Risk adjustment goes wrong in two directions. Miss a condition and the organization carries risk it was never funded for. Overstate one and it comes back two years later. RiskIQ surfaces what the record supports, models RAF under V28, checks MEAT before a code is accepted, and keeps the audit packet ready.
Inside RiskIQ
Every capability below exists because a practice asked for it. Nothing here is a roadmap item.
Capture and recapture
Notes, labs, medications, and problem lists are read continuously. Suspected conditions and chronic conditions dropped since last year surface with a confidence score.
MEAT validation
At least one of Monitor, Evaluate, Assess, or Treat has to be documented before a code is accepted — and the coder sees which one, not the payer two years later.
RAF modeling under V28
Scores computed under the V28 model with hierarchy pruning and interaction terms, matched to the correct payment year. Payment year 2026 is the first year Medicare Advantage risk scores run entirely on V28, which pays on 115 condition categories rather than 86 and recognizes 7,770 risk-adjusting diagnosis codes rather than 9,797.
Specificity
Unspecified codes are upgraded when the record supports something more specific, with the supporting language shown beside the change.
Quality in the same pass
HEDIS and Stars measures tracked beside risk, so one review of the record closes coding and quality work together.
Audit defense
A signed, attested, exportable packet per code — sentence, page, date of service, provider — ready for any sampled member.
A person decides, the evidence is already there
Coders see each suggested code with its confidence, its MEAT status, and the exact sentence behind it. Accept, reject, or return a non-leading query — the estimated RAF impact updates as they work.
| Code | HCC | Diagnosis | MEAT |
|---|---|---|---|
| E11.22 | 37 | Diabetes with chronic kidney disease | 4 / 4 |
| I50.32 | 226 | Chronic diastolic heart failure | 2 / 4 |
| N18.31 | 327 | CKD stage 3a — needs note | 0 / 4 |
“Diabetes with CKD stage 3a — stable. Metformin continued, dose adjusted to 1000 mg BID.”
Illustrative example · not real patient data
From the schedule to the signed record
Records ingested
Clinical documents, labs, medications, and claims history are read across the panel.
Conditions surfaced
Candidates and recapture opportunities appear with linked evidence and confidence.
Coder decides
MEAT is validated, the code is accepted or rejected, and provider queries stay non-leading.
Defense assembled
Accepted codes carry an audit packet; risk and quality impact roll up by panel and contract.
Facts, not promises.
These are properties of how RiskIQ is built — not projected savings. Results in your practice depend on your payers, your panel, and your documentation.
RAF computed under V28 with hierarchy pruning and interaction terms
At least one of Monitor, Evaluate, Assess, or Treat documented before a code is accepted
Sentence, page, and date of service behind every accepted code
Organizations that run on RiskIQ
A good fit when…
- ACOs and value-based organizations
- Medicare Advantage risk-bearing groups
- Organizations preparing for RADV or payer audit exposure
See RiskIQ on your own workflow.
Tell us what your organization is fighting — open care gaps, documentation, denials, coverage — and we will walk you through the part of the platform that closes it.