Forecast of the HIV epidemic progression in the Ural federal district

The aim of the study. Development of a mathematical model for forecasting the progression of the HIV epidemic in the Ural Federal District of the Russian Federation (hereinafter referred to as the UFD), taking into account socio economic indicators and HIV incidence rates. Materials and methods. The study used HIV incidence rates in the Ural Federal District (UFD) for 1998–2023. An economic indicator — unemployment for the period 1991–2024 — was used as a predictor. To account for time dependence and possible delayed effects of income on incidence, a lagged set of indicators with a shift of up to 6 years was formed. Artificial neural networks (ANN) were used to build a predictive model. The radial basis function (RBF) was used as the basic ANN architecture. Training was performed using the SANN module of the STATISTICA 12 software package. The data were divided into training and test sets (85/15), and cross-validation was used on the latent period 2021–2023 for validation. The coefficient of determination, as well as the mean absolute error and the mean absolute percentage error, were used to assess the forecast accuracy. These indicators were calculated both on the training and test samples, and during cross-validation and extrapolation of predicted values. Result and discussion. To forecast HIV incidence in the Ural Federal District, 1,000 RBF ANN models were built and tested, of which 20 with the best metrics were selected for forecasting. The best model (RBF 3–16–1) demonstrated high accuracy: the determination coefficient R2=0.9, the mean absolute error MAD=6.8. A forecast of HIV incidence through 2028 was generated, which will amount to 81.4^о/оооо. Taking into account other trained RBF ANNs with quality metrics exceeding 0.9, the incidence rate in 2028 is expected to range from 45.9^о/оооо to 112^о/оооо. Conclusion. A forecast of HIV incidence in the Ural Federal District, based on an economic predictor, demonstrated high accuracy based on quality metrics. Accounting for unemployment with a six-year lag allowed for socioeconomic factors to be taken into account. The use of application software with built-in ANN forecasting functions makes the methodology accessible to specialists and provides a basis for preventive strategies and management decisions in healthcare.

1. Abdolrasol M.G.M., Hussain S.M.S., Ustun T.S., Sarker M.R., Hannan M.A., Mohamed R., Ali J.A., Mekhilef S., Milad A. Artificial Neural Networks Based Optimization Techniques: A Review // Electronics. 2021. Vol. 10, No. 21. P. 2689. doi: 10.3390/electronics10212689.

2. Niazkar H.R., Niazkar M. Application of artificial neural networks to predict the COVID-19 outbreak // Global Health Research and Policy. 2020. Vol. 5, No. 1. P. 50. doi: 10.1186/s41256-020-00175-y.

3. Melnikova E.N. Forecasting the Epidemic Process of HIV Infection using ARIMA andMicrosoft Excel Tools. Public Health and Life Environment — PH&LE, 2024, Vol. 32, No. 7, рр. 68–75 (In Russ.). doi: 10.35627/2219-5238/2023-32-7-68-75.

4. Kondratova S.Ye., Marchenko A.N., Melnikova E.N. Modeling of forecasting the development of the HIV epidemic process in a region with a high level of HIV infection as a determinant of the direction of anti-epidemic measure. HIV Infection and Immunosuppressive Disorders, 2021, Vol. 13, No. 2, рр. 85–93 (In Russ.). doi: 10.22328/2077-9828-2021-13-2-85-93.

5. Li Z., Li Y. A comparative study on the prediction of the BP artificial neural network model and the ARIMA model in the incidence of AIDS // BMC Medical Informatics and Decision Making. 2020. Vol. 20, No. 1. P. 143. doi: 10.1186/s12911-020-01157-3.

6. Edeh M.O., Dalal S., Dhaou I.B., Agubosim C.C., Umoke C.C., Richard-Nnabu N.E., Dahiya N. Artificial Intelligence-Based Ensemble Learning Model for Prediction of Hepatitis C Disease // Frontiers in Public Health. 2022. Vol. 10. Р. 892371. doi: 10.3389/fpubh.2022.892371.

7. Kotlovsky M.Yu., Tsybikova E.B., Lorsanov S.M., Fadeev P.A., Fadeeva S.O., Gusev A.V. Development of a machine learning model predicting the incidence of newly diagnosed HIV infection in the subjects of the Russian Federation. Medical doctor and information technology, 2023, No. 3, рр. 16–29 (In Russ.). doi: 10.25881/18110193_2023_3_16.

8. Onishchenko G.G., Smolenskyi V.Yu. Role of the priority national health project in implementing HIV epidemic control strategy in the Russian Federation. Hygiene and Sanitation, 2011, No. 2, pp. 11–20 (In Russ.).

9. Kosova A.A., Chalapa V.I., Kovtun O.P. Methods for modellind and forecasting dynamics of infectious diseases. Ural Medical Journal, 2023, Vol. 22, No. 4, рр. 102–112 (In Russ.). doi: 10.52420/2071-5943-2023-22-4-102-112.

10. Kolosnitsyna M.G., Chubarov M.Yu. Socio-economic factors of mor tality from infectious diseases in the Russian regions. Social aspects of population health, 2021, Vol. 67, No. 5, р. 2 (In Russ.). doi: 10.21045/2071-5021-2021-67-5-2.

11. Pastukhova E.Ya., Morozova E.A., Chelombitko A.N. The relationship of socio-economic factors and various causes of mortality in the population of the region. Fundamental research. 2019, No. 6, рр. 121– 125 (In Russ.). doi: 10.17513/fr.42496.

