Co-dependent relationships are rarely considered positive, especially when one member of the relationship is an inanimate object. But with the advent of the smartphone, it sometimes feels like many of us are more attached to our iPhones and Androids than to our human counterparts. But like any good partner, our smartphones may know us better than we think, and according to a new study published in the Journal of Medical Internet Research, your phone may be more accurate than a self-assessment in determining whether or not you suffer from depression. In fact, researchers claim that phone data can predict with a stunning 87 percent accuracy whether or not a individual displayed signs of depression, all by examining the amount of time an individual spends on his or her smartphone.
As study author David Mohr, director of the Center for Behavioral Intervention Technologies at Northwestern University Feinberg School of Medicine, told Time magazine, “We found that the more time people spend on their phones, the more likely they are to be more depressed.” Furthermore, spending copious amounts of time on one’s cellphone is often linked with spending a lot of time at home or by oneself, two other potential symptoms of depression.
In conducting their study, researchers used Craigslist to recruit a small sample size of 28 individuals between the ages of 19 and 58, and installed an app they developed called Purple Robot, which tracked the user’s location, movement, phone usage, and other relevant activities. For two weeks, Purple Robot collected information every five minutes and sent it back to the scientists at Northwestern for analysis, and also asked users about their mood and feelings throughout the day. When this data was compared against PHQ-9, a nine-question test commonly used to survey signs of depression, study authors found that Purple Robot successfully identified 87 percent of those considered at risk for depression solely by tracking how frequently study participants moved around.
When Purple Robot examined data regarding those who used their phones the most (browsing the Web, playing games, and texting) without actually taking or making calls, it was able to predict who would fall into the at-risk category with a 74 percent rate of accuracy.
Of course, this isn’t to say that if you happen to spend a lot of time on your smartphone or enjoy the occasional lazy day alone at home in sweatpants that you’re a shoe-in candidate for depression. As study authors themselves noted, their very small study population and the short period of time over which their experiment was conducted left plenty of room for error, which is why they plan on conducting the study again with a greater number of participants over a longer trial period. Still, as Ethan Berke, an epidemiologist at Dartmouth College uninvolved in the study, told The Verge, “… those things aside, it definitely advances our knowledge base,” and Justin Baker, a psychiatrist at Harvard University, added, “The study’s novelty is in showing that tracking this information across many individuals is possible — and does a decent job at predicting depression scores.”