Topics
More on Revenue Cycle Management

Artificial intelligence holds promise in improving revenue cycle management in healthcare

By automating certain data-driven tasks, administrative waste can be dramatically reduced and RCM operations can move more efficiently.

Jeff Lagasse, Associate Editor

The presence of artificial intelligence has been increasing in the healthcare industry, and with the technology maturing and becoming more viable, the opportunities for it to make administrative and process improvements have been increasing – and revenue cycle management is one area in which this is especially manifest.

The problem with many current revenue cycle processes is that it can result in a lot of friction and waste. In a HIMSS20 digital presentation, Mark Morsch, vice president of technology at Optum360, cited data indicating that there can be as much as $200 billion in administrative waste in the healthcare system due to inefficient revenue cycle practices.

"That's waste in the system between providers and payers that's generated from a lot of inefficiency, from inaccurate documentation and coding, a lack of transparency, and both sides not being aware of the appropriate steps a lot of times," Morsch said.

HIMSS20 Digital

Learn on-demand, earn credit, find products and solutions. Get Started >>

Hiring data provided by Optum360 illustrates the extent to which administrative spending has increased. Hiring for physicians has increased since 1970, but nearly to the extent of administrative hires, which have grown 3,000% during that time.

The potential to mitigate waste with AI is joined by an overall positive sentiment toward the technology among healthcare professionals. According to Optum's data, 97% of those in the industry trust AI to handle administrative or clinical applications, while 85% are currently implementing or developing some kind of AI strategy. More than half, 55%, expect AI to achieve positive ROI in fewer than three years.

On average, organizations are investing $39.7 million in AI implementation over the next five years. Already, almost one-third of health plans, providers and employers are automating processes such as administrative tasks or customer service, and 56% of health plans are using the technology to combat fraud, waste and abuse. Thirty-nine percent of providers are using it to personalize care recommendations.

"It's not just technology," said Morsch. "When you think about leaders investing in this technology, leaders are looking for expertise. They're looking for partners who know AI and know how to apply it to their workflows and processes not just to automate or partly automate what's there, but in many ways to reinvent them. Talent is very significant across the board when you're talking about AI."

Because of that, 52% of health executives expect AI to create more work and hiring opportunities.

For revenue cycle specifically, Morsch said value comes in the form of speed, capacity and consistency. Routine things that are performed over and over can potentially be automated, and in many cases can remove flaws, errors and the fatigue that understandably comes from undertaking those things manually.

It also can help to address the increasing amount of data in healthcare, sifting through the data with a speed and efficiency that a human being simply cannot match. Specifically, natural language processing, or NLP, supports clear documentation and accurate claim coding. And machine learning, an important cog of AI technology, can optimize edits by the payer and can score denials to inform high-potential appeals.

"Natural language processing can grab info from clinical documentation and apply rules and models to see where the documentation is strong or weak – and it generates support and diagnostic coding used across care settings," Morsch said.

Another NLP application is in the area of AI-enabled case stratification. AI can examine a patient record and determine the appropriate setting for a patient, whether it be on the inpatient side or the outpatient side; if a patient is deemed likely for inpatient care, NLP can facilitate an enhanced case review, capturing the risk factors related to the case and identifying specific recommendations. A likely outpatient won't be subject to the second stage of an NLP-enhanced case review.

"You're supporting a case manager, extending their reach and letting them focus on those cases where their expert judgement can most readily apply," said Morsch. "With that comes appropriate reimbursement and appropriate reporting."

The result? Case managers can in some cases save 125 hours per month in administrative tasks.
 

HIMSS20 Digital

Experience the education, innovation and collaboration of the HIMSS Global Health Conference & Exhibition… virtually.

Twitter: @JELagasse

Email the writer: jeff.lagasse@himssmedia.com