Why Big Data still isn't putting a dent in Medicare fraud

Big data and predictive analytics were supposed help Medicare prevent fraudulent payments the same way credit card companies deny suspicious charges. Fraud schemes still plague Medicare because the Centers for Medicare & Medicaid Services (CMS) is too concerned about provider backlash to use the full force of claims data, according to an article published in Pacific Standard.

The article dives into the history of Medicare fraud and the way organized crime entities have infiltrated the system by setting up sham clinics, stealing physician and patient information and billing Medicare indiscriminately. CMS pays the claims until it recognizes an anomaly, but by then, the scammers have moved on. Some investigators have referred to this "pay-and-chase" model as an endless game of Whac-a-Mole.

CMS' Fraud Prevention System (FPS) has reportedly returned nearly $3 for every dollar spent on the program, but more than one-third of those recoveries came from investigations initiated before the system noticed a problem. Although the system was supposed to mirror the credit card industry's approach to preventing fraud, CMS Director of Program Integrity Shantanu Agrawal has said medical claims are more complicated, and therefore more difficult to immediately identify as fraudulent.  

However, fraud experts like Harvard researcher Malcolm Sparrow say CMS operates under the assumption that billing mistakes were made in error. Instead of denying fraudulent claims, CMS has merely saddled fraud investigators with more cases.

One CMS initiative that has seen some success is the Medicare Fraud Strike Force, which targeted areas of the country where fraud is particularly prevalent. Former members of the Strike Force told Pacific Standard that simply shutting down potential fraud schemes as soon as they are discovered could save $10 billion each year.

Predictive analytics has been hailed as the new frontier for fraud detection and prevention by helping fraud fighters uncover sophisticated fraud schemes. Government officials have said analytics played a major role in the government's historic fraud bust last June, and a number of states have announced initiatives of their own. However, many fraud experts have cautioned against relying solely on Big Data to uncover schemes, highlighting the "human element" as a key cog in fraud detection.

To learn more:
- read the Pacific Standard article

Suggested Articles

The HHS OIG is asking for an additional $23.7 million to support fraud oversight that has benefited from an emphasis on data analytics.

A New York surgeon was sentenced to 13 years in prison for fraud and more physician practice news from around the web.

A federal judge has ruled that the U.S. government’s remaining fraud case against UnitedHealth can move forward.