Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data

Dallas Thornton, Guido van Capelleveen, Mannes Poel, Jos van Hillegersberg, Roland M. Mueller

2014

Abstract

Fraud, waste, and abuse in the U.S. healthcare system are estimated at $700 billion annually. Predictive analytics offers government and private payers the opportunity to identify and prevent or recover such billings. This paper proposes a data-driven method for fraud detection based on comparative research, fraud cases, and literature review. Unsupervised data mining techniques such as outlier detection are suggested as effective predictors for fraud. Based on a multi-dimensional data model developed for Medicaid claim data, specific metrics for dental providers were developed and evaluated in analytical experiments using outlier detection applied to claim, provider, and patient data in a state Medicaid program. The proposed methodology enabled successful identification of fraudulent activity, with 12 of the top 17 suspicious providers (71%) referred to officials for investigation with clearly anomalous and inappropriate activity. Future research is underway to extend the method to other specialties and enable its use by fraud analysts.

References

  1. Aggarwal, C. C., 2013. Outlier analysis, New York: Springer.
  2. Aral, K. D. et al., 2012. A prescription fraud detection model. Computer Methods and Programs in Biomedicine, 106(1), pp.37-46.
  3. Bolton, R. J. & Hand, D. J., 2002. Statistical fraud detection: A review. Statistical Science, 17(3), pp.235-255.
  4. Colin, C. et al., 1994. Data quality in a DRG-based information system. International Journal for Quality in Health Care, 6(3), pp.275-280.
  5. Department of Health and Human Services, 1998. Medicare A/B Reference Manual - Chapter 21 - Benefit Integrity and Program Safeguard Contractors. Available at: https://http://www.novitas- solutions. com/refman/chapter-21.html [Accessed February 21, 2013].
  6. District of New Jersey U.S. Attorneys Office, 2013. South Jersey Doctor Admits Making Half-a-Million Dollars in Fraud Scheme Involving Home Health Care for Elderly Patients. Available at: http://www.fbi.gov/ newark/press-releases/2013/south-jersey-doctoradmits-making-half-a-million-dollars-in-fraudscheme-involving-home-health-care-for-elderlypatients [Accessed March 28, 2013].
  7. District of Texas U.S. Attorneys Office, 2013. Physician Pleads Guilty to Role in Health Care Fraud Conspiracy. Available at: http://www.fbi.gov/dallas/ press-releases/2013/physician-pleads-guilty-to-role-inhealth-care-fraud-conspiracy [Accessed March 1, 2013].
  8. Forgionne, G. A., Gangopadhyay, A. & Adya, M., 2000. An intelligent data mining system to detect healthcare fraud. In Healthcare information systems: challenges of the new millennium. Hershey PA: IGI Global, pp. 148-169.
  9. Hernández, M. A. & Stolfo, S. J., 1998. Real-world data is dirty: Data cleansing and the merge/purge problem. Data mining and knowledge discovery, 2(1), pp.9-37.
  10. Hevner, A. R. et al., 2004. Design Science in Information Systems Research. MIS Quarterly, 28(1), pp.75-105.
  11. Iyengar, V. S., Hermiz, K. B. & Natarajan, R., 2013. Computer-aided auditing of prescription drug claims. Health Care Management Science, (July), pp.1-12.
  12. Kelley, R. R., 2009. Where can $700 billion in waste be cut annually from the US healthcare system? Ann Arbor, MI: Thomson Reuters, TR-7261 10/09 LW.
  13. Lu, F. & Boritz, J. E., 2005. Detecting fraud in health insurance data: Learning to model incomplete Benford's law distributions. In Machine Learning: ECML 2005. Springer, pp. 633-640.
  14. Major, J. A. & Riedinger, D. R., 2002. EFD: A Hybrid Knowledge/Statistical-Based System for the Detection of Fraud. Journal of Risk and Insurance, 69(3), pp.309-324.
  15. Musal, R. M., 2010. Two models to investigate Medicare fraud within unsupervised databases. Expert Systems with Applications, 37(12), pp.8628-8633.
