AI in the revenue cycle: How to use a data-driven approach to prioritize optimal processes for automation  

Jackie Drees - Print  | 

The revenue cycle presents various challenges for the healthcare industry; from staffing constraints to rapidly changing regulations providers must adhere to when seeking reimbursement. AI can offset both these issues by helping hospitals and health systems automate time-consuming, repetitive processes.

Common areas for AI within the revenue cycle include claim status, eligibility and prior authorization.

In an April 21 webinar hosted by Becker's Hospital Review and sponsored by Olive, Ross Moore, general manager of revenue cycle at Olive, discussed the steps hospitals must take to establish a data-driven approach when crafting an automation program and how AI can help take revenue cycle operations to the next level.

Picking the right partner

Before healthcare organization leaders roll out AI and automation capabilities, they must first choose the right partner. Identifying the best vendor requires analyzing the company's previous work and determining if their solutions align with the hospital's revenue cycle goals.

The vendor partner should help the hospital identify organization-specific opportunities to automate and which will likely provide the greatest return on investment. Together, the hospital and AI partner should develop business cases around those processes that will generate the lowest amount of maintenance and exceptions managed on the back end.

"Make sure that the partner is not going in with a blank slate. They should have a sense of what are going to be the best things to automate," Mr. Moore said. Once the automation opportunities are identified, the organizations should narrow down their selection to which projects will drive the most value for the health system.

Scoping and mapping

Once the business cases are developed, health system leaders must consider factors such as net revenue and labor requirements for each automation opportunity. They can do this by working with their governance group to scope these processes out and then selecting the cases they want to move forward with.

"Keep in mind when you're using this data driven approach, that not all processes are going to be created equal," Mr. Moore said. "Some will give more value than others; that value will be derived from both the revenue impact and the cost impact."

Fostering a deep understanding of the core processes, systems and data involved with the automation opportunities will set the AI partner up to develop automated workflows that interface directly with the hospital's existing infrastructure.

Reducing errors and increasing revenue with AI and automation          

Automation will help hospitals "go one level beyond" capabilities such as real-time eligibility, according to Mr. Moore. RTE allows medical staff to electronically confirm patient insurance coverage for treatments. From a net revenue perspective, using this data-driven approach can identify issues with claim denials and revenue leakage.

One of the most common reasons for a denial is when a staff member may have accidentally selected the wrong insurance plan. Mr. Moore provided the following example of a patient who has Cigna insurance, but there are five different plans in the billing system. If the hospital employee selects the wrong plan, it causes a denial in the back end, which, if the team does not review, can result in a write off.

Automation can prevent these types of oversights by ensuring the right plan is selected at the very beginning of the payment process.

"Focusing on better processes and automating the eligibility up front is going to allow you to be able to drive more benefit on the back end when you're building that business case to show how much benefit you would expect to get from that automation," Mr. Moore said.

Click here to listen to the full webinar.

More articles on artificial intelligence:
Penn Medicine, Intel collaborate on AI to identify brain tumors
Mayo Clinic tests AI to map how coronavirus affects heart health
AI can categorize lung nodules' cancer risk, study suggests

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.