Carnegie Mellon, Pitt awarded $3.8M grant to diagnose suicidal thinking

The National Institute of Mental Health has awarded a $3.8 million grant to researchers from Carnegie Mellon University and the University of Pittsburgh to diagnose suicidal thinking using brain imaging.

“Suicide is the second leading cause of death among young adults in the U.S., and current assessment methods rely entirely on patients self-reporting and doctors’ observations,” says David Brent, who holds an endowed chair in suicide studies and is a professor of psychiatry, pediatrics, epidemiology, and clinical and translational science at the University of Pittsburgh School of Medicine. “Any new inroads to better diagnosis and treatment have the potential to save lives.”

Also See: EHR data, model better predict patient suicide risk

The NIMH funding is meant to advance previous research at CMU and Pitt which led to a promising approach for identifying suicidal individuals by analyzing the alterations in how their brains represent certain concepts, such as death, cruelty and trouble.

In their 2017 study, researchers presented a list of 10 death-related words, 10 words relating to positive concepts (such as carefree) and 10 words related to negative ideas (such as trouble) to two groups of 17 people with known suicidal tendencies and 17 neurotypical individuals. Using a machine learning algorithm, they were able to identify with 91 percent accuracy whether a participant was from the control or suicidal group and were able to accurately distinguish the nine who had attempted to take their lives with 94 percent accuracy.

However, the newly funded Predicting Risk Imaging Suicidal Minds (PRISM) project will enable researchers to evaluate the technology in a much larger sample of patients than in the previous study, as well as include patients with other mental illnesses as a means of comparison.

“The cornerstone of this project is our recent ability to identify what concept a person is thinking about based on its accompanying brain activation pattern or neural signature,” said Marcel Just, the D.O. Hebb University Professor of Psychology in CMU’s Dietrich College of Humanities and Social Sciences.

“We were previously able to obtain consistent neural signatures to determine whether someone was thinking about objects like a banana or a hammer by examining their MRI brain activation patterns,” added Just. “But now we are able to tell whether someone is thinking about ‘trouble’ or ‘death’ in an unusual way. The alterations in the signatures of these concepts are the ‘neurocognitive thought markers’ that our machine learning program looks for.”

Imaging Suicide-CROP.jpg

Researchers hope that by establishing reliable neurocognitive markers of suicidal ideation and attempt their study will ultimately improve how clinicians detect and treat patients with thoughts about committing suicide.

Specifically, researchers are seeking to enable physicians to do a better job of:

  • Detecting and monitoring suicidal risk
  • Understanding alterations in thinking and feelings related to suicide in their patients; and
  • Developing personalized treatment strategies for their suicidal patients based on their altered patterns of thinking and feeling that can more precisely and effectively reduce suicide risk.

The study will evaluate the differences in brain activation patterns between suicidal and non-suicidal young adults as they think about words related to suicide—such as positive and negative concepts—and use machine learning techniques to identify neural signatures of suicidal ideation and behavior.

For reprint and licensing requests for this article, click here.