Current Situation
Outright fraud is difficult to prove or quantify and may affect far less than 10% of total U.S. healthcare. However, it is estimated that up to 25% of healthcare costs are affected by the broader category of fraud, waste, and abuse.
As quickly as payers move through legal and educational means to address FWA, bad actors (frequently physicians) adapt their approaches.
Goals and Objectives
Identify fraudulent schemes and actors promptly to serve as both a deterrent and a means of reducing overall losses.
Technology Deployed
Predictive software tools, improved workflow processes, and automated outreach to medical providers and patients/members that can be used to identify schemes and likely sources of waste or abuse
AI supports predictive payment integrity by predicting members and/or providers that have a propensity to cheat the system
Use Case Summary
Bad actors have reduced the itemized amounts of FWA-related claims but increased their frequency to evade detection. This has increased the need for software and processes that can process huge quantities of claims and other data using sophisticated search techniques, especially to process data to verify and track the histories and current activities of hundreds of thousands of physicians and organizations in real time.