Detecting Healthcare Fraud through Patient Sharing Schemes

Abstract

The United States loses at least $60 billion in health-care fraud every year, and some estimates put the cost as high as 10% of the nation’s total health-care spending, which exceeds $2 trillion. The federal government is putting tremendous efforts in combating health frauds and safeguard the two largest government sponsored programs: Medicare and Medicaid. Using data analysis techniques to discover and prevent health care frauds is an important focus in all of the efforts. In this paper, we propose a new method for identifying patient sharing schemes that are prevalent in many parts of this country. Our proposed method is based on the PageRank algorithm that has been used by Google’s Web search engine. We describe our approach, discuss the similarities and differences with PageRank, and demonstrate the applicability of this method by applying it to datasets simulated from real-life scenarios.