Home/AI Suite/HCC Coding
V28 Native · MEAT Enforced · RADV Defensible

AI for HCC risk adjustment coding under V28.

V28 changed the math. Roughly 2,300 ICD-10 codes were re-weighted and over 200 removed entirely from the risk model. Across the medical groups we audit, average RAF dropped 9.3 percent on the same patient panel. Our HCC AI is built for what comes next, not what worked under V24.

200+ payers contracted 40+ states served Senior partner on every account
Why V28 matters now

The condition map changed. The math followed.

CMS finished phasing in the V28 risk model this year. The change is not a tune-up. It is a structural shift in which conditions carry weight and which do not. Several high-volume V24 capture categories now contribute less, or nothing, to your RAF score. The chart shows where the weight moved across eight common HCC categories.

AI trained on V24 surfaces opportunities that no longer pay. The right HCC AI for 2026 carries the V28 condition map native, with a V24 comparison view for finance leadership reconciling prior-year capture against current.

V24 vs V28 · coefficient comparison
V24 V28
Diabetes w/o complicationHCC 36 family
0.105
0
Major depressive disorderHCC 152 V24
0.309
0
Specified vascularHCC 108 family
0.299
0.110
COPDHCC 111
0.328
0.298
Congestive heart failureHCC 85 family
0.323
0.395
CKD stage 4-5HCC 138 family
0.422
0.480
Active cancerHCC 17 family
0.677
0.625
Acute MIHCC 86
0.224
0.220
The translationEvery 0.1 RAF point translates to roughly $1,040 in plan revenue per attributed life. A 0.10 drop across 4,000 lives is approximately $4.1M in revenue your group is no longer earning without changing a thing clinically.
Coefficients directional · CMS V28 final rule · individual values vary by segment
Inside the product

The HCC Coding AI console.

The actual operator view your coders, CDI leads, and finance teams work inside every day. V28 condition map, MEAT enforcement, RAF lift attribution, and full LLM Gateway audit on every suggested code.

aisuite.asprcm.com/hcc-coding
M-01V28 NATIVE
RAF Current
1.04
V28 measured
RAF Target
1.18
Q4 glidepath
Lift YTD
+0.14
$5.8M PMPY
AWV Complete
84%
3,360 of 4,000
Open Suspects
247
Needs MEAT
Captured PMPY
$5.8M
Per 4K lives
Suspect HCC queue
RANKED BY RAF $
Aldridge, M.
MRN 884217
CKD stage 4
N18.4 → HCC 327 · 0.514
M E A T
96%
Bhattacharya, S.
MRN 712890
CHF systolic, acute
I50.22 → HCC 226 · 0.360
M E A T
99%
Caldwell, J.
MRN 998441
DM2 w/ neuropathy
E11.42 → HCC 37 · 0.166
M E A T
71%
Dhillon, P.
MRN 651302
Active malignancy, lung
C34.90 → HCC 20 · 1.136
M E A T
98%
Esposito, R.
MRN 443218
Vascular dz, peripheral
I70.249 → HCC 263 · 1.118
M E A T
42%
V28 condition mapper
LIVE
CAPTURED · MAPPED
E11.22
DM2 w/ CKD
HCC 18 HCC 138
RAF +0.724
UNDERCODED · V28 GAP
E11.9
DM2 w/o complication
No HCC
RAF 0.000 · V28 removed
V28 LIBRARY
ICD-10 weighted2,300
V28 removed218
Hierarchies87
LLM GATEWAY
MODEL
claude-haiku-4-5
TOKENS
4,283
COST
$0.18
LATENCY
182 ms
PROMPT VER
v28.4.2
AUDIT TRAIL
● RADV-ready
The six capabilities

What moves the needle in HCC coding.

Generic AI medical billing tools rarely lift RAF. The six capabilities below are tuned for the operating reality of risk adjustment coding under V28. Each runs as part of our managed service, not as a tool you wire in alone.

01

V28-current suspect generation.

Our NLP reads chart documentation, problem lists, medication lists, recent labs, prior-year claims, and hospital discharge summaries. It surfaces suspected HCCs with the V28 condition map applied. Conditions that lost weight under V28 are de-prioritized so coder attention sits where the RAF actually lives. Outputs are ranked by combined RAF impact and documentation confidence so the coder works highest-value first.

