Detecting medical prescriptions suspected of fraud using an unsupervised data mining algorithm
- 117 Downloads
Nowadays, health insurance companies face various types of fraud, like phantom billing, up-coding, and identity theft. Detecting such frauds is thus of vital importance to reduce and eliminate corresponding financial losses. We used an unsupervised data mining algorithm and implemented an outlier detection model to assist the experts in detecting medical prescriptions suspected of fraud. The implementation ran medicine code, patients’ sex, and patients’ age variables through three successive screening steps. The proposed model is capable of detecting 25% to 100% of cases violating the standards for some medicines that are not supposed to be prescribed at the same time in one single prescription. This model can also detect medical prescriptions suspected of fraud with a sensitivity of 62.16%, specificity of 55.11%, and accuracy of 57.2%. This paper shows that data mining can help detecting potential fraud cases in medical prescriptions more quickly and accurately than by the manual inspection as well as reducing the number of medical prescriptions to be checked which will result in reducing investigators heavy workload. The results of the proposed model can also help policymakers to plan for fighting against fraudulent activities.
KeywordsFraud Unsupervised data mining Medical prescription Medical insurance
- 2.Aral KD. Prescription Fraud detection via data mining: a methodology proposal. Ankara: Bilkent University; 2009.Google Scholar
- 3.Li J, Huang K-Y, Jin J, Shi J. A survey on statistical methods for health care fraud detection. Health care management science. Springer 2008;11(3):275–287.Google Scholar
- 4.Medical Fraud Detection Through Data Mining. 2002. Megaputer intelligence.Google Scholar
- 5.Aral KD, Güvenir HA, Sabuncuoğlu İ, Akar AR. A prescription fraud detection model. Computer methods and programs in biomedicine. Elsevier 2012;106(1):37–46.Google Scholar
- 6.Copeland L, Edberg D, Panorska AK, Wendel J. Applying business intelligence concepts to Medicaid claim fraud detection. J Inf Syst Appl Res 2012;5(1):51.Google Scholar
- 9.Yoo I, Alafaireet P, Marinov M, Pena-Hernandez K, Gopidi R, Chang J-F, Hua L. Data mining in healthcare and biomedicine: a survey of the literature. Journal of medical systems. Springer 2012;36 (4):2431–2448.Google Scholar
- 10.Tan PN, Steinbach M, Kumar V. Introduction to Data Mining: Pearson Education. India: Chapter. 9; 2007, p. 624.Google Scholar
- 11.Han J, Pei J, Kamber M. Data mining: concepts and techniques. New York: Elsevier; 2011.Google Scholar
- 12.Olson DL, Delen D. Advanced data mining techniques. Berlin: Springer Science & Business Media; 2008.Google Scholar
- 13.Drug Interactions. Available from: https://online.lexi.com/lco/action/interact.
- 14.Same Classes Drugs Error in Single Prescription. Available from: https://www.drugs.com/.
- 15.Vihinen M. How to evaluate performance of prediction methods measures and their interpretation in variation effect analysis. BMC genomics. BioMed Central 2012;13(4):S2.Google Scholar