Using Artificial Intelligence to Combat Revenue Cycle Inefficiencies

By Valerie Barckhoff, principal and healthcare advisory practice lead, Windham Brannon.

Image result for Valerie Barckhoff"
Valerie Barckhoff

Hospitals and health systems throughout the country are constantly looking for ways to streamline finances and fine tune operating margins. Many are now looking outside the box for solutions to help increase their operating revenue and combat the continued pressure to stretch budgets to include data security, attracting top talent and facility upgrades. Artificial Intelligence (AI), as an example, is showing promising results in healthcare to more effectively address revenue cycle inefficiencies.

AI has penetrated nearly every touchpoint in medicine, from the way emergency medical technicians (EMTs) are dispatched to assisting physicians during surgery. AI is enabling smart devices to detect cancer or a stroke, and consumers can even get help to quit smoking or address opioid addictions with the help of AI. So, it was only a matter of time to apply AI to tackle health revenue cycle inefficiencies. But how?

RCM Represents Prime Opportunities for AI

Even as revenue cycle management (RCM) becomes increasingly more complicated, there are a number of repetitive and predictable processes involved that make it an area perfect for the efficiencies that AI and intelligent automation offer?for instance, prior authorizations.

Prior authorizations, the process by which insurance companies and payers determine if they will cover a prescribed procedure or medication, are meant to help patients avoid surprise bills and unexpected out-of-network costs. However, this largely manual process is time-consuming and error-prone, resulting in $30 billion in annual costs for wrongful denials, inefficiencies and clerical errors. AI can reduce the need to assign resources to repetitive, “simple” pre-authorization requests, allowing healthcare leaders an opportunity to deploy staff to more complex, acute requests that require additional clinical information, peer-to-peer review, and/or other payer required information

Studies show that 84% of physicians surveyed said the burdens associated with prior authorization were high or extremely high, and 86% said the burdens associated with prior authorization have increased significantly (51%) or increased somewhat (35%) during the past five years.

The ability to apply AI to the revenue cycle provides yet another tool to identify inefficiencies, then allow hospitals to redesign their processes and re-allocate internal resources to maximize their net revenues going forward? to focus on more patient care instead of administrative burdens. There is a huge opportunity to gain 25- to 50-percent efficiencies for hospitals and health systems.

AI technology differs from other prior-authorization solutions in that it leverages automation, real-time analytics and machine-learning models to make smarter decisions. It automatically checks for new cases, submits them directly to payers via secure integrations, continually monitors payers for responses, and, once authorization is received, automatically submits to providers’ Electronic Health Record (EHR) systems.

Southeast Clinic Uses AI to Improve Submitted Claims, Increase Insurance Payments

Located in a large metropolitan Southeast city, one clinic that is part of a larger comprehensive healthcare network employs more than 2,200 outpatient clinical providers who schedule procedures that potentially require payer pre-certification of services?thus, necessitating a review of payer portals and the submission of pre-certification requests. The clinic’s pre-certification department was not adequately staffed with enough resources to address each request efficiently, resulting in a high volume of high-dollar denials and write-offs as well as a reduction in reimbursements from missing pre-certifications.

With limited resources available to augment the pre-certification department’s staff, the clinic implemented AI technology to help achieve several objectives:

The decision was made to apply the AI technology to outpatient cardiology payer pre-certification request procedures. The team had to educate multiple stakeholders on the use of AI’s “digital employee.” Three people at the clinic work directly with the AI technology.

Once the AI technology was fully implemented, the clinic realized the new-found benefit of being able to address a percentage of pre-certification requests that were otherwise unresolved or not submitted to payers for completion. AI minimized the need for clinic leaders to allocate resources to less complex cardiology requests?thereby increasing visibility and the resolution ratio of more complex requests and improving the potential for reimbursement.

The clinic has been most pleased with the consistent, minute-by-minute submission of pre-certification requests that would have been left unresolved prior to implementation, drastically reducing the potential for denials and write-offs. AI will continuously submit pre-certification requests?24 hours a day?increasing productivity and improving the visibility of incomplete requests and those without required information. In contrast, a human employee submits requests only during designated work hours (between eight to 10 hours a day based on work schedules).

AI has been able to perform approximately 50 percent of the workload assigned without manual intervention with accuracy rates higher than work involving humans. Prior to the implementation of AI, claims submitted with pre-cert information may not have been processed by the department due to limited staffing availability.

AI Goes Mainstream in Healthcare

Successful RCM truly boils down to effectively using people, processes and technology, and AI is the perfect solution to help identify areas where streamlining can occur, and processes can be automated. It is the ideal solution to free staff from necessary but redundant, manual and time-consuming tasks and afford them the ability to focus on more specialized activities that will benefit the organization. It is also an affordable way to reduce labor costs and recover leaked revenue.

By automating portions of the revenue cycle, hospitals can implement a higher volume of claims at a cost-effective rate, providing a competitive edge in today’s healthcare landscape of thin margins. Additionally, as machine learning components of AI technology learns the particulars of that organization, it will provide valuable and meaningful insights to healthcare leaders to help identify and plan for perpetual opportunities for efficiencies and increased revenue.

Once thought of as “leading edge” technology, AI is the perfect solution for the here and now that can deliver an immediate return on investment. It’s time to take a closer look at how AI can help hospitals and health systems cut costs and increase revenue in their operations.

Write a Comment

Your email address will not be published. Required fields are marked *