Comprehensive Analysis of Social Determinants of Health in Russian Regions Using Machine Learning

Introduction: Social determinants are fundamental causes of causes that shape the social gradient of health and delineate the limits of effectiveness of purely clinical interventions. The toolkit of big data and machine learning enables precise, reproducible evaluation of their contributions and helps identify meaningful policy priorities aimed at narrowing gaps in life expectancy.

Objective: To quantitatively assess and rank contributions of social, economic, demographic, and environmental determinants to the variation of the Public Health Index (PHI) across Russian regions and identify factors critical for decision-making.

Materials and Methods: A panel dataset was compiled for the regions of the Russian Federation for 2010–2024. Indicator normalization and transliteration of categorical variables were performed. A predictive model for the Public Health Index was developed using gradient boosting on decision trees. Interpretation of the results, including detailed analysis of the contribution of individual determinants, was carried out using a Shapley value-based technique.

Results: We established that mortality indicators (the total number of deaths and mortality from external causes), the poverty level, and the housing affordability index contributed the most to the variations in the Public Health Index. School meal coverage, environmental protection expenditures, and crime indicators demonstrated additional, yet significant effects. The parameters traditionally used as markers of socioeconomic well-being (per capita income and unemployment rate) demonstrated statistical redundancy when the poverty variable was included in the model. A pronounced interregional gradient was identified, indicating a substantial influence of territorial specificity.

Conclusions: A comprehensive analysis of socioeconomic, demographic, and infrastructural indicators using machine learning methods provides a robust foundation for forecasting and interpreting regional differences. Public health management strategies should be adapted to the specific features of each constituent entity.

1. Sautkina VA. Social determinants of health: Global trends and regional features. Obshchestvennye Nauki i Sovremennost’. 2024;(5):98-110. doi: 10.31857/S0869049924050087

2. Jahnel T, Dassow HH, Gerhardus A, Schüz B. The digital rainbow: Digital determinants of health inequities. Digit Health. 2022;8:20552076221129093. doi: 10.1177/20552076221129093

3. Chetty R, Stepner M, Abraham S, et al. The association between income and life expectancy in the United States, 2001–2014. JAMA. 2016;315(16):1750-1766. doi: 10.1001/jama.2016.4226

4. Shartova N, Tikunov V, Chereshnya O. Health disparities in Russia at the regional and global scales. Int J Equity Health. 2021;20(1):163. doi: 10.1186/s12939-021-01502-6

5. Yi H, Li M, Dong Y, et al. Nonlinear associations between the ratio of family income to poverty and all-cause mortality among adults in NHANES study. Sci Rep. 2024;14(1):12018. doi: 10.1038/s41598-024-63058-z

6. IHME-CHAIN Collaborators. Effects of education on adult mortality: A global systematic review and meta-analysis. Lancet Public Health. 2024;9(3):e155-e165. doi: 10.1016/S2468-2667(23)00306-7

7. Sart G, Bayar Y, Danilina M. Impact of education and income inequalities on life expectancy: Insights from the new EU members. Front Public Health. 2024;12:1397585. doi: 10.3389/fpubh.2024.1397585

8. Lu J, Wu C, Zhang X, et al. Educational inequalities in mortality and their mediators among generations across four decades: Nationwide, population based, prospective cohort study based on the ChinaHEART project. BMJ. 2023;382:e073749. doi: 10.1136/bmj-2022-073749

9. Tapia Granados JA, House JS, Ionides EL, Burgard S, Schoeni RS. Individual joblessness, contextual unemployment, and mortality risk. Am J Epidemiol. 2014;180(3):280-287. doi: 10.1093/aje/kwu128

10. Meneton P, Kesse-Guyot E, Méjean C, et al. Unemployment is associated with high cardiovascular event rate and increased all-cause mortality in middle-aged socially privileged individuals. Int Arch Occup Environ Health. 2015;88(6):707-716. doi: 10.1007/s00420-014-0997-7

11. Jakovljevic M, Kozlova O, Makarova M, Neklyudova N, Pyshmintseva O. Partial contribution of socioeconomic factors to the mortality rate of the working-age population in Russia. Healthcare (Basel). 2023;11(10):1507. doi: 10.3390/healthcare11101507

12. Sanchez Rico M, Plessz M, Airagnes G, et al. Cardiovascular burden and unemployment: A retrospective study in a large population-based French cohort. PLoS One. 2023;18(7):e0288747. doi: 10.1371/journal.pone.0288747

