Study: Machine may predict suicide risk by measuring how people respond to words

In less than two months, 14 children in Georgia have killed themselves, a disturbing number that suggests a record.

Can you predict suicide risk? It may be possible, according to a new report.

» RELATED: Sleep deprivation could cause the brain to eat itself

Scientists from Carnegie Mellon University recently conducted a small experiment, published in Nature Human Behaviour, to determine if suicidal risks can be linked to biological brain patterns.

To do so, they assessed 34 young adults - 17 who had suicidal thoughts and 17 who did not - using a set of 30 words and a fMRI, an imaging machine that measures brain activity.

Scientists asked participants to read positive words, such as “bliss,” and negative words, such as “cruelty.” They were then instructed to reflect on them while undergoing the scan.

They found the machine was able to correctly identify the people with suicidal thoughts and those without them 91 percent of the time. It also pointed out the individuals who had previously attempted suicide.

After analyzing the results further,  analysts discovered the brains of people with suicidal thoughts responded much differently to the words “death,” “cruelty,” “trouble,” “carefree,” “good,” and “praise,”compared to the controlled group.

“The study explicitly shows, in a small group of patients, that one can use the brain representations of specific thoughts to classify suicidal patients from healthy controls, and more specifically, suicide attempters from non-attempters,” the authors wrote.

Researchers said that if they can replicate their results, their method has “potential to become a major medical tool for diagnosis and/or evaluation of treatment efficacy of psychiatric disorders.”

Want to learn more about the findings? Take a look here.

» RELATED: What to know about National Suicide Prevention Day in Atlanta