Data Analytics Can Save Billions in Healthcare

By Denise Fletcher 
Vice President and Chief Innovation Officer,
Healthcare Payer and Pharma,
Xerox Corporation
   





Finding fraud, waste and abuse in health insurance claims can be like finding needles in a haystack, but they’re needles worth looking for. Financial losses due to healthcare fraud are estimated to be in the tens of billions of dollars each year. This translates into higher premiums and out-of-pocket expenses for individuals and businesses, as well as reduced benefits for consumers.

Fraud, waste and abuse are already hard to detect, and you can expect more challenges with the new patients, data and requirements that healthcare reform brings. The good news: Advanced algorithms and data analytics can root out these unnecessary expenses. The logic behind this capability is simple: When payers know the misbehavior that’s taking place, they can create appropriate deterrents.

As a primer, I offer the most common types of fraud, waste, and abuse:

1. Upcoding: When a provider bills for a service that is more expensive than what was actually performed in order to receive a larger reimbursement. For example, submitting a claim that contains a code for applying a cast on a broken leg when the patient used only crutches. 
2. Unnecessary Procedures: When a physician performs a procedure above what is required because it costs more money. This could be as serious as ordering an invasive procedure, such as surgery for a dislocated knee cap that could have been stabilized with a cast.
3. Drug Abuse: Includes writing unnecessary prescriptions; recommending brand name drugs over generic; pushing prescriptions to one particular pharmacy, and more.
4. Identity Theft: Ranges from a neighbor or friend who borrows an insurance card to receive treatment, to a medical services provider who uses one insurance card to bill multiple insurance companies. 
5. Overpayment: This can appear in the form of duplicate payments, or allowing a provider to submit a claim more than once. It can also be as simple as an untapped credit balance due to overpayment.

These problems require advanced analytics and predictive modeling that looks at outlier data as well as relevant data, an improvement over the commonly-used rules-based systems. The results can help payers uncover emerging patterns and anomalies, and respond quickly.

Are you a payer struggling with FWA? What are you doing to combat this threat?

Share this post