Detection and Prevention of Medical Fraud using Machine Learning

Abstract

Presently, there is an upward trend in the mean life expectancy of individuals due to reductions in maternal and infant mortality, as well as deaths caused by noncommunicable diseases like cardiovascular disease. A decline in life expectancy results in a corresponding increase in health expenditures sustained by both public and private entities, including insurance providers. The healthcare sector has become an extremely comprehensive and critical industry due to the following factors: the increase in healthcare expenditures, particularly during the pandemic; the cost of each component in the healthcare sector; the increasingly chaotic healthcare technology ecosystem; the growing expectations of numerous and diverse stakeholders; and the presence of numerous and new actors in the sector. Nevertheless, this circumstance exposes the health sector to many hazards, thereby increasing its susceptibility to fraudulent activities. The sector’s substantial volume will inevitably lead to expensive fraudulent activities. For this reason, prospective medical frauds should be prevented and detected immediately. Machine learning is considered one of the most powerful and optimal approaches to prevent medical fraud. An example application is used to assess the efficacy of machine learning in the medical fraud detection context as part of the research. The objective of the proposed application is to classify provider-side medical fraud by applying various machine learning techniques and medical claims.

Keywords

• Machine Learning
• Artificial Intelligence
• Healthcare Sector
• Medical Fraud

References

1. Abdallah, A., Maarof, M.A. and Zainal, A. (2016). Fraud detection system: A survey. Journal of Network and Computer Applications, 68, 90-113., google scholar
2. Alpaydin, E. (2020). Introduction to machine learning. MIT press. google scholar
3. Altındiş, S., & Morkoç, İ. K. (2018). Sağlık hizmetlerinde büyük veri. Nigde Omer Halisdemir University Academic Review of Economics and Administrative Sciences. 11(2), 257-271. google scholar
4. Aral, K. D., Güvenir, H. A., Sabuncuoğlu, İ., & Akar, A. R. (2012). A prescription fraud detection model. Computer Methods and Programs in Biomedicine, 106(1),37-46. http://dx.doi.org/10.1016/j.cmpb.2011.09.003 google scholar
5. Arizton. (2022). Healthcare Fraud Analytics Market- Global Outlook & Forecast 2023-2028. https://www.arizton.com/market-reports/ healthcare-fraud-analytics-market google scholar
6. Avcı, M., and Teyyare, E. (2012). Sağlık sektöründe yolsuzluk: Teorik bir değerlendirme. TheInternationalJournalofEconomicandSocialResearch(IJESR) 8(2). 199-221. google scholar
7. Aydın, J. C., & Yaşar, G. (2020). Sağlık Harcamalarının Gelir Esnekliği Açısından Değerlendirilmesi: Sistematik Bir Derleme. JournalofAnkaraHealthSciences,9(1), 63-80. google scholar
8. Aydoğan Duman & Sağıroğlu, Ş. (2017, October). Heath care fraud detection methods and new approaches. 2017 International Conference on Computer Science and Engineering (UBMK) (pp. 839-844). IEEE. google scholar

