Skip to main content

Researchers to test wearable tech to detect problem behaviors in children with disabilities and offer intervention strategies

Share this on LinkedInNSF Smart & Connected Health Grant supports Vanderbilt researchers’ effort to detect problem behaviors in children with disabilities by using wearable tech

Vanderbilt researchers have won a National Science Foundation grant to use wearable technologies to detect problem behaviors in children and adolescents with intellectual and developmental disabilities and offer strategies to protect them from potential harm.

Children with intellectual and developmental disabilities (IDD) are at increased risk of showing problem behavior that expose them to being hurt, removed from the classroom, or hospitalized. Approximately 1 in 6 children and adolescents in the United States are diagnosed with IDD and half of them experience some form of problem behavior, according to the American Academy of Pediatrics.

Problem behaviors, including self-injury, aggression, property destruction, and wandering, not only can cause serious injury, but also interfere with the ability to participate in school, home, and other community settings.

Nilanjan Sarkar

With support from a four-year, $1.1 million NSF Smart and Connected Health grant—”Enhanced detection of impending problem behavior in people with intellectual and developmental disabilities through multimodal sensing and machine learning”—Vanderbilt engineering and pediatric researchers will integrate transdisciplinary expertise in cutting-edge wearable sensing, affective computing, machine learning, and behavioral and clinical science to transform existing models of behavioral intervention for problem behaviors in children and adolescents with IDD.

The goal is to test whether the system—the sensors, the app, and human input—can predict the precursors of problem behavior, how well it works when used in the real world with therapists, and what users think about the system.

“Specifically, small sensors worn in clothing or on the wrist could provide data about a child’s body, and/or physiological responses, like heart rate or sweat. Predictive models based on machine learning can then be developed to determine what combination of body signals imply a problem behavior is about to happen,” said David K. Wilson Professor of Engineering Nilanjan Sarkar, chair of the mechanical engineering department and the project’s principal investigator.

Amy Weitlauf

Amy Weitlauf, associate professor of pediatrics, Vanderbilt University Medical Center, and a Vanderbilt Kennedy Center researcher; and James Dieffenderfer, assistant research professor in electrical and computer engineering at North Carolina State University, are co-PIs.

“We have worked closely with John Staubitz, a board-certified behavior analyst and an assistant in the Department of Pediatrics, to design a system that can detect not only problem behavior, but also its precursors or signs it is about to happen,” said Weitlauf.

“Our goal in this project is to create a system that could be used by trained therapists to improve the safety, efficiency, and amount of data captured during activities that patients might find difficult, so they can be supported to use calming strategies or ask for help,” Weitlauf said. “We will emphasize stakeholder input in this next phase of system design and make adjustments based on people with IDD, their families, and their care providers.”

James Dieffenderfer

“Our plan is to design small measurement nodes to be placed at various locations for the purpose of analyzing physiological attributes. When we talk about wireless networks, we usually think in terms of large scale, such as providing real-time information about a structure or building. However, in this this project the various sensor nodes will all communicate amongst each other wirelessly to form a local sensor network for the individual wearer,” Dieffenderfer said.

“In this network of sensors, one of these nodes also is tasked with relaying this data to a peripheral device such as a smartphone or computer to allow for feedback to be provided to trained therapists,” he said.

The project has two stages. In the first stage, the team will design the new sensors that detect biological signals such as sweating, motion and heart rate. The team will measure how well these sensors work, which includes asking people with IDD what they think about the sensors. Then, based on that input, the team will adapt the sensors and use them in a larger study in the community. In this study, patients will wear the sensors while doing tasks with therapists, who will also input data to a custom app.

Results of this study will help researchers and practitioners understand if this kind of wearable technology is helpful and acceptable as part of supporting people with problem behavior and IDD.

This research is supported by a National Science Foundation Smart and Connected Health grant, award number 2124002.

Contact: Brenda Ellis, 615 343-6314