PREVENTIVE HEALTH CARE

Original paper

UDC 613.62:616.12

Authors: L.I. Alibalaeva, V.M. Savinova, 2025

ISSN 0041-5790 (Print) • ISSN 2412-8333 (Online) • Ugol’ – Russian Coal Journal, 2025, № 7, pp. 101-110

DOI: http://dx.doi.org/10.18796/0041-5790-2025-7-101-110

Title

FORECASTING OF HEALTHCARE INDICATORS IN COAL-MINING REGIONS OF THE RUSSIAN FEDERATION BASED ON A MACHINE LEARNING ENSEMBLE MODEL: A METHODOLOGY FOR COMPREHENSIVE ANALYSIS OF EPIDEMIOLOGICAL INDICATORS

Authors

L.I. Alibalaeva, V.M. Savinova

Plekhanov Russian University of Economics, Moscow, 115054, Russian Federation
e-mail: Alibalaeva.li@rea.ru

Authors Information

Alibalaeva L.I. – PhD (Economic), Associate Professor of the Department, Plekhanov Russian University of Economics, Moscow, 115054, Russian Federation, e-mail: Alibalaeva.li@rea.ru
Savinova V.M. – Senior lecturer, Plekhanov Russian University of Economics, Moscow, 115054, Russian Federation, e-mail: Savinova.vm@rea.ru

Abstract

Coal-mining regions of the Russian Federation are characterized with the specific conditions of the healthcare system formation due to the impact of industrial and environmental risk factors on the health of their population. Modern machine learning methods open up new opportunities for accurate forecasting of epidemiological indicators and optimization of the resource provision for medical institutions. The aim of the study is to develop and validate ensemble models to forecast healthcare indicators for the population of coalmining regions with account of the industry’s specific features and the environmental determinants. The methodological basis of the research included integration of the gradient boosting, random forest, and neural networks into a single ensemble architecture. The empirical database was formed using official healthcare statistics for seven key coal-producing regions of the Russian Federation for the period 2010-2023, supplemented by indicators of industrial production, environmental monitoring, and demographic processes. The ensemble model demonstrated high predictive accuracy with the determination coefficients R2 = 0.847 for respiratory diseases and R2 = 0.792 for cardiovascular diseases. It was found that the baseline morbidity rates in coal-mining regions were exceeded by 23.4% for respiratory diseases and by 18.7% for cancerous neoplasms. The predictive models revealed a critical dependence of the epidemiological trends on the coal production volumes with a lag of 3-5 years and on the concentration of the atmospheric pollutants. The developed algorithm provides a short-term forecast accuracy of 89.3% and medium-term forecast accuracy of 76.8%. The results of the study extend the methodological tools for epidemiological forecasting and create a basis for scientifically grounded health care planning in industrial regions. The practical significance lies in the possibility to optimize the provision of resources to medical institutions and preventive programs with account of the predicted epidemiological dynamics.

Keywords

Healthcare forecasting, сoal mining regions, machine learning ensemble model, occupational pathology, environmental determinants of health, epidemiological modeling.

