How A Person Responds To Certain Words May Predict Whether They Are Suicidal : Shots - Health News A computer program learned to identify people thinking about suicide by studying brain activity patterns associated with words like "death" and "trouble."
NPR logo

Brain Patterns May Predict People At Risk Of Suicide

  • Download
  • <iframe src="https://www.npr.org/player/embed/560837881/561041356" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript
Brain Patterns May Predict People At Risk Of Suicide

Brain Patterns May Predict People At Risk Of Suicide

  • Download
  • <iframe src="https://www.npr.org/player/embed/560837881/561041356" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript

RACHEL MARTIN, HOST:

We're going to hear now about some new research that could help mental health professionals identify people who are likely to attempt suicide. NPR's Jon Hamilton reports on an effort to assess young adults by studying their brains.

JON HAMILTON, BYLINE: Lisa Pan is a psychiatrist at the University of Pittsburgh who specializes in treating young people who are suicidal. Pan says she recalls when one of her patients showed up at her office saying he felt bad.

LISA PAN: He had come with a backpack, which is unlike him. And he had decided when he came to my office that if I didn't determine that he was at acute risk, he was going to take the backpack full of rocks and jump off a bridge.

HAMILTON: Pan made the right call. She put him in a hospital. But she says that sort of decision is often no more than an educated guess.

PAN: We're very bad at identifying which people who are presenting with risk are, in fact, going to go on and have a suicide attempt.

HAMILTON: So Pan and her colleagues started working with some researchers a mile away at Carnegie Mellon University. A psychologist named Marcel Just was using a technology called functional MRI to study what people were thinking. He'd shown that thoughts create a distinctive pattern of activity in the brain. He'd also shown that a computer program could learn to read the neural signatures of specific words, ideas and more.

MARCEL JUST: We could tell what emotion a person was feeling. We could tell what social interaction they're thinking about. And we thought, well, maybe the brain activation patterns of certain thoughts are altered in people who are thinking about suicide.

HAMILTON: So Just, Pan and a team of researchers chose a list of words they thought might reveal brain activation patterns associated with suicide.

JUST: Some are kind of obvious suicide-related words like apathy, death, desperate, fatal, funeral.

HAMILTON: Then the team had several dozen volunteers lie in a brain scanner and watch a computer screen.

JUST: The words come up on the screen one at a time. They think about them for three seconds each. And we capture the brain activity while they're thinking about what each of these concepts means.

HAMILTON: And Just says a computer soon learned how to tell which brains belong to a person who was suicidal.

JUST: It correctly identified 15 of the 17 suicidal participants and 16 of the 17 controls.

HAMILTON: What's more, the computer was very good at telling whether a person had only thought about suicide or actually made an attempt. Barry Horwitz, a brain imaging expert at the National Institutes of Health, says the results need to be confirmed by a larger study. But he says the research hints at a future in which brain scans and computers can help assess a person's mental health.

BARRY HORWITZ: Just looking at the behavior is probably inadequate for a lot of purposes. And it's much better to be able to see what the brain is doing.

HAMILTON: The new research appears in the journal Nature Human Behavior. Jon Hamilton, NPR News.

Copyright © 2017 NPR. All rights reserved. Visit our website terms of use and permissions pages at www.npr.org for further information.

NPR transcripts are created on a rush deadline by Verb8tm, Inc., an NPR contractor, and produced using a proprietary transcription process developed with NPR. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR’s programming is the audio record.