Publications on social networks can predict depression diagnoses, according to a new analysis

Browse your Facebook feed and you will probably encounter a multitude of recipes, memes and status updates from your grandmother on the occasion. But what would happen if there was a way to permanently reach the 2.2 billion active users of Facebook a month, beyond sharing fun videos on cats? A new study found that content shared by (consenting) Facebook users could help predict the future onset of depression in their medical records.

Major depression is one of the most common mental illnesses in America. According to the National Institute of Mental Health, approximately 16.2 million American adults, or 6.7% of the adult population, have experienced at least one major depressive episode. Yet about 37% of adults who have had major depressive episodes are not treated. This new study is part of a growing body of research that is studying new ways to screen for mental illness via social media.

Posted in Proceedings of the National Academy of SciencesThe study evaluated the language from a sample of 683 Facebook status histories of consenting patients. The predictive language of depression included references to sadness, loneliness, hostility and rumination, as well as a concern about personal status. The peculiarity of this study is that it is the first to compare the language used by Facebook users to the actual clinical diagnoses found in the electronic medical records of study participants. In some cases, researchers were able to predict future diagnoses of depression up to three months before they appeared in the medical records of diagnosed individuals.

The study builds on a body of research in development on the links between social media and early detection of mental illness. A 2017 study has developed computer models to help predict depression and PTSD among Twitter users based on their tweets, even going as far as to suggest that the onset of depression can be detected from Twitter data "several months" before the actual diagnosis. Another study, published in May 2018, examined the negative emotions expressed in status updates on Facebook and Twitter, suggesting that each social media platform could have different online cultures that reflected different perspectives on health. mental.

Countless articles have lamented the impact of social media on people's mental health.

"It would be irresponsible to take this tool and use it to say: you are depressed, you are not depressed," said Johannes Eichstaedt, psychologist at the University of Pennsylvania and co-author of the study. wired. He pointed out that the research could possibly prove useful in identifying people who should follow with more formal screening processes, such as a visit to a clinician.

While further research is needed in the field before a mechanism for suggesting follow-up screenings can be put in place, social media, as a mental health screening tool, appears as a promising way to explore. Countless articles have lamented the impact of social media on people's mental health. But the reality is that despite these studies, the use of social media is still ubiquitous. Assuming that technology is only applied to consenting users, if social media could itself become a tool to detect mental illness, they could one day help to alleviate a problem they could contribute to.