Healthcare expenditures in Australia have grown steadily in recent years, intensifying fiscal pressures and exposing challenges related to unequal resource distribution. While traditional statistical methods struggle to capture complex data relationships, machine learning offers a more robust approach to handling intricate and non-linear data. This study employs machine learning techniques to investigate the key determinants of healthcare expenditures in Australia from 2011 to 2021. Using advanced models, including Random Forest, XGBoost, and Multi-Layer Perceptron (MLP), along with SHAP (SHapley Additive exPlanations) analysis, we identify the most influential factors driving healthcare spending. The results reveal that funding sources, public hospital services, and geographic disparities are the primary predictors of expenditure trends. Notably, funding allocation mechanisms and regional inequities emerge as critical influences on spending patterns. By integrating feature importance metrics with SHAP analysis, this study enhances model interpretability and offers actionable insights for policymakers. The findings underscore the urgent need to optimize resource allocation and address regional disparities to promote the sustainability and equity of Australia’s healthcare system.