People who post pictures on Instagram that are bluer, darker or greyer than most users are likely to have depression, a new study reveals.
Depression shows itself in a person's social media profile - and doctors may soon use Facebook and Instagram as a method of diagnosis, according to research.
Scientists found people who are depressed post photos that are 'bluer, darker and greyer than those posted by healthy individuals'.
A team from the University of Vermont in America found that computers can successfully detect whether a person is depressed just by scanning their Instagram photos.
The researchers' computer model showed a depression detection rate of 70 per cent - significantly higher than the 42 per cent rate of detection by GPs.
Professor Chris Danforth, from Vermont University, and co-author Andrew Reece, from Harvard University, said: "Pixel analysis of the photos in our dataset revealed that depressed individuals in our sample tended to post photos that were, on average, bluer, darker, and grayer than those posted by healthy individuals."
They found that healthy individual chose Instagram filters like Valencia, which gave their photos a warmer brighter tone.
But depressed people were much more likely to use filters like Inkwell, which make the photo black-and-white.
They asked 166 people to share their Instagram feeds and mental health history in a study designed so about half the participants had reported being clinically depressed in the last three years.
In total 43,950 photos were used in the study, which is published in the EPJ Data Science journal.
The scientists added: "People suffering from depression were more likely to favour a filter that literally drained all the colour out the images they wanted to share."
They analysed photos using insights from already-established psychology research into depression about people's preferences for brightness, colour and shading.
They also found faces in photos provide signals about depression, with depressed people more likely than healthy people to post a photo with people's faces.
But it was also found those photos had fewer faces on average than the healthy people's Instagram feeds.
The researchers added: "Fewer faces may be an oblique indicator that depressed users interact in smaller settings."
They said that corresponds with other research linking depression to reduced social interaction - but added it could be that depressed people take many self-portraits, a theory so-far untested.
Professor Danforth said the computer model could pave the way for a new method of detecting depression.
He added: "This points toward a new method for early screening of depression and other emerging mental illnesses.
"This algorithm can sometimes detect depression before a clinical diagnosis is made."
More than half of a GP's depression diagnoses are false while the computational algorithm did far better, according to the study.
It also showed the computer model was able to detect signs of depression before a person's date of diagnosis.
Prof Danforth said: "This could help you get to a doctor sooner, or imagine that you can go to doctor and push a button to let an algorithm read your social media history as part of the exam.
"We have a lot of thinking to do about the morality of machines.
"So much is encoded in our digital footprint.
"Clever artificial intelligence will be able to find signals, especially for something like mental illness."