With the Center for Disease Control's recent report on the uptick in drug- and gun-related deaths, new research from Carnegie Mellon University (CMU) and the University of Pittsburgh is apropos: scientists have developed a brain-imaging method that can accurately differentiate individuals with and without suicidal thoughts.
Researchers enlisted 34 subjects for the testing, evenly split between those with and without suicidal tendencies.
The participants were all presented with three lists of 10 words. One included words with negative associations (such as "evil," "cruelty," and "trouble"), one included positive words (such as "good," "carefree," and "praise"), while the third included words related to suicide (such as "death," "hopeless," and "distressed").
During the presentation of words, participants were subject to functional MRI (fMRI) of the brain, allowing researchers to track neural feedback for each word.
The scientists found that the subjects' neural response to six words — "death," "cruelty," "trouble," "carefree," "good," and "praise" — across five specific brain regions were best for distinguishing between participants with suicidal tendencies and the controls.
Researchers then trained a "machine-learning algorithm" to analyze the data, which in turn ascertained individuals with suicidal tendencies with 91 percent accuracy. In a subsequent part of the research, scientists added neural signatures for various emotions, and the algorithm was able to predict with 85 percent accuracy.
"The benefit of this latter approach," says Just, "sometimes called explainable artificial intelligence, is more revealing of what discriminates the two groups, namely the types of emotions that the discriminating words evoke."
While the results are preliminary and require testing in larger samples, the possibility exists that suicidal risk could one day be predicted using such a method.
[Barry Horwitz, the chief of the Brain Imaging and Modeling Section at the National Institute on Deafness and Other Communication Disorders] says that if the study results are confirmed in future research, "then a case can be made that functional neuroimaging has potential to become a major medical tool for diagnosis and/or evaluation of treatment efficacy of psychiatric disorders."