Nym Health
Autonomous medical coding engine that assigns ICD-10-CM/PCS and CPT codes from patient charts and routes encounters directly to billing with no human review. The technical approach is deliberately NOT end-to-end deep learning, and that distinction is the whole record: Nym uses proprietary Clinical Language Understanding built on computational linguistics, combining machine learning models with RULES-BASED CLINICAL ONTOLOGIES that encode coding guidelines from the AMA, CMS and WHO. The engine reconstructs the clinical narrative of the encounter, then links ontological entities to codes, which is why it handles the failure mode that defeats keyword-based computer-assisted coding, most notably negation, where a note stating a patient does not have a condition must not generate that code. Reports over 95 percent accuracy, with encounters routed to billing when coding confidence exceeds that threshold and charts the engine cannot confidently code returned to human coders. Processes a reported 5.5 million or more charts annually across more than 250 US healthcare facilities, with named customers including Geisinger, Inova, Intermountain Health and OSU Physicians. Coverage began in emergency department and inpatient settings and expanded to outpatient in 2024, with multispecialty support including radiology. Built by an interdisciplinary team of physicians, computational linguists and engineers. THE DIFFERENTIATOR MOST WORTH CHECKING IS EXPLAINABILITY: every assigned code carries an audit trail stating the logic for why it was assigned, which the company contrasts explicitly with black box AI. That is a substantive claim in a domain where incorrect codes create False Claims Act exposure for the billing organisation. Indexed alongside CodaMetrix, the closest comparator, which takes a different technical approach to the same problem.
Capability Axes
The engine is the entire product and there is no coding bureau underneath, which is the distinction that separates genuine autonomous coding vendors from RCM companies claiming AI over offshore labour. Same test that earned CodaMetrix an A. The Clinical Language Understanding technology is proprietary and built by an interdisciplinary team of physicians, computational linguists and engineers, and the company sells nothing else.
The strongest autonomy disclosure in this category and the direct answer to what CodaMetrix withholds. Nym publishes both the mechanism and the threshold: encounters are routed to billing when coding confidence exceeds 95 percent, and charts the engine cannot confidently code above that accuracy threshold are returned to human coders. It also states plainly that it assigns codes only for charts it fully understands, with unintelligible charts automatically flagged and returned. CodaMetrix was graded B in this index precisely because its human-routing threshold is not published; Nym publishes it, which is the key operational disclosure for autonomous coding. Note the honest framing that this is a first-pass coder running in the background inside the existing workflow rather than a replacement for the coding function.
Unusually specific and, more importantly, explicit about what the system is NOT. The company states its own category definition, that autonomous coding may use end-to-end deep learning, NLP with rules, or a hybrid, and identifies its own approach as computational linguistics plus machine learning models combined with rules-based clinical ontologies encoding AMA, CMS and WHO coding guidelines. The pipeline stages are named: semantic representation, context extrapolation, ontological linking and narrative construction. It also names the specific failure mode it handles, negation, where keyword-based computer-assisted coding wrongly codes a condition the note explicitly rules out. A vendor that publishes its architecture, its taxonomy of alternatives, and the error class it targets is operating well above the disclosure norm here.
Stronger than most RCM vendors but still vendor-sourced. Scale is substantial and specific: over 5.5 million charts annually across more than 250 US healthcare facilities, with named health system customers including Geisinger, Inova, Intermountain Health and OSU Physicians. A KLAS Research Emerging Solutions Spotlight report is cited in which 100 percent of Nym customers said they would purchase again, which is genuine third party research rather than a vendor survey. Graded B rather than A because the headline over 95 percent accuracy figure carries no published audit methodology, sample size or independent verification, and accuracy on successfully processed charts is a different and more favourable measure than accuracy across all charts submitted, since the hardest charts are excluded by the confidence threshold. That denominator question is the one a buyer must ask.
The engine processes complete patient charts including unstructured clinical notes, so the PHI surface is large, but no published retention policy, de-identification approach or statement on whether customer chart data trains models was located at the time of review.
