• Politics
  • Diversity, equity and inclusion
  • Financial Decision Making
  • Telehealth
  • Patient Experience
  • Leadership
  • Point of Care Tools
  • Product Solutions
  • Management
  • Technology
  • Healthcare Transformation
  • Data + Technology
  • Safer Hospitals
  • Business
  • Providers in Practice
  • Mergers and Acquisitions
  • AI & Data Analytics
  • Cybersecurity
  • Interoperability & EHRs
  • Medical Devices
  • Pop Health Tech
  • Precision Medicine
  • Virtual Care
  • Health equity

Wearable Sensors Highly Accurate at Diagnosing Children with Anxiety, Depression


Scientists say motion-detecting sensors identified internalizing disorders with 81 percent accuracy.

wearable depression,wearable diagnosis,wearables disorder

Children with internalizing disorders like depression and anxiety often suffer in silence, unable to find the words to communicate their distress.

But a new study suggests they may not have to find the words anymore — because their bodies are telling their story for them.

That’s the finding of new research that examined whether wearable devices could correctly detect internalizing disorders in children between the ages of 3 and 8. Using an algorithm and a sensor, the system correctly identified disorders with 81 percent accuracy, a rate that exceeds the results of a standard parent questionnaire.

>> Wearables Are Saving Human Lives. Can They Save Hospitals Too?

“One reason we are excited about these results is that this approach was more sensitive than other screening measures out there, meaning it was more likely to find children with depression and anxiety who are otherwise being overlooked,” co-author Ellen McGinnis, Ph.D., of the University of Vermont, told Healthcare Analytics News™.

Sixty-three children were enrolled in the study. Fourteen participants came from another ongoing study, others (14) came after seeing fliers posted in the community. The majority (35) were referred from psychiatry clinics. Multimodal assessments conducted on 62 of the children identified 21 as having an internalizing disorder, such as post-traumatic stress disorder, anxiety or adjustment disorder.

The children were then equipped with a commercially available inertial measurement unit and asked to undertake a “mood induction task.” The task involved being led into a dimly lit room with the facilitator hinting something living might be inside the room. The child was then shown a draped terrarium. When the draping was removed, the child saw a fake rubber snake. After being told it was fake, the child was encouraged to touch the snake and realize that it was just a toy.

Throughout the exercise, children wore sensors which tracked movement data. That data was then analyzed using a machine learning algorithm to distinguish between children who had disorders like anxiety and depression and those who did not.

Ellen McGinnis said the results suggest wearable sensors can be “a great screening tool,” but she added, “the findings should be used to refer a child to a full psychological assessment that can capture a holistic view of the child and family needs and recommended appropriate treatment plans.”

Co-author Ryan McGinnis, Ph.D., an assistant professor and assistant director of the University of Vermont’s Biomedical Engineering Program, said while the technology behind the study is readily available, the diagnostic technique needs to be replicated in a larger study before it can be deployed widely. Investigators also need to work with pediatricians to make sure the final product could fit into the physician’s workflow.

“In this way, we maximize the chances of scaling this technology to screen children for internalizing problems,” he told Healthcare Analytics News™. “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.”

Ellen McGinnis said similar technology could be used to detect and diagnose other conditions. Researchers, for example, are looking at using wearables to detect autism in children, and teams are studying how sensors might detect eating disorders, mania and suicidality in adults.

Asked about the potential that people might be uncomfortable with the idea of machines diagnosing potentially life-threatening disorders in children, Ryan McGinnis said a highly accurate wearable and machine-learning model should be seen as a tool to get children linked to psychiatric care sooner than they otherwise might be.

“It’s important that we identify children who have internalizing disorders early in development so that they can be directed to the care that they need while the brain is still developing and they are most effective,” he said.

The study is titled, “Rapid detection of internalizing diagnosis in young children enabled by wearable sensors and machine learning.” It was published Jan. 19 in PLOS One.

Get the best insights in healthcare analytics directly to your inbox.


Healthcare, Wearables and the Fourth Industrial Revolution

The Clinical Divide: Wearable Skin Patches

How Wearable Tech Data Can Help Improve Biological Age

Related Videos
George Van Antwerp, MBA
Edmondo Robinson, MD
Craig Newman
© 2024 MJH Life Sciences

All rights reserved.