3 Reasons Why Your Health Plan Should Implement Complete Code Capture for Risk Adjustment

3 Reasons Why Your Health Plan Should Implement Complete Code Capture for Risk Adjustment

Today’s healthcare landscape is constantly evolving and with new regulations impacting risk adjustment, health plans are reevaluating their retrospective coding projects. With advances in analytics, technology, and Artificial Intelligence (AI), health plans have an opportunity to make their risk adjustment programs more efficient than ever before by implementing complete code capture.

Complete code capture is the coding of all risk-adjusting diagnosis code occurrences on every page of the medical record for all dates of service. We’re seeing many health plans move away from complete code capture for retrospective coding projects, however there are many advantages to this approach plans should consider, including capturing richer data for advanced analytics and AI, gaining a deeper understanding of provider coding behavior, and reducing the risk of RADV audits. In this blog, we’ll dive deeper into each of these benefits.

Capture More Data for Analytics and AI

Risk adjustment analytics continue to improve each year to keep up with changing risk models and to find new ways to identify suspects to close risk adjustment gaps. Analytics, especially AI chart suspecting algorithms, depend on large amounts of data to improve their targeting performance and enhance their capabilities. Diagnosis information derived from claims data is known to be incomplete and possibly inaccurate. Gathering all diagnosis occurrences and all retrieved charts from every date of service provides the most comprehensive insight into the health status of the member and allows for a thorough assessment of their chronic conditions.

The data is also valuable for care management teams to monitor any changes or gaps in care that might affect the member’s health, as well as risk and quality measures. Data can also be collected and shared with providers to address any risk and quality gaps. For AI, having more data leads to better performance and the ability to continuously improve and refine different suspecting models. Complete code capture provides the type of data that enhances analytics and AI performance.

The AI and machine learning algorithms used for chart suspecting are only as good as the data being uploaded into them—complete code capture provides the ideal data set for your analytics”

Jimmy Liu, VP of Analytics & Solutions, Advantmed

Understand Provider Coding Behavior

Most diagnosis codes utilized for risk scoring are obtained from claims data submitted by healthcare providers. However, due to generally inadequate provider documentation and incomplete diagnosis codes submitted on claims data, retrospective chart reviews are necessary to identify diagnosis codes that were documented by the provider but not submitted on claims. The provider’s likelihood to document well but submit poorly is a critical factor in risk adjustment targeting logic.

Additionally, some providers may not document well in general which significantly impacts the health plan’s ability to close risk adjustment and quality gaps. Complete code capture provides the breadth of data necessary to conduct in-depth analyses of provider documentation patterns by primary care provider or specialty. The capture of clinical documentation improvement (CDI) during chart review informs the health plan on what a provider has captured while identifying documentation flaws that affect submission for risk adjustment. Analysis of data collected through complete code capture empowers health plans to develop provider education programs and identify providers suitable for conversion to a risk-sharing or value-based payment arrangement.

Reduce RADV Audit Risk

Health plans rely on providers to document and submit risk-adjustable diagnosis codes. It’s crucial for a plan to know how well providers are doing this, as CMS will hold the plan accountable for any submitted HCCs that aren’t supported by medical record review. Focusing solely on HCC additive coding means that plans only pay attention to a small set of diagnosis codes since their primary goal is to identify HCCs that have not been reported by another provider for the member in that year. This common additive-only approach comes with disadvantages. Health plans that are exclusively adding codes lose the ability to match claims and identify potential codes to delete since these codes are not captured. As a result, health plans will need alternative strategies to minimize compliance risk.

Complete code capture allows for all instances of an HCC to be documented and protects the health plan during an audit since only one valid occurrence is needed to confirm each member HCC. Additionally, some providers are known to have documentation issues related to the same conditions. Therefore, even if there are multiple occurrences of a specific HCC for a member, they may be deemed invalid in an audit situation if they are all from the same provider.


Adopting a complete code capture approach for retrospective coding enhances data quality, improves risk adjustment accuracy, and reduces audit exposure. Health plans can leverage advanced analytics and AI to improve risk adjustment and care management by capturing more comprehensive data. Understanding provider coding behaviors also allows for targeted educational programs and effective value-based payment models.

At Advantmed, we offer complete code capture in our standard coding service. We also perform data validation and claims validation (DVCV) and provide comprehensive analytics to help health plans improve their risk adjustment accuracy, identify provider coding behavior, and reduce audit risk. Additionally, our record retrieval solutions are available for retrospective or audit projects.
To learn more about how you can enhance your risk adjustment programs, click here.