Researchers from the Medical Research Council (MRC) Cognition and Brain Sciences Unit at the University of Cambridge have used machine learning – a type of computer algorithm – to identify clusters of learning difficulties which did not match the previous diagnosis children had been given.
The study, published in Developmental Science, used a sample of 530 children (ages 5–18) who were referred to the Centre for Attention Learning and Memory (CALM) by health and education professionals because they were struggling in school. All the children in the sample completed a number of cognitive and learning assessments, they underwent a structural MRI scan, and their parents completed behaviour questionnaires.
Based on the data collected from these tests, the computer algorithm identified four groups that the children could be matched to: (1) broad cognitive difficulties and severe reading, spelling and maths problems; (2) age-typical cognitive abilities and learning profiles; (3) difficulties with working memory skills; and (4) difficulties with processing sounds in words.
While these groups aligned closely with other data on the children, such as the parents’ reports of their communication difficulties and educational data on reading and maths, there was no correspondence with their 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 the machine learning was identifying differences that partly reflect underlying biology.
The researchers conclude that these findings reinforce the need for children to receive detailed assessments of their cognitive skills to identify the best type of support.
Source: Remapping the cognitive and neural profiles of children who struggle at school (September 2018), Developmental Science