Healthcare Intelligence

Turn clinical evidence into defensible action.

Connect claims, encounters, clinical documents and member data. InferonIQ identifies supporting evidence, validates HCCs, surfaces suspected missing conditions, turns documentation gaps into a retrieval worklist and creates a traceable review workflow for Medicare Advantage Risk Adjustment, RADV and coding teams.

Book a healthcare demo See what it does

Evidence-linked · Human-reviewed · Second-level QA · Audit-ready · BYOC

Member M-20418 · PY2026Unsupported

HCC 37 · Diabetes with chronic complications

Reported on claim, but no current-year encounter documents MEAT for the complication.

Claim 837P · DOS 2026-03-14

ICD-10 E11.22 reported

Current year

Progress note · 2025-11-02

p.3 — “DM2 with CKD stage 3”

Prior year

Lab panel · 2026-02-20

eGFR 52 mL/min

Current year
Routed to coder queue · Reviewer sign-off requiredOpen evidence →

From chart to finding, in one view.

Reported HCCs reconciled against encounters and clinical documents, with the evidence one click away.

Ask AI
Demo
RADV readiness, risk evidence, documentation gaps and provider queries, in one workspace

Captured from the live product on synthetic members and charts. No real patient data (PHI) is shown.

Patient data

How we handle PHI.

The model sees only what the task needs, and every call is logged by task, provider and model, never by content.

BAA before any PHI

We sign a BAA with you, and every vendor that can see PHI signs one with us, before real patient data is loaded.

No retention, no training

Only AI providers you approve, under zero data retention. Your data never trains a model.

Masked, minimum necessary

Names, dates of birth and IDs are masked as placeholders before the model reads a chart header or summarises an answer. Writing SQL, it never sees patient records.

Rules decide, not the model

HCC mapping, hierarchies and dollar values come from CMS tables. A coder approves every finding.

Your cloud, your AI

Run InferonIQ in your own cloud (BYOC) with your own AI account. PHI never reaches InferonIQ; we receive only license checks.

Demos run on synthetic patients. See the FAQ for detail.

Clinical evidence validation

A diagnosis on the claim is not the same as a diagnosis the chart supports.

InferonIQ validates HCC-supporting documentation using MEAT-based evidence, ICD-10 to HCC mappings, source provenance and encounter context. Unsupported, conflicting, historical or incomplete diagnoses are flagged for human review — with the quoted text and page behind every call.

MEAT — Monitor, Evaluate, Assess, Treat — is the industry framework for judging whether documentation supports a diagnosis. It is not a CMS rule that every element must appear; CMS requires that submitted diagnoses be substantiated by the medical record. InferonIQ uses it to decide what a coder should look at, and a person makes the decision.

E11.22 · Type 2 diabetes with diabetic CKD → HCC 37Supported
  • M

    Monitor

    Home glucose log reviewed, fasting 140–180

    Progress note · Assessment & plan · p.2

  • E

    Evaluate

    A1C 8.1% · eGFR 52 mL/min

    Lab panel · 2026-02-20 · p.4

  • A

    Assess

    “DM2 with CKD 3a, not at goal”

    Progress note · Assessment & plan · p.2

  • T

    Treat

    Continue metformin 1000 mg BID; repeat A1C in 3 months

    Medication list · p.3

“Diabetes mellitus” — problem list only, not discussed at the visit

Problem list · p.1

Needs review · no current evidence
Evidence Assurance

How you know the findings and the dollars are right.

RADV tests the whole program, not one code. InferonIQ checks the record, checks its own RAF arithmetic against CMS, puts a second reviewer on the decisions that matter and tracks every dollar from identified to realized.

Review quality

Every decision can stand a second look

Checks the record itself
Unsigned notes, RN, LPN or MA-only signatures and non-acceptable record types are held for review, citing CMS guidance.
Second-level QA
A different reviewer samples decisions, always including the high-value ones. A failed QA goes back to the queue.
Every finding explains itself
How to review it, the RAF calculation step by step, and a history of what changed it and why.
Rules changes, previewed
A locked benchmark shows exactly which cases change before a new rules version goes live.

Value ledger

Every dollar, from identified to realized

  • Identified$5.1M
  • Validated$3.8M
  • Actioned$3.4M
  • Resolved$3.3M
  • Realized$3.2M

Each member, HCC and payment year is counted once. Illustrative figures on synthetic data.

RAF arithmetic equals CMS’s own V28 scorer on 954 test members across all seven segments.

Dollar values are estimates at your plan’s base rate. No accuracy figure is claimed on your charts until your own coders have measured it.

Outside coders see only the findings assigned to them, and only while a BAA is in force. Approved findings go out once, as FHIR R4 or CSV.

