Health Fusion: Artificial intelligence predicts suicide risk in students
If we could spot students at risk of suicide, we'd save lives. Artificial intelligence is making that possible. In this episode of NewMD's podcast, "Health Fusion," Viv Williams looks at how machine learning is helping researchers identify four predictors of suicidal behaviors.
The following statistic , noted by the Centers for Disease Control and Prevention, is alarming. Suicide is the second leading cause of death in adolescents ages 15-19. How can we prevent these tragedies from happening?
Researchers from McGill University, University of Montreal and two other organizations in France are using artificial intelligence to identify kids at risk. And they found that self-esteem is one of four main contributing factors.
"Early detection of suicidal behaviors and thoughts is the key to providing appropriate treatment,” says lead author Mélissa Macalli, a PhD Candidate at University of Bordeaux.
The research team followed more than 5,000 college students and found that out of 70 predictors, four of them — suicidal thoughts, anxiety, depressive symptoms, and self-esteem — were present in 80% of the suicidal behaviors they saw at follow up.
They singled out self-esteem as being a major factor and recommend it be included in screening. The researchers say their study may help to develop screening tools, such as questionnaires, that can accurately predict risk easily and quickly.
“The mental health specialists on our teams did not expect self-esteem to be one of the top four predictors of suicidal behaviors,” says Mélissa Macalli. “This finding would not have been discovered without the use of machine learning, which makes it possible to analyze a large amount of data simultaneously. This opens up new avenues for both research and prevention."
The study was published in the journal Scientific Reports.
For comments or other podcast episode ideas, email Viv Williams at firstname.lastname@example.org . Or on Twitter/Instagram/FB @vivwilliamstv.