The U.S. Department of Defense is seeking AI-based solutions that will help detect and address behavioral issues that troops may encounter when engaged in military operations.

In a recently issued solicitation, DoD’s Defense Innovation Unit (DIU) described the project, dubbed “Vigilant Keeper,” as a search for “commercial Artificial Intelligence solutions to aggregate, structure, and analyze data sets, capture insights, and enable an organization to better support its members who exhibit behavioral changes that may indicate increased vulnerability. Vulnerability in this case refers specifically to circumstances and behaviors that place members at higher risk of involvement in activities and situations likely to produce unwanted negative outcomes, for both people and the mission.”

The DIU is a team within DoD that can use procurement methods outside the Federal Acquisition Regulation to find nontraditional contractors to bring the latest technologies to the military.

On a military operation a teammate struggling with depression, mental health or other psychological issues can have a debilitating effect on the entire team, and the issues, if left unaddressed, can lead to mission failure, injury and death.

According to the solicitation, “(a) successful prototype will develop, train, and employ a solution to access at-rest and streaming multi-modal structured and unstructured data.”

Among the outcomes DoD is seeking:

•    Build and maintain unique behavioral models representing individuals over time.

•    Build and maintain unique historical-record tags for individuals using static data over time.

•    Identify individual behavioral deviations from their unique baseline models along with separate anomaly detection based on user-provided guidelines.

•    Create output and displays optimized to the information delivery needs of primary users, including full transparency into how and why the data drove the output (e.g. alerts, insights, graphics, histograms, timelines, recommendations, etc.).

•   Precisely steer support professionals toward the most acute individual needs (i.e., triage those who need help soonest).

“Ultimately, the DoD will measure a prototype's success by its impact on professionals' triage and care activities,” the solicitation notes, adding, “It should drive improvements where the organization already collects and maintains intervention statistics, decrease false positives, and integrate to decrease user workload while increasing accuracy. Successful prototypes for this use-case could translate beyond high-risk triage to support broader population segments across the mental health continuum.”