Scientists have used Artificial Intelligence (AI) to develop better predictions of why children struggle at school.
The study, published in Developmental Science, was undertaken by the Medical Research Council (MRC) Cognition and Brain Sciences Unit at the University of Cambridge.
Researchers from the university recruited 550 children who were referred to a clinic – the Centre for Attention Learning and Memory – because they were struggling at school.
Unlike many previous studies, this one focused on all children with learning difficulties rather than those who had been given a specific diagnosis, such as autism spectrum disorder and ADHD.
The researchers input cognitive testing data from each student into a computer algorithm. This included measures of problem-solving, memory vocabulary and listening skills.
The algorithm analysed the data and suggested the students best fit into four clusters of difficulties which aligned closely with other data on these students, such as parents’ reports of their communication difficulties and school data on reading and maths.
However, there was no correspondence with the students’ previous diagnoses.
To check if these groupings corresponded to biological differences, the groups were checked against MRI brain scans from 184 of the children.
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.
Two of the four groupings identified were: difficulties with working memory skills, and difficulties with processing sounds in words.
Difficulties with working memory – the short-term retention and manipulation of information - have been linked with struggling with maths and with tasks such as following lists.
Difficulties in processing the sounds in words, called phonological skills, has been linked with struggling with reading.
Dr Duncan Astle, from the MRC Cognition and Brain Sciences Unit at the University of Cambridge, led the study.
He said that receiving a diagnosis is “an important landmark” for parents and children with learning difficulties, which recognises the child's difficulties and helps them to access support.
However, he added that parents and professionals working with these children every day see that neat labels don't capture their individual difficulties.
“For example one child's ADHD is often not like another child's ADHD,” EurekAlert quoted Dr Astle as saying.
“Our study is the first of its kind to apply machine learning to a broad spectrum of hundreds of struggling learners.”