How AI Can Help Payers Streamline Prior Authorizations to Save Time, Improve Member Care

Many pre-approval requests are still received by fax. Natural language processing and artificial intelligence can extract and use information from faxes.

The findings below were part of a 2022 study by McKinsey & Company on the impact of applying artificial intelligence to the prior approval (PA) process. The study found that the strategic use of AI will benefit the entire healthcare ecosystem for providers, payers and members.

“Our analysis suggests that artificial intelligence-enabled pre-approval can automate 50% to 75% of manual tasks, increasing efficiencies, reducing costs, and freeing physicians from both payers and providers to focus on complex cases and can concentrate on the actual care and coordination.” according to the McKinsey study.

To understand why McKinsey researchers were able to make such a bold claim, let’s step back and examine how most health insurers receive pre-approval requests today. A 2021 AMA survey found that nearly half (47%) of providers always or almost always submit PAs for medical services by paper fax.

This means that a large proportion of the PA requests that your employees have to process come in as unstructured data on fax machines. Digital fax pages are also technically “images”, not data. And that means your employees have to manually review those faxes, prioritize the cases, and often manually enter the information into a database.

The inefficiencies of unstructured data

A 2020 CAQH study found that manually reviewing and responding to PA requests — communicating with vendors by phone, mail, or paper fax — costs payers an average of $3.14 per transaction. The researchers also estimated that payers could reduce this average cost to just pennies per transaction while ensuring timely supply by automating and digitizing at least part of the process.

Why? Because the burden of reviewing and processing unstructured data – in PAs submitted as fax, paper or cloud – poses enormous challenges for payer organizations. Just a few examples:

  • Payers have no way to automatically sort and prioritize traditional faxes based on member need or urgency.
  • Manually reviewing and processing fax-based PAs requires more staff time and results in slower responses to all PA requests.
  • Manually retyping unstructured fax content increases the likelihood of human error – which can both lead to poorer health outcomes and increase the ultimate cost of member support.

Think of it this way: If you were given 100 names in an Excel file and needed to rearrange them in alphabetical order, the task would only take a few clicks. The software has the ability to recognize the letters in the names and the built-in intelligence to sort them from A to Z.

But now imagine if you were given those 100 names on a piece of paper instead. Sorting alphabetically is no longer just a matter of clicking a few buttons. Someone has to manually rewrite every name on the list — or manually enter them into a database.

It’s a very simple analogy, but it underscores the difference between an AI-powered pre-authorization process and the names-on-paper process your employees probably struggle with every day.

How to approach the challenge

Manual handling of PAs as incoming faxes is among the least cost effective ways of managing the process. But alas, as long as providers continue to rely on fax machines and paper faxes to transmit health records – and an MGMA study found that 89% still do so – you need to find a more efficient way to review and respond to these requests. Luckily you have options.

1. Digital Cloud Faxing

Even if your providers continue to submit their PAs by fax, your employees do not have to receive the applications on paper from you.

The right digital cloud fax solution – a solution tailored to the unique needs and constraints of the healthcare industry – can ingest incoming fax content into EHRs or other recording systems. It can also use basic Optical Character Recognition (OCR) to identify key data in your faxes, such as: B. Member names, ID numbers, names of
doctors and so on.

This simple addition to your company’s digital environment can remove several time-consuming, manual steps from the review process – to help your employees optimize their PA responses and ultimately save your company money.

2. Natural Language Processing

Natural language processing (NLP) makes digital cloud faxing another important step in automating the handling of pre-approvals — or incoming fax content that your staff would otherwise have to manually review and process.

NLP embedded in your cloud fax platform can automatically sort and organize important information in an incoming fax and even take a next step if needed. For example, you can instruct your NLP solution to scan every incoming fax for key phrases – such as “urgent” – and prioritize those requests by sending notifications to the right people in your organization.

Since NLP uses machine learning, it gets better and better at identifying key terms and concepts as it consumes more data. It can even learn to read handwritten notes on fax pages.

3. Artificial Intelligence

Your organization will see the greatest operational benefits—both in terms of reducing the cost of your prior approval responses and helping you provide more timely care to your members—when you use artificial intelligence in your PA processes.

Artificial Intelligence brings together all of the above capabilities and adds layers of learning, thinking and continuous improvement to your fax solution.

The McKinsey study concluded that “an AI-enabled workflow requires fewer steps,” thereby automating most of the administrative steps that most payers today do manually. AI can also benefit payers by sorting requests into high and low priority, as well as those that can be handled by caregivers and those that require physician input.

The final result

As fax (both paper and digital) remains one of the most common methods for vendors to make prior authorization requests, payers must adopt new tools and technologies to receive, verify, and process those requests as efficiently and reliably as possible be able .

The best and easiest way to do this today is to implement the right digital cloud fax solution with built-in AI and NLP capabilities. This relieves payer staff, streamlines their ability to respond to PAs, reduces overall costs to the organization and improves member outcomes.

Bevey Miner is the Healthcare IT Strategist for Consensus Cloud Solution.