Revenue cycle · Clinical documentation integrity AI
SmarterDx
SmarterDx provides clinical documentation integrity AI that reviews charts after the encounter to find missed diagnoses, specificity gaps, and denial risk for health-system CDI and coding teams.
Strong fit
- Health systems that want AI to find missed documentation and coding gaps after the chart is written
- Billing accuracy leaders comparing clinical AI documentation tools with hiring more documentation review staff
- Buyers that need measurable denial prevention and fuller capture of patient severity
Weak fit
- Small outpatient clinics that only need visit coding for a handful of physicians
- Teams shopping for AI scribes to write notes
- Groups that refuse cloud clinical AI on EHR data
Bottom line
SmarterDx fits health systems that chart in a major EHR and still miss diagnoses and documentation detail that affect payment. It reviews documentation after the encounter. Groups that want autonomous coding for professional fees may prefer Nym, and audit programs should look at MDaudit.
Score breakdown
Weights: Outcomes 35% · Product 30% · Implementation 20% · Pricing clarity 15%.
SmarterDx is a clinical AI company in New York founded by physician CEO Michael Gao. It has a few hundred employees after a growth investment from New Mountain Capital, and in 2026 New Mountain moved to merge it with Datavant.
Its platform reviews inpatient and related documentation after the chart is written and flags missed diagnoses, missing detail, and denial risk for documentation and coding teams. Clinicians still write their own notes, and patient billing is handled elsewhere.
SmarterDx reports that customers recover millions of dollars a year and see strong returns compared with adding documentation staff alone.
Setup is an EHR data and documentation workflow project that takes weeks. Prices are quoted for each customer, as with most large clinical AI tools.
Among the billing accuracy tools we review, SmarterDx scores highest. It leads autonomous coding tools when the need is complete inpatient documentation.
Nym suits autonomous coding for professional fees, and Aptarro suits AI across billing workflows. MDaudit suits audit and compliance work after the stay.
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 | Clinical documentation and payment recovery AI software for health systems, priced by quote. |
| What usually drives cost | Facility volume, modules (documentation review, coding help, denials), EHR integration scope, and support level. |
| What to ask before you buy | Expected yearly contract cost at your discharge volume, including setup and ongoing documentation review support. |
| Published pricing | Every customer gets a custom quote. |
Prerequisites for purchase
| Need | Why it matters |
|---|---|
| What you need to get SmarterDx to function | |
| Clear owners for documentation review and coding | AI findings need reviewers to act on them. |
| EHR data access defined | Recommendations depend on a data feed. |
| Starting denial rates and case mix index | A starting point is needed to show a return. |
| Privacy and business associate review done | Security review is where clinical AI projects often stall. |
| A physician advisor to settle disputes | Clinical disagreements need a physician to settle them. |
| What will maximize your value | |
| Start with one service line | A single service line keeps early findings manageable. |
| Measure money recovered at 90 days | This shows whether documentation review helps. |
| Drop overlapping review tools used during the stay | One list keeps staff focused. |
| Deal-breakers | |
| You only need an AI scribe | |
| You allow no EHR data sharing | |
| No one can own documentation review | |
Value creation time frame
| # | Stage | Typical range |
|---|---|---|
| 1 | Security review and data mapping | 4-8 weeks |
| 2 | Test in one department | 6-12 weeks |
| 3 | Expand and adjust | 8-16 weeks |
Leadership
Recent news
- September 2026: KKR and Neuberger Berman agreed to provide $2.7 billion in preferred equity for New Mountain Capital's merger of Datavant and SmarterDx. Octus put SmarterDx's revenue at about $150 million.
- August 2026: Bloomberg Law reported on a planned $3 billion financing to combine Datavant with SmarterDx.
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.
