Payers offering Medicare Advantage, managed Medicaid, and ACA products have developed proven processes and analytics for demographic, claims, and encounter data to manage member risk. However, one piece of data missing from many member profiles is laboratory data. Using historical and current lab data to calculate risk scores ensures that all clinical conditions and comorbidities are factored into risk adjustment calculations, leading to a more complete and accurate reimbursement.

Lab data adds insight

Clinical specificity and disease burden extracted from laboratory data may be directly tied to new or previously undetected patient diagnoses. These Hierarchical Condition Categories (HCCs) can be used retrospectively to generate more accurate reporting of patient health and associated costs while informing care management. For example, lab data serves as supplemental data for diabetes with vascular manifestation, vascular disease with complication, and chronic heart failure. Without lab data, the payer would need to reach out to the provider, retrieve charts, or do an in-home assessment.

In addition to having a positive impact on payer programs, accurate member profiles can lower operational costs associated with outreach to members. When using lab data, payers are more able to accurately identify chronic disease and lower false positives, which leads to less unnecessary and expensive member outreach and chart retrieval and review. Operational resources can be focused on using a more complete member profile to inform efforts.

For two payers, one a national payer and the other a regional payer, Prognos found more HCCs versus using traditional claim-based and chart retrieval methods. The payers increased the number of identified HCCs by 15 percent, resulting in more than $2 to 3 million in value, which translated to additional risk adjustment payments to the payers.

Overcome the hurdles to using lab data

Many payers do not use clinical lab data for a variety of reasons. To begin, there is currently no standard format for clinical lab datasets, making it difficult to organize and standardize. Another challenge is the significant effort and expertise needed to clinically interpret the dataset. Because lab data is difficult to obtain, payers may only have lab data on 20 to 30 percent of their membership. And the data they have may not be integrated into their risk adjustment, quality, and care management programs, making it nearly impossible to get a comprehensive view of their members' health.

Payers can work with companies that provide multi-sourced lab data that has been aggregated and normalized, including retrospective and current data, as well as analytics. Then, use the data to enhance risk adjustment analytics and results. Data aggregation and AI companies like Prognos make the process seamless and quickly empower payer teams with the additional insight. 


The value of the additional insight gained from lab data is worth the effort and should be on the priority list for every government programs leader. To attain a complete picture of members’ health status, datasets used for risk adjustment must include diagnostic information from lab data. The clinical specificity and disease burden extracted may serve as supplemental data and ensure the payer is accurately reimbursed by CMS.

Learn more about Prognos payer solutions here.