Claim denials remain one of the most persistent and costly challenges health systems face. According to research published last year by the Healthcare Financial Management Association, “out of $3 trillion in total claims submitted by healthcare organizations, $262 billion were denied, translating to nearly $5 million in denials, on average, per provider.”
The outbreak of the Covid-19 pandemic exacerbated the problem, with national denial rates increasing 11 percent between July 2019 and June 2020.
With the Rise of AI, What IP Disputes in Healthcare Are Likely to Emerge?
Munck Wilson Mandala Partner Greg Howison shared his perspective on some of the legal ramifications around AI, IP, connected devices and the data they generate, in response to emailed questions.
The fact that a majority of denied claims are preventable is only one aspect of a much deeper problem. Reworking claims take time, money, and resources.
A health system’s claims quagmire usually cascades from several underlying internal and external problems, including:
- Complex and constantly changing undocumented adjudication rules across payers makes efficient claims management exceedingly difficult.
- Errors and inefficiencies in one area, such as benefits eligibility, can lead to downstream problems in the revenue cycle.
- Inefficiencies in processing the increasing number of prior authorizations can easily push up a provider’s denial rate.
- Reliance on manual processes is both expensive and labor-intensive.
Solutions like robotic process automation can work well for simple, repetitive tasks, but to truly optimize reimbursement, health systems should investigate the potential of artificial intelligence (AI).
A Personalized Approach to Medication Nonadherence
At the Abarca Forward conference earlier this year, George Van Antwerp, managing director at Deloitte, discussed how social determinants of health and a personalized member experience can improve medication adherence and health outcomes.
AI provides the power of automation but takes it to a completely new level by adding the predictive capabilities, ongoing learning, and insights necessary to proactively prevent claims from being denied before they are submitted, speed up and prioritize rework by humans, and leverage advanced analytics to uncover actionable insights from a health system’s own data to optimize claims management across the revenue cycle.
Level the playing field
Most claims management technology is designed to stop claims likely to be denied by payers, based on well documented payer rules, from ever being delivered.
A billing department will apply standard or customized edits to a claim, based on what a payer has publicly stated they will use to adjudicate it. After the edits are made, the clean claim is sent to a clearinghouse or the payer for adjudication.
Unfortunately, the rules payers use to adjudicate claims are constantly in flux and often change without notice. This leaves providers playing a perpetual game of catch up.
AI has the potential to level the playing field by making highly accurate calculated predictions on how likely it is a claim will be denied, including denials from undocumented payer changes. Therefore, empowering providers with real-time capabilities to monitor, and if needed, take immediate actions to correct claims prior to submission to maximize reimbursement. The key to doing this successfully requires the AI modeling to be based on the provider’s own claims and payments from their payers, not from a generic pool of comingled providers claims and payers reimbursements.
Focus on recoverable claims
The energy and resources devoted to appealing denied claims is often based on dollar amount rather than the likelihood of recovery.
It seems intuitive to focus on recovering a $100,000 claim rather than a $5,000 claim. However, if the chances of appeal for the former are vanishingly small, then claims departments are simply wasting time and money trying to collect revenue that will likely not be recovered.
Here, AI can make a real difference through sophisticated claims denial and successful re-submission/appeal modeling. Scouring the provider’s own systems of record, an AI platform can analyze the history of the claim in question, as well as similar claims to uncover such insights as past appeal success and percentage of reimbursement recovered.
This level of granularity gives providers the ability to score denials based on their likelihood of reimbursement, a methodology that will bear more fruit than focusing on claims solely because they are high dollar.
End-to-end claims management
AI platforms can do more than mere claims management. Appropriately scaled, AI can address many problems and inefficiencies that have significant downstream impacts on the revenue cycle. The two most obvious applications are related to patient eligibility and prior authorizations.
Patient access can be a major source of errors, particularly around eligibility. AI can bring intelligence to real-time eligibility checks, delivering higher levels of automation, accuracy and efficiency.
Prior authorizations and medical necessity are also a common source of claims issues. As the number of prior auths increases, the need for process improvements in claim management grows more essential. The potential for AI in this area includes automating key aspects of prior auth processes, including determining the need for pre-authorization, surfacing and attaching relevant medical documentation and images, and monitoring the status of authorizations.
Another benefit of AI is its ability to apply learning to prediction. Intelligent platforms can then flag present and future claims at risk for denial from insights it surfaces from oceans of historical remittance data. More than flagging potential roadblocks, AI programs can use its analysis to identify root causes within the claims workflow.
Impact of staff
One of the drawbacks of AI technology is the pervasive idea that the technology is a threat to human job security.
Those concerns are valid, but the intentions of AI deployment can be misconstrued. In today’s hospital billing environment, staff are increasingly burdened to do more with less. Staff that are stretched too thin leads to the fraying of essential efficiencies.
In the case of claims management, AI is best thought of as a staff enhancement, handling repetitive tasks at scale and performing complex analysis, while employees focus on reworking claims most likely to realize reimbursement.
Provider organizations may never completely eliminate their denied claims. However, the power of AI can help providers recoup more of what they are owed, better anticipate at-risk claims and identify claims that are worth the effort to appeal.
Photo: Michail-Petrov-96, Getty Images
Jason Considine is Chief Commercial Officer at Experian Health, the leading provider of revenue cycle management, identity management, patient engagement, and care management solutions for providers, physician groups and payers.
