Clustering of the Russian Federation Regions by Resource Provision of the Population in the Sphere of Healthcare and Use of Hospital Stock

The purpose of the study is to analyze and identify the structure of the parameters of resource provision of the population in the field of healthcare and the efficiency of using hospital stock in the regions of the Russian Federation. Such structuring will allow classifying both the regions of the Russian Federation and identifying among the analyzed parameters the factors that largely determine regional differences and interregional disparities in order to prioritize these factors when developing the main directions of state regulation of interregional differences in the regions of the Russian Federation in the field of healthcare.

Materials and methods. To achieve this purpose, a cluster analysis of the regions of the Russian Federation was carried out on the basis of data from the Unified Interdepartmental Information and Statistical System using the iterative k-means method implemented in the Statistica software package.

Results. As a result of the cluster analysis of the regions of the Russian Federation by six features, nine clusters were identified and their profile characteristics were determined. The main results of the multivariate statistical analysis include: analysis of variance parameters; values of total intra-cluster variances; values of intercluster sums of squared distances; a graph of average values for six features for each of the nine clusters, as well as descriptive statistics for each object within the selected clusters. Based on the results of the variance analysis for all clustering options, the magnitude (and significance level) of the F-values and the magnitude of the empirical coefficient of determination revealed a high significance for the distribution of objects into clusters of the following features: provision of hospital beds per 10 thousand population; provision of the population with mid-level medical workers working in state and municipal medical organizations (people per 10 thousand population) and provision of the population with doctors working in state and municipal medical organizations (people per 10 thousand population).

Conclusion. Descriptive statistics for each Russian region within the nine selected clusters showed that there is a relatively low variability of feature values within the clusters. This indicates a high degree of homogeneity and compactness of the constructed clusters. The obtained clustering results allow us to determine the resource profiles of Russian regions and formulate the main priorities of the regional healthcare development policy in Russia, aimed at increasing the degree of homogeneity of the country’s regions in terms of quality and accessibility of medical care. The practical significance of the study is that its results will allow us to more effectively develop regional policies and carry out state regulation of the healthcare sector in the Russian Federation, as well as to determine measures to support the industry in regions with low indexes of hospital stock efficiency.

1. Merkulova Ye.Yu., Bogopol’skiy A.S. Differentiation of Russian Regions: Economic Contrasts and Social Differences. Statistika i Ekonomika = Statistics and Economics. 2025; 22(3): 39-52. DOI: 10.21686/2500-3925-2025-3-39-52. (In Russ.)

2. Zalmanov I.A. Variable Cluster Analysis of Employment in the Cities of the Russian Federation. Statistika i Ekonomika = Statistics and Economics. 2024; 21(5): 15-25. DOI: 10.21686/2500-3925-2024-5-15-25. (In Russ.)

3. Gorpinchenko K.N., Moroz A.I., Spanidi D.A. Analysis of Economic Development of Krasnodar Krai Using Cluster Analysis. Yestestvenno-gumanitarnyye issledovaniya = Research in Natural Sciences and Humanities. 2024; 5(53): 119–123. (In Russ.)

4. Delamater Paul., Shortridge Ashton., Messina Joseph. Regional health care planning: A methodology to cluster facilities using community utilization patterns. BMC health services research. 2013. DOI: 10.1186/1472-6963-13-333.

5. Duran B., Odell P. Cluster analysis. A survey. Springer-Verlag. Berlin – Heidelberg – N.Y. 1974.

6. Kalinina V.N., Solov’yev V.I. Vvedeniye v mnogomernyy statisticheskiy analiz = Introduction to multivariate statistical analysis. Moscow: GUU; 2003. 66 p. (In Russ.)

7. Treyvish A.I. Unevenness and structural diversity of spatial economic development as a scientific problem and Russian reality. Prostranstvennaya ekonomika = Spatial economy. 2019; 15; 4: 13–35. (In Russ.)

8. Gabdullin N.M., Kirshin I.A., Shulayev A.V. Regulation of interregional differences in the constituent entities of the Russian Federation in the context of the national projects “Healthcare” and “Demography”. Uroven’ zhizni naseleniya regionov Rossii = Standard of Living of the Population of Russian Regions. 2020; 16; 3: 59–69. DOI: 10.19181/lsprr.2020.16.3.5. (In Russ.)

9. Zheleznyakova I.A., Kovaleva L.A., Khelisupali T.A., Voynov M.A., Omel’yanovskiy V.V. Methodology for assessing the effectiveness of using the bed capacity of medical organizations. FARMAKOEKONOMIKA. Sovremennaya farmakoekonomika i farmakoepidemiologiya = PHARMACOECONOMIKA. Modern pharmacoeconomics and pharmacoepidemiology. 2017; 10(4): 37-43. DOI: 10.17749/2070-4909.2017.10.4.037-043. (In Russ.)

10. Bondarenko N.Ye., Gubarev R.V. The Problem of Regional Inequality in the Socio-Economic Development of the Russian Federation. Vestnik Rossiyskogo ekonomicheskogo universiteta imeni G.V. Plekhanova = Bulletin of the Plekhanov Russian University of Economics. 2020; 17; 5(113): 56-68. (In Russ.)

11. YEMISS. Klyuchevyye pokazateli obespechennosti meditsinskikh organizatsiy vstatisticheskoy sisteme Minzdrava/Rosstata = EMISS. Key Indicators of the Provision of Medical Organizations in the Statistical System of the Ministry of Health/Rosstat [Internet]. Available from: https://www.fedstat.ru/indicator/61875. (In Russ.)

12. Jain A.K., Murty M.N., Flynn P.J. Data clustering: A Review [Internet]. ACM Computing Surveys. 1999; 31: 3. Available from: http://users.eecs.northwestern.edu/~yingliu/datamining_papers/survey.pdf.

13. Alex Smola and S.V.N. Vishwanathan. Introduction to machine learning. Cambridge University Press; 2008. 234 p.

14. Bykowska-Derda A., Zielinska-Dawidziak M., Czlapka-Matyasik M. Dietary-Lifestyle Patterns Associated with Bone Turnover Markers, and Bone Mineral Density in Adult Male Distance Amateur Runners - A Cross-Sectional Study. Nutrients. 2022; 14(10): 2048. DOI: 10.3390/nu14102048.

15. Reyting regionov - 2024. Pokazateli sistemy zdravookhraneniya = Regional Rating - 2024. Healthcare System Indicators [Internet]. Available from: https://expertnw.com/from-editors/reyting-regionov-za-2024-g-pokazateli-sistemyzdravookhraneniya/.( In Russ.)