When a person’s distress, depression or discouragement appears to have taken a sharp turn for the worse, it’s time to ask him or her a weighty question: Are you thinking of harming yourself?
If only the answer were a better guide. One study has found that nearly 80 percent of patients who took their own lives denied they were contemplating suicide in their last contact with a mental health care professional. Friends and family suffer the guilt and anguish of not having divined a loved one’s intentions, but mental health professionals rarely fare much better at doing so.
But what if the brain’s response to a series of questions — never the question, but a more indirect probe of a person’s feelings — yielded a more accurate signal?
New research suggests it can.
In a study published Monday in the journal Nature Human Behavior, researchers found that patterns of brain activation in response to a set of written words could reliably distinguish between young adults who had contemplated suicide and control subjects. These words included ones related to death and to both positive and negative emotions.
A further exercise — gauging specific brain responses to clusters of highly emotional words — made an even finer distinction: between subjects who had a history of suicide attempts and those who had pondered such a step but never acted on it.
“Suicidal ideation and attempt are associated with measurable alterations in the way a person thinks about ‘death,’ ‘suicide,’ and other positive and negative concepts,” wrote the authors of the new study, led by Carnegie Mellon University neuroscientist Marcel Just.
The interactions are complex, but computer-learning programs can tease out patterns that allow predictions to be made — or at least identify individuals most in need of immediate and intensive help.
After years of peering into the spectral images produced by a functional magnetic resonance imaging, or fMRI, scanner, Just said he and his colleagues have gotten pretty accurate at “reading” a subject’s feelings of shame, sadness, anger and pride, among others.
We humans may vary widely in how we express our emotions, Just said. But when a given emotion is aroused in a number of experimental subjects, blood flows in predictable patterns to predictable structures of the brain. With all our individual variability, he said, some emotions have very identifiable “neural signatures.”
Close to five years ago, Just delivered a talk on the neural signatures of emotion at the University of Pittsburgh. Afterward, a psychiatrist approached him and described his profession’s sorry record of predicting suicide. He asked: Could neural signatures help reveal intent?
Just and his co-authors set about devising an approach for the assessment of suicide risk. They would use machine learning to detect abnormal emotional responses to concepts such as “death” and “cruelty,” as well as to words such as “carefree” and “good.”
In a group of 34 young adult subjects, the resulting program distinguished between healthy controls and suicide-contemplators with an accuracy of 91 percent. It correctly identified 15 of the 17 suicidal participants and 16 of the 17 nonsuicidal controls.
A further iteration of the machine-learning program was able to distinguish, with 87 percent accuracy, between subjects who had engaged in suicidal thinking only and those who had attempted suicide.
The activation patterns inside the brains of young adults who had stared into that psychological abyss and acted on the impulse tended to respond to death-related words with less sadness than did subjects who had contemplated suicide but never made an attempt.
Compared to subjects with a past suicide attempt, those who had pondered suicide but not acted on such thoughts responded to death- and suicide-related words like “lifeless,” “desperate,” “overdose” and “funeral” with neural signatures suggesting more anger, and they did so reliably.
Just acknowledged that, in many cases, the breadth and depth of a subject’s depressive symptoms also can predict whether he will try to harm himself. Administering a dynamic brain scan, however, may offer earlier warning that self-destructive thought patterns are settling in, he said.
Understanding how those thought patterns manifest themselves as brain-activation patterns might also offer a way to target psychological therapies, and test whether they are working.
“Obviously it’s good to ask the person,” Just said. “We don’t try to set this up as a competing measure to existing methods, but a complementary one. These are pretty high accuracies we’re getting.”