Devices & Hardware News

Model Leverages Wearable Data for Mental Health Diagnosis

A newly developed deep-learning model collects data from wearables to help clinicians detect depression and anxiety based on ten variables.

Wearable device.

Source: Getty Images

By Mark Melchionna

- Known as WearNet, a new deep-learning model created by researchers from Washington University in St. Louis uses data from the Fitbit activity tracker to gain insights into an individual's risk for depression and anxiety.

According to a 2022 survey from the Centers for Disease Control and Prevention (CDC), 12.5 percent of adults 18 and older experienced regular feelings of anxiety. The survey also indicated that 5 percent of adults had regular feelings of depression.

Despite some uncertainty surrounding the capabilities of wearable devices, researchers have discovered potential associated with tracking capabilities. To advance the detection of mental health conditions, Washington University researchers built a deep-learning model called WearNet that leverages wearable device data.

WearNet evaluates ten variables collected by the Fitbit tracker. These include steps, calories burned, and heart rate. For a study evaluating WearNet, researchers gathered data from over 10,000 Fitbit users over a 60-day period. The study population was diverse and consisted of a wide range of ages, races, and education levels.

Based on study findings, the Washington University researchers found that WearNet efficiently detected depression and anxiety. They also noted its benefits compared to other machine-learning models, as it made individual-level rather than group-level predictions.

Researchers also noted that this study serves as supporting evidence for the capabilities of wearables in detecting mental health conditions.

“Deep learning discovers the complex associations of these variable with mental disorders,” said researcher Chenyang Lu, the Fullgraf Professor at the McKelvey School of Engineering and a professor of medicine at the Washington University School of Medicine, in a press release. “Machine learning is our most powerful tool to extract these underlying relationships. Our work provided evidence, based on a large and diverse cohort, that it is possible to detect mental disorders with wearables. The next step is to convince a hospital system or some company to implement it.”

Prior research has indicated that wearable devices have a high potential in tracking various physical and mental illnesses.

In April 2022, the University of Michigan released study details that described a smartwatch feature that used heart rate data to track COVID-19.

This research effort included a multisite cohort study that used Fitbit data from before and after the onset of COVID-19 symptoms. According to their research, heart rate increase per step rose after the start of symptoms. They also found that heart rate per step was higher among participants who reported experiencing a cough.

Another study from December 2022 described the development of a wearable smartwatch device that aimed to detect suicidality or depression.

This effort emerged as part of the ongoing response to the growing mental health crisis among teens. Conducted via a partnership between Oregon Health and Science University (OHSU) and Analog Devices, Inc (ADI), this study gathered smartwatch data from adolescents with acute suicidality. Researchers then aimed to establish a new biometric signal using a precise deidentified dataset. This would allow engineers to add machine-learning algorithms to enhance the detection of suicidal thoughts, serving as the basis for a smartwatch detector for adolescent patients with known depression and suicidality.

Do Not Sell or Share My Personal Information
©2012-2024 TechTarget, Inc. Xtelligent Healthcare Media is a division of TechTarget. All rights reserved. HealthITAnalytics.com is published by Xtelligent Healthcare Media a division of TechTarget.