HCC Risk Adjustment: From Q4 Scramble to Year-Round Work

By Jay Chowdappa, MD, co-founder and CEO, Zynix AI · Updated October 30, 2026

Key takeaways

To move HCC risk adjustment from a Q4 scramble to year-round work, rank patients whose chronic conditions are suspected or not yet documented this year, see them in the first half of the year, prepare clinicians with a pre-visit evidence summary and track documentation monthly. It works because CMS-HCC scores are prospective, and clinicians still decide every diagnosis.

A Q4 scramble leaves incomplete documentation, missed diagnoses and inaccurate RAF scores, and retrospective review catches errors only after scores are set.
Conditions documented in one year drive the next year's risk score, so a chronic condition that is not assessed this year drops out.
Medicare Advantage risk scores for 2026 use the 2024 CMS-HCC model (often called V28) in full, and CMS kept that model for 2027.
For 2027, Medicare Advantage risk scores exclude diagnoses from unlinked chart reviews and audio-only encounters, which makes documentation at the visit more important.
AI helps by surfacing suspected conditions and preparing clinicians before visits, while the clinician decides what to diagnose and document.

The Q4 Scramble Problem

Every year, healthcare organizations face the same frantic end-of-year push to capture Hierarchical Condition Category (HCC) codes before the deadline. This Q4 scramble results in incomplete documentation, missed diagnoses, inaccurate Risk Adjustment Factor (RAF) scores, and significant revenue left on the table.

Why Traditional Approaches Fail

Manual chart review processes simply cannot scale to meet the demands of accurate HCC coding across large patient populations. Retrospective coding reviews catch errors after the fact, but by then the damage is done — claims have been submitted, RAF scores have been calculated, and reimbursement has been set for the year.

AI-Driven Year-Round Risk Adjustment

AI transforms HCC risk adjustment from a reactive annual exercise into a proactive, continuous process. By analyzing clinical documentation continuously, AI identifies suspected conditions that may be undocumented, flags incomplete assessments, and prompts clinicians to capture accurate diagnoses during routine encounters throughout the year.

The Financial Impact

Accurate HCC coding directly impacts reimbursement. Organizations commonly miss legitimate HCC codes, and every condition that goes undocumented understates the expected cost of care for that patient and the reimbursement that follows. AI-powered risk adjustment tools can recover a significant portion of this revenue by ensuring comprehensive and accurate condition capture.

Building a Sustainable Strategy

The organizations that excel at risk adjustment treat it as a clinical workflow, not an administrative task. By embedding AI-powered HCC analysis into the point of care, clinicians naturally capture accurate diagnoses as part of their standard workflow, reducing the need for retrospective review and end-of-year scrambles.

Why the calendar matters in risk adjustment

Risk adjustment runs on a one-year lag, which is why a Q4 scramble is so costly. The CMS-HCC model is prospective: the current model was calibrated with 2018 diagnoses and 2019 expenditures, and conditions documented during one year's encounters set the risk score used for the following year.

Chronic conditions also have to be documented again each year. A patient whose heart failure was coded last year but who is not seen and assessed this year carries no heart failure HCC into next year's score. When most of those visits are squeezed into the last quarter, schedules fill up, documentation gets rushed, and the conditions of patients who cannot be seen in time drop out of next year's score.

CMS is also narrowing what counts after the fact. For 2027, it finalized the exclusion of diagnoses from unlinked chart review records (chart reviews not tied to a specific encounter) and from audio-only encounters when it calculates Medicare Advantage risk scores, with an exception for members who switch plans. For MA, that makes retrospective chart review a weaker fallback and documentation at the visit more important.

What a year-round program looks like

A year-round program spreads the work across every month and puts the clinician's decision at the visit. It has four parts.

First, a ranked list of patients with suspected or unconfirmed conditions, built from claims, labs, medications and prior notes and refreshed as new data arrives. Second, preparation: a short pre-visit summary of open gaps for each scheduled patient, so the clinician can evaluate and document during the visit. Third, outreach: patients with open gaps and no visit booked are invited in early in the year, often for their Annual Wellness Visit. Fourth, follow-through: monthly tracking of gaps opened, addressed and documented, by practice and clinician.

The clinician evaluates each suspected condition and decides whether to diagnose and document it; software surfaces evidence and never codes on its own. Every submitted diagnosis should be supported in the medical record, because CMS now plans to audit all eligible Medicare Advantage contracts each payment year. HCC gap ranking, pre-visit preparation and patient invitations are the tools that keep this work moving between visits.

What HCC gap closure software for ACOs should do

HCC gap closure software for ACOs should find the patients whose chronic conditions are suspected or not yet documented this year, get them in front of their own clinician early, prepare that clinician with evidence and track the work every month. It should never code a diagnosis on its own.

The model matters for both ACO types. In the Medicare Shared Savings Program, CMS calculates prospective CMS-HCC risk scores from diagnoses on final action fee-for-service claims (inpatient, outpatient and physician) and uses them to adjust the ACO’s benchmark for changes in case mix between the third benchmark year and the performance year, subject to a cap on positive adjustments. For agreement periods starting in 2024 or later, CMS applies the risk model for the performance year’s calendar year. In Medicare Advantage, CMS completed the three-year phase-in of the 2024 CMS-HCC model and calculates 100% of 2026 risk scores with it, and it will keep using that model for 2027.

