MOSCOW, ID— Two major multi-institutional grants from the U.S. Department of Defense (DoD) will support machine learning research at the University of Idaho to advance the diagnosis of post-traumatic stress disorder (PTSD) and strengthen support systems for military families experiencing stress throughout the deployment cycle. Together, the two multisite projects total more than $6 million, of which $1.33 million supports U of I research.
Colin Hsu, assistant professor in the Department of Psychological Communication in the College of Letters, Arts and Social Sciences, will lead the development of machine learning models to improve early detection of adverse health effects for military members and their families.
“These projects will examine how machine learning techniques can be applied to psychiatric and public health data to enhance military health,” Xu said. “Through these machine learning models, we hope to improve early identification and prediction of PTSD risk in service members and improve prediction and prevention of negative health outcomes for military families.”
The first award is a $4.2 million Department of Defense-funded collaborative project with $974,000 going to U of I to examine how smart wearable devices, biochemical markers, and biophysical signals can be integrated to improve screening and diagnosis of PTSD.
This multi-institutional effort includes co-principal investigators Manish Bhoumia of the Uniformed Services University, Dr. Christina La Croix of Walter Reed National Military Medical Center, Dr. Samir Sonksale of Tufts University, Dr. Stephen Cohen of Northwestern University, and Dr. CJ Brush of Auburn University. Xu's team at U of I will develop machine learning models to identify how biomarkers and biophysical data collected from wearable technology can be used to improve diagnostic accuracy for PTSD.
“PTSD is a complex and multifaceted disorder,” says Xu. “By applying machine learning models to this multimodal biosensor data, we can better understand the biology of PTSD and help clinicians improve diagnosis and early detection.”
The second award totals $1.9 million, of which $361,000 will support university research focused on understanding how deployment-related stress affects military families and increases the risk of harmful behaviors.
Xu's team will work with co-principal investigators Elizabeth Heil Gorman, Christine Ogle, and Dr. Stephen Koza from the Uniformed Services University to identify predictors of domestic violence, substance abuse, suicidality, and injury in military families.
By applying machine learning models to large-scale, long-term military family health care records, this project aims to identify risk factors for adverse behaviors within military families and understand how these risk factors evolve during pre-deployment, deployment, and post-deployment phases.
Xu's machine learning model helps identify subgroups of military families at higher risk, as well as the timing and interactions of risk factors, to support earlier and more targeted interventions.
“Military families navigate unique stressors throughout the deployment cycle,” Xu said. “Our research aims to give clinicians better insight into who is at increased risk and when, so they can proactively provide support.”
The PTSD and wearable technology project will span four years, and the military family health project will run for three years starting in 2025.
Xu is seeking three funded graduate students and two postdoctoral fellows for these projects. If you are interested, please contact colinxu@uidaho.edu.
This project was funded by the Uniformed Services University of the Health Sciences under award FAIN: HU00012520060 to the Henry M. Jackson Foundation for the Advancement of Military Medicine. Total project funding is $974,717, of which 100% is federal.
This project was funded by the Uniformed Services University of Health Sciences to the Henry M. Jackson Foundation for the Advancement of Military Medicine under award FAIN: HU00012520057. Total project funding is $361,352, of which 100% is federal.
