Can AI better predict why children struggle at school?

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

Applied STEM improves outcomes for secondary pupils with learning disabilities

Studying an applied STEM course could help pupils with learning disabilities (LD) complete secondary school and transition successfully to higher education, according to a US study published in Educational Policy.

Pupils with learning disabilities face significant academic challenges in secondary school, as well as greater risks of dropping out altogether. Studying courses like applied STEM, which focus on applying maths and science skills more directly to practical job experiences, may help them to make the connection between learning and opportunities beyond secondary school, and to see the importance of continuing with their studies.

In order to examine the role applied STEM might have in improving outcomes for LD pupils, Jay Stratte Plasman and Michael A Gottfried analysed data from the US Department of Education to see if there was any link between studying applied STEM and dropout. While pupils generally appeared to benefit from studying applied STEM, the advantages were greater for those with learning disabilities. They calculated a two percent dropout rate for LD pupils who study applied STEM versus 12 percent for LD pupils who do not. Their analysis also demonstrated that LD pupils who study applied STEM are 2.35 times more likely to enrol in college immediately after secondary school, and 2.23 times more likely to go to college two years after completing secondary school, than LD pupils who did not study applied STEM.

Source: Applied STEM coursework, high school dropout rates, and students with learning disabilities (October 2016), Educational Policy