Choose which AI vendors may process your data. Nothing goes to any other vendor, even during an outage.

Where the exposure sits today.

Extrapolated

Unsupported HCCs before RADV

RADV findings are now extrapolated across the contract. A diagnosis without current-year MEAT evidence in the chart is no longer a single-claim problem — it is a plan-level exposure.

40+ hrs/week

Claims adjudication backlogs

Claims need 4-way validation — authorization, fee schedule, eligibility and clinical edits. Manual review misses unbundling, global-period violations and duplicate lines.

$1M–$5M/yr

GPO pricing non-compliance

Medical suppliers invoice at list instead of GPO-contracted rates across thousands of SKUs and hundreds of vendors.

Capabilities

Built for the teams who have to defend the number.

HCC Validation

Reconcile every reported diagnosis against encounters and the chart, map ICD-10 to CMS-HCC V28 for the payment year, apply CMS hierarchies and put a RAF and annual dollar value on every finding.

  • ICD-10 → CMS-HCC V28 by payment year, hierarchies applied
  • RAF and annual $ impact per finding, from official CMS tables
  • Supported, unsupported, historical or conflicting

MEAT Evidence

Look for proof the provider monitored, evaluated, assessed or treated the condition — not just that it was listed. A problem-list or history-only mention is not accepted as support.

  • Assessment & plan, labs, medications and imaging cited
  • Quoted text with document and page
  • Current-year date-of-service checks

Suspect Conditions

Surface diagnoses the chart documents — or pharmacy fills and lab results imply — that no claim carries, value each one in RAF and dollars, and send it to a coder, a chart chase or a provider query. Nothing is auto-coded.

  • Documented but not submitted, or at the wrong specificity
  • Pharmacy and lab signals with no claim (apixaban, eGFR, A1c)
  • Opportunity valued net of V28 hierarchies

Documentation Gaps

Turn unsupported and chart-less diagnoses — and conditions only pharmacy or lab data shows — into a prioritized chart-chase worklist, send non-leading provider queries where the note falls short, and track every request until the returned chart has been reviewed.

  • One request per chart, ranked by HCC and RADV risk, dollar value shown
  • CSV export and status re-import for retrieval vendors
  • Returned charts matched and re-reviewed automatically

RADV Readiness

Trace every finding back to member, encounter, document, page and evidence before an auditor asks for it.

  • Member → encounter → page provenance
  • Readiness score across open findings
  • Evidence export with reviewer decisions

Evidence Assurance

Prove the program itself is right: the record is checked, the RAF arithmetic is checked against CMS, a second reviewer samples decisions and every dollar is tracked from identified to realized.

  • Signature, credential and record-type checks, citing CMS guidance
  • RAF arithmetic equals the CMS V28 scorer on 954 test members
  • Second-level QA and a value ledger, each member / HCC / year counted once

Reviewer Guidance & History

Every finding explains itself: what Agree and Disagree mean, how to review it, the RAF calculation step by step, and a history of what changed it and why.

  • “How to review this finding”, written for the coder
  • Step-by-step RAF and estimated dollar calculation
  • Change history with the cause: rules, CMS / ICD release, base rate, segment or a new chart

Healthcare Ask AI

Ask questions across claims, encounters, labs, medications and clinical documents in plain English.

  • Claims + chart in one question
  • Governed, PHI-aware answers
  • Every number traced to its source
Documentation gaps · PY2026Export for retrieval →
  1. Record needed
  2. Requested
  3. Received
  4. Analyzed
  5. Closed

  • M-20418 · Office visit · DOS 2026-03-14

    HCC 37 · HCC 329 · No chart on file

    HighRecord needed

  • M-11873 · Cardiology consult · DOS 2026-01-22

    HCC 226 · No current evidence

    HighRequested

  • M-30952 · Office visit · DOS 2026-02-05

    HCC 409 · Amputation status undocumented

    MediumReceived

  • M-09617 · Office visit · DOS 2025-12-09

    HCC 155 · Insufficient evidence

    LowAnalyzed
Returned chart for M-09617 matched to its claim and re-reviewed — finding now Supported
Documentation gaps

When the evidence is not in the chart, go and get it.

Unsupported findings and claims with no chart on file become one record request per encounter, ranked by HCC value, RADV sensitivity and date of service.

  • Filter and export a retrieval list for your vendor or provider outreach team
  • Re-import statuses from the vendor file; nothing is re-keyed
  • Returned charts are matched to the open request and re-reviewed automatically
  • Each request is timestamped at every stage, from record needed to closed
How it works

Evidence in. Reviewed action out.

Every diagnosis is reconciled across claims, encounters and the chart, evaluated against HCC rules and MEAT criteria, and classified into a finding a coder can act on — with the evidence ready for audit when it is approved.

