Brain imaging science identifies individuals with suicidal thoughts

October 30, 2017
On the left is the brain activation pattern for "death" in participants who had made a suicide attempt. The image in the right depicts the activation pattern for "death" in control participants. Credit: Carnegie Mellon University

Researchers led by Carnegie Mellon University's Marcel Just and the University of Pittsburgh's David Brent have developed an innovative and promising approach to identify suicidal individuals by analyzing the alterations in how their brains represent certain concepts, such as death, cruelty and trouble.

Suicidal risk is notoriously difficult to assess and predict, and is the second-leading cause of death among young adults in the United States. Published in Nature Human Behaviour, the study offers a new approach to assessing psychiatric disorders.

"Our latest work is unique insofar as it identifies concept alterations that are associated with and behavior, using machine-learning algorithms to assess the neural representation of specific concepts related to suicide. This gives us a window into the brain and mind, shedding light on how suicidal individuals think about suicide and emotion related concepts. What is central to this new study is that we can tell whether someone is considering suicide by the way that they are thinking about the death-related topics," said Just, the D.O. Hebb University Professor of Psychology in CMU's Dietrich College of Humanities and Social Sciences.

For the study, Just and Brent, who holds an endowed chair in suicide studies and is a professor of psychiatry, pediatrics, epidemiology and clinical and translational science at Pitt, presented a list of 10 death-related words, 10 words relating to positive concepts (e.g. carefree) and 10 words related to negative ideas (e.g. trouble) to two groups of 17 people with known and 17 neurotypical individuals.

They applied the machine-learning algorithm to six word-concepts that best discriminated between the two groups as the participants thought about each one while in the brain scanner. These were death, cruelty, trouble, carefree, good and praise. Based on the brain representations of these six concepts, their program was able to identify with 91 percent accuracy whether a participant was from the control or suicidal group.

Then, focusing on the suicidal ideators, they used a similar approach to see if the algorithm could identify participants who had made a previous suicide attempt from those who only thought about it. The program was able to accurately distinguish the nine who had attempted to take their lives with 94 percent accuracy.

"Further testing of this approach in a larger sample will determine its generality and its ability to predict future suicidal behavior, 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," said Brent.

To further understand what caused the suicidal and non-suicidal participants to have different brain activation patterns for specific thoughts, Just and Brent used an archive of neural signatures for emotions (particularly sadness, shame, anger and pride) to measure the amount of each emotion that was evoked in a participant's brain by each of the six discriminating concepts. The machine-learning program was able to accurately predict which group the participant belonged to with 85 percent accuracy based on the differences in the emotion signatures of the concepts.

"The benefit of this latter approach, sometimes called explainable artificial intelligence, is more revealing of what discriminates the two groups, namely the types of emotions that the discriminating words evoke," Just said. "People with experience different emotions when they think about some of the test concepts. For example, the concept of 'death' evoked more shame and more sadness in the group that thought about suicide. This extra bit of understanding may suggest an avenue to treatment that attempts to change the response to certain concepts."

Just and Brent are hopeful that the findings from this basic cognitive neuroscience research can be used to save lives.

"The most immediate need is to apply these findings to a much larger sample and then use it to predict future suicide attempts," said Brent.

Just and his CMU colleague Tom Mitchell first pioneered this application of machine learning to brain imaging that identifies concepts from their activation signatures. Since then, the research has been extended to identify emotions and multi- thoughts from their neural signatures and also to uncover how complex scientific concepts are coded as they are being learned.

Explore further: Older adults may need better follow-up after ER screenings for suicide

More information: Machine learning of neural representations of suicide and emotion concepts identifies suicidal youth, Nature Human Behaviour (2017). www.nature.com/articles/s41562-017-0234-y

Related Stories

Older adults may need better follow-up after ER screenings for suicide

August 9, 2017
According to the World Health Organization, suicide rates for men over the age of 70 are higher than in any other group of people. In 2015, almost 8,000 older adults committed suicide in the U.S., and the proportion of suicides ...

For suicidal veterans, loneliness is the deadliest enemy

September 29, 2017
About 20 veterans commit suicide every day. The primary enemy most veterans face after service is not war-related trauma but loneliness, according to a new study by researchers at Yale and the U.S. Department of Veterans ...

Suicide and genetics: a complicated association

April 22, 2017
Dear Mayo Clinic: Why does it seem that suicide tends to run in families? Does it have anything to do with genetics?

Psychotic experiences put kids at higher suicide risk

August 30, 2017
Otherwise healthy people who experience hallucinations or delusions are more likely to have later suicidal thoughts or attempts, an international study has found.

Brain representations of social thoughts accurately predict autism diagnosis

December 2, 2014
Psychiatric disorders—including autism—are characterized and diagnosed based on a clinical assessment of verbal and physical behavior. However, brain imaging and cognitive neuroscience are poised to provide a powerful ...

Young people with chronic illness more likely to attempt suicide

August 17, 2017
Young people between the ages of 15 and 30 living with a chronic illness are three times more likely to attempt suicide than their healthy peers, according to a new study from the University of Waterloo.

Recommended for you

Abusive avatars help schizophrenics fight 'voices': study

November 24, 2017
"You're rubbish. You're rubbish. You're a waste of space." The computer avatar pulls no punches as it lays into the young woman, a schizophrenia sufferer, facing the screen.

Ten-month-old infants determine the value of a goal from how hard someone works to achieve it

November 23, 2017
Babies as young as 10 months can assess how much someone values a particular goal by observing how hard they are willing to work to achieve it, according to a new study from MIT and Harvard University.

Stress in pregnancy linked to changes in infant's nervous system, less smiling, less resilience

November 23, 2017
Maternal stress during the second trimester of pregnancy may influence the nervous system of the developing child, both before and after birth, and may have subtle effects on temperament, resulting in less smiling and engagement, ...

Domestic violence turns women off masculine men

November 23, 2017
Women who are afraid of violence within partnerships prefer more feminine men, according to new research carried out by scientists at the University of St Andrews.

Study finds infection and schizophrenia symptom link

November 22, 2017
If a mother's immune system is activated by infection during pregnancy, it could result in critical cognitive deficits linked to schizophrenia in her offspring, a University of Otago study has revealed.

Schizophrenia drug development may be 'de-risked' with new research tool

November 22, 2017
Researchers at Columbia University Medical Center (CUMC) and the New York State Psychiatric Institute (NYSPI) have identified biomarkers that can aid in the development of better treatments for schizophrenia.

1 comment

Adjust slider to filter visible comments by rank

Display comments: newest first

moranity
not rated yet Oct 30, 2017
wow, a study that draws conclusions from a massive dataset of 34 participants

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.