MDDI Online is part of the Informa Markets Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Apixio Launches AI Healthcare Audit Solution

The emergence of electronic healthcare records and recent advancements in computing technology have created the need for Apixio’s artificial intelligence solution.

Darren Schulte, MD, CEO of Apixio

Courtesy of Apixio

Apixio is using artificial intelligence (AI) to make healthcare audits simpler and more efficient for all involved. The San Mateo, CA-based company is launching an AI solution called the HCC Auditor, to help health plans and provider organizations to undertake internal audits of their risk adjustment payment data with increased accuracy and in far less time than traditional methods.

The Centers for Medicare and Medicaid Services are increasing the frequency of health plans audits offering Medicare Advantage (MA) products to ensure correct payments. Given the potential revenue impact, it typically takes health plans and provider organizations two to three times longer to perform a thorough review of reported diagnosis codes.

“The key is to solve the problem physicians and hospitals are grappling with today,” Darren Schulte, MD and CEO of Apixio, told MD+DI. “The problems they’re dealing with are; what they’re being paid for; their healthcare delivery challenges; and how technology can help them today.”

The HCC Auditor uses Apixio’s machine learning technology to link medical records to submitted diagnosis codes and determine whether there is sufficient documentation in patient encounter notes per coding guidelines.

About 85% to 95% of risk adjustment payments for MA plans are based upon diagnosis codes on encounter claims from clinics and hospitals. The remaining 5% to 15% of payment comes from chart coding. The supporting patient notes, which are linked to codes from physician offices, are not typically reviewed by health plans prior to submission for payment. Unless a physician practice is employed by an MA plan, there are few incentives for their diagnosis coding to be accurate or complete for risk adjustment purposes.

A recent survey conducted by Apixio on coding accountability revealed that 50% of health plan coders claimed that their organization reviews less than 10% of these charts for quality assurance. In these cases, overpayment is more likely a result of insufficient oversight and review of coding practices in clinics and hospitals than from upcoding practices by health plans.

Apixio said its AI technology could significantly help with this issue.

Schulte said the healthcare landscape has changed and now it can support AI technologies.

“Ten years ago, it wouldn’t have been possible for a solution like this to exist,” he said. “Physicians and hospitals didn’t use any sort of electronic medical records therefore information about a patient’s healthcare was handwritten and put into folders tucked away into a filing cabinet. Getting that data; aggregating it; and making sense of it would be difficult.”

Schulte noted this is the first step and that the technology has the potential to grow significantly in the next five years.

“This product is just another step toward … getting the trust and credibility of the market,” Schulte said. “We’re letting them know these technologies work because they’re skeptical and AI really has a true impact in healthcare.”

Filed Under
500 characters remaining