New research published in PLOS One provides evidence that a wearable sensor can be used to identify young children with internalizing disorders like anxiety and depression.
“Young children who suffer from anxiety and depression often have a lot of difficulty understanding and communicating their suffering — and for parents, it’s really difficult to read inner emotions of someone who doesn’t even understand themselves,” said study author Ellen W. McGinnis, a postdoctoral fellow at the University of Vermont Medical Center.”
“Reporting issues led to young children with anxiety and depression being overlooked, so for my graduate school dissertation I wanted to help find objective feasible measures of internalizing disorders in children younger than 8 years.”
“This is also a large problem, with up to 1 in 5 children experiencing an internalizing disorder during childhood, that can lead to increased risk for serious health problems like chronic anxiety and depression, substance abuse, and suicide, later in life if left untreated,” added co-author Ryan S. McGinnis, an assistant professor at the University of Vermont.
The researchers tested a wearable motion sensor on 63 children between the ages of 3 and 8. The sensor monitored the child’s movement, and a machine learning algorithm was used to analyze their movement.
Children were led into a dimly lit room, while a research assistant built anticipation with scripted statements 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.
The researchers found that children with internalizing disorders tended to turn away from the potential threat before the snake was revealed. The machine learning algorithm picked up on subtle variations in the way the children turned that helped distinguish between the two groups. It identified children with internalizing disorders with 81 percent accuracy.
“Feasible objective screening of child anxiety and depression in young children is possible using wearable technology and is proving to be very sensitive – meaning we can find those previously overlooked kids and connect them to the services they need,” Ellen McGinnis told PsyPost.
“Hopefully people will start to see technologies like these being deployed during their children’s pediatric well visits in the coming years,” Ryan McGinnis remarked.
But the study — like all research — includes some limitations.
“A big caveat is that, although our results are intriguing and promising, we need to replicate them in a much larger, more diverse sample. In so doing, we’d like to partner with pediatricians to ensure that the resulting technology can easily fit within the workflow of a standard pediatric well visit,” Ellen McGinnis explained.
The researchers hope to develop a battery of assessments that could be used in schools or doctors’ offices to screen children as part of their routine developmental assessments.
“This approach maximizes the chances of scaling this technology to screen all children for internalizing problems. We are also in the process of developing additional instrumented mood induction tasks to accompany the task presented in this paper. We think that the resulting assessment battery may be even better at identifying children with underlying internalizing psychopathology,” Ryan McGinnis said.
The study, “Rapid detection of internalizing diagnosis in young children enabled by wearable sensors and machine learning“, was authored by Ryan S. McGinnis, Ellen W. McGinnis, Jessica Hruschak, Nestor L. Lopez-Duran, Kate Fitzgerald, Katherine L. Rosenblum, and Maria Muzik.