9. Bauder, R. A., and Khoshgoftaar, T. M. (2016, December). A probabilistic programing approach for outlier detection in healthcare claims. 2016 15th IEEE international conference on machine learning and applications (ICMLA) (pp. 347-354). IEEE. google scholar
10. Bauder, R. A., Khoshgoftaar, T. M., Richter, A., & Herland, M. (2016, Kasım). Predicting medical provider specialties to detect anomalous insurance claims. 2016 IEEE 28th international conference on tools with artificial intelligence (ICTAI) (ss. 784-790). IEEE. google scholar
11. Belgiu, M., & Drâgu]., L. (2016). Random Forest in Remote Sensing: A review of Applications and Future Directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31. google scholar
12. Bircan, H. (2004). Lojistik regresyon analizi: Tıp verileri üzerine bir uygulama. Kocaeli University Journal of Social Sciences, (8), 185-208. google scholar
13. Branting, L. K., Reeder, F., Gold, J., & Champney, T. (2016, Ağustos). Graph analytics for healthcare fraud risk estimation. 2016 IEEE/ACM Intl Conf. on Advances in Social Networks Analysis and Mining (ASONAM) (ss. 845-851). IEEE. google scholar
14. Bolton, R. J., & Hand, D. J. (2001). Unsupervised profiling methods for fraud detection. Credit scoring and credit control VII, 235-255. google scholar
15. Bolton, R. J., & Hand, D. J. (2002). Statistical fraud detection: A review. Statistical science, 17(3), 235-255. google scholar
16. Bozhenko, V. (2022). Tackling corruption in the health sector. Health Economics and Management Review, 3, 32-39. google scholar
17. Brugman, S. (2019). pandas-profiling: exploratory data analysis for Python. https://github.com/pandas-profiling/pandas-profiling. google scholar
18. Burkov, A. (2019). Hundred-page Machine Learning Book. Quebec City, QC, Canada: Andriy Burkov. google scholar
19. Centers for Medicare and Medicaid Services (CMS). (2021). Medicare Fraud & Abuse: Prevent, Detect, Report. https://www.cms.gov/Outreach-and-Education/Medicare-Learning-Network-MLN/MLNProducts/Downloads/Fraud-Abuse-MLN4649244.pdf google scholar
20. Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACCM signed international conference on knowledge discovery and data mining (ss. 785-794). google scholar
21. Couffinhal, A., and Frankowski, A. (2017). Wasting with intention: Fraud, abuse, corruption, and other integrity violations in the health sector. google scholar
22. Dora, P. and Sekharan, G. H. (2015). Healthcare insurance fraud detection leveraging big data analytics. IJSR, 4(4), 2073-2076. google scholar
23. Ekin, T. (2019). An Integrated Decision-Making Framework for Medical Audit Sampling. google scholar
24. Ekin, T., Frigau, L., & Conversano, C. (2021). Health care fraud classifiers in practice. Applied Stochastic Models in Business and Industry, 37(6), 1182-1199. google scholar
25. European Commission, Directorate-General for Migration and Home Affairs (EC). (2017). Weistra, K., Swart, L., Oortwijn, W., et al., Updated study on corruption in the healthcare sector: final report, Publications Office. https://op.europa.eu/en/publication-detail/-/publication/ 9537ddb7-a41e-11e7-9ca9-01aa75ed71a1/language-en google scholar
26. Euronews. (2022). Sağlık harcamalarının milli gelire oranı: OECD ve AB’de sağlığa en çok pay ayıran ülkeler hangileri? Retrieved from https://tr.euronews.com/next/2022/04/05/sagl-k-harcamalar-n-n-milli-gelire-oran-oecd-ve-ab-de-sagl-ga-en-az-pay-ay-ran-ulke-turkiy google scholar
27. J. Fan, S. Upadhye. Ve Worster, A. (2006). Understanding Receiver Operating Characteristic (ROC) Curves. Canadian Journal of Emergency Medicine, 8(1), 19-20. google scholar
28. Federal Bureau of Investigation (FBI). (1989). White collar crime: a report to the public. Washington, DC: Government Printing Office. google scholar
29. Francis, C., Pepper, N., & Strong, H. (2011, Ağustos). Using support vector machines to detect medical fraud and abuse. 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (ss. 8291-8294). IEEE. google scholar
30. Gee, J., Button, M., & Brooks, G. (2010). The financial cost of healthcare fraud: data from around the world. (London: MacIntyre Hudson/CCFS. google scholar
31. Georgetown University Memory Disorders Program (2023). Allegations of fraud in Alzheimer’s disease research: Death of the amyloid hypoth-esis?, https://memory.georgetown.edu/news/allegations-of-fraud-in-alzheimers-disease-research-death-of-the-amyloid-hypothesis%EF% BF%BC/ google scholar
32. He, H., Graco, W., & Yao, X. (1999). Application Of Genetic Algorithm And K-Nearest Neighbor Method İn Medical Fraud Detection. Lecture Notes in Comput. Sci. 1585 74—81. Springer, Berlin. google scholar
