KFU. Card publication. Assessment of healthy life years factors across European countries based on neural networks analysis.

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

ASSESSMENT OF HEALTHY LIFE YEARS FACTORS ACROSS EUROPEAN COUNTRIES BASED ON NEURAL NETWORKS ANALYSIS.

Form of presentation

Articles in international journals and collections

Year of publication

2025

��

��

Authors, employees of KFU

Kirshin Igor Aleksandrovich, author

Bibliographic description in the original language

Kirshin I. Assessment of healthy life years factors across European countries based on neural networks analysis. International Journal of Computational Economics and Econometrics. 2025. Vol.15. No.4. pp. 333-367. DOI:10.1504/IJCEE.2025.150005

Annotation

The objective of this paper is to identify, test and evaluate the influence of health and disability factors on the healthy life years. Panel data from the Eurostat European Health Survey and Health Statistics covering 31 European countries from 2011 to 2022 were used to examine how healthy life years are associated with health and disability factors. A cross-country multiple regression analysis with dummy variables for the COVID-19 period was performed using the multiple linear regression model and the multilayer perceptron neural network in two versions: regression and time series (regression). The results obtained convincingly confirm the proposed hypothesis: healthy life years were significantly associated with self-assessed disability level and self-assessed long-term limitations in usual activities due to health problems, and to a lesser extent with share of people with good or very good perceived health and people with long-term diseases or health problems. Global sensitivity analysis showed that all networks determine the level of disability variable to be the most important. To test the robustness of the model, the random forest model was applied. The identified factors can be used as significant predictors of healthy life years assessment for European countries population.

Keywords

healthy life years; time series analysis and forecasting; multiple linear regression analysis; neural networks; global sensitivity analysis; health inequalities; self-reported health

The name of the journal

International Journal of Computational Economics and Econometrics

URL

https://www.inderscience.com/info/inarticle.php?artid=150005

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=320267&p_lang=2

Resource files

File name	Size (MB)	Format
F_Article_Final_3.pdf	1,57	pdf	show / download

Full metadata record

Field DC	Value	Language
dc.contributor.author	Kirshin Igor Aleksandrovich	ru_RU
dc.date.accessioned	2025-01-01T00:00:00Z	ru_RU
dc.date.available	2025-01-01T00:00:00Z	ru_RU
dc.date.issued	2025	ru_RU
dc.identifier.citation	Kirshin I. Assessment of healthy life years factors across European countries based on neural networks analysis. International Journal of Computational Economics and Econometrics. 2025. Vol.15. No.4. pp. 333-367. DOI:10.1504/IJCEE.2025.150005	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=320267&p_lang=2	ru_RU
dc.description.abstract	International Journal of Computational Economics and Econometrics	ru_RU
dc.description.abstract	The objective of this paper is to identify, test and evaluate the influence of health and disability factors on the healthy life years. Panel data from the Eurostat European Health Survey and Health Statistics covering 31 European countries from 2011 to 2022 were used to examine how healthy life years are associated with health and disability factors. A cross-country multiple regression analysis with dummy variables for the COVID-19 period was performed using the multiple linear regression model and the multilayer perceptron neural network in two versions: regression and time series (regression). The results obtained convincingly confirm the proposed hypothesis: healthy life years were significantly associated with self-assessed disability level and self-assessed long-term limitations in usual activities due to health problems, and to a lesser extent with share of people with good or very good perceived health and people with long-term diseases or health problems. Global sensitivity analysis showed that all networks determine the level of disability variable to be the most important. To test the robustness of the model, the random forest model was applied. The identified factors can be used as significant predictors of healthy life years assessment for European countries population.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject		ru_RU
dc.title	Assessment of healthy life years factors across European countries based on neural networks analysis.	ru_RU
dc.type	Articles in international journals and collections	ru_RU