  1. 1ConnectClaims · Encounters · Labs · Medications · Clinical PDFs
  2. 2UnderstandDocument AI · Clinical concepts · ICD-10 · Member timeline
  3. 3ReconcileClaims ↔ Encounter ↔ Clinical evidence
  4. 4EvaluateHCC rules · MEAT · Current-year evidence · Conflicts
  5. 5FindingsClassified, evidence-linked, ranked by impact
    SupportedUnsupportedMissing candidateHistoricalConflictNeeds review
  6. 6ActCoder review → Record request → Provider query → Audit evidence
Healthcare Ask AI

Ask across claims and the chart in the same sentence.

The same NL2SQL and Document AI engine behind Enterprise Intelligence, tuned for clinical vocabulary. Structured tables and unstructured notes are answered together, and every number links back to the rows and pages it came from.

ClaimsEncountersLabsMedicationsClinical PDFs & scansMember eligibility

  • Risk Adjustment

    Which reported HCCs lack current-year clinical evidence?

  • RADV

    Show every document supporting HCC 85 for this member.

  • Coding

    Which members have diabetes complications documented but not coded?

  • Suspects

    Which members have pharmacy or lab evidence of a condition nobody documented this year?

Connects to the systems your clinical data already lives in

FHIR R4 APIs, HL7 v2 feeds over SFTP or network drives, claims warehouses and document stores.

EpicORACLEHealthFHIR R4HL7v2
Governance

Designed for audit from the first query.

Every finding has a source

Member, encounter, document, page and quoted text are attached to each result. Nothing is asserted without evidence.

People make the call

AI proposes; coders and reviewers approve, correct or reject. Every decision is attributed and timestamped.

Full audit trail

Every chart read by AI (model, time and the exact output), Ask AI questions and answers, reviewer and QA decisions and exports are logged for compliance and RADV defence.

Read-only connections

Connectors read from EHR, claims and document stores. Corrections flow through your existing systems.

COMPLIANTHIPAAHIPAABuilt for HIPAA · BAA available
GDPRCompliant
TYPE IISOC 2IN PROGRESSSOC 2 Type IIIn progress
Healthcare operations

The same deployment covers the business side.

Provider groups and hospital networks use Enterprise Intelligence alongside clinical review — for payment integrity, supplier pricing and contract terms.

Claims & payment integrity

Authorization, fee schedule, eligibility and billed amount reconciled per claim line. Unbundling and duplicate lines flagged before payment.

Learn more

Supplier & GPO pricing

Medical-supply invoices checked against GPO tier and contract rates across every facility and SKU.

Learn more

Implant & device billing

Device and implant invoices validated against surgical logs, quantities and authorized substitutions.

Learn more

Payer & supplier contracts

Terms, escalators, renewal dates and obligations extracted from agreements and monitored against actual spend.

Learn more
4-WAYMATCHAUTHORIZATIONPre-approvedFEE SCHEDULE$3,950/unitELIGIBILITYActiveCLAIM BILLED$4,800/unit

Spinal implant claim: authorization approved, GPO fee schedule $3,950, eligibility active, billed $4,800 — an $8,500 overcharge across 10 units, caught before payment.

Claims and supply checks that run on every line

  • 4-way claims match: authorization ↔ fee schedule ↔ eligibility ↔ claim
  • WAC pricing variance — invoices above wholesale acquisition cost
  • Cold-chain, hazmat and controlled-substance surcharge detection
  • GPO tier-rate compliance on every medical-supply invoice
  • Implant and device billing validated against surgical logs
  • Duplicate claim and line-item detection
  • Supply PO ↔ receipt ↔ invoice 3-way match across facilities
  • Tolerances configurable by category, vendor and facility

Ask operations

  • Show claims denied for missing authorization in the last 90 days
  • Which suppliers are invoicing above GPO contract rates?
  • What implant invoices have quantity mismatches vs surgical logs?
  • Show providers with the highest unbundling rate this quarter
Clinician reviewing patient information

Clinical review and payment integrity, from one deployment.

Health plans, provider groups and hospital networks.

Not a second product. The same platform.

Healthcare Intelligence runs on the NL2SQL, Document AI, Agent Studio, workflow and governance layers that power Enterprise Intelligence — so revenue-cycle, supply-chain and contract teams can work from the same deployment.

