A Comprehensive Review and Evaluation Framework for Explainable Healthcare Insurance Fraud Detection Models

• Author(s): Shravya Caroline Pallat; Prof. Rakshitha B S
• Paper ID: 1717969
• Page: 2542-2550
• Published Date: 19-05-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 11 May-2026

Abstract

Healthcare insurance fraud poses a significant challenge to healthcare systems worldwide, resulting in substantial financial losses and inefficiencies. Traditional detection methods have proven inadequate in handling large-scale and complex fraud patterns, leading to the adoption of machine learning and deep learning techniques. Existing studies have focused primarily on improving detection accuracy using various models such as random forests, neural networks, and hybrid approaches. While these techniques demonstrate strong predictive performance, they often operate as black-box systems and lack transparency. Additionally, there is limited comparative analysis of explainability techniques across models. This study identifies a critical research gap in the lack of auditor-centric explainability and absence of frameworks that balance accuracy with interpretability. To address this, the paper proposes an evaluation framework that assesses multiple fraud detection models based on both performance metrics and interpretability criteria. The proposed approach involves applying selected models to healthcare datasets, analyzing their predictions using explainability techniques, and comparing them based on usability for real-world auditing. The expected outcomes include identifying models that provide both accurate and interpretable results. This research contributes by providing a structured literature review, identifying key gaps, and proposing a practical evaluation framework to enhance transparency and decision-making in healthcare fraud detection systems.

Keywords

Healthcare Fraud Detection, Machine Learning, Explainable AI, Interpretability, Fraud Detection Models, Healthcare Analytics

Citations

IRE Journals:
Shravya Caroline Pallat, Prof. Rakshitha B S "A Comprehensive Review and Evaluation Framework for Explainable Healthcare Insurance Fraud Detection Models" Iconic Research And Engineering Journals Volume 9 Issue 11 2026 Page 2542-2550 https://doi.org/10.64388/IREV9I11-1717969

IEEE:
Shravya Caroline Pallat, Prof. Rakshitha B S "A Comprehensive Review and Evaluation Framework for Explainable Healthcare Insurance Fraud Detection Models" Iconic Research And Engineering Journals, 9(11) https://doi.org/10.64388/IREV9I11-1717969