The authors of a recent study in the Journal of Medical Internet Research found that is it not only accurate but also feasible to use GPS data from smartphones to discover time-imperative behavioral symptoms of patients with depression.
Researchers from the University of Virginia had 72 undergraduate students between the ages of 18 and 23 participate in the study with a customized Android app. The mHealth app was used to administer surveys to the students that allowed them to self-report measures of social anxiety, depression, and state effect. By using GPS and self-reported data, the researchers capitalized on a technique called “mobile sensing.”
The mental health app allowed the researchers to extract GPS data and see whether students responded in their home or out in public. The data revealed the symptoms and conditions that were most prevalent at home and socially isolated settings.
The study acts as a critical use-case for mHealth use as the researchers were able to model and identify mental health conditions using personal devices as the data capturepoint. Being able to pinpoint mental health conditions has been a significant challenge for researchers over several years but may now have an effective way of doing so.
“Until recently, mental health researchers had to rely mostly on static and imprecise self-report measures to infer crucial behavioral patterns, such as avoidance and social isolation (unless they were able to invest enormous resources to do in-person observations, which are rare and typically provide only a small sample of a person’s behaviors),” Chow et al. wrote.
Supporting several existing theories, the researchers found that respondents who spent more time at home within four-hour periods showed higher instances of social anxiety.
The main effect of increased social anxiety was the amount of time a person stayed at home, but this wasn’t the case for depression rates.
Rates of depression did not increase throughout these four-hour periods, but the data revealed that people were more depressed the less time they spent at home between the hours of 10:00AM and 6:00PM, finding countering common theories.
The research team concluded that general worsening of feelings occurred at patients spent extended periods of time at home. Additionally, Chow et al. claimed that the results and methodology of the study are applicable to most collegiate environments because they effectively captured the behaviors of a heavily smartphone-enabled generation of college students.
“Advances in mobile phone technology now make it possible to continuously and unobtrusively monitor where someone is without needing to ask,” they said. “For example, previous research has found that passively sensed location information can predict depressive symptoms with impressive accuracy, and researchers have begun to explore passively and actively sensed indicators of stress and health behaviors in college students, although little work has focused on how to integrate passively sensed data with affective experiences generated from in situ repeated assessments.”
Limitations of the study included gaps in GPS data where respondents more likely than not either turned off their device or lost internet/cellular connectivity. The researchers also rewarded the respondents college credits for participating, and is uncertain how a similar study would be adopted into healthcare/clinical environments.
However, Chow et al. contended that this is the first step in using GPS and self-reporting data capture to translate emotional conditions into qualitative research on a larger scale.
“Even taking into consideration these limitations, the ability to integrate fine-grained location data with self-reported affect in situ has tremendous potential to help explicate how short-term, real-time emotional experiences are related to important behavioral patterns in both healthy emotional functioning and in depression and social anxiety,” the researchers said.
“Improving our ability to assess and model variations in affect and GPS patterns may enhance detection of mental disorders through early recognition of signature patterns or change in patterns indicating an increase in isolation, as well as inform treatment planning and assessment of outcomes,” they concluded.
This piece was origially published on ‘mHealth Intelligence’ March 9, 2017.