When it comes to psychiatric illness in children, it is extremely difficult to monitor or diagnose the condition early. Children’s internalizing disorders are not well understood and many cases remain undiagnosed. If left untreated, children with internalizing disorders are at greater risk of substance abuse and suicide later in life. Can wearable tech help?
University of Vermont (UVM) researchers have developed a movement sensor that can identify children with internalizing disorders – including anxiety and depression – with 81% accuracy, according to a research published in PLoS One.
Ryan McGinnis, PhD, a biomedical engineer and assistant professor of biomedical engineering teamed up with Ellen McGinnis, a clinical psychologist at UVM and colleagues, to develop a tool that could help screen children for internalizing disorders to catch them early enough to be treated, reports University of Vermont.
“This is the first study [on wearable technologies] that targets internalizing disorders like anxiety and depression in young kids and also the first to use this type of approach for identifying individuals likely to have a diagnosis.” McGinnis told Infectious Diseases in Children. “We are excited about this result because it points toward the future use of these technologies for screening children with otherwise hidden problems.”
The researchers used a common research method designed to elicit specific behaviors and feelings such as anxiety. They used “mood induction task” to test 63 children, some of whom were known to have internalizing disorders.
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” and “Let’s be quiet so it doesn’t wake up.” At the back of the room was a covered terrarium, which the facilitator quickly uncovered, then pulled out a fake snake. The children were then reassured by the facilitator and allowed to play with the snake.
During this task, children wore a commercially available sensor on their waist that tracked their motion. Researchers used a machine-learning algorithm to compare the movements of children with internalizing disorders with the movements of those without the disorders. Diagnoses were confirmed by a parental questionnaire and a diagnostic interview conducted by the researchers.
The system was able to differentiate the children with 81% accuracy (67% sensitivity, 88% specificity).