CMS Employs New Fraud-Fighting Tool

Published May 31, 2016

In an effort to combat Medicare fraud that cost at least $49 billion in the last fiscal year, the Centers for Medicare and Medicaid Services on July 1 began using new technology to stop fraudulent payments.

The new technology is predictive modeling, similar to what credit card companies use to root out fraud. Northrup Grumman received the contract to administer the new initiative, which was a result of the Affordable Care Act’s mandate that CMS do more to combat improper Medicare payments.

According to CMS, “Northrop Grumman will deploy algorithms and an analytical process that looks at CMS claims—by beneficiary, provider, service origin or other patterns—to identify potential problems and assign an ‘alert’ and assign ‘risk scores’ for those claims. These problem alerts will be further reviewed to allow CMS to both prioritize claims for additional review and assess the need for investigative or other enforcement actions.”

Tackling Long-Term Problem

Medicare has long had a problem with fraud. A March 2011 report from the Government Accountability Office termed Medicare a “high risk program” because it was “particularly vulnerable to fraud, waste, abuse, and improper payments.” It went on to state that “Medicare is considered high-risk in part because of its complexity and susceptibility to improper payments.”

At the time of the GAO report, the organization called for CMS to institute prepayment controls like predictive modeling: “Prepayment reviews of claims help ensure that Medicare pays correctly the first time.”

At the time, CMS was in the process of instituting its new system. However it sounded a note of caution then, stating, “CMS has not implemented certain GAO recommendations related to prepayment review.”

Overly Optimistic?

Peter Budetti, director of CMS’ Center for Program Integrity, holds high hopes the new technology will help fix the fraud problems.

“CMS has worked with public and private stakeholders throughout the process of developing this program, and the key insights they shared on their successes and innovations have helped ensure it will significantly help us address fraud in the Medicare program,” Budetti said.

Donald Berwick, administrator of CMS, echoed this confidence in a statement, saying, “This new technology will help us better identify and prevent fraud and abuse before it happens and helps to ensure the solvency of the Medicare Trust Fund.”

Michael Cannon, director of health care policy at the Cato Institute, isn’t as optimistic.

“Predictive modeling is a very promising tool for fighting fraud—which is exactly why Medicare won’t make full use of it,” predicts Cannon. “Even the best anti-fraud tools will inconvenience legitimate providers. The moment that happens, Congress will pull back the use of predictive modeling. Why? Because it’s the lowly taxpayers’ money that gets lost to fraud, not theirs.”

 

Marc Kilmer ([email protected]) is a senior fellow at the Maryland Public Policy Institute.