Revenue cycle · Radiology autonomous coding
Maverick Medical AI
Maverick Medical AI makes AI software that assigns billing codes to radiology reports in seconds and flags missing documentation to radiologists before reports are signed.
Strong fit
- Radiology groups and imaging center networks with high report volume
- Billing teams that want codes assigned within seconds of a report being signed
- Practices on RamSoft or similar radiology systems
Weak fit
- Hospitals that need coding across all inpatient and outpatient specialties
- Small practices with low report volume
- Buyers who need a published price list
Bottom line
Maverick Medical AI makes AI software that reads radiology reports as they are finalized and assigns billing codes in seconds, sending most claims straight to billing with no coder touch. A second tool flags missing documentation to the radiologist before the report is signed. It fits imaging groups that want faster coding and fewer addenda.
Score breakdown
Weights: Outcomes 35% · Product 30% · Implementation 20% · Pricing clarity 15%.
Yossi Shahak and Michael Brozino, both former senior executives at McKesson, founded Maverick Medical AI in 2019.
Its mCoder product reads each finalized report and assigns ICD-10 and CPT codes in seconds. Its models are trained on millions of reports and kept current with CMS and payer updates.
At least 87% of reports are coded with no human effort, and true exceptions go to coders for review.
CodePilot works inside the radiologist's reporting system. It suggests missing text before the report is signed, which cuts addenda and billing delays.
RadNet, the largest outpatient imaging provider in the US, rolled out mCoder across all 399 of its sites. It had run more than 10 million reports through it by 2024, raising the share of claims that go straight to billing.
RamSoft added Maverick's coding and CodePilot to its PowerServer and OmegaAI radiology systems. Infinx, a billing services company, invested in Maverick in 2025 to bring real-time coding to its customers.
One customer codes all of its reports with Maverick, sends 85% straight to billing, and has the fewest days to collect payment in its history. Another had it live within two months with little staff effort.
Compare CodaMetrix when a large health system wants automated coding across many specialties. Fathom Health or Nym fit buyers who want another automated coding engine for professional or facility charts.
Arintra fits when coding should happen inside the EHR. SmarterDx fits when the main goal is reviewing clinical documentation before billing, and MDaudit fits coding audits and billing accuracy.
Competitor landscape
| Vendor | Overall | Ease of implementation |
|---|---|---|
| SmarterDx | 7.6 | 7.2 |
| CodaMetrix | 7.6 | 7.3 |
| Fathom | 7.5 | 7.2 |
| Charta Health | 7.5 | 7.5 |
| MDaudit | 7.4 | 7.1 |
| Arintra | 7.2 | 7.1 |
| Maverick Medical AI | 7.2 | 7.1 |
| Nym | 6.6 | 6.4 |
Pricing
| Item | Detail |
|---|---|
| Model | Custom contract quoted by Maverick Medical AI. |
| What usually drives cost | Report volume, the imaging types and specialties covered, whether CodePilot is added for radiologists, and connections to the RIS, PACS, and billing system. |
| What to ask before you buy | Whether you pay per report or per claim, what share of claims it promises to send straight to billing, and how coding audits and payer updates are handled. |
| Published pricing | Maverick Medical AI does not publish a price list. |
Prerequisites for purchase
| Need | Why it matters |
|---|---|
| What you need to get Maverick Medical AI to function | |
| A coding or billing leader | Owns the change. |
| RIS, PACS, and billing system access | Reports in, codes out. |
| Coding policies and payer rules | Sets what bills automatically. |
| Your starting share of claims sent straight to billing, and days to collect payment | You need them to show the change later. |
| Coders to work exceptions | Some reports still need a person. |
| What will maximize your value | |
| Start with the imaging types you read most | Shows value quickly. |
| Add CodePilot for radiologists | Fixes gaps before signing. |
| Review exceptions by reason each month | Raises the share billed automatically. |
| Deal-breakers | |
| Low report volume | |
| No integration path to the RIS or billing system | |
| No owner for coding | |
Value creation time frame
| # | Stage | Typical range |
|---|---|---|
| 1 | Contract and integration | 1-2 months |
| 2 | Automated coding live | 1-2 months |
| 3 | CodePilot and more sites | 3-9 months |
Methodology
| Weight | Factor | What it measures |
|---|---|---|
| 35% | Customer outcomes | Whether buyers get measurable operational or clinical-workflow results after go-live |
| 30% | Product | Capability depth, reliability, and fit for the job the category buys |
| 20% | Implementation | How hard it is to stand up, integrate, train, and stabilize |
| 15% | Pricing clarity | Whether a buyer can model total cost without a mystery quote |
| Label | Meaning |
|---|---|
| Highly recommend | Strong outcomes and product with manageable caveats |
| Recommend | Solid fit for the right buyer; know the tradeoffs |
| Conditional | Only with a specific use case or heavy caveats |
| Not recommended | Avoid for most buyers in this category |
Read our full methodology for how we weight scores and assign recommend labels.