Digital phenotyping is a term used to describe data collection on an individual’s behavior and characteristics relating to their use of technology and digital devices.
Digital phenotyping can be performed using sensors, wearable devices, and other technology to collect data on an individual’s activity, behavior, and other metrics. This data can then be analyzed to identify patterns that can be used to improve an individual’s health and well-being.
Generalized Anxiety Disorder (GAD) is a mental health condition characterized by excessive and persistent worry and anxiety about various events or activities. People with GAD may find it impossible to control their worry and experience physical symptoms such as muscle tension, restlessness, and difficulty sleeping.
GAD has far-reaching societal impacts, leading to lower labor productivity and increased healthcare costs.
Wearable movement sensors are devices worn on the body to collect data on an individual’s physical activity and movement.
This technology can provide accurate measurements of physical activities, body postures, and movements in clinical and everyday daily life environments, thereby providing clinicians with data that can guide, personalize, and optimize therapy.
Some common examples of wearable movement-tracking devices include fitness trackers, smartwatches, and activity monitors. Many studies have been conducted in the past examining the utility of digital phenotyping to study depression but have neglected to study GAD symptoms.
One particular digital phenotyping study used smartphone sensor data to predict the severity of social anxiety disorder symptoms accurately. The most important feature here is the individual’s movement patterns, not social features such as calling or texting.
The present study aimed to examine the feasibility of predicting GAD symptom severity within a large national cohort using passive wearable sensor data in a week.
Five hundred ninety-three participants consented to participate in this study and were recruited as part of the National Health and Nutrition Examination Study (NHANES) from 2003-04.
Composite International Diagnostic Interview (CIDI, version 2.1) was used for Generalized Anxiety Disorder symptoms according to DSM 5 criteria. Each of these items on the test was standardized and summed to produce a composite score of GAD symptom severity.
To measure actigraphy, participants were asked to wear the ActiGraph AM-7164 (formerly the CSA/MTI AM-7164), manufactured by ActiGraph of Ft. Walton Beach, FL.
Participants donned them via an elastic cloth belt individually fitted to each subject and worn around the right hip. The participants were also instructed to keep the device dry and remove it before bed.
Current research suggests that integrating passive perception may offer the potential for a non-invasive assessment of GAD symptoms.
In the current study, the results also highlight the importance of looking at individual GAD symptoms and overall symptom severity.
Although the actigraphy risk models had straightforward clinical utility, the risk score was significantly different from all individual GAD symptoms, including multiple worry experiences, periods of uncontrolled worry, and lifelong disability since it wasn’t related.
Using actigraphy risk models to assess the symptoms of GAD has proved to be a blessing in identifying common mental health disorders, enabling patients to seek professional help quickly.
Also, requesting patients to wear a device across their body to understand their symptoms in a better manner will help reduce the stigma against mental health, which patients otherwise have to face by undertaking assessments in the form of physical paperwork.
To conclude, using artificial intelligence techniques, such as digital phenotyping, has brought about a massive development in the mental health field, which can help professionals better understand the state of their patients and hence contribute to the field.
