Updated on: June 22, 2012

RAC Game Changer: Predictive Modeling

By
Original story posted on: June 22, 2011

mspivey100WASHINGTON, D.C. - The Centers for Medicare & Medicaid Services (CMS) is poised to begin using predictive modeling technology to fight Medicare fraud, federal officials said late last week.

 

The scheduled launch date for the technology - which is being implemented as part of the White House's newly introduced Campaign to Cut Waste, an administration-wide initiative to crack down on waste, fraud and abuse - is July 1, according to a news release issued by CMS.

 

Similar in nature to technology already being used by credit card companies to detect fraud, predictive modeling is expected to identify potentially fraudulent Medicare claims on a nationwide basis, helping stop fraudulent claims before they are paid, officials said. The initiative builds on new anti-fraud resources made available by the Patient Protection & Affordable Care Act of 2010, tools that federal authorities hope will help CMS advance beyond simple "pay and chase" recovery operations to an approach focusing on preventing fraud and abuse in the first place.

 

"President Obama is committed to hunting down and eliminating waste, fraud and abuse throughout the federal government," U.S. Department of Health and Human Services Secretary Kathleen Sebelius said. "Our work to fight Medicare fraud is an important part of the Obama Administration's effort to root out wasteful spending and change the way government does business."

 

"Today's announcement is bad news for criminals looking to take advantage of our seniors and defraud Medicare," agreed CMS Administrator Donald Berwick. "This new technology will help us better identify and prevent fraud and abuse before it happens, and (it) helps to ensure the solvency of the Medicare Trust Fund."

 

Starting July 1, original Medicare claims will be analyzed using technology that applies predictive models, a strategy that for years has been used by the private sector to identify fraud, officials said. As such, CMS for the first time will have the ability to use real-time data to spot suspect claims, giving it the power to take action to stop fraudulent payments before they are paid.

 

Northrop Grumman, a global provider of advanced information solutions, has been selected through a competitive procurement to develop the predictive model technology format that will be used by CMS, according to federal officials. The company has partnered with National Government Services and Federal Network Systems LLC, a Verizon company, in this effort; CMS also used industry guidance, concepts gleaned from private and provider entities, and related data in developing the scope of work for the program, authorities said.

 

"CMS has worked with public and private stakeholders throughout the process of developing this program, and the key insight they shared on their successes and innovations have helped ensure it will significantly help us address fraud in the Medicare program," said Peter Budetti, director of the CMS Center for Program Integrity (CPI).

 

Northrop Grumman is expected to move rapidly to implement the new technology, deploying algorithms and an analytical process that examines CMS claims by beneficiary, provider, service origin and via other patterns to identify potential problems. In doing so, the company will generate automatic alerts and assign "risk scores" for claims. The alerts will be reviewed further to allow CMS to prioritize claims for additional review and assess the need for investigative or other enforcement actions, officials said.

 

One expert in the national healthcare field, professor Stephen T. Parente, at the Department of Finance, Carlson School of Management, University of Minnesota, who has reported on this developing story in the past for RACMonitorEnews, expressed optimism about the announcement - calling it a "welcome first step" to improve value to the program and something that could "mitigate the hassle" providers feel about the current pay-and-chase model - but he added a strong caveat.

 

"The use of predictive modeling to detect fraud could transform Medicare IT systems and help get the best value from the program for seniors and the disabled ... if proven successful, this approach could be used in other publicly financed insurance programs such as Medicaid," Parente said. "To be successful, CMS must not only commit to score the claims like credit card transaction vendors; they must be willing to act quickly to realize the savings of such a program."

 

"This was a major cultural shift in the financial services industry over two decades ago when banks, credit card issuers and merchants implemented predicting modeling to not pay high-risk transactions," Parente explained. "It will likely require the leadership of CMS to undergo a change in culture as well if they go forward to stop payment automatically based on a claim's predicted high risk score."

 

Parente also said communication about the change should be a priority.

 

"Northrop Grumman, National Government Services and Federal Network Systems LLC must still be celebrating the CMS announcement," he noted, "since it has yet to be posted on their websites."

 

To comment on this article please go to editor@racmonitor.com

 

Audit Impact: Expanded Liablity for Overpayments


This email address is being protected from spambots. You need JavaScript enabled to view it.