The study, published in Nature Mental Health, analysed electronic health records for more than 140,000 children. Researchers trained a specialised AI model to review medical history from birth through early childhood. The model detected combinations of developmental, behavioural and clinical events that often appear years before an ADHD diagnosis.
The tool was highly accurate at estimating future ADHD risk in children aged five and older. Its performance was similar across patient characteristics such as sex, race, ethnicity and insurance status. The researchers stress that the AI does not diagnose; instead, it highlights children who may need closer attention from their paediatric primary care provider or an earlier specialist referral for assessment.
Lead author Elliot Hill and senior author Matthew Engelhard said the tool could help clinicians target time and resources so children get help sooner. The team links earlier identification and support to better academic, social and health outcomes and recommends further studies before the tool is used in routine care. The research also received funding from the National Institute of Mental Health and the National Center for Advancing Translational Sciences.
Difficult words
- electronic health record — digital file with a person's medical historyelectronic health records
- specialised — made or trained for a particular purpose
- developmental — relating to growth and development in children
- behavioural — connected with a person's actions or conduct
- diagnosis — identification of a medical condition
- paediatric — relating to the medical care of children
- specialist referral — sending a patient to a medical expert
- outcome — result or effect of an actionoutcomes
Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.
Discussion questions
- Do you think AI tools should be used to find children at risk of ADHD? Why or why not?
- How could earlier identification and support help a child's school or social life?
- What concerns might parents or doctors have about using this kind of tool?
Related articles
Gene Variant Raises Heart Failure Risk After Myocarditis in Children
A study found that a cardiomyopathy gene variant is more common in children who develop dilated cardiomyopathy after myocarditis. Researchers describe a "double hit" model and advise genetic testing to identify higher risk.
Most young users still smoke nicotine, tobacco or cannabis
A 2022–23 study of people aged 12–34 found most young Americans who use nicotine, tobacco or cannabis still smoke one or more combustible products. The research groups users by their usual product patterns and urges targeted prevention.
When to Give a Child a Phone and Why Some Families Use Landlines
Child development experts say middle school is often a good time for a personal phone. Some parents choose a home landline because it limits apps and supports family conversations. Experts advise guided use rather than banning technology.