Healthcare Case Study
Underpass Health
A model rebuild that fixed accuracy issues in an existing in-house model.
-15%Admin Time Saved
The Challenge
Where things stood before
Underpass Health came to us with a problem that had been building for a while: administrative and clinical workflows that hadn't kept pace with the volume they were handling.
The problem was quietly getting more expensive to ignore every month it went unaddressed.
The Solution
What we built
We started by getting a clear picture of exactly where things were breaking down before proposing anything.
What we ultimately delivered was a model rebuild that fixed accuracy issues in an existing in-house model, built specifically around what Underpass Health needed.
- Validated thoroughly before deployment to avoid production surprises
- Benchmarked against clear, agreed-upon success metrics from day one
- Structured so Underpass Health's own team could monitor and maintain it going forward
- Designed around Underpass Health's actual data and workflow, not a generic template
Results
The impact, by the numbers
-15%
Admin Time Saved
95.8%
Model Accuracy
-41%
Patient Wait Time
+37%
Staff Satisfaction
Tech Stack
Built with
PythonPyTorchscikit-learnMLflow
Vertexa Consulting
Want results like this for your business?
Let's talk about your project — no pressure, just a straightforward conversation about what you need.
Talk to an AI Expert