitivity analysis and practical identifiability of some mathematical models in biology. Siberian Journal of Industrial Mathematics. 2020;23(1):107–125. (In Russ.) https://doi.org/10.33048/SIBJIM.2020.23.110

18. Sysoeva OV, Vasina AV, Kiseleva ON, Goryacheva TV. Regions clusterization by achieving a sustainable development while strengthening the technological sovereignty of the country. Ars Administrandi. 2025;17(2):374–402. (In Russ.) https://doi.org/10.17072/2218-9173-2025-2-374-402.

19. Seltsovskiy PP, Chizhova OV, Belilovskiy EM. Classification of territories by incidence and mortality rates from tuberculosis. Tuberculosis and Socially Significant Diseases. 2025;13(2):4–11. (In Russ.) https://doi.org/10.54921/ 2413-0346-2025-13-2-4-11.

20. Hernandez JBR, Kim PY. Epidemiology Morbidity And Mortality. In: StatPearls. Treasure Island (FL): StatPearls Publishing; 2022. Available at: https://www.ncbi.nlm.nih.gov/books/NBK547668/.

21. Austin PC. A Tutorial on Multilevel Survival Analysis: Methods, Models and Applications. Int Stat Rev. 2017;85(2):185–203. https://doi.org/10.1111/insr.12214.

22. Nascimento AQ, Dantas DB, Melo GS, Gomes FC, de Melo Neto J. Impact of sociodemographic factors and screening, diagnosis, and treatment strategies on colorectal cancer mortality in Brazil: A 20-year ecological study. PLoS ONE. 2022;17(9):e0274572. https://doi.org/10.1371/journal.pone.0274572.

23. Popkov AYu. Randomized machine learning of nonlinear models with application to forecasting the development of an epidemic process. Automation and Telemechanics. 2021;(6):149–168. (In Russ.) https://doi.org/10.31857/S0005231021060064.

24. Redko AN, Mikhaylova YuV, Sterlikov SA, Mikhaylov AYu, Pankova YaYu. Labor Losses due to Tuberculosis in Russia in 2010–2022. Tuberculosis and Lung Diseases. 2025;103(2):80–87. (In Russ.) https://doi.org/10.58838/2075-1230-2025-103-2-80-87

25. Veselova EI, Kaminskiy GD, Kocharyan KA, Peregudova AB, Lovacheva OV, Samoylova AG. A Predictive Model of the HIV Infection Course. Tuberculosis and Lung Diseases. 2024;102(1):6–11. (In Russ.) https://doi.org/10.58838/2075-1230-2024-102-1-6-11.

26. Zagdyn ZM, Kobesov NV, Rusakova LI, Vasilyeva TP, Aleksandrova OYu, Galoyan AS. Global tuberculosis burden in Russia and the world as a public health problem (historical and analytical review). Tuberculosis and Lung Diseases. 2023;101(5):78–88. (In Russ.) https://doi.org/10.58838/20751230-2023-101-5-78-88.

27. Burykhin VS, Vasilyeva IA, Sterlikov SA, Testov VV, Kudrina VG, Urushadze ND. Simulation of Conditions and Results of Implementation of Short-Course Treatment Regimes in Tuberculosis Patients. Tuberculosis and Lung Diseases. 2023;101(6):8–12. (In Russ.) https://doi.org/10.58838/2075-1230-2023-101-6-8-12.

28. Starshinova AA, Dovgalyuk IF, Osipov NN, Kudlay DA. Lessons Learned from the COVID-19 Pandemic: Simulation of the Tuberculosis Epidemic as a Function of Population Coverage with Screening. Tuberculosis and Lung Diseases. 2023;101(6):56–65. (In Russ.) https://doi.org/10.58838/20751230-2023-101-6-56-65.

29. Kravchenko AF, Smerdin SV, Desyatskova EM, Frolov EG, Untanova LS. Digital technologies in the monitoring system for preventive examination of persons at risk of tuberculosis. Tuberculosis and Socially Significant Diseases. 2025;13(3):4–11. (In Russ.) https://doi.org/10.54921/2413-03462025-13-3-4-11.

30. Markelov YuM, Shyegoleva LV. Use of mathematical model (simulator) for estimation of the amount of undetected bacillary patients in administrative regions of the Russian Federation. Ekologiya Cheloveka (Human Ecology). 2010;(1):50–55. (In Russ.) Available at: https://elibrary.ru/kyzhgh.

31. Markelov YuM, Schegoleva LV. Evaluation of Clinical and Economic Efficiency and Impact of Mass Fluorography Screening on Tuberculosis Epidemiological Rates in Four Federal Districts of the Russian Federation with Different Levels of Population Coverage with Mass Fluorography Screening. Tuberculosis and Lung Diseases. 2023;101(1):8–16. (In Russ.) https://doi.org/10.58838/2075-1230-2023-101-1-8-16.