DURHAM, N.C. — Attention-deficit/hyperactivity disorder (ADHD) affects millions of children, but it goes undiagnosed for years and, even when early signs are present, they miss out on early support that could change long-term outcomes.
In a new study, Duke Health researchers found that an artificial intelligence tool can accurately estimate a child’s risk of developing ADHD years before a typical diagnosis is made by analyzing routine electronic health records. By reviewing patterns in routine medical data, this approach could help flag children who may benefit from early assessment and follow-up.
The study, published April 27 in Nature Mental Health, highlights how powerful insights can be gained from information already collected during routine medical visits to support early decision-making by primary care providers.
“We have this incredibly rich source of information stored in electronic medical records,” said Elliott Hill, lead author of the study and a data scientist in the Department of Biostatistics and Bioinformatics at Duke University School of Medicine. “The aim was to see if the patterns hidden in that data could help us predict which children were likely to later be diagnosed with ADHD, usually well before that diagnosis was made.”
To arrive at this finding, researchers analyzed electronic health records of more than 140,000 children with and without ADHD. They trained a specialized AI model to examine medical history from birth to infancy. The model has learned to recognize a combination of developmental, behavioral, and clinical events that often appear years before an ADHD diagnosis.
The model was highly accurate in estimating future ADHD risk in children aged 5 years and older, with consistent performance across patient characteristics such as gender, race, ethnicity, and insurance status.
Importantly, this tool is not diagnostic. This identifies children who may benefit from close attention by a pediatric primary care provider or early referral for professional ADHD evaluation.
“This is not an AI doctor,” says Matthew Engelhard, MD. , PhD in the Department of Biostatistics and Bioinformatics at Duke University and senior author of the study. “This is a tool that allows clinicians to focus their time and resources so that children in need don’t have to fail or wait years for answers.”
Researchers note that early identification through screening may lead to earlier diagnosis and, in turn, earlier support, which may lead to better academic, social, and health outcomes for children with ADHD. They also stress that further research is needed before such tools can be used in clinical practice.
Study author Dr Naomi Davis said: “Children with ADHD can really struggle if their needs aren’t understood and the right supports aren’t in place.” , associate professor in the Department of Psychiatry and Behavioral Sciences. “Bringing families together with timely, evidence-based interventions is essential to helping them achieve their goals and laying the foundation for future success.”
Hill and Engelhardt also studied the use of AI models in predicting the potential risks and causes of mental illness in adolescents.
In addition to Hill Engelhard and Davis, the study’s authors include De Rong Loh, Benjamin A. Goldstein, and Geraldine Dawson.
This research was supported by grants from the National Institute of Mental Health (K01-MH127309, UL1 TR002553) and the National Center for the Advancement of Translational Science.
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or position, and all views, positions, and conclusions expressed herein are solely those of the authors. Read the full text here.