13. Kawachi I, Kyriopoulos I, Vandoros S. Economic uncertainty and cardiovascular disease mortality. Health Econ. 2023;32(7):1550-1560. doi: 10.1002/hec.4678

14. D’Alessandro D, Appolloni L. Housing and health: An overview of the literature. Health Affairs Health Policy Brief. 2018;5(1):17-21. doi: 10.1377/hpb20180313.396577

15. de Bont J, Jaganathan S, Dahlquist M, Persson Å, Stafoggia M, Ljungman P. Ambient air pollution and cardiovascular diseases: An umbrella review of systematic reviews and meta-analyses. J Intern Med. 2022;291(6):779-800. doi: 10.1111/joim.13467

16. Brown JRG, Baptiste PJ, Hajmohammadi H, Nadarajah R, Gale CP, Wu J. Impact of neighbourhood and environmental factors on the risk of incident cardiovascular disease: A systematic review and meta-analysis. Eur J Prev Cardiol. 2025;32(18):1903-1912. doi: 10.1093/eurjpc/zwaf165

17. Holt-Lunstad J, Smith TB, Baker M, Harris T, Stephenson D. Loneliness and social isolation as risk factors for mortality: A meta-analytic review. Perspect Psychol Sci. 2015;10(2):227-237. doi: 10.1177/1745691614568352

18. Wang F, Gao Y, Han Z, et al. A systematic review and meta-analysis of 90 cohort studies of social isolation, loneliness and mortality. Nat Hum Behav. 2023;7(8):1307-1319. doi: 10.1038/s41562-023-01617-6

19. Naito R, McKee M, Leong D, et al. Social isolation as a risk factor for all-cause mortality: Systematic review and meta-analysis of cohort studies. PLoS One. 2023;18(1):e0280308. doi: 10.1371/journal.pone.0280308

20. Mackenbach JP, Stirbu I, Roskam AJ, et al.; European Union Working Group on Socioeconomic Inequalities in Health. Socioeconomic inequalities in health in 22 European countries. N Engl J Med. 2008;358(23):2468-2481. doi: 10.1056/NEJMsa0707519

21. Mackenbach JP. Nordic paradox, Southern miracle, Eastern disaster: Persistence of inequalities in mortality in Europe. Eur J Public Health. 2017;27(Suppl 4):14-17. doi: 10.1093/eurpub/ckx160

22. Kino S, Hsu YT, Shiba K, et al. A scoping review on the use of machine learning in research on social determinants of health: Trends and research prospects. SSM Popul Health. 2021;15:100836. doi: 10.1016/j.ssmph.2021.100836

23. Seligman B, Tuljapurkar S, Rehkopf D. Machine learning approaches to the social determinants of health in the health and retirement study. SSM Popul Health. 2017;4:95-99. doi: 10.1016/j.ssmph.2017.11.008

24. Bhavnani SK, Zhang W, Bao D, et al. Subtyping social determinants of health in the “All of Us” program: Network analysis and visualization study. J Med Internet Res. 2025;27:e48775. doi: 10.2196/48775

25. Rahman MS, Shiddik AB. Utilizing artificial intelligence to predict and analyze socioeconomic, environmental, and healthcare factors driving tuberculosis globally. Sci Rep. 2025;15(1):13619. doi: 10.1038/s41598-025-96973-w

26. Tarasenko EA, Russkikh SV, Vasilyeva TP, Makarova EV, Gorbacheva NA, Rotov VM. Social determinants of health as a methodological basis to develop strategies on public health improvement: Foreign experience and lessons for Russia. Sotsial’nye Aspekty Zdorov’ya Naseleniya. 2024;70(2):3. doi: 10.21045/2071-5021-2024-70-2-3

27. Vasilieva TP, Larionov AV, Russkikh SV, Zudin AB, Vasunina AE, Vasiliev MD. Methodological approaches to measuring public health as the sociomedical resource and potential of the society. Zdorov’e Naseleniya i Sreda Obitaniya. 2022;30(11):7-15. (In Russ.) doi: 10.35627/2219-5238/2022-30-11-7-15

28. Solovyeva YuV, Gorelova JYu, Letuchaya TA, Mirskaya NB, Zaretskaya AR. Assessment of healthy eating awareness of schoolchildren in a digital environment. Zdorov’e Naseleniya i Sreda Obitaniya. 2021;29(10):41-46. (In Russ.) doi: 10.35627/2219-5238/2021-29-10-41-46