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

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.

[1]  James W. Henderson,et al.  Health Economics and Policy , 1998 .

[2]  John A. Major,et al.  EFD: A Hybrid Knowledge/Statistical-Based System for the Detection of Fraud , 2002 .

[3]  B. Minaei-Bidgoli,et al.  Using Data Mining to Detect Health Care Fraud and Abuse: A Review of Literature , 2014, Global journal of health science.

[4]  Izak Benbasat,et al.  The Case Research Strategy in Studies of Information Systems , 1987, MIS Q..

[5]  Jos van Hillegersberg,et al.  Electronic Fraud Detection in the U.S. Medicaid Healthcare Program: Lessons Learned from other Industries , 2011, AMCIS.

[6]  Yin Shan,et al.  Mining Medical Specialist Billing Patterns for Health Service Management , 2008, AusDM.

[7]  Pedro A. Ortega,et al.  A Medical Claim Fraud/Abuse Detection System based on Data Mining: A Case Study in Chile , 2006, DMIN.

[8]  Ihsan Sabuncuoglu,et al.  A prescription fraud detection model , 2012, Comput. Methods Programs Biomed..

[9]  Hyunjung Shin,et al.  A scoring model to detect abusive billing patterns in health insurance claims , 2012, Expert Syst. Appl..

[10]  Charu C. Aggarwal,et al.  Outlier Analysis , 2013, Springer New York.

[11]  Rommel N. Carvalho,et al.  Analyzing Suspicious Medical Visit Claims from Individual Healthcare Service Providers Using K-Means Clustering , 2015, EGOVIS.

[12]  Kee Siong Ng,et al.  Detecting Non-compliant Consumers in Spatio-Temporal Health Data: A Case Study from Medicare Australia , 2010, 2010 IEEE International Conference on Data Mining Workshops.

[13]  William N. Dilla,et al.  Data visualization for fraud detection: Practice implications and a call for future research , 2015, Int. J. Account. Inf. Syst..

[14]  Graham J. Williams,et al.  On-Line Unsupervised Outlier Detection Using Finite Mixtures with Discounting Learning Algorithms , 2000, KDD '00.

[15]  Jos van Hillegersberg,et al.  Predicting Healthcare Fraud in Medicaid: A Multidimensional Data Model and Analysis Techniques for Fraud Detection , 2013 .

[16]  L. Weiss.  License to Steal: How Fraud Bleeds America's Health Care System , 2001 .

[17]  MingJian Tang,et al.  Unsupervised Fraud Detection in Medicare Australia , 2011, AusDM.

[18]  Jos van Hillegersberg,et al.  Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data , 2014, ICEIS.

[19]  Vijay S. Iyengar,et al.  Computer-aided auditing of prescription drug claims , 2014, Health care management science.

[20]  Jionghua Jin,et al.  A survey on statistical methods for health care fraud detection , 2008, Health care management science.

[21]  R. Yin.  Case Study Research: Design and Methods , 1984 .

[22]  Fletcher Lu,et al.  Detecting Fraud in Health Insurance Data: Learning to Model Incomplete Benford's Law Distributions , 2005, ECML.

[23]  Rasim Muzaffer Musal.  Two models to investigate Medicare fraud within unsupervised databases , 2010, Expert Syst. Appl..

[24]  P. Rousseeuw,et al.  Unmasking Multivariate Outliers and Leverage Points , 1990 .

[25]  G. Forgionne,et al.  An intelligent data mining system to detect healthcare fraud , 2000 .

[26]  David J. Hand,et al.  Statistical fraud detection: A review , 2002 .

[27]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[28]  San-Yih Hwang,et al.  A process-mining framework for the detection of healthcare fraud and abuse , 2006, Expert Syst. Appl..