Data analytics can spot fraud patterns, but humans offer a 'gut instinct'

State-of-the-art data analytics technology can edit claims to prevent fraudulent Medicare payments, but the human element found in initiatives like the Senior Medicare Patrol still play a crucial role in fraud detection, according to an article by FedTech.

Tony Trenkle, chief information officer for IBM's Global Healthcare Industry unit, spoke last month at MeriTalk's Second Annual Big Data Brainstorm about how new technology is allowing healthcare payers to edit claims before they are paid and how it is identifying anomalies that could lead to bigger fraud investigations.

Trenkle, who previously worked at the Centers for Medicare & Medicaid Services (CMS), and others at the session cautioned that technology, while helpful in identifying fraud, is not singularly effective. Trenkle said programs like CMS' Senior Medicare Patrol, which helps beneficiaries interpret summary notices and bills and identify potential threats of identity theft, play an equal role in uncovering fraud. Johan Bos-Beijer, director of analytics services for the U.S. General Services Administration, added that software is not a cure-all for many fraud threats.

"And 90 percent of the time, it's the human that has the gut instinct, that has the behavioral reference, that understands what another human being might do to take advantage of a program," he said, according to FedTech.

Healthcare payers have found success in using predictive analytics to detect sophisticated fraud schemes, and using rules-based software to identify erroneous claims. At the federal and state level, analytics has served as an critical tool in the government's historic $712 million fraud bust. However, the human element has proven to be an important compliment to fraud detection software, especially when it comes to investigations.   

For more:
- read the FedTech article