Outlier detection in healthcare fraud: A case study in the Medicaid dental domain

• Published in: International journal of accounting information systems Vol. 21; pp. 18 - 31
• Main Authors: van Capelleveen, Guido, Poel, Mannes, Mueller, Roland M., Thornton, Dallas, van Hillegersberg, Jos
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 01.06.2016; Elsevier Science Publishing Company, Inc
• Subjects: Algorithms; Automation; Decision support; Dental care; Fraud; Insurance claims; Insurance fraud; Medicaid; Medical fraud detection; Outlier detection; Studies; Outlier detection; Medical fraud detection; Decision support
• ISSN: 1467-0895; 1873-4723
• DOI: 10.1016/j.accinf.2016.04.001

Health care insurance fraud is a pressing problem, causing substantial and increasing costs in medical insurance programs. Due to large amounts of claims submitted, estimated at 5 billion per day, review of individual claims or providers is a difficult task. This encourages the employment of automated pre-payment controls and better post-payment decision support tools to enable subject matter expert analysis. This paper presents how to apply unsupervised outlier techniques at post-payment stage to detect fraudulent patterns of received insurance claims. A special emphasis in this paper is put on the system architecture, the metrics designed for outlier detection and the flagging of suspicious providers which may support the fraud experts in evaluating providers and reveal fraud. The algorithms were tested on Medicaid data encompassing 650,000 health-care claims and 369 dentists of one state. Two health care fraud experts evaluated flagged cases and concluded that 12 of the top 17 providers (71%) submitted suspicious claim patterns and should be referred to officials for further investigation. The remaining 5 providers (29%) could be considered mis-classifications as their patterns could be explained by special characteristics of the provider. Selecting top flagged providers is demonstrated to be a valuable as an targeting method, and individual provider analysis revealed some cases of potential fraud. The study concludes that, through outlier detection, new patterns of potential fraud can be identified and possibly utilized in future automated detection mechanisms. •A case study of fraud analysis using was performed on Medicaid claims of 369 primary dental providers of one state•Examples of strong cases of potential fraud schemes detected are presented and discussed•Outlier detection can be utilized in automatic detection systems and may identify new patterns of potential healthcare fraud•Healthcare subject matter expertise or claim documentation remain important when classifying claim patterns as fraudulent