How AI is revolutionizing mental health care

In honor of Bell Let’s Talk Day, here are four examples of using artificial intelligence to combat mental health issues

David Venturi
Jan 26, 2017 · 4 min read
Canadian Prime Minister Justin Trudeau discussing mental health awareness on Bell Let’s Talk Day 2016. Photo via Bell Media.

This year’s Bell Let’s Talk Day fell on January 25th, 2017. If you’re unfamiliar, Bell is a Canadian telecom and media company that started a wildly successful mental health awareness campaign in 2010. The basics: for every text and call sent from a Bell phone, tweet and Instagram post with #BellLetsTalk, view of their campaign video on Facebook, and Snapchat geofilter use on that day, Bell contributes 5¢ to mental health initiatives. From their website:

[In 2010], most people were not talking about mental illness. But the numbers spoke volumes about the urgent need for action. Millions of Canadians, including leading personalities engaged in an open discussion about mental illness, offering new ideas and hope for those who struggle, with numbers growing every year.

With 131 million total interactions this year, Bell will donate over $6.5 million in funding to mental health care programs. They are well on their way to their $100 million commitment through 2020.

In honor of their campaign, here are a few examples of how artificial intelligence (AI) is being used to revolutionize mental health care. Below you’ll find university researchers, startups, and major companies all working to help those who suffer from anxiety, depression, bipolar disorder, and more.

Tess, a psychological AI that communicates via text

Use cases for Tess

Tess, a psychological AI by X2_AI, “holds conversations with the patient, administering psychotherapy and providing psychoeducation through a variety of existing technology-based communications, including SMS, WhatsApp and web browsers.” The interactive use case demos on X2AI’s website illustrate Tess’ power.

In an interview with Alison E. Berman on Singularity Hub, X2AI CEO and co-founder Michiel Rauws discusses how the accuracy of Tess’ emotions and conversation algorithms have improved. The former evaluates how the person is feeling. The latter uses “natural language processing to understand what the user is actually talking about, to pick up expressions like, ‘I don’t want to wake up anymore in the morning.’” The full interview can be read here.

Using Instagram photos to diagnose depression

The right photo, which was more likely to be posted by a depressed participant, has more blues, grays, and is darker than the left photo. These photos were included in the study mentioned below.

Researchers from Harvard University and the University of Vermont are combining machine learning tools and Instagram to improve depression screening. Using color analysis, metadata, and algorithmic face detection, they were able to reach 70 percent accuracy in detecting signs of depression (previous studies have GPs around 42 percent accuracy).

Participants diagnosed with clinical depression were more likely to post bluer, grayer, and darker-colored photos. They weren’t likely to use an Instagram filter, though when they did they “most disproportionately favored the Inkwell filter, which converts color photographs to black-and­-white images.” More comments received meant photos were more likely to be posted by depressed participants, though they found the opposite to be true for likes received. The full study can be read here.

Detecting speech patterns in psychiatric interviews

The promo video for IBM Research’s feature on AI in mental health care.

IBM Research is using transcripts and audio from psychiatric interviews, coupled with machine learning techniques, to find patterns in speech to help clinicians accurately predict and monitor psychosis, schizophrenia, mania, and depression. Today, it only takes them about 300 words to help clinicians predict the probability of psychosis in a user.

Check out the full feature, titled “IBM 5 in 5: With AI, our words will be a window into our mental health,” where “5 in 5” is short for “five innovations that will help change our lives within five years.”

Using computer vision to diagnose ADHD in children

Photo from ICSB

Scientists at the University of Texas at Arlington and Yale University are combining computing power and psychiatric expertise to diagnose ADHD in children. They use the latest in computer vision and machine learning to assess children while they are performing certain physical and computer exercises. The exercises test a child’s attention, decision-making, and ability to manage emotions.

More details on the project can be found in this Singularity Hub article by Peter Rejcek. The article also outlines a few other mental health tools that use artificial intelligence.

Those are only a few examples of using AI to combat mental health issues. There are more that together target the full spectrum of care, including screening, diagnosis, and treatment. End-to-end, mental health care is being revolutionized as you read/listen.

The future is bright. And you are not alone.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store