Novel AI tool to instantly help assess self-harm risk

New Delhi, May 9 (SocialNews.XYZ) A team of US researchers on Thursday announced the development of a novel artificial intelligence-(AI) based tool that can instantly predict whether a person exhibits suicidal thoughts and behaviours.

The tool, which focuses on a simple picture-ranking task along with a small set of contextual/demographic variables was on average 92 per cent effective, said researchers from the universities of Northwestern, Cincinnati, Aristotle, and Massachusetts General Hospital/Harvard School of Medicine.

“A system that quantifies the judgement of reward and aversion provides a lens through which we may understand preference behaviour,” said first author Shamal Shashi Lalvani, a doctoral student at Northwestern University.

“By using interpretable variables describing human behaviour to predict suicidality, we open an avenue toward a more quantitative understanding of mental health and make connections to other disciplines such as behavioural economics,” Shamal added.

In the study, published in the journal Nature Mental Health, researchers noted that the tool may help medical professionals, hospitals, or the military to 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, revealed that the software was able to predict suicidal desire without a plan; current and specific thoughts; plan of suicide; and strategies to prevent self-harm.

Source: IANS

Facebook Comments

About Gopi

Gopi Adusumilli is a Programmer. He is the editor of SocialNews.XYZ and President of AGK Fire Inc.

He enjoys designing websites, developing mobile applications and publishing news articles on current events from various authenticated news sources.

When it comes to writing he likes to write about current world politics and Indian Movies. His future plans include developing SocialNews.XYZ into a News website that has no bias or judgment towards any.

He can be reached at gopi@socialnews.xyz

Share

This website uses cookies.

%%footer%%