By Floro Mercene
In the future, AI might able to predict a person who is contemplating suicide. A new study published in Nature Human Behaviour could help identify those suffering from suicidal thoughts.
Researchers looked at 34 young adults, 17 of whom were experiencing suicidal thoughts, and another 17 is a control group. Each person underwent brain imaging with an MRI machine while being shown a series of words that were related to different emotions. All the words were related to suicide (words like “death”, “distressed,” or “fatal”), positive effects (“carefree,” “kindness,” “innocence”), or negative effects (“boredom,’ “evil,” “guilty”). The researcher also used previously mapped neutral signatures that show the brain patterns of emotions like “shame” and “anger.”
Five brain locations, along with six of the words, were found to be the best markers to distinguish the suicidal patients from the controls. For example, the suicidal participants were shown the word “death,” the “shame” area of their brain lit up more than it did in the control group. Likewise, “trouble” also evoked more activity in the “sadness” area.
Using just those locations and words, the researchers trained a machine-learning classifier that was able to correctly identify 15 of 17 suicidal patients and 16 of 17 control subjects. Next they devised an algorithm to spot the same thing.
Researchers then applied the algorithm to the group of participants experiencing suicidal thoughts – half had previously attempted suicide and half had not. The algorithm correctly identified 94 percent of the participants who had attempted suicide.
Artificial Intelligence has already made waves in the medical field at large. There are algorithms so good at detecting tumors and other problems in CT scans. Identifying particular emotional responses to suicide-related terms could also be useful to psychotherapists treating their patients.