Windfall serves weak and deprived communities via compassionate, high-quality care. As one of many largest nonprofit well being techniques in america—with 51 hospitals, over 1,000 outpatient clinics, and greater than 130,000 caregivers throughout seven states—our potential to ship well timed, coordinated care relies on reworking not solely medical outcomes but in addition the workflows that assist them.
Probably the most urgent cases is automating the way in which we deal with faxes. Regardless of advances in digital well being, faxes stay a dominant type of communication in healthcare, particularly for referrals between suppliers. Windfall receives greater than 40 million faxes yearly, totaling over 160 million pages. A good portion of that quantity have to be manually reviewed and transcribed into Epic, our digital well being file (EHR) system.
The method is sluggish, error-prone and contributes to multi-month backlogs that in the end delay take care of sufferers. We knew there needed to be a greater means.
Tackling messy workflows and unstructured information at scale
The core problem wasn’t simply technical—it was human. In healthcare, workflows fluctuate extensively between clinics, roles and even people. One workers member would possibly print and scan referrals earlier than manually coming into them into Epic, whereas one other would possibly work inside a wholly digital queue. The shortage of standardization makes it tough to outline a “common” automation pipeline or create take a look at situations that mirror real-world complexity.
On prime of that, the underlying information is usually fragmented and inconsistently saved. From handwritten notes to typed PDFs, the variety of incoming fax paperwork creates a variety of inputs to course of, classify and extract data from. And if you’re coping with a number of optical character recognition (OCR) instruments, immediate methods and language fashions, tuning all these hyperparameters turns into exponentially more durable.
This complexity made it clear that our success would hinge on constructing a low-friction testing ecosystem. One which lets us experiment quickly, examine outcomes throughout 1000’s of permutations and repeatedly refine our fashions and prompts.
Accelerating GenAI experimentation with MLflow on Databricks
To satisfy that problem, we turned to the Databricks Information Intelligence Platform, and particularly MLflow, to orchestrate and scale our machine studying mannequin experimentation pipeline. Whereas our manufacturing infrastructure is constructed on microservices, the experimentation and validation phases are powered by Databricks, which is the place a lot of the worth lies.
For our eFax undertaking, we used MLflow to:
- Outline and execute parameterized jobs that sweep throughout combos of OCR fashions, immediate templates and different hyperparameters. By permitting customers to offer dynamic inputs at runtime, parameterized jobs make duties extra versatile and reusable. We handle jobs via our CI/CD pipelines, producing YAML information to configure massive exams effectively and repeatably.
- Observe and log experiment outcomes centrally for environment friendly comparability. This offers our group clear visibility into what’s working and what wants tuning, with out duplicating effort. The central logging additionally helps deeper analysis of mannequin habits throughout doc varieties and referral situations.
- Leverage historic information to simulate downstream outcomes and refine our fashions earlier than pushing to manufacturing. Catching points early within the testing cycle reduces danger and accelerates deployment. That is notably essential given the variety of referral kinds and the necessity for compliance inside closely regulated EHR environments like Epic.
This course of was impressed by our success working with Databricks on our deep studying frameworks. We’ve since tailored and expanded it for our eFax work and huge language mannequin (LLM) experimentation.
Whereas we use Azure AI Doc Intelligence for OCR and OpenAI’s GPT-4.0 fashions for extraction, the true engineering accelerant has been the flexibility to run managed, repeated exams via MLflow pipelines—automating what would in any other case be guide, fragmented improvement. With the unifying nature of the Databricks Information Intelligence Platform, we’re in a position to rework uncooked faxes, experiment with totally different AI methods and validate outputs with velocity and confidence in a single place.
All extracted referral information have to be built-in into Epic, which requires seamless information formatting, validation and safe supply. Databricks performs a vital position in pre-processing and normalizing this data earlier than handoff to our EHR system.
We additionally depend on Databricks for batch ETL, metadata storage and downstream evaluation. Our broader tech stack contains Azure Kubernetes Service (AKS) for containerized deployment, Azure Search to assist retrieval-augmented technology (RAG) workflows and Postgres for structured storage. For future phases, we’re actively exploring Mosaic AI for RAG and Mannequin Serving to reinforce the accuracy, scalability and responsiveness of our AI options. With Mannequin Serving, we will likely be in a greater place to successfully deploy and handle fashions in actual time, making certain extra constant workflows throughout all our AI efforts.
From months of backlog to real-time triage
In the end, the beneficiaries of this eFax answer are our caregivers—clinicians, medical data directors, nurses, and different frontline workers whose time is presently consumed by repetitive doc processing. By eradicating low-value guide bottlenecks, we purpose to return that point to affected person care.
In some areas, faxes have sat in queues for as much as two to a few months with out being reviewed—delays that may severely affect affected person care. With AI-powered automation, we’re transferring towards real-time processing of over 40 million faxes yearly, eliminating bottlenecks and enabling sooner referral consumption. This shift has not solely improved productiveness and diminished operational overhead but in addition accelerated remedy timelines, enhanced affected person outcomes, and freed up medical workers to concentrate on higher-value care supply. By modernizing a traditionally guide workflow, we’re unlocking system-wide efficiencies that scale throughout our 1,000+ outpatient clinics, supporting our mission to offer well timed, coordinated care at scale.
Because of MLflow, we’re not simply experimenting. We’re operationalizing AI in a means that’s aligned with our mission, our workflows, and the real-time wants of our caregivers and sufferers.
