Higher Self-Reported Mental Health Predicts Better Perceived Physical Health in Aging Adults

Aging is a global phenomenon that has driven interest in successful aging (SA), characterized by optimal physical, psychological, and social functioning without major disabilities. This study leveraged Machine Learning (ML) models to predict factors influencing SA using self-reported physical health data from the University of Michigan’s 2022 Wave 10 National Poll on Healthy Aging (n = 2,277). ``Logistic Regression (LR), Decision Tree (DT), and Random Forest (RF) models were evaluated, with LR achieving the highest accuracy (77.7%) and F1 score (78.2%). LR identified significant predictors of physical health outcomes, demonstrating a moderate positive correlation (r = 0.29) between physical and mental health, especially in individuals with “Very good” and “Fair” mental health ratings. These findings underscore the critical role of mental well-being in SA and highlight the potential of ML models to enhance healthcare strategies by identifying key health interdependencies.