Predictive Modeling for Healthcare Cost Analysis in the United States: A Comprehensive Review and Future Directions

Abstract

Healthcare expenditure in the United States represents the largest component of national spending, accounting for approximately 17.8% of GDP as of 2024. The complexity and volatility of healthcare costs necessitate sophisticated predictive modeling approaches to enable effective resource allocation, policy planning, and cost containment strategies. This comprehensive review examines the current state of predictive modeling for healthcare cost analysis in the United States, evaluating methodological approaches, data sources, challenges, and emerging trends. We analyze various machine learning and statistical techniques employed in healthcare cost prediction, their effectiveness across different patient populations and healthcare settings, and provide recommendations for future research directions. Our analysis reveals that ensemble methods and deep learning approaches show the most promise for accurate cost prediction, while highlighting the critical importance of data quality, feature engineering, and model interpretability in healthcare applications.