Machine Learning-Driven Healthcare Fraud Detection: A Comprehensive Framework for Pattern Recognition and Predictive Analytics
Year: 2025
Type: article
Abstract: This article presents a comprehensive framework for detecting healthcare fraud, abuse, and waste using advanced machine learning techniques. The article introduces an integrated approach combining pattern recognition, predictive modeling, unsupervised learning, and explainable AI to enhance the detection and prevention of fraudulent healthcare claims. The methodology addresses the limitations of traditional rule-based systems by implementing deep autoencoders for anomaly detection and developing interpretable models that provide actionable insights for investigators. The results demonstrate significant improvements in detection accuracy and efficiency compared to conventional methods, while maintaining transparency through explainable AI features. The framework's effectiveness is validated through extensive testing across diverse healthcare datasets, showing robust performance in identifying suspicious patterns and predicting potential fraud cases. This article contributes to the growing body of knowledge in healthcare fraud detection by providing a scalable, interpretable, and efficient solution that can be adapted to various healthcare organizations while addressing critical challenges in data privacy and regulatory compliance.
Author: Vijaya Kumar Guntumadugu
Institution: Sri Krishnadevaraya University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4407601739