Instaglum? Program can spot if users are depressed

PICTURES posted on social media can be used to predict if someone is depressed.

Psychologists say photographs placed online contain several indicators of potential depression.

If they are darker, more likely to be black and white, and feature fewer people, the pictures may suggest sufferers are retreating from social contact.

More obviously, a so-called ‘sadness selfie’ would highlight that someone was struggling.

Warning signs were identified in 43,950 images taken from picture-sharing site Instagram.

A computer program trained to diagnose depression from the images was correct 0 per cent of the time, a study led by Harvard University and Dr Christopher Danforth, of Vermont University, found.

In contrast, a British study found GPs pick up depression accurately in only 42 per cent of cases.

Dr Danforth said: ‘With an increasing share of our social interactions happening online, the potential for identification of early-warning signs for a host of mental and physical illnesses is enormous.

‘Imagine an app on your phone that alerts your doctor for a check-up when your behaviour changes for the worse, potentially before you realise there is a problem.’

The researchers analysed Instagram history of 166 people, of whom 1 had been diagnosed with depression in the past three years.

The study, published in open access journal EPJ Data Science, concluded that social media could be used to diagnose people with mental health problems earlier.

Dr Danforth added: ‘This study is not yet a diagnostic test. But it is a proof of concept of a new way to help people.’

‘A new way to help people’