CLOSE
iStock
iStock

How You Instagram Can Reveal Whether or Not You’re Depressed, Study Says

iStock
iStock

How you Instagram might reveal more about you than just what you did last weekend. One study found that certain Instagram photos can predict the markers of depression, as New York Magazine's Select All reports. And it's not the first study to link social media use and mental illness.

The study, in EPJ Data Science, looked at almost 44,000 posts from 166 people (71 of them depressed) using color analysis, metadata, and face detection software. (While less than 200 people isn’t a big enough number to really cement these findings, they at least analyzed a whole lot of brunch pics.) They found machine learning could successfully distinguish between the behavior of people diagnosed with depression and those with a clean bill of mental health by looking at the Instagram filter type of photos, the setting, whether or not there were people, color, brightness, and how many “likes” and comments it got. They also looked at how often people used the app and how often they posted.

The researchers’ Instagram model worked the majority of the time to correctly identify depression, even in posts made before the researchers diagnosed the person’s mental health status. Compare that to general practitioners' rates for correctly diagnosing depressed patients, which studies have found hover around 42 percent.

Depressed people tended to post darker photos, often using Instagram’s black-and-white Inkwell filter. They received more comments, but fewer likes on their posts. They tended to post photos of faces, but typically fewer faces than non-depressed users (social isolation is often linked to depression). By contrast, healthy people loved Valencia, which lightens images, and tended to get more likes.

Loving a black-and-white photo doesn't necessarily mean you're depressed. Maybe you’re just trying out your best Ansel Adams impression. But given the outsized role social media plays in modern life, it might be able to provide doctors with insights into patients' inner thoughts and feelings that they might not otherwise be privy to.

Other studies, too, have found that technology use can provide a window into people's souls, mental health and all. Research has found that unhappy people use their smartphones to cope with negative feelings, linking increased phone usage to anxiety and depression. A 2015 study found that smartphones could predict depression by tracking how often and where people moved.

In some cases, though, social media seems to play an active role in making people unhappy, rather than simply revealing their existing unhappiness. A 2017 study of 5000 people found that the more time people spent using Facebook, the worse their sense of well-being. (And that's even before you start talking about reading the news.) Other surveys have found that for teenagers, Instagram and Snapchat usage are associated with low self-esteem, bullying, and more.

But even if obsessively Instagram is making you unhappy in the first place, how you use social media could be an important factor for doctors to consider when evaluating mental health. It's hard to open up to people about depressive thoughts, especially if it's a medical professional you only see once a year. You might tell your doctor you feel fine, but be more honest about your inner darkness on Instagram—whether you realize it or not. So although you probably don’t want to hand over your social media history to your medical providers on a regular basis, it could provide a useful way to screen patients who aren't able to fully convey their mental health issues.

nextArticle.image_alt|e
iStock
arrow
technology
AI Could Help Scientists Detect Earthquakes More Effectively
iStock
iStock

Thanks in part to the rise of hydraulic fracturing, or fracking, earthquakes are becoming more frequent in the U.S. Even though it doesn't fall on a fault line, Oklahoma, where gas and oil drilling activity doubled between 2010 and 2013, is now a major earthquake hot spot. As our landscape shifts (literally), our earthquake-detecting technology must evolve to keep up with it. Now, a team of researchers is changing the game with a new system that uses AI to identify seismic activity, Futurism reports.

The team, led by deep learning researcher Thibaut Perol, published the study detailing their new neural network in the journal Science Advances. Dubbed ConvNetQuake, it uses an algorithm to analyze the measurements of ground movements, a.k.a. seismograms, and determines which are small earthquakes and which are just noise. Seismic noise describes the vibrations that are almost constantly running through the ground, either due to wind, traffic, or other activity at surface level. It's sometimes hard to tell the difference between noise and legitimate quakes, which is why most detection methods focus on medium and large earthquakes instead of smaller ones.

But better understanding natural and manmade earthquakes means studying them at every level. With ConvNetQuake, that could soon become a reality. After testing the system in Oklahoma, the team reports it detected 17 times more earthquakes than what was recorded by the Oklahoma Geological Survey earthquake catalog.

That level of performance is more than just good news for seismologists studying quakes caused by humans. The technology could be built into current earthquake detection methods set up to alert the public to dangerous disasters. California alone is home to 400 seismic stations waiting for "The Big One." On a smaller scale, there's an app that uses a smartphone's accelerometers to detect tremors and alert the user directly. If earthquake detection methods could sense big earthquakes right as they were beginning using AI, that could afford people more potentially life-saving moments to prepare.

[h/t Futurism]

nextArticle.image_alt|e
iStock
arrow
Medicine
New Peanut Allergy Patch Could Be Coming to Pharmacies This Year
iStock
iStock

About 6 million people in the U.S. and Europe have severe peanut allergies, including more than 2 million children. Now, French biotechnology company DBV Technologies SA has secured an FDA review for its peanut allergy patch, Bloomberg reports.

If approved, the company aims to start selling the Viaskin patch to children afflicted with peanut allergies in the second half of 2018. The FDA's decision comes in spite of the patch's disappointing study results last year, which found the product to be less effective than DBV hoped (though it did receive high marks for safety). The FDA has also granted Viaskin breakthrough-therapy and fast-track designations, which means a faster review process.

DBV's potentially life-saving product is a small disc that is placed on the arm or between the shoulder blades. It works like a vaccine, exposing the wearer's immune system to micro-doses of peanut protein to increase tolerance. It's intended to reduce the chances of having a severe allergic reaction to accidental exposure.

The patch might have competition: Aimmune Therapeutics Inc., which specializes in food allergy treatments, and the drug company Regeneron Pharmaceuticals Inc. are working together to develop a cure for peanut allergies.

[h/t Bloomberg]

SECTIONS

arrow
LIVE SMARTER
More from mental floss studios