Related Experiment Video
Updated: Sep 20, 2025
Assessing Dominant-Submissive Behavior in Adult Rats Following Traumatic Brain Injury
Published on: December 16, 2022
Using Machine Learning to Examine Suicidal Ideation After Traumatic Brain Injury: A Traumatic Brain Injury Model
Lauren B Fisher1, Joshua E Curtiss, Daniel W Klyce
1From the Department of Psychiatry, Massachusetts General Hospital, Boston, Massachusetts (LBF, JEC, JTG); Department of Psychiatry, Harvard Medical School, Boston, Massachusetts (LBF, JEC); Central Virginia Veterans Affairs Health Care System, Richmond, Virginia (DWK, PBP); Sheltering Arms Institute, Richmond, Virginia (DWK); Virginia Commonwealth University Health System, Richmond, Virginia (DWK); Departments of Psychology and Physical Medicine and Rehabilitation, Virginia Commonwealth University, Richmond, Virginia (PBP); Department of Physical Medicine and Rehabilitation, UT Southwestern Medical Center, Dallas, Texas (SBJ); Department of Rehabilitation Counseling, Virginia Commonwealth University, Richmond, Virginia (KWG); Department of Psychology, University of Alabama, Birmingham, Alabama (JPN); Department of Physical Medicine and Rehabilitation, Indiana University School of Medicine, Indianapolis, Indiana (FMH); Rehabilitation Hospital of Indiana, Indianapolis, Indiana (FMH); Mayo Clinic College of Medicine and Science Rochester, Minnesota (TFB); Departments of Physical Medicine & Rehabilitation and Neuroscience, Center for Neuroscience, Safar Center for Resuscitation Research, Clinical and Translational Science Institute, University of Pittsburgh, Pittsburgh, Pennsylvania (AKW); Moss Rehabilitation Research Institute, Elkins Park, Pennsylvania (ARR); Department of Physical Medicine and Rehabilitation, Spaulding Rehabilitation Hospital, Boston, Massachusetts (JTG, RDZ); Department of Physical Medicine and Rehabilitation, Massachusetts General Hospital, Boston, Massachusetts (RDZ); Department of Physical Medicine and Rehabilitation, Brigham and Women's Hospital, Boston, Massachusetts (RDZ); and Department of Physical Medicine and Rehabilitation, Harvard Medical School, Boston, Massachusetts (RDZ).
Objective:
The aim of the study was to predict suicidal ideation 1 yr after moderate to severe traumatic brain injury.
Design:
This study used a cross-sectional design with data collected through the prospective, longitudinal Traumatic Brain Injury Model Systems network at hospitalization and 1 yr after injury. Participants who completed the Patient Health Questionnaire-9 suicide item at year 1 follow-up ( N = 4328) were included.
Results:
A gradient boosting machine algorithm demonstrated the best performance in predicting suicidal ideation 1 yr 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.
Conclusions:
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.