What you get
  • V28 condition map, refreshed quarterly
  • Handles negation, uncertainty, history
  • Suspect list ranked by RAF impact
  • Hospital discharge data integrated
02

Recapture campaign management.

A suspect list without a workflow is just a more sophisticated way of missing the same revenue twice. Our model identifies attributed members whose chronic conditions were captured last year but not yet reaffirmed this year, then drives pre-visit prep, Annual Wellness Visit outreach, and clinician huddles ahead of those visits. Campaign progress is tracked at the panel level, with measurement at the patient, provider, and pod level.

What you get
  • Patient-level recapture queue
  • AWV scheduling integration
  • Provider-level recapture scorecards
  • Year-end glidepath dashboard
Recapture funnel · 4,000-life MA panel · anonymized client
Attributed members
4,000
100%
Eligible for recapture
1,840
46% of panel
AWV scheduled
1,320
72% scheduled
AWV completed
1,050
80% completed
HCC re-affirmed
902
86% closed clean
Industry baseline recapture sits at 62-72% · our top-quartile clients close at 86-88%
03

Clinical documentation review.

Every AI-surfaced code is paired with the documentation snippet that supports it, dated and signed. MEAT criteria (Monitored, Evaluated, Assessed, Treated) are extracted from the note and flagged when implied but not explicit. The coder sees a missing-MEAT prompt before the chart closes. Problem-list copy-forwards are explicitly rejected as standalone evidence. The output is documentation that reads as audit-ready before the encounter is locked.

What you get
  • MEAT extraction per code
  • Pre-close MEAT-gap alerts
  • Re-affirmation enforcement per year
  • No-copy-forward discipline
04

RAF lift attribution.

Leadership needs to know where lift came from. Our dashboard breaks RAF gains into four buckets: suspect-driven new captures, recapture-driven re-affirmations, gap closures from documentation prompts, and new diagnoses from clinical encounters. This lets the CFO defend the program to the board, the Chief Medical Officer evaluate clinician training impact, and operations attribute lift to the workflow change that produced it.

What you get
  • Four-bucket lift attribution
  • Provider and pod scorecards
  • Trend tracking against baseline
  • Executive monthly readout
90-day RAF lift · attribution by source · anonymized client
Suspect-drivenNew HCC captures surfaced by V28 NLP from labs, meds, discharge data.
RecapturePrior-year conditions re-affirmed via pre-visit prep and AWV outreach.
MEAT promptsGap closures from real-time documentation alerts during encounters.
New diagnosesGenuine new conditions captured during this year's clinical visits.
90-day total lift on attributed panel · +0.14 RAF
05

RADV audit defense.

The CMS RADV final rule is now in force. Audit samples extrapolate across the full membership, so a 200-chart finding becomes a multi-million-dollar clawback. We log every AI-assisted capture: the source documentation, the MEAT signal, the date and clinician of record, the coder confirmation step, and the version of the AI model that suggested it. The result is an audit trail that defends each code on its own merits, end to end.

What you get
  • Per-code RADV audit log
  • MEAT evidence packaged
  • Model version traceability
  • Appeal-ready documentation
06

Pattern analytics across the panel.

Beyond per-patient coding, the model surfaces patterns. Under-coded condition categories. Comorbidities consistently missed by clinician or pod. Regional variations across multi-site groups. These patterns feed clinician education, CDI program design, and pre-visit huddle priorities. The result is a continuously improving documentation system, not a one-time bump.

What you get
  • Cohort-level miss analysis
  • Provider education feeds
  • CDI roadmap recommendations
  • Regional benchmarking
Workflow

Three workflows. One operating system.

The highest-leverage HCC AI deployments do not bolt onto a single moment in the chart. They run across the encounter lifecycle, with the right action at the right time. Here is how ours sequences.

Step 01 · Highest leverage

Pre-visit planning.

AI surfaces the suspect HCC list for the upcoming Annual Wellness Visit so the clinician walks in knowing which chronic conditions need re-affirmation, which suspects need clinical assessment, and which prior-year captures are at risk if the visit closes without follow-up. Pre-visit huddles become structured, not improvised.

When it runs3 to 7 days before the scheduled visit, refreshed the night before.
Step 02 · In-encounter

Concurrent prompts.

As the note is being written, our model prompts the clinician on MEAT gaps in real time. The prompts appear inside the EHR chart workflow, not in a side application. A suggested HCC requires the clinician to confirm or decline before the encounter closes. This puts the decision where the clinical judgment lives, when the chart is most fresh.

