Researchers at the department of psychology at Carnegie Mellon University in Pittsburgh (USA) have developed an algorithm able to read our thoughts. It can recognize people with suicidal ideation. In other words, researchers had created artificial intelligence that could read your thoughts.
Marcel Just, a professor of psychology at Carnegie Mellon and director of the Center for Cognitive Brain Imaging, developed a computer program to recognize and identify emotions and hoped the technology could find ways to prevent suicidal behavior.
“Suicidal ideation and attempt are associated with measurable alterations in the way a person thinks about ‘death,’ ‘suicide,’ and other positive and negative concepts,” said Just.
The high-tech system employs a combination of brain imaging and machine learning, a subset of artificial intelligence, to map a subject’s brain activity on the mention of keywords and concepts such as “death” or “cruelty.”
Researchers found with the help of a functional magnetic resonance imaging (fMRI) machine, that each emotion we feel had a specific signature in the brain and lit up in uniquely identifiable ways.
This study included 17 people with known suicidal tendencies and a control group of 17 people without such tendencies. While in a brain scanner, the participants were presented with and asked to think about words relating to six concepts: death, cruelty, trouble, carefree, good and praise.
The system delivers 91 percent accuracy as it analyzes the brain readings and flags the individual if the pulses and patterns overlap with those related to suicidal thoughts. Artificial intelligence could one day be used to help identify a person contemplating suicide.
“Further testing of this approach in a larger sample will determine its ability to predict future suicidal behavior,” said David Brent, co-head author of the study. “And could give clinicians in the future a way to identify, monitor and perhaps intervene with the altered and often distorted thinking that so often characterizes seriously suicidal individuals.”
Now it is possible to tell what a person is thinking. This study used machine-learning algorithms (Gaussian Naive Bayes) to identify suicidal ideators. The study was published in the journal Nature, Human Behavior.