VA Launches Smart Tool to Reduce Veteran Wait Times for Disability Claims
OIT’s new smart tool uses machine-learning to deliver benefits to Veterans more quickly.
Veterans deserve fast access to their disability benefits. The Department of Veterans Affairs (VA) is using a new machine-learning tool to deliver these benefits to Veterans more quickly.
The tool’s name isn’t easy to remember—Content Classification Predictive Service (CCPS) Application Programming Interface (API)—but the results are certainly hard to ignore. VA’s Office of Information and Technology (OIT), working collaboratively in partnership with Veterans Benefits Administration (VBA), developed and implemented CCPS to reduce the average time to establish Veteran disability compensation claims by three and a half days.
CCPS is also helping VA improve service to Veterans by increasing the speed and accuracy of disability claims reviews. The tool automatically performs repetitive tasks that formerly required staff review and input.
During its first week of use, CCPS helped VA establish 3,994 out of 8,368 claims (48 percent) automatically without the need for manual intervention. Previously, VBA only processed about two percent of disability compensation claims automatically.
CCPS is the first machine-learning API implemented at VA. The tool reads what a Veteran wrote as their current disability on a Disability Compensation Form and uses complex artificial intelligence (AI) to match that entry to a technical classification in the Veterans Benefits Management System (VBMS). For example, if a Veteran indicates, “ringing in my ears,” CCPS classifies it as “Hearing Loss,” so the Veteran can get an appointment with an audiologist.
In the past, when a Veteran’s written entry on the Disability Compensation Form did not perfectly match a technical classification, VBMS was unable to process the claim without staff review. Even a missing dot over an “i” was a problem because, without the dot, VA’s Digits 2 Digits system read the “i” as a “1.”
To create CCPS, VBA mapped disability claim descriptions to VA-approved classifications using Natural Language Processing and Machine Learning. OIT used the previous system’s fail cases to improve the predictions model by “teaching” CCPS to handle system failure cases.
Given the success thus far, plans are already underway for the next version of CCPS. One goal is to attach special priority labels to claims—for example, those submitted by homeless Veterans.
As OIT continues to modernize and improve customer service, new tools like CCPS help VA make inroads to faster claims processing. These tools also open the door to even more innovation of the IT and AI products that VA staff can use to do their jobs serving Veterans.