Optimizing referral management with AI
How a large health system in Florida automates faxed referral transcription to reduce turnaround time from 48 hours to 10 minutes
order transcription completed via
automation
faxed referrals automatically transcribed
projected staff hours saved per year
upskilled for higher-value work
The challenge
A large, community-focused health system in Florida with multiple hospitals, emergency centers, and points of outpatient care wanted to make changes to ensure its patients were receiving the proper care quickly and efficiently across all of its service lines.
Like many healthcare organizations, this health system relies heavily on inbound faxes for its referrals, creating a high administrative burden with 12.5 full-time employees indexing faxed orders and an average processing time of 48 hours from faxed document receipt to transcription. If a fax indexer was out of office, standard turnaround times suffered, sometimes getting as high as five business days. Fifteen percent of the health system’s faxed referrals were also hand-written, making an already manual process that much more time-consuming for staff. Additionally, faxes were incoming from multiple queues and fax lines, making it difficult to understand their total volume, throughput, and operational service levels.
With additional challenges presented by the need to integrate with three different systems, RightFax, OnBase, and Epic, this backlogged fax queue presented a continuously growing, unsustainable, and heavily manual burden for the health system’s staff. Work was monotonous, and staff were unable to wade through the high volume of faxes to focus on the most timely and high-value cases first.
The health system’s leadership recognized that it needed a solution that would free staff capacity, enabling team members to focus time on top-of-license work and engage with patients who require more assistance. Additionally, processing referrals quickly would allow patients to access care faster, decreasing patient leakage and improving continuity of care. Being able to prioritize high-value referral orders would ensure that the health system was seeing the right patients quickly, providing impactful business value to the organization.
The solution
This large health system partnered with Notable to deploy an automated faxed referral transcription and entry process that could reduce turnaround time, process a large number of referrals without human intervention, and ultimately free up staff for more valuable work.
To start, it quickly and efficiently deployed Notable’s Referrals Coordinator AI Agent across three fax lines in its contact center, automating the order entry of 14 different order types: MRI, x-ray, CT, ultrasound, mammography, DEXA, CTA, PFT, nuclear medicine, barium swallow, IR, lab, ambulatory, and PET. The health system was initially focused on measuring turnaround time from faxed referral receipt to transcription, as this was the most intensive part of the process for its staff and the highest priority area to reduce time spent.
Notable’s AI Agents for referral automation work 24/7, enabling referrals to be transcribed outside of working hours and leading to increased scheduling speed. The technology can capture and work with both structured and unstructured data. For structured data, it connects directly to databases or APIs within EHR systems to retrieve information from specific fields; for unstructured data, such as a faxed referral document or a clinician’s handwritten note, the Agent can extract the necessary details even when they appear in different formats or locations. It can also flag duplicate orders, orders that fail medical necessity, or orders that are missing information from the referring provider, helping to wade through troublesome referrals and surface the right cases for necessary staff involvement.
Now, Notable’s AI Agents handle the health system’s referral transcription process seamlessly and autonomously, reducing the need for human interaction and only routing the most complex cases to humans for review.
The Results
With the quick deployment of Notable’s AI Platform, this Florida-based health system has automated the transcription of over 10,000 faxed orders to date without staff intervention, with a projection to automate 60,000 total faxed orders without intervention in 2025. This saves 8,000 hours annually, yielding a 2.6x ROI on multiple referral transcription alone. Referral automation has allowed the cross-training of 5 FTEs to focus on other areas of opportunity for professional growth and strategic business priorities, with more FTEs upskilling as the organization scales its referral automation.
The health system now has an 85% referral completion rate to date, allowing automation to handle straightforward order transcription while only routing the most complex cases to humans for review. The average turnaround time from referral received to transcription has been reduced from 48 hours to 10 minutes, with Notable’s platform working 24/7 to reduce the backlog without relying on humans. Continuous automation allows patients to move through the process quicker, leading to increased scheduling speed and faster access to care.