When it runsWhile the chart is open, sub-second latency on prompts.
Step 03 · Backstop

Retrospective sweep.

At month-end, AI re-sweeps every chart that closed without confirming open suspects. Each one is queued for clinician review, addendum, or outreach for a follow-up visit before the calendar year closes. This is the safety net that catches what pre-visit and concurrent prompts miss, with full audit trail.

When it runsLast business day of each month, dashboard updates within 48 hours.
M
Monitored
E
Evaluated
A
Assessed
T
Treated
Chart coverage · 10 chronic conditions · anonymized sample
ConditionMEAT
CHF
CKD 4
COPD
DM2 w/comp
MDD recurrent
Asthma severe
A-fib
Cancer breast
Vascular periph
CKD 3 w/HTN
Coverage score 87%Top quartile
RADV defense layer

MEAT, every chart, every chronic condition.

Documentation defensibility now matters more than capture rate. The CMS RADV audit final rule extrapolates findings across the full membership. A 12 percent error rate on a 200-chart sample becomes a multi-million-dollar clawback for a practice with 8,000 attributed lives. The right defense is not retroactive appeal. It is documentation that satisfies MEAT at the point of capture.

Our model extracts MEAT signals from progress notes, problem lists, medication lists, and labs. Every AI-suggested code carries the MEAT evidence with it. The heatmap shows what audit-ready coverage looks like in practice: green where MEAT is fully documented, amber where one element is implied but soft, red where coverage is missing entirely. Coverage is scored at the chart, provider, and pod level with month-over-month trend tracking.

Size your opportunity

What is your panel leaving on the table?

The math behind HCC capture is unforgiving and surprisingly simple. Every missed HCC is roughly $1,800 in plan revenue, and the average high-utilization MA patient carries four to seven missed conditions when documentation discipline lapses. Multiply that across your attributed panel and you are looking at the real cost of a coding workflow that has not been updated for V28.

Adjust the sliders to your panel size and current capture rate. The calculator shows annual revenue at risk and the lift opportunity if you reach the top quartile. These are the same numbers our senior partners walk through on a 30-minute free audit call.

Revenue at Risk Calculator · live math
Attributed MA panel 4,000lives
5005K10K15K20K
Current capture rate 68%
50%65%75%85%95%
Annual revenue at risk
$2.9M
Lift opportunity at 88% capture
$1.4M
RAF lift to top quartile
+0.20
Math: $1,800 per missed HCC × 0.4 missed per life × eligible panel · PMPY basis
What clients see

Outcomes from well-implemented engagements.

Measured across mid-sized multi-specialty groups, ACOs, and IPAs running our HCC AI for at least 90 days. Anonymized; individual results depend on panel size, payer mix, and current documentation discipline.

+0.14
Average RAF lift in 90 days
Measured against the prior-year baseline on the same attributed panel. Attributable to suspect captures, recapture campaigns, and MEAT-prompted documentation upgrades together.
88%
Top-quartile recapture rate
Most groups we audit baseline at 62 to 72 percent recapture. Reaching the top quartile typically takes one full year of pre-visit and recapture campaign discipline.
4-7
Missed HCCs per high-utilization patient
Across our audits of practices that have not run V28 reconciliation, this is the typical gap. At $1,800 per missed HCC, this scales quickly across a 4,000-life MA panel.

Numbers are typical ranges from anonymized engagements. The free 30-day audit gives you a tailored projection based on your panel size, payer mix, and current capture rate, with the math attached.

Why our HCC AI

Built by senior operators, not generic AI vendors.

Most HCC AI on the market is software you license and wire in yourself. Ours is delivered as a managed service with senior partners accountable for outcomes. The differences below are the reasons CFOs choose us over the alternatives.

01

Service, not software.

Certified coders validate AI output. A named senior partner is accountable for your RAF target. You do not buy a tool and then staff it yourself.

02

SLA-bound outcomes.

RAF lift and recapture rate are in writing in your contract. We get paid when your captured revenue actually closes, not on AI usage.

03

RADV-defensible by design.

Every code carries source documentation, MEAT evidence, timestamps, and model version. Appeal-ready out of the box, not a feature roadmap.

04

V28-current, V24-aware.

