Data analytics algorithms have the ability to identify unique patterns within your claims, such as claims that are being repeatedly declined but are then never re-billed correctly. This is a red-flag that a fraudster is fishing to see if your rules-based payment engine can be abused. If there is a weakness there, the provider will continue billing those codes and abusing the system, defrauding you out of thousands of dollars and potentially never being caught.

Examples of Abuse

A prime example is where a claim should be filed for one unit of a 60 mg drug, but the provider bills for 60 units instead. If you don’t have an automated rule to catch this, the provider may be reimbursed for 60x’s what they should be reimbursed for.  Over time, the provider will take advantage of this and continue to bill in the same way, in hopes that they do not get caught by more advanced technology. However, implementing ML and AI can assist you in identifying these patterns and allow you to squash fraudsters quickly.

Catching Fraud

When caught, fraudsters will oftentimes lay the blame back on the company by saying “Well, we thought it was okay because it was paid out”. While it can be murky laying the blame there, it’s also difficult for them to justify such obvious over-billing. With AI and ML algorithms, these issues can be easily identified, as well as who is committing them. Investigators can act quickly, the rules can be altered, and lost money can be mitigated. AI and ML algorithms can easily find such issues and identify who is committing them. Recovering overpayments can be difficult if not done swiftly, so it’s imperative to jump on it as quickly as possible.

Leave a Reply