The Centers for Medicare and Medicaid Services estimates the United States spent $2.5 trillion (17.6 percent of GDP) on healthcare in 2009. As healthcare expenditures increase, so does the amount being wasted on improper and fraudulent payments.
The National Health Care Anti-fraud Association conservatively estimates that 3 percent of all healthcare spending, or $60 billion, is lost to fraud. In 2010 alone, Medicare and Medicaid paid an estimated $68.3 billion in improper payments. Cases of medical identity theft are increasing as well, with more than 1.5 million people victimized by medical identity theft so far in 2011, at an average cost of $20,000 to the victim.
In addition to the financial costs associated with healthcare fraud, there are also the patient costs, which include wasteful over-treatment, under-treatment and outright dangerous treatment, like the prescribing of unnecessary narcotics.
Most healthcare fraud detection occurs at the back end of the workflow, after claims are submitted by providers and are paid, without sufficient analytics to determine their legitimacy. If a payer finds that a claim that has already been paid is questionable, it must try to recover money that has already gone out the door. Clearly this system does not focus on fraud prevention but, rather, detection after the fact. It is a "cops and robbers" system of addressing healthcare fraud that, in the long run, is not sustainable.
To make real progress in healthcare fraud prevention, both government and private payers must integrate fraud risk controls at the front end of their claims payment workflow processes. The most effective fraud detection programs use a layered approach to analyzing claims that includes analytics that focus on identity integrity, claims legitimacy and relationships.
Identity Analytics
In order to protect consumers (and themselves) from medical identity theft and fraud, health enterprises are more frequently considering implementation of enterprise fraud risk and identity management programs. Implementing an enterprise-wide "true" identity management system allows both providers and members to be verified and authenticated, enabling both more efficient post-payment recovery and, when implemented in a pre-payment environment, limiting the scope of services for which certain providers are paid and/or removing providers from a payer's network altogether.
A truly comprehensive identity management program will allow users to: (1) verify the identity of an individual; (2) authenticate that identity; (3) evaluate the identity's eligibility for participation (assess against legislation, regulations and rules to determine if you meet eligibility criteria); and (4) provide on-going monitoring of the individual to ensure that s/he continues to meet eligibility criteria.
Claims Analytics
Traditional rules-based fraud detection systems analyze claims and identify outliers post-payment. Moving this operation to the front-end of the claims payment process allows for comprehensive pre-pay claims analytics that consist of rules-based screens and edits as well as predictive modeling that identifies the potential for improper payments by "scoring" claims and/or providers before a claim is paid.
Using pre-pay analytics also allows for the identification of fraudulent and abusive patterns and trends and the ability to recognize characteristics of a claim or a provider's billing habits that suggest fraudulent activity. When that information is applied to claims as they are being processed – pre-payment – claims that require further review can be separated out before they are paid or reviewed more efficiently post-payment.
Social Network Analytics
Organized crime loves the healthcare industry. Much safer than traditional crime, healthcare fraud also features lower penalties and great rewards. Increasing sophistication of fraudulent behavior by networks is here to stay. Criminals are perpetrating collusive fraud schemes against Medicare, Medicaid and private health insurance companies.
New technology, called social network analytics (SNA), can help identify relationships, links and hidden patterns and interactions within clusters of individuals, including:
• Patient relationships with known perpetrators of healthcare fraud;
• Links between recipients, businesses, assets and relatives and associates;
• Links between licensed and non-licensed providers; and
• Inappropriate relationships between patients, providers, employees, suppliers and partners.
Advanced technology is now available that is highly optimized for systemically determining relationships and links. Additionally, access to vast public records databases that go beyond phone and address information makes previously hidden relationships between entities, assets and people transparent. SNA enables investigations that reveal the hidden roots of fraud within a provider network, as opposed to the traditional claim-by-claim approach.
The advances being made in the healthcare industry must include changes to the way we currently handle the detection and prevention of improper payments, including fraud, waste and abuse. Implementing a pre-pay claims processing system that leverage analytics at the front end of the workflow will help to eliminate billions of dollars in improper payments that currently weigh down the U.S. healthcare system and free that money to be spent on caring for patients.
Bill Fox is senior director of commercial healthcare at LexisNexis.