Case Study

When Veterans apply for disability benefits through VA.gov, they’re asked to describe their medical conditions in their own words. Then a U.S. Department of Veterans Affairs’ (VA) system classifies each condition to determine what medical exams are required and route claims to the right reviewers. Previously, VA couldn't classify about 25% of submitted conditions because the system required Veterans' descriptions to exactly match entries in a predetermined conditions table.

Veteran service representatives (VSRs) manually reviewed thousands of unmatched entries each week — a time-consuming process that could delay claim decisions. For Veterans waiting to learn if they qualify for benefits, these delays meant waiting weeks longer for the support they need.

Aquia Nava II LLC, our joint venture with Aquia Inc., helped VA develop an automated classification system that handles varying Veteran descriptions and evolving medical terminology. The joint venture ensured the new system maintains strict data security standards and only uses current, valid classification codes. The new system also integrates seamlessly with VA's existing systems. 

Approach

To handle the variety of condition responses, we helped VA develop a hybrid classification system that combines the precision of rule-based lookup tables with the flexibility of machine learning (ML). Now, when a Veteran submits a claim, the VA’s system first checks if the condition matches known terminology in the agency’s taxonomy. If it’s not, a machine learning model analyzes the text to predict the appropriate classification.

Throughout development, the joint venture worked closely with VA's Chief Artificial Intelligence Office (CAIO) team to ensure responsible data science practices and AI governance. We also helped complete a model training and draft an AI impact assessment and risk mitigation plan. The open source approach ensured thorough documentation and extensive testing, making the system maintainable and transparent.

Outcomes

Since launching the machine learning classifier, 100% of conditions are now automatically classified upon submission — up from 74% before the expanded classifier went live. That means nearly 20,000 additional conditions are automatically categorized each week, with sub-second processing times.

The automation also reduced manual classification work by approximately 80%, saving VSRs an estimated 4,131 hours — or 172 days — of working time annually. This frees them to focus on complex adjudication tasks rather than routine data entry. 

For Veterans, faster claim processing means quicker decisions about their benefits. The system now handles thousands of claims daily while maintaining accuracy and ensuring expired classification codes aren’t assigned to conditions — improving data quality throughout VA's downstream systems.

Conclusion

By automating this manual process, VA is able to serve Veterans more effectively and efficiently. The hybrid approach to classification means the system can handle the many ways in which Veterans might describe their conditions while maintaining the accuracy VA requires for decision-making.

Aquia Nava II LLC partnered with the Department of Veterans Affairs Disability Benefits Crew to develop and deploy this solution under the VA Secure, Performant, Reliable, and User-Centered Experiences (SPRUCE) contract vehicle.