News: Artificial intelligence in 2020 Medicare audits

With the launch of the CMS AI Health Outcomes Challenge, healthcare facilities should expect to see investigations on artificial intelligence being used for auditing. CMS says the AI Health Outcomes Challenge is an “opportunity for innovators to demonstrate how AI tools […] can be used to predict unplanned hospital and skilled nursing facility admissions and adverse events.”

Given the alleged losses of $21 billion per year in Medicare waste and fraud (or potentially more), CMS has been instructed through an executive order to investigate AI’s use for auditing. CMS issued a request for information following the order, asking questions such as if access to AI review tools should be allowed before or after an audit, or if the use of such tools would reduce provider burden if they also reduce rejected claims and claims audits. The aim is to change the “pay and chase” model of auditing to a predictive system. Rather than employing the old system of using algorithms to search through data for fraud and abuse, CMS has the goal of using AI to prevent bad payments from the start.

For the AI Health Outcomes Challenge, CMS recently selected 25 participants. If the technology is developed, it will be used to predict adverse events and unplanned admissions to healthcare facilities. According to the schedule, seven finalists will be announced this spring. In September, a winning participant will receive $1 million  in seed money.

Editor’s note: The CMS AI Health Outcomes Challenge can be found here. An ACDIS article on Medicare waste and fraud can be found here.