Automatic Recommender System for Smart-Contracts-based Healthcare Insurance Fraud Detection Development Platform: Design, Implementation, and Performance Evaluation (Preprint)

Abstract

BACKGROUND Healthcare insurance fraud is on the rise in many ways, such as falsifying information and hiding third-party liability. This can result in significant losses for the medical health insurance industry. Consequently, fraud detection is crucial. Currently, companies employ auditors who manually evaluate records and pinpoint fraud. However, an automated and effective method is needed to detect fraud with the continually increasing number of patients seeking health insurance. Blockchain is an emerging technology among businesses and is constantly evolving to meet their needs. With its characteristics of immutability, transparency, traceability, and smart contracts, it demonstrated its potential in the healthcare domain. In particular, smart contracts are essential to reduce the costs associated with traditional methods, which are mostly manual, while preserving privacy and building trust among healthcare stakeholders, including the patient and the health insurance networks. However, with so many blockchain options available, selecting the right one for healthcare insurance can be difficult. OBJECTIVE This paper aims to develop and implement smart contracts for detecting healthcare insurance fraud efficiently. Therefore, we provide a taxonomy of fraud scenarios and implement their detection using a blockchain platform that is suitable for healthcare insurance fraud detection. To automatically and efficiently select the best platform, we propose and implement a decision-map-based recommender system. For the aim of developing the recommender system, we propose a taxonomy of 102 blockchain platforms. METHODS We developed and implemented smart contracts for 12 fraud scenarios that we identified in the literature. We used the two top blockchain platforms selected by our proposed decision-making map-based recommender system, which is tailored for healthcare insurance fraud. In addition, we present a taxonomy of 102 blockchain platforms classified according to the application domains for which they can be used. RESULTS The developed decision-map-based recommender system demonstrates that Hyperledger Fabric is the best blockchain platform for identifying healthcare insurance fraud. We demonstrate the effectiveness of our recommender system by comparing the performance of the top two platforms selected by our system. The blockchain platforms taxonomy that we created for this revealed that 59 blockchain platforms are suitable for all application domains, 25 for financial services, and 18 for various application domains. We designed and implemented fraud detection based on smart contracts. CONCLUSIONS Our decision-map recommender system, which is based on our proposed taxonomy of 102 platforms, automatically selected the top two platforms, which are Hyperledger Fabric and Neo, for the implementation of healthcare insurance fraud detection. Our performance evaluation for the two platforms indicates that Fabric surpassed Neo in all performance metrics, as depicted by our recommender system. We provided an implementation of fraud detection based on smart contracts.