Fighting fraud with predictive analytics and link analysis
Fraud remains a stubborn and growing problem for the U.S. healthcare industry, raising costs for patients and cutting sharply into margins for insurance payers. Of the more than $2.5 trillion spent on healthcare in the United States annually, some $60 billion to $250 billion is lost to fraud, waste and abuse, according to industry experts. Organized crime groups and a small minority of healthcare providers commit most healthcare fraud, reports the National Health Care Anti-Fraud Association.
To date, much of the effort to combat fraud has focused on the laborious process of trying to recover money from false claims after they have been paid. On average, this "pay-and-chase" approach takes about one to two years, and in some cases, many years. A much more effective and efficient method is to identify false claims before they are paid. To do this, healthcare payers are now harnessing the same kind of sophisticated predictive analytics and link analysis that are already used by a wide variety of businesses to improve their decision making.
Predictive analytics: More dynamic and efficient fraud prevention
Predictive analytics combats fraud by identifying patterns in claims that may point to fraudulent activity and by understanding payers' transactional and relationship data to uncover wider instances of fraud. Predictive analytics enable healthcare payers to target unknown types of fraud, identify new schemes and discover networks of fraud. By uncovering this hidden fraud, the technology helps to avoid losses in the first place and to boost recoveries.
Payers often start with a rules-based approach that flags claims that fall outside certain parameters. The first step is to identify potentially fraudulent patterns and then develop the rules to flag them as claims are processed. The rules could include instances such as specialist providers who bill using a particular code more than a certain number of times a month, or charges for services outside their areas of expertise.
Predictive analytics make this rules-based approach more dynamic and effective, identifying more fraud and creating a line of defense against unknown schemes that rules do not catch. As predictive analytic models identify emerging types of fraud, new rules are developed. The intelligence in the predictive analytic system then "learns" from the new rule patterns and builds increasingly more sophisticated models. The most effective, predictive models not only highlight claims with the highest likelihood of fraud but also describe the reasons each claim looks suspicious, so claims can be assessed with high productivity.
Link analysis: Adding a new dimension to fraud prevention
Fraud rings are a major concern for payers. When a reviewer is examining a single claim, it is very helpful to see the larger picture for a given provider or claim. This is where link analysis comes in. Link analysis - a data analysis technique that examines relationships among claims, people and transactions - has been gaining popularity in recent years as a means of enhancing fraud investigations. It is commonly used by banks and insurance companies to improve fraud investigations, expose money laundering schemes, uncover criminal rings and detect insider fraud. Government agencies use link analysis to enhance screening processes, understand and uncover terrorist networks and investigate crime. It also has general applicability for any organization that wants to better understand its customer relationships and consider the impact of both formal and informal networks of people, groups, organizations and events.
In combatting insurance fraud, link analysis works by ferreting out related claims in seemingly unrelated instances, such as "crash-for-cash" auto fraud schemes where criminals cause collisions in order to file whiplash and other fraudulent claims. Applying link analysis to a wide variety of databases creates a visualization of the relationships between various parties, including doctors, lawyers, vehicle owners, drivers, etc. By applying link analysis, payers can see how separate claims may actually be part of a larger scam involving a fraud ring.
Predictive analytics can deliver significant savings for healthcare payers. Insurers deploying analytics as part of their anti-fraud efforts have seen reductions in fraudulent claim losses of 20 to 50 percent and loss adjustment expenses of 20 to 25 percent. Predictive analytics and link analysis help payers detect more fraud, prioritize claims by likelihood of fraud, reduce false positives by more accurately identifying real fraud, stop fraud rings and improve customer satisfaction by streamlining the payment of legitimate claims. By making it easier to stop fraudulent claims before they are paid, analytics helps to cut costs, not only for insurance payers, but ultimately, for patients too.
Russ Schreiber is vice president of the healthcare practice at decision management firm FICO.
