By Lalithya Yerramilli

When it comes to uncovering fraud, waste, and abuse (FWA) in healthcare, payers and providers can learn a lesson from the ongoing battle against hackers looking to commit identity theft: The culprits are unlikely to be immediately obvious – at least if they don’t want to get caught.

They often hide in plain sight. For example, they may disguise a bogus Wi-Fi connection as one supplied by restaurant or coffee shop, especially near a large corporation. Login to check your email or do a little shopping and zap! – your information is stolen. They also use phishing schemes to make you think you’re responding to a friend or a legitimate company when they ask for your credentials. The more they work to "fit in”, the more successful they’re likely to be.

Similarly, this is what the more sophisticated participants in FWA in healthcare do. For example, those looking to obtain large quantities of opioids, whether for their own use or to sell to others, don’t go all-in with a single provider or pharmacy. They spread their requests across many providers and pharmacies, keeping the individual numbers at each "under the radar" to avoid calling attention to them. It’s only when you look at them in the aggregate that the numbers become suspicious.

The challenge is that most payers and providers don’t have the human or technology resources to look at the massive quantity of claims data in the aggregate to find the subtle patterns that indicate the possibility of FWA. Given that FWA has been estimated to cost anywhere from $80 billion to $272 billion each year, it’s critical that payers and providers find a new way to address it. This is where adding machine learning to human expertise can make a huge difference in the battle against FWA.

Understanding the relationships through machine learning
Where machine learning excels is in parsing massive amounts of data and hundreds of potential decision points to find hidden patterns and relationships between seemingly unrelated events. These relationships are so subtle, humans will often miss them – a fact those purposely committing FWA count on to hide their activities.

Using predictive analytics, machine learning can quickly build an initial set of models of what the “normal” patterns are, then use those models to detect anomalies or occurrences that fall outside those patterns. It can then alert human experts who can investigate further to determine if an action needs to be taken.

As more information about the outcomes becomes available, the models can be further refined, enabling the organization’s limited resources to focus on the areas where they’re most needed while paring down the number of false positives.

Health IT Homepage