Using Machine Learning to Examine Suicidal Ideation After Traumatic Brain Injury: A Traumatic Brain Injury Model Systems National Database Study

Amy Wagner, MD, professor and director of the brain injury medicine fellowship, University of Pittsburgh Department of Physical Medicine and Rehabilitation – along with a team of experts from across the country – published “Using Machine Learning to Examine Suicidal Ideation After Traumatic Brain Injury: A Traumatic Brain Injury Model Systems National Database Study” in the American Journal of Physical Medicine & Rehabilitation.

The aim of this study was to predict suicidal ideation a year after moderate to severe traumatic brain injury. The study used a cross-sectional design with data collected through the prospective, longitudinal Traumatic Brain Injury Model Systems network at hospitalization and one year after injury. Participants who completed the Patient Health Questionnaire-9 suicide item at year one follow-up ( N = 4328) were included.

A gradient boosting machine algorithm demonstrated the best performance in predicting suicidal ideation one year after traumatic brain injury. Predictors were Patient Health Questionnaire-9 items (except suicidality), Generalized Anxiety Disorder-7 items, and a measure of heavy drinking.

Results of the 10-fold cross-validation gradient boosting machine analysis indicated excellent classification performance with an area under the curve of 0.882. Sensitivity was 0.85 and specificity was 0.77. Accuracy was 0.78 (95% confidence interval, 0.77-0.79). Feature importance analyses revealed that depressed mood and guilt were the most important predictors of suicidal ideation, followed by anhedonia, concentration difficulties, and psychomotor disturbance.

The team found that, overall, depression symptoms were most predictive of suicidal ideation. Despite the limited clinical impact of the present findings, machine learning has potential to improve prediction of suicidal behavior, leveraging electronic health record data to identify individuals at greatest risk, thereby facilitating intervention and optimization of long-term outcomes after traumatic brain injury.

Learn more.

Study collaborators
Lauren Fisher, PhD

Joshua Curtiss, MA

Daniel W. Klyce, PhD, LCP, ABPP

Paul B. Perrin, PhD

Shannon Juengst, PhD

Kelli Williams Gary, PhD, OTR/L

Janet P. Niemeier, PhD, ABPP

Flora Hammond, MD

Thomas F. Bergquist, PhD, ABPP

Amanda Rabinowitz, PhD

Joseph T. Giacino, PhD

Ross Zafonte, DO