Researchers use AI, brain MRI to predict learning difficulties in children
In a recent institutional study, artificial intelligence (AI) was found to identify learning difficulties in children struggling in school not previously detected or that did not match an existing diagnosis—such as attention deficit hyperactivity disorder (ADHD), an autism spectrum disorder or dyslexia.
Researchers led by Duncan Astle, PhD, from the Medical Research Council (MRC) Cognition and Brain Science Unit at the University of Cambridge found that their first-of-its-kind study reinforces the need for cognitive skill assessment exams in children. The research was published online Sept. 1 in Developmental Science.
"As researchers studying learning difficulties, we need to move beyond the diagnostic label and we hope this study will assist with developing better interventions that more specifically target children's individual cognitive difficulties,” Astle said in a prepared statement.
Astle and colleagues recruited 550 children with all types of learning difficulties—regardless of diagnosis—who were referred to the Center for Attention Learning and Memory at the University of Cambridge.
The team trained a machine learning computer algorithm with measurements from the children’s listening skills, spatial reasoning, problem solving, vocabulary, memory, communication and educational data. The data was then split them into four clusters of learning difficulties.
The four groups were then compared to MRI brain scans from 184 of the children to check if the groupings corresponded to biological differences.
“The groupings mirrored patterns in connectivity within parts of the children's brains, suggesting that that the machine learning was identifying differences that partly reflect underlying biology,” according to the researchers.
Two of the four groupings identified were difficulties with working memory skills—linked with struggling with math and with tasks such as following lists—and difficulties with processing sounds in words—linked with struggling with reading. The other two clusters were children with broad cognitive difficulties and children with normal cognitive test results for their age.
"Our work suggests that children who are finding the same subjects difficult could be struggling for very different reasons, which has important implications for selecting appropriate interventions,” senior author Joni Holmes, PhD, from the MRC Cognition and Brain Sciences Unit, said in the prepared statement.
A recent graduate from Dominican University (IL) with a bachelor’s in journalism, Melissa joined TriMed’s Chicago team in 2017 covering all aspects of health imaging. She’s a fan of singing and playing guitar, elephants, a good cup of tea, and her golden retriever Cooper.