Assessment of healthy life years factors across European countries based on neural networks analysis

Igor Kirshin

International Journal of Computational Economics and Econometrics, 2025, vol. 15, issue 4, 333-367

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.

Keywords: healthy life years; time series analysis and forecasting; multiple linear regression analysis; neural networks; global sensitivity analysis; health inequalities; self-reported health. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=150005 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijcome:v:15:y:2025:i:4:p:333-367

Access Statistics for this article

More articles in International Journal of Computational Economics and Econometrics from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().