CHICAGO, July 16 (UPI) -- Smartphone location and usage time data can accurately predict if somebody is depressed with 87 percent accuracy, according to researchers in a recent study.
Regardless of the phone applications or functions used, less real-world activity and more phone use were shown to line up with symptoms of depression.
"The significance of this is we can detect if a person has depressive symptoms and the severity of those symptoms without asking them any questions," said David Mohr, director of the Center for Behavioral Intervention Technologies at Northwestern University Feinberg School of Medicine, in a press release. "We now have an objective measure of behavior related to depression. And we're detecting it passively. Phones can provide data unobtrusively and with no effort on the part of the user."
The goal of the research was to find ways to passively detect depression and levels of emotional states to monitor people especially at risk for the condition and intervene if necessary. Spending most of your time at home or in fewer locations and having a less-regular day-to-day schedule that involves leaving the house for work, among other things, can indicate depression and reinforce its effects.
At the start of the study, researchers gave 40 participants a self-reported depression survey. Researchers then analyzed data from 28 of the people's cell phones with sufficient data for the review. They looked at GPS data and amounts of phone usage, finding that 14 did not have signs of depression and 14 showed symptoms that ranged from mild to severe depression.
"The data showing depressed people tended not to go many places reflects the loss of motivation seen in depression," Mohr said. "When people are depressed, they tend to withdraw and don't have the motivation or energy to go out and do things. People are likely, when on their phones, to avoid thinking about things that are troubling, painful feelings or difficult relationships. It's an avoidance behavior we see in depression."
The study is published in the Journal of Medical Internet Research.
