RCM & Prior Auth AI
C

Complex Claims Audit

Complex Claims Audit is the AI module in Abacus Insights' payment integrity offering for health plans. It uses AI enabled prioritization to surface complex claims that may have been paid in error, assembles the claims, clinical, provider and payment integrity context for each case automatically, and leaves the decision to the plan's auditors, in the company's words "your team makes the call, not a black box." The module runs on the Payment Integrity Data Foundation, a governed layer that brings a plan's internal claims and program data together with results from its outside payment integrity vendors. A third module, payment policies and claim editing run before or after payment, runs on CoverSelf's platform and its Concept Library. A plan can start with whichever of the three answers its most urgent problem.

Abacus Insights launched the three modules on August 5, 2026. The Boston company, founded by physician and former health plan executive Dr. Minal Patel, who remains chief executive, serves 35 health plan customers covering 65 million lives with a payer data platform that also supports risk adjustment, quality measurement and CMS interoperability. Cambia Health Solutions built common payer data models and external connectors with Abacus for its enterprise platform. No health plan is yet named for the audit module, and its price is set in a commercial discussion, while the broader data platform lists on AWS Marketplace at $125,000 a year.

AI Health Index verifiedNovember 20, 2026
Compare Complex Claims Audit with other vendors
Founded
—
Headquarters
Boston, Massachusetts
Categories
rcm-and-prior-auth, vbc-intelligence
Indexed Products
Complex Claims Audit, Payment Integrity Suite, Payment Integrity Data Foundation
Buyer Segments
Health plan payment integrity teams, Health plan claims auditors, Managed care organizations, Payer finance teams
Assessment

Capability Axes

An AI Health Index grade measures what a buyer can verify from public sources on the date shown. It is not a rating of how good the product is. A vendor can build an excellent system and grade low on an axis because it publishes nothing an outsider can check. How grades read

AI Capability
BB on AI CentralityThe model is the engine of a core module. The platform carries other value, but this capability does not exist without it.
Vendor Published

Prioritization is the module's engine. AI decides which complex claims rise to the top of the review queue and assembles their supporting context from claims, provider, clinical and payment integrity data, so auditors start with the cases most likely to hold an error and the research already gathered. The other two modules carry value without it: the data foundation unifies payer data, and claim editing runs CoverSelf's rules and Concept Library before or after payment. Inside the audit module, though, the selection and evidence assembly are the product, and without the model it would be an ordinary review queue.

BB on Autonomy and Oversight ModelThe oversight structure is described and one part is missing, commonly the threshold at which the system stops or what happens after it is wrong.
Vendor Published

Auditors make every determination: the module prioritizes cases and assembles evidence, and a person investigates and decides whether a payment error occurred, with Abacus describing the approach as human in the loop supervision. Claim editing, which can act automatically before or after payment, sits in a separate module running CoverSelf's rules. The structure is clear on who decides.

What is missing is the mechanics: the score or threshold that puts a claim in the queue, how an auditor overrides or reorders a priority, what happens when the assembled evidence conflicts, and whether auditor decisions feed back into the model.

CC on Model and Technology TransparencyThe architecture is described in general terms with nothing identified. Proprietary is asserted rather than explained.
Vendor Published

The module uses AI to rank complex claims for review and gather supporting information, working on payment integrity data from claims, clinical and provider records joined in the data foundation. Its learned prioritization is separate from the configured policies and edits in the claim editing module. That describes the approach in general terms.

The model type, whether it is Abacus' own or built on an outside model, what audit outcomes train it, and how a new version is introduced to a plan's review queue are not described, so the AI is asserted rather than explained.

CC on Model Supply Chain DisclosureThe architecture is described and no model provider is named. Naming a hosting provider alone does not lift a record out of this band. Record the host in the note, because it matters for residency and breach scope, and grade on the model layer, which is the question this axis is named for.
Vendor Published

AWS and Azure host the wider platform, and CoverSelf supplies the separate claim editing module with its Concept Library. The data foundation takes in results from a plan's existing payment integrity vendors. No model or inference provider is named for the audit module's prioritization and evidence assembly, and nothing says whether claim records and clinical documents in a case reach an outside model service, or on what retention and training terms. The infrastructure is named and the model layer is not, which leaves open who else sees a plan's members' claims.

