FWA in healthcare: What the battle against identity thieves can teach us
October 08, 2018
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.
Again going back to the example of FWA around opioids, one of the challenges payers and providers face is separating legitimate instances of patients/members seeing multiple providers and filling prescriptions at multiple pharmacies (such as a cancer patient with other comorbid conditions) from patient/member drug-seeking behavior. How many different physicians and/or pharmacies are too many?
It could take a dozen human experts many months to go through the amount of data required to gain enough understanding to develop rules around these questions. Even then, the answer would likely be incomplete. But machine learning can uncover patterns in the data in hours, or a few days at most, helping reduce false positives while showing with a high degree of certainty that a patient/member who goes to five providers and five pharmacies to get five prescriptions filled within a certain amount of time is exhibiting drug-seeking behavior. The payer or provider can then take action to address it with reasonable certainty that the time will be well-spent, ideally resolving the issue to benefit the patient/member’s health, and preventing future FWA.
As it gains more experience within the organization, machine learning can not only point out areas of variability but also begin to score the severity of those variations. Having that information enables investigators to set priorities for both the highest probability of uncovering FWA and the best ROI for containing those costs.
The human factor
Machine learning doesn’t mean that FWA efforts can go on auto-pilot. While machine learning does a great job of teasing out the variables and finding patterns humans wouldn’t ordinarily see, human expertise is still required to determine what to do about them.
Human expertise is also required to improve the basic models. Keep in mind that machine learning bases what’s “normal” on what it sees across the organization. If the proper chronic condition code has never been included in a particular diagnosis, machine learning will view that as normal. It is up to the human experts to recognize this issue and provide a framework that allows the algorithm to “train” itself to understand which medications are normally associated with which conditions and point out any discrepancies.
Another example is determining whether hospital bills have been overpaid. Suppose anesthesia is coded for a procedure in the emergency department that doesn’t ordinarily require it. The difference might go unnoticed by humans, but machine learning will see the anesthesia as unusual and will point it out. It will then be up to a human reviewer to determine whether there was a legitimate exception or the claim should be amended before being submitted. If it should be amended, the algorithm will automatically be improved to “understand” the next time something similar occurs, saving time and the cost of another review down the road.
Out of the shadows
No matter which figures you accept, FWA in healthcare is a multibillion-dollar problem in the U.S. Those are billions of dollars that could be dedicated instead to delivering care. Yet uncovering instances of FWA can be difficult – especially when, like identity thieves, the perpetrators use their knowledge of the healthcare system to hide their efforts within it.
Machine learning can help uncover the subtle variations and patterns that indicate FWA is occurring, and help healthcare organizations focus their anti-FWA efforts in areas that will deliver the best ROI. It’s the best bet to level the playing field.
About the author: Lalithya Yerramilli is vice president of analytics at SCIO Health Analytics. She has 15 years of experience in analytics in the insurance, healthcare, and life sciences industries, working with customer info-base, transactional, physician level, patient level, claims, and longitudinal data sets.
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.
Again going back to the example of FWA around opioids, one of the challenges payers and providers face is separating legitimate instances of patients/members seeing multiple providers and filling prescriptions at multiple pharmacies (such as a cancer patient with other comorbid conditions) from patient/member drug-seeking behavior. How many different physicians and/or pharmacies are too many?
It could take a dozen human experts many months to go through the amount of data required to gain enough understanding to develop rules around these questions. Even then, the answer would likely be incomplete. But machine learning can uncover patterns in the data in hours, or a few days at most, helping reduce false positives while showing with a high degree of certainty that a patient/member who goes to five providers and five pharmacies to get five prescriptions filled within a certain amount of time is exhibiting drug-seeking behavior. The payer or provider can then take action to address it with reasonable certainty that the time will be well-spent, ideally resolving the issue to benefit the patient/member’s health, and preventing future FWA.
As it gains more experience within the organization, machine learning can not only point out areas of variability but also begin to score the severity of those variations. Having that information enables investigators to set priorities for both the highest probability of uncovering FWA and the best ROI for containing those costs.
The human factor
Machine learning doesn’t mean that FWA efforts can go on auto-pilot. While machine learning does a great job of teasing out the variables and finding patterns humans wouldn’t ordinarily see, human expertise is still required to determine what to do about them.
Human expertise is also required to improve the basic models. Keep in mind that machine learning bases what’s “normal” on what it sees across the organization. If the proper chronic condition code has never been included in a particular diagnosis, machine learning will view that as normal. It is up to the human experts to recognize this issue and provide a framework that allows the algorithm to “train” itself to understand which medications are normally associated with which conditions and point out any discrepancies.
Another example is determining whether hospital bills have been overpaid. Suppose anesthesia is coded for a procedure in the emergency department that doesn’t ordinarily require it. The difference might go unnoticed by humans, but machine learning will see the anesthesia as unusual and will point it out. It will then be up to a human reviewer to determine whether there was a legitimate exception or the claim should be amended before being submitted. If it should be amended, the algorithm will automatically be improved to “understand” the next time something similar occurs, saving time and the cost of another review down the road.
Out of the shadows
No matter which figures you accept, FWA in healthcare is a multibillion-dollar problem in the U.S. Those are billions of dollars that could be dedicated instead to delivering care. Yet uncovering instances of FWA can be difficult – especially when, like identity thieves, the perpetrators use their knowledge of the healthcare system to hide their efforts within it.
Machine learning can help uncover the subtle variations and patterns that indicate FWA is occurring, and help healthcare organizations focus their anti-FWA efforts in areas that will deliver the best ROI. It’s the best bet to level the playing field.
About the author: Lalithya Yerramilli is vice president of analytics at SCIO Health Analytics. She has 15 years of experience in analytics in the insurance, healthcare, and life sciences industries, working with customer info-base, transactional, physician level, patient level, claims, and longitudinal data sets.