ARLINGTON, Virginia – U.S. military researchers are asking industry for new ways to analyze and treat depression and other mental health issues among U.S. military personnel to help stressed combatants say in combat.
Officials at the U.S. Defense Advanced Research Projects Agency (DARPA) in Arlington, Va., on Friday released a broad agency announcement (HR001122S0032) regarding the Neural Evidence Aggregation Tool (NEAT) in the purpose of diagnosing and treating mental health problems.
NEAT aims to bring together advances in cognitive science, neuroscience, physiological sensors, data science and machine learning to develop processes that can measure what a person believes to be true.
Declining trends in mental health and mental fitness were alarming before the COVID-19 pandemic, but worsened during the pandemic, with rates of depression and anxiety rising precipitously. These findings are particularly detrimental to US military personnel who face the added strains of combat, long deployments and more than two decades of war.
Related: Raytheon to develop smart sensors, machine learning and digital signal processing for military targeting
Veterans between the ages of 18 and 34 are almost three times more likely to commit suicide than their civilian peers. Current methods of detecting early signs of behavioral health risk factors such as anxiety, depression or substance abuse that may lead to suicide rely on self-report and screening questionnaires, which are inadequate.
Worse still, a combatant’s commitment to stay in the fight, combined with the lingering stigma of seeking behavioral health assistance, makes current screening methods particularly challenging among military personnel.
NEAT seeks to use preconscious cues, sensors, and machine learning to identify what someone believes to be true about their own behavioral health risk factors, especially when what they believe to be true may be difficult to recognize.
The use of preconscious cues will eliminate the possibility of explaining dangerous mental conditions because the new methods will pick up cues before one has the ability to consciously formulate their responses.
Related: Military researchers observe electro-optical sensors with machine learning algorithms for defense applications
NEAT will revolutionize behavioral health screening to help clinicians minimize long-term vulnerabilities and get the most out of fighter readiness.
The NEAT program will develop processes that can measure what a person believes to be true by presenting carefully crafted stimuli designed to evoke specific preconscious mental processes; detect preconscious processes using physiological sensors, digital signal processing and neural analysis; and using machine learning to aggregate preconscious responses into a final metric that quantifies what a person believes to be true for a specific topic.
NEAT proponents should leverage existing, commercially available (COTS) sensor technologies to support the development of NEAT processes. NEAT is a 42-month, two-phase effort divided into two technical areas: research and development, and independent validation and verification.
The first two-year phase of the program is to demonstrate effectiveness, and the second 18-month phase is to develop a system. Demonstrating effectiveness will demonstrate the essential proof of principle and show the basic feasibility of the NEAT process.
Related: Air Force seeks help to boost air logistics capability through machine learning and sensor integration
The development of a system will build on the work of the first phase by refining models and stimuli, improving overall performance, evaluating the possible sensitivity of the NEAT process to confounding variables, and testing the NEAT process outside of the laboratory settings.
Interested companies should submit abstracts by March 29, 2022 and full proposals by May 23, 2022 on the DARPA BAA website at https://baa.darpa.mil/.
Email your questions or concerns to DARPA’s Gregory Witkop, the NEAT Program Manager, at NEAT@darpa.mil. More information is online at https://sam.gov/opp/f72c8f446c8144359478c07b97bd275b/view.