No published BAA terms or HIPAA posture statement located, notable given deployment across more than 250 facilities.
No third party attestation such as SOC 2 Type II or HITRUST was retrieved at the time of review. Company materials describe the platform as secured and scalable without naming a certification.
Not an FDA regulated product. Medical coding and billing automation sit outside Software as a Medical Device. The governing regulatory surface is coding compliance under AMA, CMS and WHO guidelines, which the rules-based ontologies encode directly, plus False Claims Act exposure on submitted claims.
No demographic bias disclosure located, but the governance risk in autonomous coding is not demographic and this vendor addresses the real one structurally. The CODING DRIFT exposure flagged on CodaMetrix, where a model learns a health system's historical coding intensity and reproduces its upcoding tendencies, is materially mitigated here by architecture: because code assignment is driven by rules-based ontologies encoding published AMA, CMS and WHO guidelines rather than learned from a customer's historical coding patterns, the system is anchored to the standard rather than to the institution's habits. The audit trail explaining why each code was assigned makes drift detectable rather than invisible, and the company states the system is automatically updated to reflect current coding guidelines. Graded B rather than A because no independent audit of coding appropriateness, as distinct from accuracy, was located.
Designed to layer on top of the existing enterprise IT stack and integrate into the normal revenue cycle flow without change or interruption, running in the background as a first-pass coder inside the current workflow rather than requiring process redesign. That low-disruption posture is a genuine deployment advantage and is corroborated across sources. Graded B rather than A because no specific EHR or billing system integrations were named in located materials, unlike Candid Health's documented API-first approach.
No hosting architecture, deployment option or data residency disclosure was located at the time of review.
No pricing published and no pricing basis disclosed. For autonomous coding the pricing unit matters more than usual, since charging per chart processed, per chart successfully autocoded, or as a platform fee produces very different economics when the autonomous rate varies by specialty and documentation quality. None of that is public. Consistent with Candid Health and the wider RCM lane, where commercial opacity is the norm.
Genuine multispecialty coverage with a clear expansion path: emergency department and inpatient origins, outpatient capabilities added in 2024, and radiology among supported specialties, deployed across health systems, hospitals and physician groups in more than 250 facilities. Emergency department coding in particular is a high-volume, high-complexity proving ground. Graded B rather than A because CodaMetrix in this index documents a wider specialty span including pathology, surgery, GI and inpatient professional coding, and Nym's per-specialty autonomous rates are not published so depth of coverage by specialty cannot be verified.
Pricing
Vendor-published figures are labeled as such. Figures labeled “Estimated” are derived from third-party sources and have not been confirmed by the vendor.
| Entry Price | Pricing Basis | BAA Tier | Implementation | Source |
|---|---|---|---|---|
|
Not published
|
Undisclosed. Autonomous rate by specialty is the decisive commercial variable and is not published. | — | — | Vendor Published |
No pricing published and no pricing basis disclosed. The pricing unit is more consequential in autonomous coding than in most categories, because the value delivered depends entirely on the autonomous rate, meaning the share of charts coded without human touch, and that rate varies substantially by specialty, facility and documentation quality. Charging per chart processed, per chart successfully autocoded, or as a flat platform fee produces very different economics for the same deployment, and none of it is public. Buyers should establish the pricing unit first, then press on the measurement question that determines actual value: the reported over 95 percent accuracy applies to charts the engine confidently codes, since charts below the confidence threshold are returned to human coders, so the operationally decisive number is what proportion of total submitted charts clear the threshold in the buyer's own specialty mix. A high accuracy rate on a low autonomous rate delivers far less than the headline suggests. Also worth requesting is the audit methodology behind the accuracy figure and any independent coding audit results, since the vendor publishes the number without a stated sample or verification approach. The KLAS Emerging Solutions Spotlight report, in which the company reports 100 percent of customers would purchase again, is the most useful independent reference point available and is worth obtaining directly.