The United States spends more on healthcare than any other nation in the world. In 2019, the annual healthcare spending was 3.6 trillion USD, which is an astounding 18 percent of the US GDP. This is more than twice the rate of healthcare spending of any other OECD country. Of this astronomical cost, the National Healthcare Anti-Fraud Association estimates that healthcare fraud annually costs the US about $68 billion. Other estimates range as high as $230 billion. While there is a tangible financial impact to the taxpayer, there’s an intangible human impact as well – this money could have been used to actually treat deserving patients for bona fide care, potentially saving many lives.
Clearly, healthcare fraud is an ongoing issue, and one that needs to be tackled head-on. Recently, the DOJ conducted its biggest healthcare fraud takedown yet, where 345 people from 51 federal districts were charged in connection with cases responsible for over $6 billion in losses. Among the guilty were over 100 doctors, nurses, and other medical professionals.
With cases like this increasing by the day, enforcement agencies have started zeroing in on healthcare organizations with regards to telemedicine and other fraud.
This is where healthcare AI tools like Felix’s Payor ProtectionTM come in. Felix’s Payor ProtectionTM AI platform helps to proactively identify and predict potential fraud, waste and abuse cases in patient care using a patent-pending technology. The AI engine keeps constant watch over the necessary data and detects a variety of suspect factors such as diagnoses and incidents, as well as deviations overcharging for medical equipment, pharmacy gaps and overall cost. This technology has been proved in the real world, saving ACOs (and the CMS) millions of dollars YTD.
Fraud investigations can take years and a large number of resources both in payors’ special investigation units and government fraud units, so streamlining the identification of fraud and the necessary examples within a fraud packet to justify the investigation is a key requirement for any AI system that tackles Fraud, Waste and Abuse. During the course of an investigation, the suspect operator may change behavior patterns to stay under the radar of rules-based-systems, so a self-learning and real-time prediction AI system like Felix Payor can help the Payor stay current and update the investigation as needed.
Explainability is key and a central tenet to the Felix Payor ProtectionTM offering. Whether the payor or ACO has their own front-endapplication to utilize or would like to use Felix’s, the engine clearly explainsits reasons for flagging an operator as potentially fraudulent. Our ergonomic Fraud dashboard allows for quick, easy and concise access to relevant insight and supporting information to identify/predict suspect cases of fraud, waste and abuse.
Felix Payor ProtectionTM keeps in check the growing fraction of healthcare providers and other operators who systematically and insidiously overcharge or otherwise take advantage of patients who have put their trust in them. For more information on Felix Payor ProtectionTM, write to us at info@felixhealthcare.ai.