Fraud and abuse schemes in medicare have been a serious issue for many years. These are especially dangerous since the victims risk not only their money but their health and, sometimes, lives. The most common methods of deceit are billing for appointments that did not take place, procedures that were not performed, or unnecessary medical services (Johnson and Khoshgoftaar, 2019). The last one is the most dangerous and is often described as an abusive practice because it usually implies directly deluding patients. A lot of fraud complaints become OIG cases and are actively investigated. According to Ogrosky and Shuren (2020), an OIG case is the one investigating fraud committed by federal payers since only this organ has the authority to issue subpoenas to those organizations. Theoretically, any report of a significant fraud can become an OIG case, but not every one of them is resolved.
The hardship of combatting fraud lies in the complexity of this process and well-prepared methods of concealing it. Despite that, there are ways of minimizing fraud and abuse cases by detecting them and gaining control. One of the strategies is using machine learning and big data for fraud detection. As explained in a study by Johnson and Khoshgoftaar (2019), smart medicare data sets are very effective at indicating anomalies and frauds in healthcare institutions’ computerized systems. However, neural networks are far from being absolutely stable and require additional investments. Until that, there is another essential action Medicare beneficiaries can do to reduce deceit cases — bringing attention to this issue. If both the patients and the local government become aware of fraud possibilities, they will act more cautiously and monitor their interactions with healthcare institutions.
References
Johnson, J.M., & Khoshgoftaar, T.M. (2019) Medicare fraud detection using neural networks. Journal of Big Data, 6(63), 1-35. Web.
Ogrosky, K., & Shuren, A. (2020). DOJ and OIG Health Care Fraud Enforcement in 2020 and Beyond. Journal of Health Care Compliance, 22(1), 17-24. Web.