Assessing the Effects on General Government Health Expenditures With Machine Learning-Based Causality Analysis

This study uses machine learning-based causal analysis to analyze the relationship between government health spending and socioeconomic characteristics. The research aims to enhance public health and promote economic stability by allocating significant resources to healthcare. Conventional forecasting techniques may struggle to identify complex causal relationships within health data. Machine learning models like causal forest offer a robust analytical tool for understanding health spending dynamics. Data from developed countries between 1970 and 2021 is used, focusing on factors such as cigarette and alcohol use, net savings, average life expectancy, and rates of drug, alcohol, and suicide deaths. The results show that healthcare spending is significantly influenced by life expectancy and income level, while other factors vary based on regional and demographic variations. The study provides valuable insights for policymakers to develop data-driven, equitable health interventions that address specific needs across diverse populations.