Global Patterns and Inequalities in Healthy Aging: A Multidimensional Analysis Using Composite Index and Explainable AI

Background: Population aging is a global phenomenon with significant implications for public health systems. Understanding the multidimensional determinants of healthy aging is essential for developing effective and equitable policies across countries. Methods: This study develops a composite Healthy Ageing and Prevention Index (HAPI) to assess global healthy aging patterns using indicators of life span, health span, work span, income, environmental performance, and happiness. Missing data are addressed using Multiple Imputation by Chained Equations (MICE). Principal Component Analysis (PCA) is employed to construct the composite index, while entropy weighting determines the relative contribution of each dimension. K-means clustering is applied to group countries with similar healthy aging profiles. To improve interpretability, SHapley Additive exPlanations (SHAP) are used to quantify the contribution of each variable. Inequality in healthy aging outcomes is assessed using the Gini coefficient and Lorenz curve. Results: The findings indicate that life span, health span, income, environmental performance, and happiness are the primary drivers of healthy aging, while work span has a relatively limited contribution. Cluster analysis reveals substantial heterogeneity in healthy aging patterns across countries. Inequality analysis shows moderate but notable disparities in HAPI scores (Gini = 0.318), suggesting uneven distribution of healthy aging outcomes globally. Conclusion: Healthy aging is a multidimensional construct shaped largely by socio-economic and environmental determinants rather than healthcare factors alone. These findings highlight the need for context-specific and integrated public health strategies tailored to country clusters. The proposed framework provides a robust and interpretable tool for policymakers to evaluate and improve healthy aging outcomes at the global level.