DD on Clinical and Operational EvidenceNo named deployment and no performance claim a reader can check. A figure published with no source sits here rather than higher.
Vendor Published

No health plan is named as using Complex Claims Audit, and no result is reported for it: no change in review time, recoveries, accuracy or false positives. The August 2026 launch release states goals such as better payment accuracy without data. Cambia Health Solutions is a named customer of the broader data platform, where it built common payer data models and external connectors, and Abacus reports 35 customers covering 65 million lives across its business. None of that measures the audit module, which leaves nothing a buyer can check on the AI itself.

CC on AI Safety and PHI StewardshipGeneral assurances of privacy and security that do not answer the questions artificial intelligence raises: what is retained, what reaches a model, and what happens to it there.
Vendor Published

The module combines a plan's claims, clinical and provider data with outside vendor results to build each case. Abacus' trust material describes encryption of customer data at rest, identity controls and least privilege access for administrators across its platform, and protection for health information and personal identifiers drawn from plan records. Those are general platform safeguards.

How long assembled case data and model inputs are kept, whether audit outcomes train the prioritization model, whether identifiers are removed before inference and how a model error is investigated are not stated for the audit module.

Regulatory and Compliance
CC on HIPAA and BAA PostureA status is stated but not supported: compliance is claimed, or business associate status stated, without the underlying document, including where the only privacy notice published covers the website rather than the service that handles patients. The mirror case grades here as well: a substantive privacy document that reaches the service, with no statement of business associate status anywhere and no scope position taken. One of the two elements the band above asks for is present, which is a grade below it and not a grade at the floor.
Vendor Published

Abacus' customer security program addresses protected health information and safeguards for the records its data service holds, and the privacy policy, mainly about website visitors, carries a customer security overview reaching payer data. The Marketplace contract for the data platform incorporates standard data security terms.

Health plans are covered entities and Abacus processes their members' data, yet no business associate status, agreement or subcontractor terms are stated for customers of the audit module. The posture rests on security material rather than a privacy document for the service.

BB on Security Certifications and Trust CenterA recognized certification is named in the vendor own material without the artifact, or with a scope or renewal question the buyer has to raise. A recognized certification here is an audit of how the vendor operates security, such as SOC 2, HITRUST or ISO/IEC 27001. A certification has a scope and a clock, and both are part of this grade. A certification the vendor attaches to its data center, hosting facility or cloud provider, rather than presenting as its own, is the host's and does not count here.
Vendor Published

The security program for the Abacus data platform names SOC 2 Type II and HITRUST r2 and describes encryption, least privilege access and monitoring across its cloud footprint. The audit module runs on the same governed data foundation. No trust center opens the reports, so the audit periods, and whether the August 2026 module falls inside the certified scope, are visible only once Abacus supplies them. HITRUST r2 is the most demanding of HITRUST's assessment levels, which fits a platform holding claims and clinical data for 65 million covered lives.

CC on FDA and Regulatory StatusNo device claim is made and the product is scoped accordingly. Most administrative and operational products sit here and are not penalized for it, because this axis grades the appropriateness of the positioning rather than possession of a clearance. A stated limit on use, such as research use only or a clause that the product gives no medical advice, beside marketing that sells the product for clinical decisions also sits here, with both quoted, because the buyer has to ask which one governs.
Vendor Published

The module supports administrative review of potentially incorrect insurance payments: it selects cases, assembles context and leaves the payment decision to the plan's auditors. Clinical documents can inform a case, but only to show what a claim represents. Nothing the module produces is a diagnosis, treatment recommendation or coverage determination about a patient, and medical necessity questions that arise in an audit stay with the plan's own clinical reviewers. Abacus makes no device claim and the product's scope fits that, as payment integrity software sold to health plan audit teams.

CC on AI Governance and Bias DisclosureResponsible artificial intelligence is committed to in policy language with no evaluation behind it. Most of the index sits here.
Vendor Published

Abacus describes its payment integrity approach as governed, trustworthy and supervised by people, with auditors able to see the evidence behind each case and the plan's team making the final call. Prioritization is kept separate from the claim editing rules a plan configures. That is the commitment in policy terms.

No evaluation shows how the prioritization performs across claim types, provider specialties, lines of business or provider sizes, and nothing addresses whether some providers are surfaced for audit more often than their error rates justify, which is the fairness question payment integrity raises.

