Suicidal thoughts can be identified using AI

Artificial intelligence could be used to identify whether or not someone is feeling suicidal, a study has found.

In a study published in the journal Nature Human Behaviour, a team of US researchers used an AI programme to examine brain scans of 34 people, half of whom were known to be suicidal, for specific thought patterns relating to suicide.

Each participant was presented with three lists of ten words, reports MIT Technology Review - ten death-related words, ten words relating to positive concepts (e.g. “carefree”) and ten words related to negative ideas (e.g. “trouble”). Their brains were then scanned using an MRI.

The Week

Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.

SUBSCRIBE & SAVE

Sign up for The Week's Free Newsletters

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

Sign up

The scientists used the AI programme to search the scans to see how the participants responded to the lists of words. The results showed that healthy patients and those with suicidal thoughts showed markedly different reactions. For example, when the suicidal participants were shown the word “death”, the “shame” area of their brain lit up more than it did in the control group.

Of the 34 participants, says Engadget, the system was able to identify those known to be “suicidal ideators” with an accuracy of 91%.

However, while the system could potentially be used to help people with suicidal thoughts, Wired warns, the small sample group may not accurately reflect the “broader population”.

AI technology is being developed by researches across the world in a bid to help the medical industry.

Earlier this week, researches from Showa University, in Yokohama, Japan, revealed a similar technology that can identify bowel cancer through a colonoscopy in “less than a second”.