  16. Ng, K. S. et al., 2010. Detecting Non-compliant Consumers in Spatio-Temporal Health Data: A Case Study from Medicare Australia. In Data Mining Workshops (ICDMW), 2010 IEEE International Conference on. pp. 613-622.
  17. Ortega, P. A., Figueroa, C. J. & Ruz, G. A., 2006. A Medical Claim Fraud/Abuse Detection System based on Data Mining: A Case Study in Chile. In Proceedings of the 2006 International Conference on Data Mining. DMIN. Las Vegas, Nevada, USA: CSREA Press, pp. 224-231.
  18. Phua, C. et al., 2010. A comprehensive survey of data mining-based fraud detection research. arXiv preprint arXiv:1009.6119.
  19. Rousseeuw, P. J. & van Zomeren, B. C., 1990. Unmasking Multivariate Outliers and Leverage Points. Journal of the American Statistical Association, 85(411), pp.633- 639.
  20. Shan, Y. et al., 2008. Mining Medical Specialist Billing Patterns for Health Service Management. In Proceedings of the 7th Australasian Data Mining Conference - Volume 87. AusDM 7808. Darlinghurst, Australia, Australia: Australian Computer Society, Inc., pp. 105-110.
  21. Shin, H. et al., 2012. A scoring model to detect abusive billing patterns in health insurance claims. Expert Systems with Applications, 39(8), pp.7441-7450.
  22. Sparrow, M. K., 2000. License To Steal: How Fraud bleeds america's health care system Updated., Boulder: Westview Press.
  23. Tang, M. et al., 2011. Unsupervised fraud detection in Medicare Australia. In Proceedings of the Ninth Australasian Data Mining Conference-Volume 121. pp. 103-110.
  24. Thornton, D. et al., 2013. Predicting Healthcare Fraud in Medicaid: A Multidimensional Data Model and Analysis Techniques for Fraud Detection. Procedia Technology, 9, pp.1252-1264.
  25. Travaille, P. et al., 2011. Electronic Fraud Detection in the US Medicaid Healthcare Program: Lessons Learned from other Industries.
  26. U.S. Federal Bureau of Investigation, 2013. FBI news blog. Available at: http://www.fbi.gov/news/ news_blog [Accessed April 18, 2013].
  27. U.S. Government Accountability Office, 2012. Medicare Fraud Prevention: CMS has Implemented a Predictive Analytics System, but Needs to Define Measures to Determine its Effectiveness. Available at: http://www.gao.gov/products/GAO-13-104 [Accessed March 28, 2013].
  28. Weng, X. & Shen, J., 2008. Detecting outlier samples in multivariate time series dataset. Knowledge-Based Systems, 21(8), pp.807-812.
  29. Yamanishi, K. et al., 2004. On-line unsupervised outlier detection using finite mixtures with discounting learning algorithms. Data Mining and Knowledge Discovery, 8(3), pp.275-300.
  30. Yang, W.-S. & Hwang, S.-Y., 2006. A process-mining framework for the detection of healthcare fraud and abuse. Expert Systems with Applications, 31(1), pp.56-68.
Download


Paper Citation


in Harvard Style

Thornton D., van Capelleveen G., Poel M., van Hillegersberg J. and Mueller R. (2014). Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data . In Proceedings of the 16th International Conference on Enterprise Information Systems - Volume 2: ISS, (ICEIS 2014) ISBN 978-989-758-028-4, pages 684-694. DOI: 10.5220/0004986106840694


in Bibtex Style

@conference{iss14,
author={Dallas Thornton and Guido van Capelleveen and Mannes Poel and Jos van Hillegersberg and Roland M. Mueller},
title={Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data},
booktitle={Proceedings of the 16th International Conference on Enterprise Information Systems - Volume 2: ISS, (ICEIS 2014)},
year={2014},
pages={684-694},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004986106840694},
isbn={978-989-758-028-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 16th International Conference on Enterprise Information Systems - Volume 2: ISS, (ICEIS 2014)
TI - Outlier-based Health Insurance Fraud Detection for U.S. Medicaid Data
SN - 978-989-758-028-4
AU - Thornton D.
AU - van Capelleveen G.
AU - Poel M.
AU - van Hillegersberg J.
AU - Mueller R.
PY - 2014
SP - 684
EP - 694
DO - 10.5220/0004986106840694