January 09 2019 | 0 Comments | 97 reads Average Rating: 4
4 Ways Machines can Help in the Fight Against FWA
Fraud, waste and abuse (FWA) in the healthcare industry has been estimated to cost anywhere from $80 billion to $272 billion each year.1,2 Unfortunately, fighting FWA is not easy. It typically takes dozens of highly trained experts months just to go through the amount of data required to successfully identify complex patterns of FWA.
Machine learning could come to the rescue with its ability to uncover these types of patterns in a fraction of the time. Case in point: Machine learning could quickly determine 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.
Machine learning does this better than humans by:
1. Parsing through massive amounts of data and hundreds of potential decision points to find hidden patterns and relationships between seemingly unrelated events.
2. Using predictive analytics to quickly build an initial set of models of what the “normal” patterns are, then using those models to detect anomalies or occurrences that fall outside those patterns.
3. Refining models as more information about the outcomes becomes available. Such refinements enable organizations to focus limited resources on the areas where they’re most needed while paring down the number of false positives.
4. Scoring the severity of variations, which enables investigators to set priorities for both the highest probability of uncovering FWA and the best ROI for containing those costs.
Even though machine learning does a great job of finding patterns that people typically wouldn’t see, human expertise is still required to determine what to do about them. Human expertise is also required to improve the basic models. For example, machine learning bases what’s “normal” on what it sees across the organization. So, 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.
This blog is based on FWA in Healthcare: What the Battle Against Identity Thieves Can Teach Us, an article that was published in HealthCareBusiness daily news.
1. LexisNexis. Fraud, Waste and Abuse Tool Kit. https://www.smartbrief.com/sites/default/files/pdf/about/executive_summary.pdf.
2. The Economist. The $272 billion swindle. https://www.economist.com/united-states/2014/05/31/the-272-billion-swindle.