Investigators at Cincinnati Children’s make strides in predicting which teens are most at risk
Every two hours in America, a young person commits suicide. Every few minutes, another young person tries.
Few people outside the mental health field may realize it, but national data shows that families are more than twice as likely to lose an adolescent child to suicide than to cancer. Nearly 4,400 young people – ages 15 to 24 – commit suicide each year, making intentional self-harm the third leading cause of death for this age group, according to the American Association of Suicidology. That compares to nearly 1,700 people ages 15 to 24 who die of cancer each year, according to the Centers for Disease Control and Prevention.
“This is an extraordinarily complex problem because both biology and psychology are interacting. Better ways to identify suicidal behavior are needed,” says John Pestian, PhD, MBA, a leading researcher in the Division of Biomedical Informatics at Cincinnati Children’s.
Now, two projects at Cincinnati Children’s are evaluating ways to help hospital staff better detect teens at high risk of suicide, and to predict which suicide attempt survivors are most likely to try again.
Improving emergency care for at-risk teens
Investigators at Cincinnati Children’s and Nationwide Children’s Hospital are using a three-year, $1.2 million grant from the Centers for Disease Control and Prevention to evaluate a new intervention for teens who present at the emergency department.
When adolescents arrive at the hospital after a suicide attempt, their need for mental health care is fairly obvious. But what about teens who present to the emergency department for non-psychiatric concerns, but may have an underlying suicide risk?
“No evidence-based standards exist for how to appropriately screen and intervene for patients who are treated in the emergency department and who show an elevated risk for suicide,” says Jackie Grupp-Phelan, MD, MPH, principal investigator and director of research in the Division of Emergency Medicine at Cincinnati Children’s.
The research team plans to recruit 160 adolescents (80 per site) who were seeking treatment in the emergency department for non-psychiatric concerns, but are identified via systematic screening as being at risk for suicide. Participants will be randomly assigned to receive either the new intervention or enhanced usual care.
Enhanced usual care consists of a brief consultation and a mental health referral. The new intervention, termed Suicidal Teens Accessing Treatment after an ED Visit (STAT-ED), targets family engagement, problem solving, assistance with referral and limited case management during the transition from the emergency department to outpatient care.
“The goal is to maximize the initiation of mental health treatment and aftercare among adolescents screening positive for previously unrecognized suicide risk,” says Jeff Bridge, PhD, principal investigator in the Center for Innovation in Pediatric Practice at Nationwide Children’s.
STAT-ED already has appeared more effective than enhanced usual care in a small pilot study. The new study will provide a larger, more diverse sample. If successful, the intervention could be implemented at more hospitals nationwide.
Learning from the language of suicide
John Pestian is among a handful of investigators nationwide combing through the wording of suicide notes for clues that could help prevent other teens from making the attempt.
Pestian and colleagues have amassed one of the world’s largest collections of suicide notes and they are using the latest in natural language processing science to better understand what a suicidal person is thinking. The goal: to develop an evidence-based tool that pediatricians, psychiatrists, social workers and others can use to predict the likelihood of future suicide attempts.
“People have a natural propensity for self-preservation. Many of us may wish we were dead at some point in our lives, but we do not carry out the act,” Pestian says. “So what moves a person from self-preservation to self-annihilation? The words that people leave behind are the closest thing we have to their final thoughts.”
Efforts to study suicide notes date back at least as far as the 1960s. But no one has attempted to apply this level of computational rigor to the task.
Over a period of nearly eight years, Pestian and colleagues collected and digitized more than 1,300 suicide notes. More than 150 family survivors, members of suicide prevention groups and mental health experts helped annotate the collection by assigning emotions to key words and phrases.
This database was plugged into an experimental computer algorithm that analyzes sentence lengths; key words and phrases; specific references to time, people or religion; even the overall length of responses. It uses the patterns gleaned from the suicide notes to look for similar patterns in the speech of people thought to be at risk of suicide.
In a recently completed clinical trial, Pestian’s team reported that their computer algorithm was 90 percent accurate at distinguishing suicidal patients from non-suicidal control cases. Clinicians interpreting the same results were about 50 percent accurate.
Why such a difference? Pestian calls it psychological phenomology. That is, when we hear something, the content of the message is important because we associate it with past experiences. Computers consider the structure of the message, not just the content.
Ultimately, the goal is to produce a software product that will support a clinician’s decisions by providing real-time information. The next step is to launch a multicenter clinical trial to evaluate the algorithms in larger, more diverse groups.
“We’ve tested it here. But now we want to test it in other hospitals,” Pestian says.