References

1. Wiens J., Shenoy E.S. Machine learning for healthcare: on the verge of a major shift in healthcare epidemiology. Clinical Infectious Diseases. 2018;66(1):149-153. DOI: 10.1093/cid/cix731.
2. Gavrilov D.V., Abramov R.V., Kirilkina A.V., Ivshin A.A., Novitskiy R.E. COVID-19 pandemic prediction model based on machine learning in selected regions of the Russian Federation. FARMAKOEKONOMIKA. Modern Pharmacoeconomics and Pharmacoepidemiology. 2021;14(3):342-356. DOI: 10.17749/2070-4909/farmakoekonomika. 2021.108.
3. Wang P., Zheng X., Ai G., Liu D., Zhu B. Time series prediction for the epidemic trends of COVID-19 using the improved LSTM deep learning method: Case studies in Russia, Peru and Iran. Chaos, Solitons & Fractals. 2020;(140):110214. DOI: 10.1016/j.chaos.2020.110214.
4. Reshetnikov A., Berdutin V., Zaporozhtsev A., Romanov S., Abaeva O., Prisyazhnaya N., Vyatkina N. Predictive algorithm for the regional spread of coronavirus infection across the Russian Federation. BMC Medical Informatics and Decision Making. 2023;(23):135. DOI: 10.1186/s12911-023-02135-1.
5. Muhammad L.J., Algehyne E.A., Usman S.S., Ahmad A., Chakraborty C., Mohammed I.A. Supervised Machine Learning Models for Prediction of COVID-19 Infection using Epidemiology Dataset. SN Computer Science. 2021;2(1):11. DOI: 10.1007/s42979-020-00394-7.
6. Altuntas S., Dereli T., Kusiak A. Advanced text-mining for trend analysis of Russia’s extractive industries. Futures. 2020;(115):102495. DOI: 10.1016/j.futures.2019.102495.
7. Chaurasia V., Pal S., Tiwari B.B. Baseline accuracies of forecasting COVID-19 cases in Russian regions on a year in retrospect using basic statistical and machine learning methods. Procedia Computer Science. 2021;(193):276-284. DOI: 10.1016/j.procs.2021.10.028.
8. Yu B., Wang B., Zhang Y. Application of artificial intelligence in coal mine ultra-deep roadway engineering – a review. Artificial Intelligence Review. 2024;(57):98. DOI: 10.1007/s10462-024-10898-w.
9. Qi C., Chang X., Haugen B., Rhee G., Do T. Prediction into the future: A novel intelligent approach for PM2.5 forecasting in the ambient air of open-pit mining. Atmospheric Pollution Research. 2021;12(9): 101084. DOI: 10.1016/j.apr.2021.101084.
10. Beeche C.A., Garcia M.A., Leng S., Roghanchi P., Pu J. Computational risk modeling of underground coal mines based on NIOSH employment demographics. Safety Science. 2023;(164):106170. DOI: 10.1016/j.ssci.2023.106170.
11. Martinez D.A., Hinson J.S., Klein E.Y., Irvin N.A., Liu H., Patel E.U., Fenstermacher K.Z.J., Levin S. Machine learning and artificial intelligence: applications in healthcare epidemiology. Antimicrobial Stewardship & Healthcare Epidemiology. 2021;1(1):e28. DOI: 10.1017/ash.2021.195.
12. Wieczorek M., Si?ka J., Wo?niak M. Neural network powered COVID- 19 spread forecasting mode. Chaos, Solitons & Fractals. 2020;(140):110203. DOI: 10.1016/j.chaos.2020.110203.
13. Arumugam K., Naved M., Shinde P.P., Leiva-Chauca O., Huaman-Osorio A., Gonzales-Yanac T. Multiple disease prediction using Machine learning algorithms. Materials Today: Proceedings. 2023;(80):3682-3685. DOI: 10.1016/j.matpr.2021.07.361.
14. Zheng N., Du S., Wang J., Zhang H., Cui W., Kang Z., Yang T., Lou B., Chi Y., Long H. Predicting COVID-19 in China using hybrid AI model. IEEE Transactions on Cybernetics. 2020;50(7):2891-2904. DOI: 10.1109/TCYB.2020.2990162.
15. Chen S., Yu J., Chamouni S., Wang Y., Li Y. Integrating machine learning and artificial intelligence in life-course epidemiology: pathways to innovative public health solutions. BMC Medicine. 2024;(22):354. DOI: 10.1186/s12916-024-03566-x.

For citation

Alibalaeva L.I., Savinova V.M. Forecasting of healthcare indicators in coal-mining regions of the Russian Federation based on a machine learning ensemble model: a methodology for comprehensive analysis of epidemiological indicators. Ugol’. 2025;(7):101-110. (In Russ.). DOI: 10.18796/0041-5790-2025-7-101-110.

Paper Info

Received June 03, 2025
Reviewed June 17, 2025
Accepted June 27, 2025