Both models live in the dashboard. Finance leadership reconciles prior-year RAF runs against V28 capture without spreadsheet gymnastics.

Common questions

Frequently asked questions: AI for HCC coding.

How is V28 different from V24 and why does it matter for our HCC AI?
V28 is materially different. Roughly 2,300 ICD-10 codes were re-weighted and over 200 were removed entirely from the risk model. Conditions that drove RAF in V24 like uncomplicated diabetes, MDD, and several vascular categories now carry less weight or none at all. Across the medical groups we audit, average RAF dropped 9.3 percent under V28 on the same patient population. AI that was trained on V24 coefficients surfaces stale opportunities. Our model carries the V28 condition map and coefficients native, with a V24 comparison view for groups still reconciling prior-year RAF runs.
How do you keep AI-suggested codes audit-defensible against RADV?
Every AI-suggested HCC is paired with the documentation snippet that supports it, dated, signed, and traceable to the encounter. We enforce MEAT criteria visibility before a code is surfaced to a coder for confirmation. Conditions documented in prior years require explicit re-affirmation in the current year. Problem-list copy-forwards are not accepted as standalone evidence. The output is a RADV-ready audit trail per code, per encounter.
What outcomes can we expect in the first 90 days?
Across well-implemented engagements with mid-sized multi-specialty groups, our model averages a 0.14 RAF lift in 90 days, drives recapture rates from a typical 62 to 72 percent baseline into the 80 to 88 percent range, and surfaces 4 to 7 missed HCCs per high-utilization patient that the prior workflow was missing. Actual numbers depend on panel size, payer mix, and current documentation discipline. The free 30-day audit gives you a tailored projection before you sign anything.
Does this work for groups still on V24 or running V24 and V28 in parallel?
Yes. We carry both models. Most groups working with Medicare Advantage plans on cost-of-care arrangements need to reconcile prior-year V24 RAF against current V28 capture to size the actual recoverable revenue. Our dashboard surfaces both views side by side, so finance leadership can attribute lift to V28 transition versus genuine documentation improvement.
How does AI handle MEAT criteria specifically?
MEAT is the documentation standard CMS and payers use to defend HCC capture. Our NLP extracts MEAT signals from progress notes, problem lists, medication lists, and lab values, then flags conditions where MEAT is implied but not explicit. The coder sees a missing-MEAT prompt and can either confirm in the chart or escalate to a clinician. The result is documentation that reads as audit-ready before the chart is closed.
What is the workflow? Concurrent, retrospective, or pre-visit?
All three, sequenced to where the dollars are. Pre-visit (highest leverage): AI surfaces the suspect HCC list for the upcoming Annual Wellness Visit so the clinician walks in knowing which chronic conditions need re-affirmation. Concurrent: as the note is being written, the AI prompts on MEAT gaps in real time. Retrospective: at month-end, AI sweeps charts that closed without confirming open suspects, flags them for outreach, and queues recapture visits before year-end.
How does it integrate with our EHR?
Native FHIR integration with Epic, Cerner, Athena, eClinicalWorks, NextGen, and Greenway, plus 12 additional platforms via HL7 or 837 fallback. Real-time bi-directional. AI prompts surface inside the clinician's existing chart workflow, not in a side application. For ACO clients we also pull from the payer roster and claims feed so the suspect list reflects attribution-aware risk.
Is this software we license or a service ASP-RCM runs?
Service. Our HCC AI is delivered as part of a full revenue cycle engagement with senior partners on every account. We do not sell the AI as standalone software. You get the platform, our certified coders for validation, a dedicated senior partner accountable for outcomes, a written SLA on RAF lift and recapture rate, and a monthly executive scorecard. The economics are aligned: we earn when your captured revenue actually closes.
What does the free 30-day audit include?
Send us a 90-day encounter sample of your Medicare Advantage panel (we sign a BAA the same day). We return a four-page written audit covering: current measured capture rate against a peer benchmark by group size and panel mix, top ten missed HCC categories by frequency and dollar impact, V28 vs V24 RAF comparison on your sample, RADV-readiness flags on documentation, and a tailored implementation roadmap. The audit is useful whether you hire us or not.

Bring your panel data. We bring the V28 math.

A free 30-day audit. We take a 90-day encounter sample, run it through our V28 and V24 models, and return a four-page written report on where your RAF is leaking. No sales deck, no SDR triage. A senior partner on the call.