OpenAdapt
Qualify one workflow

Customer case study · Healthcare

Recovering missed billables with automated RVU audits

The automated audit helped recover about $75,000 a year in billables that otherwise would have been missed and replaced several hours of repetitive monthly chart review with review-ready results.

Dr. Victor Abrich, MD
Board-certified cardiac electrophysiologist
A US cardiology electrophysiology practice

Disclosure: Dr. Abrich is the founder’s brother. This is OpenAdapt’s founding deployment, not independent validation.

≈$75,000

in missed billables recovered per year

Several hours

of physician audit work saved each month

More complete

audits than manual review alone

The challenge

High-value work hidden inside a manual audit

Reviewing every relevant chart and reconciling the findings against monthly RVU reports took several hours each month, and manual review still missed billable work.

The workflow

Let automation handle the repetition

  1. 01Load the month’s RVU report spreadsheets.
  2. 02Navigate Cerner PowerChart and collect the relevant clinical notes for each patient and service date.
  3. 03Compare the documented procedures with the procedure codes and RVUs credited in the reports.
  4. 04Produce an analysis workbook and a copy-ready email listing the missing credits for follow-up.

The result

More complete audits without spending physician hours collecting and reconciling data by hand

“The audit automation saved me several hours every month and helped recover about $75,000 a year in billables I would otherwise have missed.”
Dr. Victor Abrich, MD

Review-ready outputs

  • A row-by-row analysis workbook showing credited and missing procedure codes.
  • A copy-ready recovery email organized for billing follow-up.
  • Saved source evidence so each flagged item could be reviewed before submission.

Synthetic product validation

A six-month governed validation profile

The current product contract is exercised against a reproducible 2,880-case synthetic cohort shaped around the same monthly audit: identity before action, persisted-state verification after action, and explicit refusal when the result cannot be proven.

480/month

synthetic encounter cases across six monthly cohorts

99.2%

VERIFIED outcomes (2,856 of 2,880 cases)

0

silent incorrect successes in the cohort

$0.03

modeled reference execution cost per case

Full outcome set
2,856 VERIFIED · 18 HALTED for identity, ambiguity, or effect refusal · 6 FAILED before actuation.
Execution boundary
Customer-controlled Windows/RDP profile · Standard execution · OpenAdapt Flow 1.23.0 · cardiology RVU workflow pack 0.4.2.
Independent adjudication
A separate persisted-state judge compares the intended and observed record digests. A mismatched write can never count as VERIFIED.
Data boundary
Synthetic records only, zero model calls, and no observed external network calls. Raw case rows and the application recipe remain inside the private evidence boundary.

Customer outcomes above come from Dr. Abrich’s audit work. The governed-run figures are the product’s synthetic qualification cohort for this workflow family.

Evidence reference: rvu-audit-standard-synthetic-v1 · rollup sha256 66c0731c4b754f2beb780562cddc03bdfe66f74acb5a64445c22ea97f64974b9

Bring your workflow

Qualify the UI-only work your APIs cannot reach

Show us one repeated workflow, its target application, and the business result that proves it worked.

Qualify one workflow

Figures on this page are preliminary and under review pending final customer confirmation.