An AI and machine learning framework integrating XGBoost and ARIMA models achieved 92% prediction accuracy, reduced billing disparities by 70%, and improved administrative efficiency by 47%.
An AI and machine learning-driven framework can significantly improve healthcare pricing transparency, prediction accuracy, and administrative efficiency.
This paper introduces an advanced framework for healthcare pricing transparency by leveraging cutting-edge artificial intelligence (AI), machine learning (ML), and robust cloud computing infrastructure. The proposed model integrates diverse datasets, including historical claims, provider costs, and patient demographics, to enable precise cost prediction, reduce billing disparities by 70%, and improve administrative efficiency by 47%. A combination of XGBoost and ARIMA models achieved 92% prediction accuracy, supported by federated learning for privacy-preserving analytics and real-time predictive modeling. The framework empowers stakeholders with actionable insights, fosters trust across the healthcare ecosystem, and establishes a scalable, regulation-compliant solution for addressing the challenges of pricing opacity in the U.S. healthcare system.
Santhosh Kumar Pendyala (Tue,) conducted a other in Healthcare pricing opacity (n=50). AI and ML-driven framework (XGBoost and ARIMA) vs. Traditional pricing methods was evaluated on Prediction accuracy. An AI and machine learning framework integrating XGBoost and ARIMA models achieved 92% prediction accuracy, reduced billing disparities by 70%, and improved administrative efficiency by 47%.