States are turning to data analytics to improve efforts to foil healthcare fraud and other crimes poaching government-funded programs, according to The Pew Charitable Trusts.
The Indiana Department of Revenue, for instance, launched a data-driven identity matching program that's saved taxpayers $85 million to date, providing "a tantalizing glimpse of the cost savings states could get from applying a government-wide 'big data' approach to combating the fraudulent claims states face in an internet age when identity theft is rampant," the article noted.
"States are data engines at their core," Doug Robinson, executive director of the National Association of State Chief Information Officers, said to Pew. But "just because states have a lot of data doesn't mean they've met the definition of big data…Very few states have taken an enterprise approach to it."
Obstacles to integrating data and leveraging information include privacy concerns and getting data out of agency silos, the article added.
Still, there's been progress. North Carolina consolidated data analytics efforts, including its data-based fraud detection program, under an office of information technology services. The state's goal is to apply big-data-style analytics across the board. Florida, too, is finding fraudulent Medicaid claims by verifying claimants' identities through a database before payment. In its last fiscal year, that program prevented $32.8 million in losses across various state programs.
In a like vein, mining collections of billing data can enhance payer anti-fraud efforts. Here are suggestions for improving this work from a Compliance Today article (.pdf) published by the Health Care Compliance Association:
- Compare Medicare provider utilization and payment data on physicians and other suppliers with in-house data on network providers. Look for patterns in facility place of service vs. office place of service.
- Review the Centers for Medicare & Medicaid Services' Program for Evaluating Payment Patterns Electronic Reports (or CMS PEPPER) data reported for your company to spot trends.
- Compare demographic trends using the CMS Chronic Conditions Warehouse and Geographic Variation dashboards.
- Consider using vendors to run organizational billing data through algorithms that flag outliers.
- Finally, remember that, while data provide a valuable starting point, "a deeper dive into the supporting documentation behind what was billed is always necessary," HCCA cautioned. "Sometimes, the discrepancy is explainable.