Carnegie Mellon University researchers believe they’ve isolated the brain signature for suicidal thoughts using machine learning algorithms. According to the results of a study they published in the journal Nature Human Behavior, their testing overall is 91 percent accurate.

While the 34 test volunteers sat in an MRI for 30 minutes, they were shown a series of life- and death-related words. Meanwhile, a computer analyzed the neural patterns, noting the differences between test subjects with and without suicidal thoughts. The computer was able to identify the nine volunteers who had attempted suicide in the past with 94 percent accuracy.

Despite the very small sample size, the results—if they confirmed with larger test samples—could have a massive impact on mental health care. Currently, there’s no quantitative way to determine if anyone has repressed suicidal thoughts, and less than 80 percent of those who have them share this with others.

The demand for such a test, if it proves effective within a broader population, would be significant. More than 44,000 Americans take their own lives each year, and it is the second-leading cause of death among young adults in the U.S.

TruNews copy