Siri may be smarter than you think. A new study showed that data from smartphone usage can be used to detect if the phone’s owner is depressed.

As NDTV reports, research done at Northwestern University and published in the Journal of Medical Internet Research tracked the smartphone usage of 28 people over 2 weeks. The team used the phones’ GPS information and usage time. Using these criteria, author David Mohr asserted that, “we can detect if a person has depressive symptoms and the severity of those symptoms without asking them any questions.”

The study was able to determine if the user had depressive symptoms with 87% accuracy.

The individuals who showed symptoms were had less regular schedules than their counterparts, leaving the house at different times every day, or simply stayed at home more frequently, visiting fewer new places. Individuals with depression also spent an average of 68 minutes per day on their smartphone, while non-depressed study participants only spent 17 minutes per day.

The study summarized that, “people are likely, when on their phones, to avoid thinking about things that are troubling, painful feelings, or difficult relationships. It is an avoidance behavior.”

The authors maintain that tracking user data may be a good way to identify possible depression and to both monitor and encourage a depressed individual’s engagement in the world.