[Skip to Navigation]
Views 2,030
Citations 0
Original Investigation
September 1, 2021

Development and Validation of a Model to Predict Posttraumatic Stress Disorder and Major Depression After a Motor Vehicle Collision

Author Affiliations
  • 1Department of Health Care Policy, Harvard Medical School, Boston, Massachusetts
  • 2Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts
  • 3Halıcıoğlu Data Science Institute, University of California, San Diego
  • 4Department of Emergency Medicine, Washington University School of Medicine, St Louis, Missouri
  • 5Department of Emergency Medicine & Department of Health Services, Policy, and Practice, The Alpert Medical School of Brown University, Rhode Island Hospital and The Miriam Hospital, Providence, Rhode Island
  • 6Institute for Trauma Recovery, Department of Anesthesiology, University of North Carolina at Chapel Hill
  • 7Department of Biostatistics, Gillings School of Global Public Health, University of North Carolina at Chapel Hill
  • 8Department of Psychology and Neuroscience & Department of Sociology, University of North Carolina at Chapel Hill
  • 9Department of Epidemiology, Mailman School of Public Health, Columbia University, New York, New York
  • 10Department of Epidemiology, Harvard T. H. Chan School of Public Health, Harvard University, Boston, Massachusetts
  • 11Department of Psychiatry, Harvard Medical School, Boston, Massachusetts
  • 12Division of Depression and Anxiety, McLean Hospital, Belmont, Massachusetts
  • 13Department of Emergency Medicine, University of North Carolina at Chapel Hill
JAMA Psychiatry. Published online September 1, 2021. doi:10.1001/jamapsychiatry.2021.2427
Key Points

Question  Is it possible to predict which patients will have posttraumatic stress disorder (PTSD) or major depressive episode (MDE) 3 months after presenting to an emergency department (ED) because of a motor vehicle collision?

Findings  In this cohort study of 1003 patients evaluated in 28 US EDs, a machine learning model restricted to 30 variables found good validated area under the curve and calibration in predicting 3-month PTSD or MDE. The 30% of patients with highest predicted risk accounted for 65% of all 3-month PTSD or MDE.

Meaning  These results suggest that patients at high risk can be identified in the ED for targeting if cost-effective preventive interventions are developed.


Importance  A substantial proportion of the 40 million people in the US who present to emergency departments (EDs) each year after traumatic events develop posttraumatic stress disorder (PTSD) or major depressive episode (MDE). Accurately identifying patients at high risk in the ED would facilitate the targeting of preventive interventions.

Objectives  To develop and validate a prediction tool based on ED reports after a motor vehicle collision to predict PTSD or MDE 3 months later.

Design, Setting, and Participants  The Advancing Understanding of Recovery After Trauma (AURORA) study is a longitudinal study that examined adverse posttraumatic neuropsychiatric sequalae among patients who presented to 28 US urban EDs in the immediate aftermath of a traumatic experience. Enrollment began on September 25, 2017. The 1003 patients considered in this diagnostic/prognostic report completed 3-month assessments by January 31, 2020. Each patient received a baseline ED assessment along with follow-up self-report surveys 2 weeks, 8 weeks, and 3 months later. An ensemble machine learning method was used to predict 3-month PTSD or MDE from baseline information. Data analysis was performed from November 1, 2020, to May 31, 2021.

Main Outcomes and Measures  The PTSD Checklist for DSM-5 was used to assess PTSD and the Patient Reported Outcomes Measurement Information System Depression Short-Form 8b to assess MDE.

