Mastercard: Using AI To Cure Healthcare’s $240B Fraud, Waste And Abuse Problem

Healthcare in the U.S. is a massive industry.

According to the Centers for Medicare and Medicaid, $3.5 trillion — or roughly $11,000 per person — was spent in the U.S. in 2017 on healthcare services. By the year 2027, the expectation is that those costs will have swelled to $6 trillion annually or roughly $17,000 per citizen or 19 percent of the GDP.

There is a lot of value purchased with those trillions — life-saving treatments and medication among them — but as Beth Griffin, vice president-Healthcare, Cyber & Intelligence, Mastercard, noted in a recent PYMNTS Masterclass interview with Karen Webster, a staggering amount of that money is buying nothing at all. Instead, she noted, an estimated $240 billion is going out the door to fraud, waste and abuse (FWA).

That’s a lot of money to lose, and enough to have a real impact on costs in the system — both for the insurance companies that are the main payors in the system, and for the patients who are picking up an increasing share of out-of-pocket healthcare costs and feeling the pinch of price in both premiums and services rendered.

Mastercard is no stranger to healthcare, Griffin said, as it has been deeply enmeshed in the payments side of the business for two decades. But when the company started looking more closely at the healthcare system, it realized it had relevant capability when it came to using artificial intelligence (AI) to secure the system in such a way that the process moves smoothly for legitimate interactions while locking out the bad ones.

“We securely store over 18 petabytes of sensitive data — this is a significant amount of data that we’re dealing with every day,” she said. “And we detect and defeat over 200 attacks on our network every minute of every day. So as we looked for areas to focus on in healthcare, we recognized that fraud, waste and abuse could benefit from our experience and competencies, given our leadership in fraud mitigation and security,” Griffin said, noting Mastercard’s 2017 acquisition of AI firm Brighterion.

The challenge, she said, is to bring the real-time, scalable predictive power out of the world of payments into the adjacent, but incredibly complex, world of healthcare. But the effects, at least so far, have been immediate.

Augmenting a Manual Process

The world of FWA in healthcare is often successfully targeted by fraudsters because there are so many weak points, Griffin noted. From a transactional perspective, what typically happens today is that a claim file is sent from a provider to the insurance company payer who edits and adjudicates the claims, and then sends the file and the payment back to the provider.

After the fact, when the money has already changed hands, the FWA team will review the claim files to identify suspicious activity, either coming directly from providers or from those posing as providers. These teams are often highly skilled investigators who know how to pinpoint irregularities, errors and other overpayments issued from the payer, Griffin said.

From those manual reviews, these highly experienced investigators create rules, monitor suspicious activity and collaborate with law enforcement to mitigate fraud in the system, she continued. The problem is that when they identify something that may be fraudulent, wasteful or inappropriate, they have to go back and try to get reimbursement from the provider. That often doesn’t go all that well — only an estimated 5 percent to 10 percent of FWA funds are ever recovered.

Mastercard’s proposed improvement to the system, Griffin noted, is simple: leverage AI and move the fraud fight efforts up in the process, so that fraud is identified before it happens, and funds are blocked before overpayments are made.

Modifying the System

As Griffin pointed out, the goal is not to get rid of the existing processes or the investigators that work with them. To the contrary, by building AI into the process, the intention is to make their jobs easier and more efficient.

“We’re not trying to replace what exists today — we’re really trying to complement what exists today,” she said. “In the end, if I’m in a special investigative unit, I can take advantage of the AI on top of what we’re already doing, and it decreases the false positives. So instead of having 500 alerts per day to investigate, my team might have just 50 that are highly likely to be fraud or abuse of the system.”

By the numbers, when they apply the Brighterion AI to the transaction flow in legacy solutions, they see a 10-20 times reduction in false positives. And they are spotting on average 2-3 times more fraud that has managed to slip under the radar, in some cases for years.

Griffin recalled one example of a series of genetic tests that were ordered for a cancer patient, which didn’t trigger any traditional rules because of the lower individual procedure costs and relation to the disease. However, the AI detected that the testing was ordered after the patient had been in a hospice instead of early in her cancer treatment, which might not have been appropriate. Pulling at that string caused the AI to find that there were a lot of tests that might have been requested earlier in the treatment process, but were actually ordered inappropriately late in the patient’s treatment to capture funding for medical procedures that never happened.

As Griffin pointed out, Mastercard recognizes the complexities in healthcare, which is a highly regulated, very fragmented, very interconnected system with a staggering number of interactions and friction points waiting to be addressed, with legacy systems that may not be quite up to the task of addressing them.

In a system this big, real and lasting change is a delicate proposition.

But unlike even 15 years ago, when industry players were far less open to new innovations like AI and new processes for fighting fraud and curbing abuse, industry leaders are coming around to the idea that this is no time to wait around when it comes to modernizing their infrastructure.

Griffin said that’s because at the end of the day, since an estimated 3 percent to 10 percent of all healthcare costs are attributed to FWA, everyone — patients like you and me — are being directly impacted with an increase in our healthcare expenses. By leveraging AI and other advanced technologies, we are contributing to a market in which we are all positively impacted by the services we provide, with lower healthcare costs and the ability to interact with our healthcare providers and payers, confident that our healthcare activity is safe and reliable.

A transformation takes time, but it’s worth the effort.