It’s been a particularly tragic couple of weeks in the press: two beloved public figures committed suicide in short succession. First, we lost Kate Spade, followed by Anthony Bourdain. Both individuals left behind young children, fortune, fame and seemingly everything else a successful person could possibly want. Except, mental health, neurology and physiology care not how powerful, successful, well-known or beloved you may happen to be — depression and/or suicidal thoughts can affect anyone and everyone equally.
It’s no secret suicide prevention is top-of-mind for many medical professionals. They are on the rise across most age cohorts in this country, and up a full 30% in the last 20 years alone. They often happen in clusters — likened to a contagion — in younger populations. Even shows depicting suicide, like Netflix’s ‘13 Reasons Why’, have come under fire from all directions for potentially glorifying the act. It’s a tricky subject to talk about, there can still be negative stigma attached to the subject matter, the impacts of suicide are widespread and spreading, it’s notoriously hard to predict who will take their own life and when, and the medical community is left trying to figure out how to better predict and prevent these heartbreaking scenes from repeating themselves.
A.I. might have just the thing to help out.
In late 2017, The Verge reported:
“In a study published today in the journal Nature Communications, researchers observed the brain activity of two groups of adults — one who had suicidal thoughts and one who didn’t — while they thought about words such as “evil” or “praise.” They fed this data to an algorithm that learned to predict who had suicidal thoughts with 91 percent accuracy. It also predicted whether someone had attempted suicide before with 94 percent accuracy.”
Essentially, scientists trained an algorithm to identify individuals with suicidal thoughts based on a simultaneous brain scan. It bears noting the study was quite small (34 subjects), meaning the results may not hold for a larger, more inclusive population. But, the method could potentially be used one day for diagnosing mental health conditions, the researchers say.
Getting a little more into the weeds on the test itself, The Verge went into the methodology and it’s worth getting into:
“Researchers found that the responses to six words — “death,” “trouble,” “carefree,” “good,” “praise,” and “cruelty” — showed the biggest differences between the two groups of participants [one experienced suicidal thoughts, the other did not]. So, they gave a machine-learning algorithm these results for every person except one. For any given word, they told the program which neural activation patterns came from which group. Then, they gave them the missing person’s results and asked the algorithm to predict which group the person belonged to. The machine got it right 91 percent of the time. In a second experiment, scientists used the same methods to teach an algorithm to distinguish people who had attempted suicide from those who hadn’t, this time with 94 percent accuracy.
Those results hint at multiple positive conclusions. But, several scientists caution against unbridled optimism at the results — the test is a small sample size, brain scans are expensive, 91 or 94 percent predictivity sounds great but needs to be higher to be clinically useful, etc. But, as A.I. improves, the test could improve dramatically — perhaps even enough so that this could be a useful tool to mental health professionals.
Start a conversation with our talented team today!
Subscribe to our mailing list to receive updates about new posts to the ENO8 blog