Abstract
Objective: The aim of this study is to identify the main predictors associated with countries’ health status and to classify countries based on these variables using the decision tree method.
Methods: This study employed a quantitative, cross-sectional research methodology based on secondary data to identify the main predictors associated with countries’ health status and to classify countries according to these variables using a decision tree approach. The study covered 224 countries for which World Bank data were available for 2022 or for a period of up to 5 years preceding 2022. The research data were obtained from the World Bank database in January 2025. Life expectancy at birth was used as the dependent variable, while the independent variables included alcohol and tobacco consumption, unemployment rate, Gini coefficient, rural population ratio, dependent population ratio, annual PM2.5 exposure level, number of hospital beds, number of physicians and nurses, and health expenditure. A decision tree model was developed using the Classification and Regression Trees (CART) algorithm to identify the key predictors of life expectancy and examine their relative importance in explaining differences in health status across countries. The analysis was conducted using the Orange Data Mining software package.
Results: In the study, various key predictors of health status were identified, including health expenditures, the number of hospital beds, the availability of nurses, the dependency ratio, the unemployment rate, and the rural population ratio. A decision tree model was used. Using the CART algorithm, it was found that the model’s classification accuracy was 80.80%, while the precision rate for health status prediction was 81.38%. These findings highlight the key factors affecting health outcomes and demonstrate the model’s effectiveness in classifying countries based on these variables.
Conclusion: The study revealed that per capita healthcare expenditure is the most important predictor of health status. Future research should also take additional variables into account. This will help to provide a more comprehensive understanding of the factors affecting health outcomes.
Cite this article as: Kaya M. Analysis of risk factors affecting countries’ health status using the decision tree method. Arch Health Sci Res. 2026, 13, 0075, doi: 10.5152/ArcHealthSciRes.2026.26075.