Retraction: Association analysis between pharmacies and pharmaceutical companies in Healthcare Insurance systems

Abstract

With increasing personal health care costs, governments are working hard on individual health insurance. In this context, insurance systems are improved to cover especially expensive drugs. As the scope of the drug increases, the expenditures in the system increase accordingly. Malicious people take advantage of the health care system and cause incidents that exploit the system financially. Detecting such frauds attempts requires serious work and time. In this study, after the drugs were categorized, the possible anomalies paired with pharmacy and pharmaceutical companies, which are more than normal sales of drugs of similar category, were determined by statistical methods. Drug manufacturers can deal with pharmacies and aim to sell their own medication, which is a counterpart to a drug specified in the doctor’s prescription. In this study, the relationship between the two different entities by normalizing the data has been tried to be correlated with the statistical approach. With the results obtained, statistical analysis was made and the pharmaceutical manufacturers which are prone to fraud were further narrowed. As a result, it was ensured that the data pool, which required fraud detection, was narrowed and this determination was facilitated.

This article was retracted on March 26, 2021.

Keywords

• Heath Insurance Fraud
• Fraud anomaly detection
• Data mining
• Normalization

Geri Çekildi: SAĞLIK SİGORTACILIĞINDA ECZANE – İLAÇ ÜRETİCİ FİRMASI ARASINDA İLİŞKİLENDİRME ANALİZİ

Abstract

Artan kişisel sağlık giderleri ile birlikte devletler bireysel sağlık sigortaları üzerinde ciddi çalışmalar yapmaktadır. Bu kapsamda sigorta sistemleri özellikle pahalı ilaçları kapsayacak şekilde iyileştirilmektedir. İlaç kapsamı arttıkça sistem içerisindeki harcamalar da buna paralel olarak artmaktadır. Sistemdeki bu durumu gören kötü niyetli kişiler Tıbbi Dolandırıcılık adı verilen ve sistemi büyük maddi zararlara uğratacak girişimlerde bulunmaktadır. Yapılan sahtekârlıkları tespit etmek ciddi çalışma ve zaman gerektirmektedir. Bu çalışmada, ilaçlar sımıflandırılarak benzer kategorideki ilaçların normalden fazla satışı olan eczane ve ilaç firmaları eşleştirilmiş muhtemel anomaliler istatistiksel yöntemlerle tespit edilmiştir. İlaç üretici firmalar ve eczaneler aralarında anlaşma yaparak doktor reçetesinde belirtilen bir ilacın muadili olan kendisine ait ilacı satmayı hedefleyebilmektedirler. Bu çalışmada, verilerin ölçeklenerek iki farklı varlık arasındaki ilişki istatiksel yaklaşımla değerlendirmeye çalışılmıştır. Elde edilen sonuçlarla istatistiksel analizi yapılarak dolandırıcılığa meyilli ilaç üretici firmaları daha da daraltılmıştır. Sonuç olarak dolandırıcılık tespiti yapılması gereken veri havuzunun daraltılarak bu tespitin kolaylaştırılması sağlanmıştır. 

Bu makale 26 Mart 2021 tarihinde geri çekildi. 

Keywords

• Kümeleme analizi
• Sağlık sigortacılığı sahtekarlığı
• Sahtekarlık anomaly tespiti
• Veri Madenciliği
• Normalizasyon

References

1. [1] Bauder, R. A., Khoshgoftaar, T. M., Medicare Fraud Detection Using Machine Learning Methods, 16th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 858-865(2017),. Cancun,
2. [2] Herland, M., Bauder, R.A., Khoshgoftaar, Approaches for identifying U.S. medicare fraud in provider claims data, T.M. Health Care Manag Sci (2018) Oct 27. doi: 10.1007/s10729-018-9460-8.
3. [3] Bauder, R.A., Khoshgoftaar, T.M., Multivariate outlier detection in medicare claims payments applying probabilistic programming methods, Health Services and Outcomes Research Methodology 17 (3-4), (2017) 256-289
4. [4] Tsai, Y.H., Ko C. H., Using CommonKADS Method to Build Prototype System in Medical Insurance Fraud Detection, Journal Of Networks, Vol. 9, No. 7, (2014) July
5. [5] Pedro, O. A., Cristián J. F., Gonzalo, R. A Medical Claim Fraud/Abuse Detection System based on Data Mining, A Case Study in Chile. DMIN. 6. (2006). 224-231
6. [6] Hoda, E., Juan, L., Ying, Z., Markus, F., Fraud Detection for Healthcare. KDD2013 Workshop On Data Mınıng For Healthcare(2013, August) 11–14.
7. [7] Bolton, R.J., Hand D. J., Statistical Fraud Detection: A Review, Statistical Science Vol. 17, No. 3 (2002 Aug.,), 235-249
8. [8] Chan, P. K., Fan, W., Prodromidis A. L., Stolfo, S. J., Distributed data mining in credit card fraud detection, in IEEE Intelligent Systems and their Applications, vol. 14, no. 6, (1999Nov.-Dec)..pp. 67-74,

9. [9] Yufeng, K., Lu, C.T,., Sirwongwattana, S., Huang, Y.-P., Survey of fraud detection techniques. 2. 749 - 754 Vol.2. (2004). 10.1109/ICNSC.2004.1297040.
10. [10] Lapeyre-Mestre M., · Gony M.,· Carvajal A.,· Macias D., · Conforti A.,· D’Incau P. ,· Heerdink R. and· Van der Stichele R., A European Community Pharmacy-Based Survey to Investigate Patterns of Prescription Fraud through Identification of Falsified Prescriptions, European Addiction Research 2014; 20:174-182
11. [11] Gangopadhyay A., Chen S., Yesha Y., Detecting Healthcare Fraud through Patient Sharing Schemes, ICISTM 2012. Communications in Computer and Information Science, vol 285: 421-426
12. [12] Konijn R.M., Kowalczyk W. , Finding Fraud in Health Insurance Data with Two-Layer Outlier Detection Approach Data Warehousing and Knowledge Discovery. DaWaK 2011 Lecture Notes in Computer Science, vol 6862. Springer, 394-405