A machine-learning system used to spot differences in networks of brain activity was able to identify suicidal users 91% of the time. The system also identified users who had previously attempted suicide 94% of the time. These findings were reported in “Machine Learning Of Neural Representations Of Suicide And Emotion Concepts Identifies Suicidal Youth” by Marcel Adam Just, Lisa Pan, Vladimir L. Cherkassky, Dana L. McMakin, Christine Cha, Matthew K. Nock, and David Brent. The study was done using two groups of participants, including 17 suicidal ideators and 17 healthy controls, who were placed in an fMRI scanner and . . .