33. He, H. X., Wang, J. C., Graco, W., & Hawkins, S. (1997). Application of Neural Networks detect Medical Fraud. Expert Systems with Applications 13 329-336. google scholar
34. ISSA. (2022). Detecting fraud in healthcare through emerging Technologies. https://ww1.issa.int/analysis/ detecting-fraud-health-care-through-emerging-technologies google scholar
35. Johnson, J. M., & Khoshgoftaar, T. M. (2019). Medicare fraud detection using neural networks. Journal of Big Data, 6(1), 1-35. google scholar
36. Joudaki, H., Rashidian, A., Minaei-Bidgoli, B., Mahmoodi, M., Geraili, B., Nasiri, M., and Arab, M. (2015). Using data mining to detect healthcare fraud and abuse: a review of literature. Global Journal of Health Sciences 7(1), 194. google scholar
37. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma W, et al. & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30. google scholar
38. Kirlidog, M., and Asuk, C. (2012). A fraud detection approach with data mining in health insurance. Procedia-Social and Behavioral Sciences, 62, 989-994. google scholar
39. Kurşun, A. (2021). Büyük Veri ve Sağlık Hizmetlerinde Büyük Veri İşleme Araçları. Hacettepe Sağlık İdaresi Dergisi, 24(4), 921-940. google scholar
40. Küçük, A. (2022). Sağlık Hizmet Ödemelerinde Usulsüzlük Türleri ve Mücadele Stratejileri. Sayıştay Dergisi, 33(127), 585-607. google scholar
41. Li, J., Huang, K. Y., Jin, J., & Shi, J. (2008). Survey on statistical methods for healthcare fraud detection. Health Care Management Science, 11(3), 275-287. http://dx.doi.org/ 10.1007/s10729-007-9045-4. google scholar
42. C. Lin, C. M. Lin, S. T. Li, and S. C. (2008). Intelligent physician segmentation and management based on KDD approach. Expert Systems with Applications, 34(3), 1963-1973. http://dx.doi.org/10.1016/j.eswa.2007.02.038 google scholar
43. Liou, F. M., Tang, Y. C., & Chen, J. Y. (2008). Detecting hospital fraud and claim abuse through diabetic outpatient services. Health Care Manag Sci. 11, 353-358. google scholar
44. Liu, Q., |& Vasarhelyi, M. (2013, Kasım). Healthcare fraud detection: A survey and clustering model incorporating geo-location information. Brisbane, 29th World Continuous Auditing and Reporting Symposium (29WCARS). google scholar
45. Major, J. A., & Riedinger, D. R. (1992). Efd: A Hybrid Knowledge/Statistical-Based System for Detecting Fraud. International Journal Of Intelligent Systems. 687-703. google scholar
46. National Health Care Anti-Fraud Association (NHCAA). (2021). The Challenge of Health Care Fraud. https://www.nhcaa.org/tools-insights/about-health-care-fraud/the-challenge-of-health-care-fraud/ google scholar
47. OECD (2020). Public Integrity for an Effective COVID-19 Response and Recovery. https://read.oecd- ilibrary.org/view/?ref=129_ 129931-ygq2xb8qax&title=PublicIntegrityforanEffectiveCOVID-19ResponseandRecovery google scholar
48. Ogunbanjo, G. A., and D. K. (2014). Ethics in health care: healthcare fraud. South African Family Practice, 56(1), S10-S13. google scholar
49. Ogunleye, A., & Wang, Q. G. (2019). XGBoost Model for Chronic Kidney Disease Diagnosis. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 17(6), 2131-2140. google scholar
50. Orhan, M. S., & Serçemeli, M. (2015). İç denetim stratejisinde sürekli denetimin uygulanabilirliğine ilişkin bir araştırma. Giresun Üniversitesi İktisadi ve İdari Bilimler Dergisi, 1(2), 83-110. google scholar
51. Özbek, A. (2024). Muhasebe Meslek Mensuplarının Yapay Zekâ Kaygılarının Gelecekte İstihdam Edilebilirlik Algıları Üzerine Bir Çalışma. Alanya Akademik Bakış, 8(1), 254-267. google scholar
52. Özkan, Y. (2016). Veri Madenciliği Yöntemleri. İstanbul: Papatya Yayıncılık. google scholar
53. Öztırak, M. (2023). A study on the impact of artificial intelligence anxiety on innovation-oriented behaviors of employees. Optimum Ekonomi ve Yönetim Bilimleri Dergisi, 10(2), 267-286. google scholar
54. Price, M., & Norris, D. M. (2009). Health care fraud: physicians as white-collar criminals? Journal of the American Academy of Psychiatry and the Law Online, 37(3), 286-289. google scholar
55. Saravanan, R., and Sujatha, P. (2018, Haziran). State-of-the-art machine learning algorithms: a perspective of supervised learning approaches in data classification. In 2018 Second international conference on intelligent computing and control systems (ICICCS) (ss. 945-949). IEEE. google scholar
56. Savedoff, W. D., & Hussmann, K. (2006). The causes of corruption in the healthcare sector: a focus on health care systems. Transparency International. Global Corruption Report, 4-16. google scholar
