Intelligence Article

Can Artificial Intelligence Predict Suicide?

In this article the author comes out talking about how suicide is the second highest cause of death for young adults. They also say that the patients hide their true feelings as part of the plan. They say they do this so that they can avoid restrictive care.

In the article they talk about many reasons why people may be having suicidal thoughts and/or behaviors. Not only do they say that major depression is doing this to people but many other things. Some of the things are developmental trauma, anxiety disorders, psychotic disorders and more.

In this article they also talked about a study performed on two control groups. One of the groups had suicidal thoughts while the other didn’t. While watch and observing Just and a couple of his colleagues tried to answer these three questions: Do study subjects with differ from controls in terms of neural representations of death-related and suicide-related concepts, such that a computer can consistently tell the difference from imaging? Can a machine-learning model tell the difference between people who have attempted suicide and those who have not? And are there different emotional signatures between subjects and controls which would allow a computer to tell whether someone is a member of the suicidal ideation group or the control group? In the control groups there were 79 young adults. They all were going through suicidal thought or had no personal or family psychiatric history. They used different instruments to find depression and a couple other conditions. They used an fMRI (functional magnetic resonance imaging) to look at the brain activity to detect suicidal thinking. During the test they were given a piece of paper that had three groups of ten words. These words had to do with positive and negative emotions, and suicide. The subjects were asked to describe this words in detail. While they were doing this, they said the words in a pattern the provided a good amount of time and variation allowing them to analysis the underlying brain activity.

By the end of the study they were able to use fMRI to locate the neural semantic representations. Now they will be able to tell if a person is having any suicidal thoughts and behaviors.