12. Sociological Institute of the Russian Academy of Sciences, St Petersburg, Rusinova N.L., Safronov V.V., Sociological Institute of the Russian Academy of Sciences, St Petersburg. The Effects of Unemployment on Health in European Countries: The Role of Welfare State // Sociological Journal. 2017. Vol. 23, No. 2. Р. 28–50. doi: 10.19181/socjour.2017.23.2.5158.

13. Kostina L.N., Gareeva G.A. Neural networks in time series forecasting problems. Innovative science. 2015. Vol. 6–2 (In Russ.).

14. Kondratyev M.A. Forecasting methods and models of disease spread // Computer Research and Modeling. 2013. Vol. 5, No. 5. P. 863–882. doi: 10.20537/2076-7633-2013-5-5-863-882.

15. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V., Kravchenko A.V. HIV infection. Information Bulletin No. 30. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2007. 32 р. (In Russ.).

16. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V. HIV infection. Information Bulletin No. 31. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2008. 82 р. (In Russ.).

17. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V. HIV infection. Information Bulletin No. 33. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2009. 82 р. (In Russ.].

18. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V. HIV infection. Information Bulletin No. 34. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2010. 52 р. (In Russ.).

19. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V. HIV infection. Information Bulletin No. 35. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2011. 51 р. (In Russ.).

20. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V. HIV infection. Information Bulletin No. 36. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2012. 53 р. (In Russ.).

21. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V. HIV infection. Information Bulletin No. 38. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2013. 53 р. (In Russ.).

22. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V., Tushina O.I. HIV infection. Information Bulletin No. 39. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2014. 53 р. (In Russ.).

23. Pokrovsky V.V., Ladnaya N.N., Tushina O.I., Buravtsova E.V., Kravchenko A.V. HIV infection. Information Bulletin No. 40. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2015. 56 р. (In Russ.).

24. Pokrovsky V.V., Ladnaya N.N., Simashev T.I., Buravtsova E.V., Siritsa A.V. HIV infection. Information Bulletin No. 41. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2016. 56 р. (In Russ.).

25. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V. HIV infection. Information Bulletin No. 42. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2017. 56 р. (In Russ.).

26. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V. HIV infection. Information Bulletin No. 43. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2018. 56 р. (In Russ.).

27. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V., Kravchenko A.V. HIV infection. Information Bulletin No. 44. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2019. 58 р. (In Russ.).

28. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V., Buravtsova E.V., Kravchenko A.V. HIV infection. Information Bulletin No. 45. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2020. 58 р. (In Russ.).

29. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V. HIV infection. Information Bulletin No. 46. Moscow: Federal Scientific and Methodological Center for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2021. 83 р. (In Russ.).

30. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V. HIV infection. Information Bulletin No. 47. Moscow: Specialized Scientific Research Department for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2023. 82 р. (In Russ.)

31. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V. HIV infection. Information Bulletin No. 48. Moscow: Specialized Scientific Research Department for Prevention and Control of AIDS, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2024. 82 р. (In Russ.)

32. Pokrovsky V.V., Ladnaya N.N., Sokolova E.V. HIV infection. Information Bulletin No. 49. Moscow: Reference Center for Monitoring of HIV and HIV-associated Infections, FSBI Central Research Institute of Epidemiology of Rospotrebnadzor, 2024. 80 р. (In Russ.).

33. Alimov A.V., Zakharova Yu.A., Pitersky M.V., Bykov R.O., Ladygin O.V. HIV Infection in the Urals Federal District: Information Bulletin for 2019. 2020. 35 p. (In Russ.).

34. Zakharova Yu.A., Pitersky M.V., Yarantseva O.Ya., Semenov A.V. HIV Infection in the Urals Federal District: Information Bulletin for 2020. 2021. 30 p. (In Russ.).

35. Pitersky M.V., Makovskaya Ya.V., Yarantseva O.Ya., Panova A.V., Semenov A.V. HIV Infection in the Urals Federal District: Information Bulletin for 2023. 2025. 34 p. (In Russ.).

36. Derkach A.Yu., Chernyaev I.A. The Impact of Employment and Unemployment Rates on Tuberculosis Incidence and Mortality. Bulletin of USMU, 2023, No. 1, рр. 39–46 (In Russ.).

37. Wang G., Wei W., Jiang J., Ning C., Chen H., Huang J., Liang B., Zang N., Liao Y., Chen R., Lai J., Zhou O., Han J., Liang H., Ye L. Application of a long short-term memory neural network: a burgeoning method of deep learning in forecasting HIV incidence in Guangxi, China // Epidemiology and Infection. 2019. Vol. 147. P. e194. doi: 10.1017/S095026881900075X.

38. He J., Li J., Jiang S., Cheng W., Jiang J., Xu Y., Yang J., Zhou X., Chai C., Wu C. Application of machine learning algorithms in predicting HIV infection among men who have sex with men: Model development and validation // Frontiers in Public Health. 2022. Vol. 10. P. 967681. doi: 10.3389/fpubh.2022.967681.

39. Li X., Xu X., Wang J., Li J., Qin S., Yuan J. Study on Prediction Model of HIV Incidence Based on GRU Neural Network Optimized by MHPSO // IEEE access: practical innovations, open solutions. 2020. Vol. 8. P. 49574–49583. doi: 10.1109/ACCESS.2020.2979859.

40.