News Feature | March 10, 2015

Predictive Analytics Deter Healthcare Fraud

Katie Wike

By Katie Wike, contributing writer

12_CS_BIAnalytics_FINAL

Predictive analytics used by CMS prevented more than $210 in healthcare fraud in just one year.

The use of predictive analytics by the CMS has helped to identify or prevent more than $210 in healthcare fraud between 2012 and 2013, but critics are responding by saying that isn’t enough.

iHealth Beat provides some background, noting that in 2010 over $100 million was dedicated to the adoption of predictive analytics tools to prevent Medicaid and Medicare fraud. CMS chose to employ four different analytics tools at that time:

  • anomaly models, which alert officials based on factors that appear improbable
  • predictive models, which compare charges with a fraud profile and raise suspicion
  • rules-based models, which automatically flag certain charges
  • social networking models, which alert officials based on a provider's associations

In a 2012 report, it was revealed that the CMS analytics systems generated 536 investigations and assisted in another 511 prevent $115.4 in fraud. A 2014 report found the system resulted in fewer investigations but yielded more money, totaling 469 investigations generated, 348 existing investigation assisted, and identifying $210.7 million in in fraud.

Modern Healthcare reports that these figures are not satisfactory for some experts including Stephen Parente, a professor of health finance at the University of Minnesota, who called the savings a “fraction of what's possible.” He authored a paper in 2012 pointing out that between 3 and 10 percent of healthcare spending is fraudulent. That works out to between $75 and $250 billion since 2009.

Parente believes CMS could be doing more to stop payments automatically, based simply on the algorithms. “Where CMS is trying to intervene is probably too late in the day,” he said.

Others, like Andrew Asher, a senior fellow at research organization Mathematica Policy Research, say the pace of adoption has been slow, but “there's some significant analytical and technical challenges to get this right. It's really critical to have a high level of accuracy.”

“My premise has been for quite a while, (the hackers are) not taking these records so they can know whether or not I've had a colonoscopy,” said Marc Probst, the chief information officer of Intermountain Healthcare. “They're doing it to profit. And the profit they're getting is through fraudulent medical billing, whether that's Medicare or other insurers. If we can stop paying fraudulent claims … people would stop trying to take the data.”