Machine Learning Methods for Predicting Life Expectancy

Forecasting of life expectancy is associated not only with serious social and financial factors, but also with the state of public health and economy, as well as with the state of the environment. The use of mathematical methods makes it possible to identify the most informative indicators affecting life expectancy. The aim of the paper is to predict life expectancy from World Bank data using machine learning (ML) methods, and to compare the effectiveness of life expectancy prediction using different machine learning algorithms, including such widely used methods as support vector method, decision tree, random forest, Fisher’s linear discriminant, neural networks, two variants of gradient bousting, logistic regression and statistically weighted syndrome method. The database included data for 238 countries. Standard non-parametric chi-square (χ²) and Mann-Whitney criteria (U-test) were applied. Eleven significant indicators were identified. Machine learning (ML) methods of Data Master Azforus data analysis system was used. The prediction result of the statistically weighted syndrome (SWS) method achieved a ROC AUC = 0.986. One-dimensional and two-dimensional diagrams of the relationship between the studied socio-economic and medical indicators on life expectancy are presented. From these charts, predictions can be derived for changes in individual indicators to improve quality and length of life. Thus, the Data Master Azforus data analysis system will enable researchers to create recommendation systems for life expectancy prediction. In addition, the conducted research will help to create a more advanced forecasting system using machine learning models that can serve as a guide for politicians makers in improving life expectancy forecasting.

1. Kukkoev S. P. Modeling of life expectancy in the Russian Federation. Bulletin of the National Scientific Research Institute of Public Health named after N.A. Semashko. 2018;1:29–37. URL: https://nriph.ru/images/assets/files/archive/2018/2018-1.pdf#page=29 (In Russ.).

2. Stepanov V.S., Bobkov V.N., Shamaeva E.F., Odintsovo E.V. Building a model linking the indicator of the standard of living of the population with a set of indicators of socio-economic policy in the regions of Russia. The standard of living of the population of the Russian regions. 2022;18(4):450–465. (In Russ.). DOI: 10.19181/lsprr.2022.18.4.3

3. Kudelina O.V., Kaneva M.A. The choice of health capital indicator in Russian regions. Human ecology. 2020;9:18–27. (In Russ.). DOI: 10.33396/1728-0869-2020-9-18-27

4. Stepanov V.S. Forecast of cancer prevalence among residents of the Moscow region based on a regression model. Modeling, optimization, and information technology. 2024;12(3). (In Russ.). DOI: 10.26102/2310-6018/2024.46.3.023

5. SK Khader Basha S. K., et al. Machine learning method for life expectancy prediction. Mukt Shabd Journal. 2022;9(6):140–145. URL: https://www.researchgate.net/publication/378874579_MACHINE_LEARNING_METHOD_FOR_LIFE_EXPECTANCY_PREDICTION

6. Bergeron Boucher V.-P., Strozza C., Simonacci Y., Oeppen J. Modeling and Forecasting Healthy Life Expectancy with Compositional Data Analysis Demography. 2025;62(3):787–810. DOI: 10.1215/00703370-11974712

7. Aburto J. M., Schöley J., Kashnitsky I., Zhang L., et al. Quantifying impacts of the COVID-19 pandemic through life-expectancy losses: a population-level study of 29 countries. Int. J. Epidemiol. 2022;51(1):63–74. DOI: 10.1101/2021.03.02.21252772

8. Borisova L., Zhukova G., Kuznetsova A., Martin J. Features of machine learning in the study of the main factors of development of countries of the world. SHS Web of Conferences. 2021;110(5):02006. DOI: 10.1051/shsconf/202111002006

9. Kirilyuk I.L., Volynsky A.I., Kruglova M.S., Kuznetsova A.V., Rubinstein A.A., Senko O.V. Empirical verification of the theory of institutional matrices by data mining methods. Computer research and modeling. 2015;7(4):923–939. (In Russ.). DOI: 10.20537/2076-7633-2015-7-4-923-939

10. Borisova L. R., Kuznetsova A.V., Aleshchenko A.V., Kirilyuk I. L. Dependence of quantitative indicators of the standard of living of the population on the economic structure of the country. New technologies of higher education. Science. Technic. Pedagogy. Proceedings of the conference. Moscow: Moskovsky Polytech; 2021:127– 132. URL: https://www.elibrary.ru/ublkvx (In Russ.).

11. Kuznetsova A.V., Borisova L. R., Demina I.A. Machine learning methods for predicting the course of the disease using the example of the development of severe pneumonia. Digital solutions and artificial intelligence technologies. 2025;1(1):6–19. (In Russ.).

12. Borisova L. R., Kuznetsova A.V. Using a working computer simulator Data Master Azforus for teaching machine learning methods. Digital transformation of social and economic systems. Proceedings of the International Scientific and Practical Conference; January 28, 2022; Moscow: Witte Moscow University; 2022:264–270. URL: https://www.elibrary.ru/ohcndx (In Russ.).