Researchers at the universities of Northwestern, Cincinnati, Aristotle, Massachusetts General Hospital/Harvard School say the tool, which focuses on a simple picture-ranking task with a small set of contextual/demographic variables, was 92 percent effective on average. Medicine.
"A system that measures judgments of reward and aversion provides a lens through which we can understand preference behavior," said first author Shama Shashi Lalwani, a doctoral student at Northwestern University.
Shamal said, "By using explanatory variables that describe human behavior to predict suicidality, we open a path toward a more quantitative understanding of mental health and make connections to other disciplines such as behavioral economics."
In the study published in the journal Nature Mental Health, researchers note that the tool could help medical professionals, hospitals or the military assess who is most at risk of self-harm.
The findings, based on a survey of 4,019 people aged 18 to 70 across the US, showed that the software was able to predict suicidal ideation without any planning and specific thoughts; suicide plans; and strategies to prevent self-harm.
"A system that measures judgments of reward and aversion provides a lens through which we can understand preference behavior," said first author Shama Shashi Lalwani, a doctoral student at Northwestern University.
Shamal said, "By using explanatory variables that describe human behavior to predict suicidality, we open a path toward a more quantitative understanding of mental health and make connections to other disciplines such as behavioral economics."
In the study published in the journal Nature Mental Health, researchers note that the tool could help medical professionals, hospitals or the military assess who is most at risk of self-harm.
The findings, based on a survey of 4,019 people aged 18 to 70 across the US, showed that the software was able to predict suicidal ideation without any planning and specific thoughts; suicide plans; and strategies to prevent self-harm.