Results  A total of 1003 patients (median [interquartile range] age, 34.5 [24-43] years; 715 [weighted 67.9%] female; 100 [weighted 10.7%] Hispanic, 537 [weighted 52.7%] non-Hispanic Black, 324 [weighted 32.2%] non-Hispanic White, and 42 [weighted 4.4%] of non-Hispanic other race or ethnicity were included in this study. A total of 274 patients (weighted 26.6%) met criteria for 3-month PTSD or MDE. An ensemble machine learning model restricted to 30 predictors estimated in a training sample (patients from the Northeast or Midwest) had good prediction accuracy (mean [SE] area under the curve [AUC], 0.815 [0.031]) and calibration (mean [SE] integrated calibration index, 0.040 [0.002]; mean [SE] expected calibration error, 0.039 [0.002]) in an independent test sample (patients from the South). Patients in the top 30% of predicted risk accounted for 65% of all 3-month PTSD or MDE, with a mean (SE) positive predictive value of 58.2% (6.4%) among these patients at high risk. The model had good consistency across regions of the country in terms of both AUC (mean [SE], 0.789 [0.025] using the Northeast as the test sample and 0.809 [0.023] using the Midwest as the test sample) and calibration (mean [SE] integrated calibration index, 0.048 [0.003] using the Northeast as the test sample and 0.024 [0.001] using the Midwest as the test sample; mean [SE] expected calibration error, 0.034 [0.003] using the Northeast as the test sample and 0.025 [0.001] using the Midwest as the test sample). The most important predictors in terms of Shapley Additive Explanations values were symptoms of anxiety sensitivity and depressive disposition, psychological distress in the 30 days before motor vehicle collision, and peritraumatic psychosomatic symptoms.

Conclusions and Relevance  The results of this study suggest that a short set of questions feasible to administer in an ED can predict 3-month PTSD or MDE with good AUC, calibration, and geographic consistency. Patients at high risk can be identified in the ED for targeting if cost-effective preventive interventions are developed.

Limit 200 characters
Limit 25 characters
Conflicts of Interest Disclosure

Identify all potential conflicts of interest that might be relevant to your comment.

Conflicts of interest comprise financial interests, activities, and relationships within the past 3 years including but not limited to employment, affiliation, grants or funding, consultancies, honoraria or payment, speaker's bureaus, stock ownership or options, expert testimony, royalties, donation of medical equipment, or patents planned, pending, or issued.

Err on the side of full disclosure.

If you have no conflicts of interest, check "No potential conflicts of interest" in the box below. The information will be posted with your response.

Not all submitted comments are published. Please see our commenting policy for details.

Limit 140 characters
Limit 3600 characters or approximately 600 words
    1 Comment for this article
    Suggestions of new questions about prediction of PTSD or MDE
    Sebastian Salim, MD Psychoanalyst | Professor at Faculty of Medicine - Universidade Federal de Minas Gerais
    I congratulate the authors for the importance and quality of their paper. I would like to suggest two questions regarding emergency centers protocols applied to predict 3-month posttraumatic stress disorder (PTSD) and major depression (MDE) after a motor vehicle collision.

    First question: if during the traumatic event, the victim felt a death sensation, which is a central element mentioned in DSM-5?

    Second: if the victim has autistic traits in his psychological features?

    These suggestions are based on interdisciplinary studies (psychiatry, psychanalysis, ontogenesis, phylogenesis, animal compared psychology, and neurobiology studies on implicit memory) and my clinical practice
    with PTSD or MDE patients. These allowed me to establish an etiology and to observe that there is necessarily a predisposition to the development of these disorders.

    I developed a hypothesis for these disorders’ etiology connecting a fetal or newborn trauma with death sensation and two phylogenetic defenses triggered to maintain life and to auto appease the trauma victim. The first response is based on the reduction of oxygen consumption and absorption by the cells to preserve its main functions, as Blackstone et al. (2005) presented. The second is based on the auto-generation of sensorial sensations between hard and smooth objects of the own body over its mucosa and skin, as Tustin (1990) studies about psychogenic autism. Moreover, if the fetus or newborn is not assisted by a "sufficient good mother", as described by Winnicott (1962), they may become held on this response that is the core of predisposition and etiology of autism. Generally, they become insufficient for personal, social, and professional life and are commonly diagnosed as depressive patients.

    In case of a traumatic incident at an older age, the victim returns to this previously mentioned metabolic state. I name this biological return as “somatic regression”. This is described in my book “The Body as a Subject of Psychoanalysis”, Editora Artesã, published in 2019.