Why it’s time to bring HCC coding in-house

Accurate risk adjustment is not just a box to check; it is now a strategic lever. Hierarchical Condition Category (HCC) coding underlies the risk scores that determine Medicare Advantage and other value-based payments. With more than half of Medicare beneficiaries now enrolled in Medicare Advantage for 2025 (equivalent to approximately 35.7 million people), coding accuracy directly affects financial performance and compliance.

Many well-intentioned organizations outsource HCC coding to third parties who promise turnkey scalability and accuracy. But in practice, outsourcing can be expensive, difficult and risky. However, recent advances in generative AI have made it much easier and safer to integrate HCC coding internally, reducing costs and strengthening audit readiness.

The hidden costs (and risks) of outsourcing

The business model behind outsourced HCC coding creates misaligned incentives. Essentially, you’re trading higher expenses for smoother accuracy guarantees. Health plans can spend millions on chart pricing models, but vendors rarely provide the transparent, verifiable evidence needed to show that coding accuracy is actually better.

Meanwhile, CMS estimates the Part C (Medicare Advantage) payment error for FY 2024 at $19.07 billion – a reminder that documentation gaps remain a systemic risk if you can’t see and defend every code.

What’s worse? Audit exposure is up to you, not the vendor. Although CMS has mechanisms in place to recover overpayments, including extrapolation, and where diagnostics are not supported in the chart, it is not a perfect system. If an outsourced partner “pushes” the codes, you retain responsibility when auditors review the recordings, and they keep their fees.

Additionally, with most outsourced templates, you submit protected health information (PHI) and agree to someone else’s thresholds, editing logic, and risk tolerance. This lack of oversight and transparency is a problem if CMS or a plan auditor asks “why was this HCC awarded?” » and you cannot produce an explainable and defensible lead.

Changing regulatory objectives

Imagine hiring a tax firm that charges 20% of your deductions instead of an hourly rate. They have every interest in finding more deductions and pushing the limits. If you are audited, you are responsible; they keep their share. This is the risk dynamic of many outsourced HCC models: vendors maximize short-term revenue, while you face long-term audit risk.

In Medicare Advantage, the stakes are high. Payments for 2025 continue to increase as enrollment increases, increasing oversight of the accuracy of risk scores and coding practices. The policy updates provide for continued payment increases tied in part to risk score changes, fueling increased attention from CMS and oversight agencies.

Regulators are making the risks even clearer. The Office of Inspector General (OIG) has repeatedly cautioned against diagnoses that come solely from health risk assessments (HRAs) or chart reviews but are not supported anywhere else in the medical record. These types of codes increase payouts but often do not hold up to audit. In other words, you’re taking calculated regulatory risks if the coding isn’t secure.

The homemade alternative

Thanks to advances in generative AI, bringing HCC coding in-house can solve many of these problems at a fraction of the cost and risk profile. Your organization (not a vendor) is in the driver’s seat when it comes to changing logic, thresholds, evidence requirements, and escalation pathways. This means audit readiness is built into the design, with full provenance for every suggested and accepted code.

Think about it: you already employ clinical coders. When equipped with the right AI, they can pre-review charts, surface high-yield evidence, and easily accelerate second-tier review without adding headcount. Perhaps most importantly, solutions that run in your environment avoid sharing PHI while providing your team with full observability.

A few years ago, “DIY” meant building a natural language processing (NLP) platform from scratch. No more. New AI-driven generative HCC coding tools can be integrated into existing workflows to read messy, siled, and multimodal data, keep pace with evolving models, operate on-premises or in a private cloud environment, and allow you to customize to meet your own organization’s needs.

The safer, smarter way forward

Regulators have made their expectations clear: unsubstantiated diagnoses will be uncovered and funds will be recovered. The OIG continues to highlight vulnerable coding channels such as HRAs and chart reviews when they are not supported elsewhere in the medical record. And work on the CMS Part C error rate shows that billions are at stake each year.

Outsourcing made sense when the technology gap was large. This gap has since closed. Today, organizations can deploy AI-native HCC platforms behind their own firewall, scale them to their compliance posture, and operate at a predictable cost per patient, while remaining audit-ready.

Risk adjustment is too strategic to leave outside your four walls. The future of HCC coding is in-house, and through a combination of generative AI and your own clinical coders, organizations can directly address each of these realities with control, transparency, and cost savings.

Photo: LeoWolfert, Getty Images

This message appears via the MedCity Influencers program. Anyone can post their views on healthcare business and innovation on MedCity News through MedCity Influencers. Click here to find out how.