Leveraging artificial intelligence to predict mental health risk among youth presenting to rural primary care clinics

The National Institute of Mental Health awarded Duke University a $30.078 million cooperative agreement on September 10, 2025, to enhance, deploy, and validate the Duke Predictive Model of Adolescent Mental Health (DUKE-PMA), a neural network-based tool designed to identify youth at high risk for psychiatric illness in primary care settings.

The project responds to RFA-MH-25-195 under the Mental Health Research Grants program (CFDA 93.242). Duke will optimize the DUKE-PMA by incorporating behavioral tasks from the NIH Toolbox and applying trustworthy AI techniques to reduce performance variation across diverse clinical settings and demographic groups. The model, which has demonstrated high accuracy in predicting psychiatric risk one year in advance in youth aged 10–15, identifies sleep disturbances as a key modifiable predictor and measures the p-factor, a general psychopathology indicator applicable across multiple psychiatric conditions. After optimization, Duke will deploy the DUKE-PMA in rural primary care and pediatric clinics and enroll 2,000 youth to validate the model's effectiveness in settings where mental health service access is limited.

Work is performed in Durham, North Carolina, with a period of performance through September 9, 2029. Wake Forest University Health Sciences is a sub-recipient, receiving a sub-award with an award date of January 9, 2026, to contribute to the study activities.

Abstract

This study, in response to RFA-MH-25-195, aims to enhance, deploy, and rigorously validate the duke predictive model of adolescent mental health (duke-PMA), which uses a novel clinical signature derived from affordable, accessible measures to identify youth at high risk for psychiatric illness in primary care settings. The duke-PMA, a neural network-based predictive tool, has already demonstrated high accuracy in predicting psychiatric risk one year in advance in youth aged 10-15, using data from the adolescent brain and cognitive development (abcd) study. Notably, sleep disturbances have emerged as a key modifiable predictor in the model. Unlike most predictive models that rely on current symptoms to anticipate outcomes, the duke-PMA bases its predictions on underlying disease mechanisms and protective factors, making IT better suited to inform preventive interventions. Furthermore, the model identifies an elevated p-factor, a general measure of psychopathology that spans multiple psychiatric conditions, making IT broadly applicable across diverse youth populations. Our project will begin by optimizing the duke-PMA through the incorporation of behavioral tasks from the NIH toolbox to enhance its prediction performance. Following duke AI health's algorithm-based clinical decision support oversight framework, we will ensure the model adheres to the highest standards of transparency, quality, and equity. Additionally, we will apply trustworthy AI techniques designed to reduce effects of distribution shifts on model performance to ensure the model remains effective and equitable across diverse clinical settings and demographic groups. After optimization, the duke-PMA will be deployed in rural primary care and pediatric clinics, where access to mental health services and research participation is often limited. We will enroll 2,000 youth from rural clinics in the southeast and midwest, partnering with the science, technology, and research (star) clinical research network. We will also explore the benefit of adding a measure of home environments to the duke-PMA through digital envirotyping, which uses an AI-driven approach to assess home environments remotely without requiring in-person visits, making IT much more resource-efficient and accessible than current approaches. Model performance will be validated through psychiatric diagnostics conducted one year after the initial assessment. If successful, this project has the potential to transform mental health resource allocation particularly in underserved communities by offering an accessible, low-cost, data-driven approach to identify vulnerable youth and highlight modifiable risk factors for early intervention.