The Washington University researchers studied the data of more than 10,000 Fitbit users, the largest wearable cohort to be part of a study, by developing a deep-learning model called WearNet, in which they studied 10 variables collected by the Fitbit activity tracker.
WearNet did a better job at detecting depression and anxiety than state-of-the-art machine learning models.
Further, it produced individual-level predictions of mental health outcomes, while other statistical analyses of wearable users assess correlations and risks at the group level.
Variables included everything from total daily steps and calorie burn rates to average heart rate and sedentary minutes.
The researchers compiled Fitbit data for individuals for more than 60 days.
The team presented its findings on 10 May at the ACM/IEEE Conference on Internet of Things Design and Implementation. The paper was awarded the Best Paper Award for IoT Data Analytics at the conference.
“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 School of Medicine.
“It is possible to detect mental disorders with wearables”
“Machine learning is our most powerful tool to extract these underlying relationships. Our work provided evidence 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.”
Wearable data could be a boon to mental health diagnosis and treatment, according to Lu.
“Going to a psychiatrist and filling out questionnaires is time consuming, and then people may have some reticence to see a psychiatrist,” he said.
“People are going about their lives while suffering from a disease that results in lower productivity and poorer life quality. This AI model is able to tell you that you have depression or anxiety disorders. Think of wearable data as an automated screening tool that could recommend that you go see a psychiatrist.”
There is “an urgent need for an unobtrusive approach to detecting mental disorders,” the researchers said.
“Early detection can help clinicians diagnose and treat mental disorders in a timely manner. It can also enable individuals to adjust their behaviours and mitigate the impact of the disorders.”
Hoping to find simple ways to detect such disorders, mental health professionals are considering the role of popular wearable fitness monitors in providing data that could alert wearers to potential health risks.
(Source: Medical Xpress)
