A team at Duke University School of Medicine has received a $15 million grant from the National Institute of Mental Health to improve and expand an artificial intelligence (AI) tool that helps catch early signs of mental health problems in teenagers and adolescents.
The AI model, called the Duke Predictive Model of Adolescent Mental Health (Duke-PMA), analyzes data on behavior, emotions, and brain function to identify kids at high risk for mental illness even before symptoms appear. It looks at a range of easy to measure factors, like sleep patterns and family stress, and has already shown it can predict worsening mental health up to a year in advance with 84% accuracy in kids ages 10 to 15.
Unlike prior models that focus on existing symptoms, the Duke-PMA aims to find root causes, such as poor sleep and family conflict, that could be addressed early on. This capability could make it easier for primary care providers, such as family doctors and pediatricians, to spot mental health issues and connect young patients to the care they need.
The team published their work in Nature Medicine earlier this year. Now they’re planning to test and improve the model in real-world clinics in areas where access to mental health services is often limited.
The new project will enroll 2,000 youth from rural clinics in North Carolina, Minnesota, and North Dakota. The study will be led by Jonathan Posner, MD, J. P. Gibbons Distinguished Professor of Psychiatry and vice chair for research in the Department of Psychiatry & Behavioral Sciences, and Matthew Engelhard, MD, PhD, assistant professor of biostatistics & bioinformatics.
“Much like how primary care doctors use predictive analytics to determine heart disease risk and intervene before a heart attack, the Duke-PMA has the potential to give primary care doctors an easy way to identify kids who may need help before serious problems begin.”
— Jonathan Posner, MD
“Our goal is to shift from reacting to mental health crisis to preventing them,” said Posner. “Much like how primary care doctors use predictive analytics to determine heart disease risk and intervene before a heart attack, the Duke-PMA has the potential to give primary care doctors an easy way to identify kids who may need help before serious problems begin.”
Engelhard added, “Most AI models never make it out of the lab, so we’re delighted to have this chance to prove our approach can detect early warning signs in communities deeply affected by mental health challenges.”
“We’re delighted to have this chance to prove our approach can detect early warning signs in communities deeply affected by mental health challenges.”
— Matthew Engelhard, MD, PhD
If successful, the project could improve how mental health care is delivered—including in underserved communities—by giving doctors a low-cost, data-driven approach to help young people early, when interventions are most effective.