The artificial intelligence future of identifying suicidal thoughts

Scientists have discovered groundbreaking research regarding the possibility of utilizing brain scans and artificial intelligence to recognize suicidal thoughts. 

The current method of asserting suicidal ideology is mere client verbal assertion of their feelings to others. However, people do lie or deny their negative feelings, possibly out of fear or embarrassment. 

“Nearly 80 percent of patients who die by suicide deny suicidal ideation in their last contact with a mental health care professional,” reads a study published in Nature Human Behavior. 

Moreover, data allocates that suicide is the second-leading cause of death among young adults. This issue directly affects and influences our campus due to the majority age demographic which college students fall under. 

The algorithm, which uses brain scans to determine if someone is suicidal or not, is based on a functional magnetic resonance imaging machine and seeing what words may trigger responses and or behaviors. 

One study using this intelligence involved 34 participants, 17 who were suicidal and 17 who said they were not. The clients read 30 words that were positive and negative, such as “carefree” or “good,” and “cruelty” or “shame.” They also read words related to death, such as “overdose” or “hopeless.” 

Meanwhile the machine tracked how their brains lit up on the scans as the clients read the words during the study. Conclusively, the machine had an accuracy of 91 percent, correctly identifying 15 of the 17 suicidal participants and 16 of the 17 non-suicidal controls. Therefore, although it is in the early stages of the program, it has the potential to have grand prospects for positive societal growth, increased knowledge for the mental health profession and identifying early warning signs of self-destructive thinking.

Marcel Just, a professor of psychology at Carnegie Mellon and director of the Center for Cognitive Brain Imaging further asserted that, “It won’t completely prevent suicide, but is a major step in understanding ‘thought disorders.’” 

She continued: “This isn’t a wild pie in the sky idea. We can use machine learning to figure out the physicality of thought. We can help people.”

However, there is some skepticism from other professionals in the field, such as Blake Richards, a neuroscientist at the University of Toronto who acknowledges the test is “interesting, but may not be strong enough to make the test useful for diagnosis.” 

Richards continued to claim the immense difference between correlation and causation and how this study highlights activity patterns, which feature correlation, not causation. “There is undoubtedly a biological basis for whether someone is going to commit suicide. There’s a biological basis for every aspect of our mental lives, but the question is whether the biological basis for these things are sufficiently accessible by MRI to really develop a reliable test that you could use in a clinical setting.”

Thus, the test is very much in its experimental stages, however, if the study could validate its validity and effectiveness based on quantifiable data and more experiments, this artificial intelligence program could save the lives of students here on campus. 

JoAllie Paluchak can be reached at voices.spectator@gmail.com.

RELATED ARTICLES