DEVELOPMENT OF AN ONLINE HOSPITAL BILLING SYSTEM ENHANCED WITH ADAPTIVE BOOSTING TECHNIQUES

Abstract

The rapid evolution of digital health infrastructure necessitates intelligent and efficient billing systems in healthcare 
environments. This study presents the design and implementation of an online hospital billing system that leverages 
the AdaBoost (Adaptive Boosting) algorithm to enhance accuracy in billing classification and fraud detection. The 
system is designed to automate billing workflows, ensure secure storage and retrieval of patient data, and generate 
real-time, error-minimized invoices. By integrating AdaBoost into the predictive analytics engine, the solution 
improves classification performance on diverse billing scenarios. Additionally, the system supports multi-user 
access for stakeholders including patients, healthcare professionals, and administrative staff while leveraging 
contemporary web frameworks and database technologies to ensure fast processing, data integrity, and regulatory 
compliance Evaluation results show that the AdaBoost-enhanced model achieved promising accuracy compared to 
traditional methods, demonstrating its suitability for real-time hospital billing automation. This project contributes to 
the broader goal of smart healthcare systems by introducing a machine learning-driven approach to hospital billing, 
promoting operational efficiency and cost transparency. This predictive capability is crucial in reducing revenue 
leakage, ensuring billing transparency, and improving operational efficiency in hospital environments. The system 
also benefits from its integration with secure databases and real-time processing features, allowing for seamless 
interactions among patients, healthcare providers, and administrative users. The predictive insights provided by 
AdaBoost not only streamline the billing process but also support data-driven decision-making in healthcare finance 
management.