57. Shan, Y., Jeacocke, D., Murray, D. W., & Sutinen, A. (2008, Kasım). Medical specialist billing patterns for health service management. Proceedings of the 7th Australasian Data Mining Conference, 87 (ss. 105-110). google scholar
58. Shan, Y., Murray, D. W., & Sutinen, A. (2009, Aralık). Discover inappropriate billings using a local density-based outlier detection method. Proceedings of the Eighth Australasian Data Mining Conference, 101 (ss. 93-98). google scholar
59. Shin, H., Park, H., Lee, J., & Jhee, W. C. (2012). A scoring model to detect abusive billing patterns in health insurance claims. Expert Systems with Applications, 39(8), 7441-7450. http://dx.doi.org/10.1016/j.eswa.2012.01.105. google scholar
60. Sokol, L., Garcia, B., Rodriguez, J., West, M., & Johnson, K. (2001). Using data mining to find fraudulent HCFA healthcare claims. Topics in Health Information Management, 22(1), 1-13. google scholar
61. Srinivasan, U., & Arunasalam, B. (2013). Leveraging big data analytics to reduce healthcare costs. IT professional, 15(6), 21-28. google scholar
62. Thomson Reuters. (2021). Organized crime using sophisticated technology in next wave of government healthcare fraud schemes. https: //www.thomsonreuters.com/en-us/posts/investigation-fraud-and-risk/healthcare-fraud-webinar/ google scholar
63. Transparency International. (2006). Global Corruption Report 2006. https://images.transparencycdn.org/images/2006_GCR_HealthSector_EN. pdf google scholar
64. Transparency International. (2023). Health. https://www.transparency.org/en/our-priorities/health-and-corruption google scholar
65. Turgay, İ., Doğan, S., & Mengi, B. T. (2020). İç Denetim Faaliyetlerinde Sürekli Denetim: Analitik İnceleme Prosedürlerinin Kullanımı. Denetişim, (21), 5-26. google scholar
66. U.S. Department of Justice (2023). Retrieved from https://www.justice.gov/opa/pr/hospice-medical-director-sentenced-150m-hospice-fraud-scheme. google scholar
67. U.S. Department of Justice (2024). Criminal Resource Manual CRM 500-999, 976- Health Care Fraud—Generally. https://www.justice.gov/ archives/jm/criminal-resource-manual-976-health-care-fraud-generally# google scholar
68. USSC (2022). Quick Facts—Health Care Fraud Offenses. https://www.ussc.gov/sites/default/files/pdf/research-and-publications/quick-facts/ Health_Care_Fraud_FY22.pdf google scholar
69. Van Capelleveen, G., Poel, M., Mueller, R. M., Thornton, D., and van Hillegersberg, J. (2016). Outlier detection in healthcare fraud: A case study in the Medicaid dental domain. International Journal of Accounting Information Systems 21, 18-31. google scholar
70. Vangara, V., Vangara, S. P., & Thirupathur, K. (2020). Opinion mining classification using naive bayes algorithm. International Journal of Innovative Technology and Exploring Engineering (IJITEE), 9(5), 495-498. google scholar
71. Vian, T. (2020). Corruption and administration in healthcare. In Handbook on corruption, ethics, and integrity in public administration (pp. 115-128). Edward Elgar Publishing. google scholar
72. Vincke, P. ve Cylus, J. (2011). Healthcare fraud and corruption in Europe: An overview. Eurohealth, 17(4), 14-18. google scholar
73. Wang, D. N., Li, L., & Zhao, D. (2022). Corporate finance risk prediction based on LightGBM. Information Sciences, 602, 259-268. google scholar
74. World Health Organization (WHO). (2023a). World health statistics 2023: monitoring health for the SDGs, sustainable development goals. google scholar
75. World Health Organization. Retrieved from https://www.who.int/publications-detail-redirect/9789240074323. google scholar
76. World Health Organization (WHO). (2023b). Reducing Health System Corruption. https://www.who.int/activities/reducing-health-system-corruption google scholar
77. Zamost, S. & Brewer, C. (2023). Inside the mind of criminals: How to brazenly steal $100 billion from Medicare and Medicaid. https://www.cnbc.com/2023/03/09/how-medicare-and-medicaid-fraud-became-a- 100b-problem-for-the-us.html#:~:text= Fraud%20flourishes&text=Taxpayers%20are%20losing%20more%20than,Health%20Care%20Anti%2DFraud%20Association. google scholar
78. Zhang, C., Xiao, X., & Wu, C. (2020). Medical fraud and abuse detection system based on machine learning. International journal of environmental research and public health, 17(19), 7265. google scholar
79. Zhu, S., Wang, Y., & Wu, Y. (2011, Ağustos). Health care fraud detection using nonnegative matrix factorization. 2011 6th International Conference on Computer Science & Education (ICCSE) (ss. 499-503). IEEE. google scholar