CC on AI Liability and RecourseMechanisms exist that let someone challenge an output, such as audit trails, source traceability or review before commit, with nothing standing behind the output and no route for the harmed party.
Vendor Published

Each surfaced case comes with its supporting information, so an auditor can examine why it was selected and check it against the plan's source records before deciding whether a payment error occurred. The final determination, and any recovery from a provider, stay with the plan. The AWS Marketplace terms for the wider data platform cover conformance to documentation in defined circumstances, and they do not reach the audit module's recommendations. No correction commitment, warranty or remedy applies when the prioritization misses an error or flags a sound claim, and a provider has no route to Abacus at all.

Integration and Deployment
CC on EHR and Interoperability DepthIntegration is claimed through standards or a middleware layer with no system named and nothing to verify.
Vendor Published

Health plans have no EHR of their own, so the integrations that matter are payer systems: the data foundation pulls claims, clinical, provider and outside vendor data into one governed layer, and Cambia's enterprise build included external connectors. Abacus' separate interoperability offering uses Onyx for CMS data exchange rules.

No named claims platform, clinical record source or payment integrity vendor feed is shown running into the audit module in production, and how clinical records reach a case, whether from provider submissions or exchange data, is not described.

CC on Deployment Model and Data ResidencyA single hosted option with location implied rather than committed.
Vendor Published

Abacus runs its platform on AWS and Azure and also delivers work inside a client's own data environment for its payer offerings, and the Marketplace edition runs on AWS. Those options describe the wider platform. For the audit module, where the prioritization model runs, which region holds assembled cases and their history, and how each plan's data is isolated in a shared or client hosted arrangement are not committed. Residency is implied by the cloud providers named rather than stated, for data that can include clinical records alongside claims.

Commercial
CC on Commercial TransparencyNo price is published and the posture is discoverable: a buyer can establish how the product is sold and what drives the cost before contacting the vendor. Most of the index sits here.
Vendor Published

A plan can start with any of the three modules, and Complex Claims Audit is sold through a conversation with Abacus' team. The broader data platform, listed on AWS Marketplace as the Health Plan Data Management and Usability Solution, costs $125,000 for an annual subscription. Whether the audit module is priced per claim reviewed, per recovery, per member or as a flat subscription, and what configuration and integration work comes with it, are not given. A buyer knows the platform's entry cost and how the module is sold, but not what the AI part costs.

CC on Setting and Specialty CoverageCoverage is claimed broadly without specifics, or stated clearly with nothing validating it yet.
Vendor Published

The module serves health plan payment integrity teams reviewing complex claims, alongside a plan's existing payment integrity vendors, which can keep working on the shared data foundation. A plan can begin with the audit module alone, without moving its claim editing to CoverSelf, and the work centers on identifying, investigating and resolving complex claim payment errors.

Abacus' wider platform serves health plans across risk adjustment, quality measurement, analytics and interoperability, with 35 customers and 65 million covered lives. The audit module is stated clearly as a payer tool, with no plan named and no result yet showing how it performs across commercial, Medicare Advantage or Medicaid lines of business.

Alternatives

Alternatives to Complex Claims Audit

Other products that do the same kind of work as Complex Claims Audit, and what each one does.

Machinify sells payment integrity software and services to health plans, and it exists as the result of several companies being combined under one private equity owner.

Codoxo helps health plans, pharmacy benefit managers and government agencies find payment errors, investigate fraud and review complex claims.

Cohere Health sells a clinical intelligence platform, Cohere Unify, to health plans. Its modules cover utilization management, payment integrity, appeals, care management, claims operations and HEDIS quality work.

Agentic AI for health plan claims operations, sold to payers as software or as a fully managed clinical review service.

Anterior sells clinical AI to health plans and to the organizations that run clinical review for them.

Autonomize AI, founded in Austin in 2022, sells the Autonomize Intelligence Platform for healthcare operations, with health plans as its main buyer and provider organizations and life sciences companies alongside.

Commercial

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
Contact sales
Health plans can start with Complex Claims Audit or either of the other payment integrity modules through a conversation with Abacus. The audit module's price and unit of charge are not given. Abacus describes safeguards for protected health information in its customer security program. No business associate agreement is stated for the audit module. The audit module runs on the shared payment integrity data foundation. No separate integration, configuration or onboarding fee is stated. Vendor Published

The broader data platform, the Health Plan Data Management and Usability Solution, lists on AWS Marketplace at $125,000 for an annual subscription. That price covers the platform rather than the audit module.