Researchers at the University of Vermont and the University of Michigan have teamed up to create a tool to screen young children for anxiety and depression, among other internalising disorders, so they can be treated earlier.
The research was published in the latest PLOS ONE journal.
Go deeper with GlobalData
Around one in five children struggle with anxiety and depression issues, which can start as early as the preschool years. Often referred to as ‘internalising disorders’, these conditions can be hard to detect because the symptoms are inward-facing and doctors, parents and teachers often fail to notice them. If left untreated, children with these disorders are at greater risk of substance abuse and suicide later in life.
University of Vermont biomedical engineer and research team member Ryan McGinnis said: “Because of the scale of the problem, this begs for a screening technology to identify kids early enough so they can be directed to the care they need.”
For the project, McGinnis collaborated with University of Vermont clinical psychologist Ellen McGinnis and researchers in the Department of Psychiatry at the University of Michigan, Maria Muzik, Katherine Rosenblum and Kate Fitzgerald.
The team used a mood induction task to elicit anxiety in 63 children, some of whom were known to have internalising disorders.
How well do you really know your competitors?
Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.
Thank you!
Your download email will arrive shortly
Not ready to buy yet? Download a free sample
We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form
By GlobalDataThe children were led into a dimly lit room, while the facilitator gave scripted statements to build anticipation, such as “I have something to show you”. At the back of the room was a covered terrarium, which was quickly uncovered to reveal a fake snake. The children were then reassured and allowed to play with the snake.
The researchers used a fake snake to induce anxiety in the experiment.
Each child wore a motion sensor and a machine learning algorithm was used to analyse their movement to distinguish between children with anxiety or depression and those without. The algorithm identified differences in the way the two groups moved and was able to identify children with internalising disorders with 81% accuracy. This is better than the standard parent questionnaire.
The algorithm determined that movement before the ‘snake’ was revealed was the most indicative of potential psychopathology. The researchers reported that children with internalising disorders tended to turn away from the potential threat more than the control group. Subtle variations in the way the children turned also helped to distinguish between the two groups.
The results were said to correlate well with what was expected from psychological theory. The algorithm needed just 20 seconds to make an assessment.
Ellen McGinnis said: “Something that we usually do with weeks of training and months of coding can be done in a few minutes of processing with these instruments.
“Children with anxiety disorders need an increased level of psychological care and intervention. Our paper suggests that this instrumented mood induction task can help us identify those kids and get them to the services they need.”
If these conditions are caught early then treatment is more likely to work as young children’s brains are extremely malleable.
The researchers say the next step is to refine the algorithm and develop additional tests for analysing voice data and other information that could enable the technology to tell the difference between anxiety and depression. The ultimate objective is to develop assessments that could be used easily in schools or doctors’ offices as part of their routine developmental assessments.
