Abstract

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.
Original languageEnglish
Pages (from-to)18-31
Number of pages14
JournalInternational journal of accounting information systems
Volume21
DOIs
StatePublished - Jun 2016
Event16th International Conference on Enterprise Information Systems, ICEIS 2014 - Lisbon, Portugal

Fingerprint

Insurance
Health care
Fraud
Health insurance
Costs
Medicaid
Encompassing
Outliers

Keywords

  • METIS-316639
  • Decision support
  • Outlier Detection
  • EWI-26992
  • IR-100380
  • Medical fraud detection

Cite this

@article{34d99e687e7d41268bf7b0389e0f7be8,
title = "Outlier detection in healthcare fraud: A case study in the Medicaid dental domain",
abstract = "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.",
keywords = "METIS-316639, Decision support, Outlier Detection, EWI-26992, IR-100380, Medical fraud detection",
author = "{van Capelleveen}, {Guido Cornelis} and Mannes Poel and Roland Mueller and Dallas Thornton and {van Hillegersberg}, Jos",
note = "eemcs-eprint-26992",
year = "2016",
month = "6",
doi = "10.1016/j.accinf.2016.04.001",
volume = "21",
pages = "18--31",
journal = "International journal of accounting information systems",
issn = "1467-0895",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Outlier detection in healthcare fraud: A case study in the Medicaid dental domain

AU - van Capelleveen,Guido Cornelis

AU - Poel,Mannes

AU - Mueller,Roland

AU - Thornton,Dallas

AU - van Hillegersberg,Jos

N1 - eemcs-eprint-26992

PY - 2016/6

Y1 - 2016/6

N2 - 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.

AB - 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.

KW - METIS-316639

KW - Decision support

KW - Outlier Detection

KW - EWI-26992

KW - IR-100380

KW - Medical fraud detection

U2 - 10.1016/j.accinf.2016.04.001

DO - 10.1016/j.accinf.2016.04.001

M3 - Article

VL - 21

SP - 18

EP - 31

JO - International journal of accounting information systems

T2 - International journal of accounting information systems

JF - International journal of accounting information systems

SN - 1467-0895

ER -