Collecting Earned Revenue: How AI Maximizes Radiology Payments – Radiology Business

Today’s most pioneering radiology groups are using artificial intelligence to maximize reimbursement and minimize staff time required to chase down payments.

“The biggest chunk of uncollected revenues is sitting with the payers, not with patients” explains Navaneeth Nair, MBA, a healthcare AI developer with special expertise in rescuing lost revenues. “Their posture is, Hey, if you want it, come and get it.”

Artificial intelligence — along with machine learning and automation — empowers radiology groups and imaging centers to go and get those revenues. These tools work together via a revenue cycle management solution. 

More than software and more than labor-outsourcing, AI-driven solutions combine the impartiality of data and analytics with the insights of experienced revenue cycle managers working alongside provider billing staffers. It can take both to resolve substantial backlogs of claim denials and rejections.

Big data, mined and understood

Starting about 2014, payers and other large business entities started leveraging AI-driven solutions to provide clarity, minimize costs, and improve revenue. In 2017, Infinx Chair and Cofounder Jaideep Tandon realized that the company could better serve providers by expanding past automation to understandable AI.

Infinx led the push to unify all provider data into one source where artificial intelligence could learn from comprehensive past experience. The data includes information on which claims and denials were reimbursed, which got reimbursed at the highest levels, and which were paid in a timely way. Based on this data, AI and machine learning create rules that predict which new claims and denials providers are most likely to recoup. When the AI’s rules have been verified, it doubles down on those rules. When a different result appears, the algorithm takes that into account and recalibrates. In complex cases, Infinx specialists intervene to establish a human connection with the payer’s representative.

Radiology has been suspicious of AI

Computer scientists have been predicting that the diagnostic abilities of AI will surpass those of radiologists for a few years now — in the clinical space. One computer scientist who won the field’s highest honor, the Turing Award, claims, “We should stop training radiologists now; it is just completely obvious deep learning is going to do better than radiologists.”

Despite this prediction, recent research from Washington’s Brooking’s Institute show healthcare is going slowly in adopting AI. Overall, just one in 1,850 healthcare job postings analyzed from 2015 to 2018 requestedAI-related skills. Researchers blame this lag on hesitancy to use AI for clinical insights.

Administration is a different story. When incorporating AI, a group moves from sifting through endless spreadsheets and balancing stakeholder opinions to data-driven, intelligent insights.

When Infinx took its revenue cycle management solution into the C-suite, “The CFOs got it right away,” Nair says. “Financial leaders in healthcare are all about bringing in every dollar that could and should be coming through the door. If you can promise them even a 1% or 2% lift in revenues received, they recognize that as worth investing in.”

Directors and managers of RCM operations expressed a kind of intrigued skepticism. “They’d heard many such pitches before,” Nair explains. “They knew what it was like to get sold on revenue software that, in day-to-day use, turns out to be nothing more than glorified analytics of some kind.”

It was all Infinx needed to get started with a prototype.

Exceeding expectations

Having proven the concept of AI for solving AR backlogs, Infinx lined up one of its largest RCM customers as a design partner. This would present real-world monies to collect and a chance to tweak user-facing details like interfaces and alerts.

The collaborating partner was a Los Angeles-based provider of outpatient imaging services. Operating at more than 330 sites and employing a staff of more than 8,500 individuals, they would help Infinx scale and custom-fit the Infinx solution across a far-flung catchment area.

The two companies spent six months building out the solution. They put it into production as an alpha product, then beta-tested it for performance. Finally, Infinx began internally beta-testing for some of its full-cycle billing customers. 

The results exceeded Nair’s expectations. Among the highlights, as documented in a recently published case study, the product’s first year with their radiology partner produced:

●      28% increase in collections from denials and aged AR;

●      90% of denials addressed in less than five days, bringing in faster cash flows;

●      120-day aging AR cut by 60%; and

●      90+ days aging AR reduction by 20% in just 2 months. 

Nair continues, “We also reduced the amount of our partner’s outstanding revenues from $115 million in 2019 to $80 million in 2020. This was especially impressive because 2020 was, of course, the year of COVID.”

The striking successes owed much to Infinx’s prowess for separating AR cold cases that warranted hunting down from those that called for writing off. 

Boosting patient experience

Thanks to the work of Nair, colleagues and corporate leadership at Infinx and their testing partner, AI has now taken root as a reliable tool to help wring “new” revenues from cold AR cases. Due to the urgency to collect revenue, it initially focused exclusively on the payer sector. Infinx and their collaborating provider both knew how important it would be to improve the patient experience.

The patient experience comprises everything from making a doctor appointment to seeing the doctor and on through to the closing of the account. 

It’s well known that even patients who have good coverage spend much more time with billing and admin than clinicians. They examine explanations of benefits, trying to make sense of their share versus that of the payer, why the procedure cost what it did, and more.

Given the confusion and frustration medical statements cause, Nair encourages, “if the provider can help the patient have a better experience with the financial peace, they’re going to remember a better overall patient experience.”

Nair continues that revenue cycle managers and their teams can improve the patient experience by referring to patients as consumers. Patient can convey helplessness whereas the word consumer recasts the individual as informed, empowered and actively making market choices.

Nair draws his conclusions from a long history in artificial intelligence and healthcare. After contributing to the development of IBM’s Watson analytic engine for healthcare, he worked for health insurance giants Aetna and Anthem. He’s refined his skills and built his knowledge base at Infinx, where he’s served as chief product officer for revenue cycle management. The 3,000-plus employee firm brought him aboard specifically to incorporate AI and machine learning into its already successful automation products. 

Recognizing revenue

Asked to compare expectations around the Infinx AR recovery solution in 2019 with the actuality of what it’s delivering now, Nair pinpoints the sweet spot at which machine intelligence marries up with human expertise.

“Over the past two years we’ve realized that, as we applied machine learning to understand what needed to be recovered—and as we selected which cases to pursue and which to write off—we still had to factor in the human limitation,” he says. “The work of bringing in revenues from cold-case AR files is, after all, still hard work.”

In addition to providing data intelligence, Infinx has lifted much of the back office administrative burden by incorporating sophisticated automation. Nair explains, “The goal in this is to omit as many redundant and repetitive tasks as we can from cold-case revenue generation. This allows the provider’s staff to concentrate on knowledge-based and value-adding tasks.” The robotic automation engineered into their solutions carries out claim status and eligibility checks as well as automated appeals.

Nair is confident that AI-powered revenue cycle management can improve the quality and cost-effectiveness of American healthcare for patients, providers and payers alike. He shares that, after working with small provider organizations to those with billion-dollar revenues, all healthcare entities suffer from revenue write-offs. All can leverage AI to improve revenue streams from AR cold cases.

Spread the love

Leave a Reply

Your email address will not be published.