A novel machine learning technology can help identify clusters of learning difficulties that children struggle with at school with health conditions such as attention deficit hyperactivity disorder (ADHD), autism or dyslexia.
The researchers, from the University of Cambridge, fed a computer algorithm with cognitive testing data, including measures of listening skills, spatial reasoning, problem solving, vocabulary and memory.
Based on these data, the algorithm suggested that the children best fit into four clusters of difficulties — difficulties with working memory skills and difficulties with processing sounds in words.
The others were children with broad cognitive difficulties in many areas and children with typical cognitive test results for their age.
"By looking at children with a broad range of difficulties we found unexpectedly that many children with difficulties with processing sounds in words don't just have problems with reading — they also have problems with maths," said lead author Duncan Astle from the varsity.
"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."
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.
"Our study is the first of its kind to apply machine learning to a broad spectrum of hundreds of struggling learners," Astle said.
The study, published in the journal Developmental Science, recruited 550 children who were struggling at school.
Much of the previous research into learning difficulties has focussed on children who had already been given a particular diagnosis, such as ADHD, autism or dyslexia.
By including children with all difficulties regardless of diagnosis, this study better captured the range of difficulties within, and overlap between, the diagnostic categories.
"These are interesting, early-stage findings which begin to investigate how we can apply new technologies, such as machine learning, to better understand brain function," the researchers noted.