Moving from OnBase to Gallery?

See how we do it
Sumit Mahendru, Founder and CEO of Abstrakt Health
95%+ Face Sheet Accuracy

How Abstrakt Health Processes 12,000 Face Sheets With AI

Customer
Abstrakt Health
Role
Sumit MahendruFounder and CEO
Impact
Automated Processing of Face Sheets
How Dexit Helps Abstrakt Health Process Up to 12,000 Face Sheets a Month

End manual document processing with AI.

Make the smart move.

Book a Demo
Summary

The Customer

Abstrakt Health is a revenue cycle management company out of California, USA. Senior care providers are part of its clientele. They are usually clinicians who treat patients inside assisted living and skilled nursing facilities which they don't own.

The Challenge

One client of Abstrakt Health alone touches over 900 facilities, and with that comes 7,000 to 12,000 claims a month. Each claim cycle begins life as a scanned face sheet. Someone had to read it, type the data manually, and guess how to map insurance details and which are actually correct.

Key Results

  • Automated a face sheet process that used to be manual and error prone
  • Hit 95%+ extraction accuracy, with human review on track to disappear entirely by year's end
  • Cut onboarding time by an estimated 30 to 45 days, since Dexit's AI already understood healthcare documents rather than starting cold
  • Now expanding into EOB extraction, a capability Sumit had long wanted but hadn't found a workable path to, despite years of trying with other vendors and in-house

Ready to Stop Keying In Face Sheets by Hand?

Dexit turns scanned face sheets, EOBs, and every other inbound document into clean, structured data. 95%+ accuracy, no manual extraction.

900 Facilities. A Pile of Face Sheets. One Team Trying to Keep Up.

Sumit Mahendru Sumit Mahendru Founder and CEO · Abstrakt Health

Sumit Mahendru, Founder and CEO of Abstrakt Health, has been working with Dexit for close to a year.

Abstrakt handles revenue cycle management for a range of provider clients. One segment is senior care: clinicians who treat patients in assisted living and skilled nursing facilities. Without direct access to those facilities' EHRs, the paperwork arrives as scanned face sheets, and each one has to be read and typed in manually into the systems.

Stack of Paper, Processed One by One Manually

Before Dexit, the workflow started with a stack of paper. Facilities scanned face sheets from each patient visit and sent them to Abstrakt Health, where they sat in a document storage system until someone opened them one by one, pulled out the demographic and insurance information manually, and worked out which details were actually correct.

That doesn't scale, not at the volume Abstrakt was running. Sumit points to its largest client as the clearest example: 7,000 to 12,000 claims a month, each with its own face sheet, each needing the same manual processing step. Getting the numbers wrong was never a small thing. One incorrect digit in an insurance number can mean a patient gets billed for a service that should have been covered, and the cost of denials and rework lands on Abstrakt and the providers they serve.

If one field or one digit is incorrect in the insurance number, then potentially a patient is billed or denials are happening, which creates such havoc on the back end and so much more cost for both me and my practices, as well as potential headache for patients.

No Time Wasted on Healthcare 101

Sumit shopped around. Other vendors doing document extraction with AI, OCR, or RPA all got a look before Dexit won the business. What separated the conversation wasn't accuracy alone. It was that 314e already knew healthcare and revenue cycle management, so Sumit didn't have to spend hours just teaching a vendor what a denial even is before any real work could start.

It wasn't like, hey, we're going to spend two calls with me teaching you what healthcare is, and what the importance of getting corrected information is. It was, hey, we've done this before, we've done Epic implementations, and that gave me a comfort that otherwise wasn't there.

That existing domain knowledge saved real time off implementation. There were no month-long scoping calls to explain why accuracy mattered or what the data even meant. The pitch was direct. "Send over some documents," Sumit says. "Let us extract them, and we'll tell you what's missing."

Filling In the Edges, Not Starting From a Blank Canvas

Dexit's AI was already built for healthcare documents, so onboarding never turned into a from-scratch buildout. Most vendor onboarding, in Sumit's experience, starts with a blank canvas. This time the canvas already existed. The work was refining it: dialing in Abstrakt's specific document types and the fields particular clients needed.

I believe onboarding is truly painting a picture. With most companies, it's a blank canvas. With you guys, it was like, hey, we're just filling in the edges and the outlines, and cleaning up what is missing or added.

Sumit puts a number on that difference: 30 to 45 days saved in onboarding. The team also worked around Abstrakt's overseas operation in India, running separate call slots across time zones so both sides could show up without anyone losing sleep over it.

Accuracy High Enough to Make Human Review Optional

Extraction accuracy for Abstrakt now sits above 95%, and it keeps climbing. That's high enough that Sumit and his head of ops are looking at making human review an option rather than a required step on every document.

The conversation and the joke I have with my head of ops: hey, if you had an employee at this percent accuracy, what would you do? Typically the answer is, well, I'd probably give that employee a promotion or a raise.

A Vendor That Still Treats a Boutique RCM Firm Like a Priority

Sumit judges support responsiveness, and he's tested that repeatedly by pushing the team toward building EOB extraction, something he'd chased for years with other vendors and once tried to build himself at an AI company. His description of how 314e responds is consistent: take on the ask, don't deflect it.

Finding the right vendor mattered to Sumit for another specific reason. He didn't want to end up as a small account sitting one contract renewal away from being outgrown. He'd seen it happen before: a prior vendor shifted its focus toward larger health systems, then priced him right out as a result.

You do a lot of work with health systems, but you're working with customers such as myself. I'm a small business, and a fear for me as a company is that vendors will stop servicing a business like mine. I feel like you guys have a dedicated team to focus on small companies, which is very helpful and very comforting as a business owner.

Expanding From Face Sheets Into EOBs, With One Vendor Instead of Ten

Abstrakt started with face sheets, and the roadmap with Dexit now reaches into EOB extraction, where early accuracy numbers look promising to Sumit. The bigger draw for him is consolidation. Rather than managing ten vendors for ten document types and processes, he wants one platform that covers all of it.

We started on face sheets, we're moving on to processing more and more new document types. That's been the game changer for me because I don't have to go to ten vendors to do all my different document types.

That confidence shows in how he talks about Dexit with his peers.

I've referred over, probably 10 or 15 of my peers, RCM companies, over to Dexit. I don't make referrals lightly.

Ready to Stop Keying In Face Sheets by Hand?

Dexit turns scanned face sheets, EOBs, and every other inbound document into clean, structured data. 95%+ accuracy, no manual extraction.