How the platform worksEnterprise Intelligence

Healthcare Intelligence — frequently asked questions

MEAT, V28, RAF dollars, chart chase, provider queries, evidence assurance, RADV and PHI

How do we know the findings and dollar values are right?
Evidence Assurance checks the program, not just the finding. The RAF arithmetic equals CMS's own V28 scorer on 954 test members across all seven segments; the record itself is checked for signature, provider credential and record type, citing the CMS guidance; a second reviewer samples decisions, always including the high-value ones; and a value ledger tracks each finding from Identified to Realized, counting each member, HCC and payment year once. Every finding records the rules version that decided it, and a locked benchmark shows which cases change before you adopt a new rules version. Dollar values are estimates at your plan's base rate, and no accuracy figure is claimed on your charts until your own coders have measured it.
What is MEAT in risk adjustment?
MEAT stands for Monitor, Evaluate, Assess (or Address) and Treat — the evidence a coder looks for in the visit note to show a condition was actually managed, not just listed. InferonIQ looks for that evidence in the assessment and plan, labs, medications and imaging, quotes it with the document and page, and does not accept a problem-list or history-only mention as support.
Does InferonIQ support CMS-HCC V28?
Yes. Every diagnosis is mapped to the CMS-HCC model for its payment year — V28 from payment year 2026 — with CMS hierarchies and interactions applied, using the official CMS model software and Rate Announcement. The tables stay current through a managed nightly sync, or you can upload and activate your own copy.
How is the RAF dollar value of a finding calculated?
InferonIQ scores the member with and without the finding under the payment-year model, then converts the RAF change to an estimated annual amount: RAF change ÷ normalization factor × (1 − MA coding adjustment) × your plan's monthly base rate × 12. Supported diagnoses show what is protected, unsupported ones what is at risk in an audit, and suspects the opportunity. It is a prioritization estimate, not a CMS payment calculation.
What is a chart chase, and how does InferonIQ help?
A chart chase is the work of retrieving medical records from provider offices to support or find diagnoses. InferonIQ builds the list for you — claims with no chart on file, charts that do not support the claim, and conditions only pharmacy or lab data shows — ranks every request by audit risk and dollar value, exports it for your retrieval team or vendor, re-imports statuses, and matches returned charts back automatically.
Can pharmacy and lab data find suspect conditions?
Yes. A fill such as apixaban or donepezil, or a lab result such as eGFR below 60 or HbA1c of 6.5% or more, that implies a risk-adjusting condition no claim carries that year becomes a chart request or a provider query, with the evidence and the dollar value. Pharmacy and lab data can come from a connection to your systems or from a CSV extract you upload. These are prompts for review, never codes.
How do provider queries work? Is this CDI?
When a note does not support a claimed condition, or pharmacy and lab data point to a condition nobody documented this year, InferonIQ drafts a non-leading query to the treating provider: the clinical indicators, a question that asks for clinical judgment, and options that always include another diagnosis, not present and unable to determine. Providers never see HCCs or dollar values. Queries are exported or answered in the app and close automatically once a reviewed chart documents the condition. It supports your clinical documentation improvement (CDI) and in-year suspect programs; it does not replace your CDI team.
Does InferonIQ code charts automatically?
No. AI reads the chart and quotes it; ICD-10 to HCC mapping, hierarchies and dollar values come from CMS files and deterministic rules; and a coder accepts or rejects every finding. Nothing is written back to a claim.
How does InferonIQ help with RADV audits?
Every finding is traced from member to encounter, document, page and quoted evidence, with the reviewer's decision attached. Unsupported diagnoses surface before an auditor finds them, and a member-level evidence package can be exported in one click.
Which data sources does it connect to?
EHRs over Epic, Oracle Health, FHIR R4 and HL7 v2; claims warehouses and databases over JDBC or API; document stores for charts; and CSV upload for pharmacy and lab extracts. Connections are read-only.
Will you sign a BAA?
Yes. We sign a Business Associate Agreement with you, and every vendor that can see PHI signs one with us, before any real patient data is loaded. Demos and trials run on synthetic data.
Do you send PHI to AI models?
Only what the task needs. When writing SQL the model sees table structure, never patient records. Before it reads a chart header or summarises an Ask AI answer, names, dates of birth and IDs are masked as placeholders, and the real values are restored only in the answer you see. Clinical text a coder needs is read by approved AI providers under BAA and zero data retention, and is never used to train models. Coding and payment decisions are made by CMS tables and rules, not the model.
Where does our PHI live?
In our managed cloud, PHI is stored per tenant, encrypted and access-controlled, under a BAA. For maximum control, run InferonIQ in your own cloud (BYOC) with your own AI account (OpenAI, Anthropic or Azure OpenAI): PHI never reaches InferonIQ, which receives only license checks. Either way, every access and decision is logged.
Does InferonIQ support ACA (HHS-HCC) risk adjustment?
Not today. InferonIQ is built for Medicare Advantage risk adjustment under the CMS-HCC model.

Have more questions? Contact us

See it on a real evidence review.

We will walk your team through a scoped HCC evidence review — on sample or de-identified data, in our cloud or yours — and every finding behind it.

Book a healthcare demo Deploy in your cloud