Guest Column: Fight Healthcare Fraud With Analytics

By Bill Fox, JD, MA, and Senior Director of Healthcare for LexisNexis

This article highlights how a pre-pay claims processing system that leverages claims review, predictive modeling, and linking analytics technologies can help healthcare payers save the billions of dollars lost annually to fraud.

The healthcare reform debate has cast a bright light on the issue of healthcare fraud, waste, and abuse. The Patient Protection and Affordable Care (PPACA) and American Recovery Reinvestment (ARRA) Acts have made improper payment control and risk mitigation in healthcare a mission-critical priority. As state and federal governments begin to implement, or attempt to block implementation of, the various pieces of this legislation, participants in the healthcare industry will face an avalanche of new and sometimes shifting or vague regulations and requirements. In addition, the paradigm shift in open data exchange, electronic medical record (EMR) adoption, Regional Health Information Organizations (RHIOs), Health Information Exchanges (HIEs), and Accountable Care Organizations (ACOs) creates unprecedented risks for the Health Insurance Portability and Accountability Act (HIPAA), Identity Theft Red Flags, and re-identification of Personal Health Information (PHI). While it is unclear what the final version of this iteration of healthcare reform will look like when the dust settles, what is known is that money paid for fraudulent or abusive claims is money not spent on the delivery of quality care.

According to the Centers for Medicare and Medicaid Services (CMS), in 2009 healthcare spending in the United States reached $2.5T (17.6% of GDP) and with the proposed reform initiatives under the Affordable Care Act (ACA), the number of Americans covered and the amount spent will grow dramatically. In the U.S., healthcare fraud has skyrocketed over the last decade with billions of dollars being paid on improper claims. The National Health Care Anti-fraud Association (NHCAA) conservatively estimates that 3% of all healthcare spending, or C60B, is lost to healthcare fraud. In 2010 alone, Medicare and Medicaid paid an estimated $68.3B in improper payments. In 2008, it was reported that Medicare spent less than two tenths of a cent of every dollar of its $456B annual budget combating fraud, waste, and abuse. Adding further injury is the increased incidence of identity theft – in 2011, more than 1.5 million people have been victimized by medical identity theft at an average cost of $20,000 to the victim.

Today most fraud is detected and recovered at the back-end of the workflow – claims are submitted by providers and are paid without a thorough review to determine their legitimacy. If after a claim has been paid, the payer finds it questionable, they must then embark on the laborious, costly, and resource-intensive process of trying to recover the money that has already gone out the door. The results are, at best, partially successful, and often less than that. This current "cops and robbers" system of addressing healthcare fraud by chasing money after it has gone out the door is simply not sustainable; HHS, CMS, and the FBI are aggressively transforming their approach to combat fraud, waste and abuse in the healthcare industry. It is incumbent upon health insurance executives to understand the risks facing their organizations and to be prepared for the tidal wave of increased enforcement, enhanced financial penalties and more stringent sentencing guidelines.

Measurable gains in healthcare fraud prevention hinge on the ability of both government and private payers to integrate fraud risk controls at the front end of their claims payment workflow processes. The move to integrated front end solutions is not simply a matter of plugging in new technologies. Strategic and tactical considerations around implementation of this fundamental change in the healthcare payment workflow will be crucial to success. Effective fraud detection is best achieved through a layered approach to claims analysis, including identity analytics, claims analytics, and social network analytics. Access This Content To Read This Article In Its Entirety.