Build a ranked suspect and recapture list. Combine claims, labs, medications and prior notes to list conditions documented last year but not yet this year, and conditions the evidence suggests but no one has assessed. A population-level view of who is due and why keeps the list current as data arrives.
Score against the model CMS is using. Rank gaps under the 2024 CMS-HCC model for Medicare Advantage and the model CMS applies to your MSSP performance year, so outreach goes to conditions that actually affect the risk score.
Prepare the clinician before the visit. Put the evidence for each open gap in a short summary for the scheduled visit, so the clinician can evaluate the condition and document it if it is present.
Bring unseen patients in early. Invite patients with open gaps and no visit booked, often for their Annual Wellness Visit, in the first half of the year. Voice and text agents through AI Patient Engagement can run the invitations, booking and reminders.
Keep every diagnosis with the clinician. The software surfaces evidence; the clinician decides and documents, and coders review what is submitted. That record is what a CMS risk adjustment data validation audit checks.
Track monthly by practice and clinician. Report gaps opened, addressed and documented, and patients with open gaps but no visit, so leaders can act long before the fourth quarter.

Frequently asked questions

What should HCC gap closure software for ACOs do?

It should rank patients with suspected or not-yet-documented chronic conditions, score gaps under the CMS-HCC model in use for the year, give clinicians a pre-visit summary of the evidence, invite patients with no visit booked, and track documentation monthly by practice and clinician. It should not code diagnoses on its own: the treating clinician evaluates the patient and decides what to document.

Why do HCC gaps pile up in the fourth quarter?

Because many organizations run risk adjustment as a year-end project. Chronic conditions must be documented at least once each year to count, and when outreach and chart preparation start late, the visits needed to assess those conditions crowd into the last months. Schedules fill, documentation is rushed, and patients who cannot be seen in time leave their conditions out of the next year's risk score.

What should an ACO do about HCC gaps in the fourth quarter?

Work first on the patients most likely to drop out of next year’s score: a chronic condition documented last year, not yet assessed this year, and no visit booked before December 31. Offer those visits now and prepare each clinician with the evidence. Rely on documentation at the visit, because Medicare Advantage risk scores for 2027 exclude diagnoses from unlinked chart reviews and audio-only encounters. Then build next year’s list in January.

How does HCC risk adjustment work in the Medicare Shared Savings Program?

CMS calculates prospective CMS-HCC risk scores for an ACO’s assigned beneficiaries from diagnoses on fee-for-service claims and uses them to adjust the historical benchmark for changes in case mix between the third benchmark year and the performance year. Positive adjustments are capped over the agreement period. Conditions that are never documented do not appear in the score, so undocumented illness makes the population look healthier than it is.

Does AI replace coders or clinicians in HCC risk adjustment?

No. AI ranks patients, assembles evidence from claims, labs, medications and prior notes, and flags documentation that looks incomplete. The treating clinician evaluates the patient and decides what to diagnose and document, and coders review what is submitted. Keeping that split matters because CMS risk adjustment data validation audits check that every diagnosis used for payment is supported by the medical record.

How does the Annual Wellness Visit support HCC accuracy?

The Annual Wellness Visit brings Medicare patients in once every 12 months to review their medical history, prescriptions and risk factors and to update a prevention plan. Booking it early in the year, within the AWV billing rules, gives clinicians a structured chance to review chronic conditions too, and risk and HCC gap analytics can show which patients to prioritize. Any diagnosis still has to come from the clinician's own evaluation.

Source notes

CMS: 2027 Medicare Advantage and Part D Rate Announcement (fact sheet). https://www.cms.gov/newsroom/fact-sheets/2027-medicare-advantage-part-d-rate-announcement

CMS: CMS Rolls Out Aggressive Strategy to Enhance and Accelerate Medicare Advantage Audits (May 21, 2025). https://www.cms.gov/newsroom/press-releases/cms-rolls-out-aggressive-strategy-enhance-and-accelerate-medicare-advantage-audits

Medicare.gov: Yearly "Wellness" visits. https://www.medicare.gov/coverage/yearly-wellness-visits

CMS: 2026 Medicare Advantage and Part D Rate Announcement (fact sheet). https://www.cms.gov/newsroom/fact-sheets/2026-medicare-advantage-and-part-d-rate-announcement

CMS: Medicare Shared Savings Program, Shared Savings and Losses, Assignment and Quality Performance Standard Methodology Specifications, Version 14 (April 2026). https://www.cms.gov/files/document/medicare-shared-savings-program-shared-savings-losses-assignment-methodology-specifications-version.pdf-0

About the author

Jay Chowdappa, MD is co-founder and CEO of Zynix AI. He is a physician, and ACOs led by him generated $300M+ in shared savings before he started Zynix AI to help care teams follow through on what their data already shows.

Transforming HCC Risk Adjustment: From Q4 Scramble to Year-Round Success