{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T07:05:09Z","timestamp":1791270309829,"version":"4.1.0"},"reference-count":48,"publisher":"American Medical Association (AMA)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"\n Importance<\/jats:title>\n Military deployment involves significant risk for life-threatening experiences that can lead to posttraumatic stress disorder (PTSD). Accurate predeployment prediction of PTSD risk may facilitate the development of targeted intervention strategies to enhance resilience.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To develop and validate a machine learning (ML) model to predict postdeployment PTSD.<\/jats:p>\n <\/jats:sec>\n \n Design, Setting, and Participants<\/jats:title>\n This diagnostic\/prognostic study included 4771 soldiers from 3 US Army brigade combat teams who completed assessments between January 9, 2012, and May 1, 2014. Predeployment assessments occurred 1 to 2 months before deployment to Afghanistan, and follow-up assessments occurred approximately 3 and 9 months post deployment. Machine learning models to predict postdeployment PTSD were developed in the first 2 recruited cohorts using as many as 801 predeployment predictors from comprehensive self-report assessments. In the development phase, cross-validated performance metrics and predictor parsimony were considered to select an optimal model. Next, the selected model\u2019s performance was evaluated with area under the receiver operating characteristics curve and expected calibration error in a temporally and geographically distinct cohort. Data analyses were performed from August 1 to November 30, 2022.<\/jats:p>\n <\/jats:sec>\n \n Main Outcomes and Measures<\/jats:title>\n Posttraumatic stress disorder diagnosis was assessed by clinically calibrated self-report measures. Participants were weighted in all analyses to address potential biases related to cohort selection and follow-up nonresponse.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n This study included 4771 participants (mean [SD] age, 26.9 [6.2] years), 4440 (94.7%) of whom were men. In terms of race and ethnicity, 144 participants (2.8%) identified as American Indian or Alaska Native, 242 (4.8%) as Asian, 556 (13.3%) as Black or African American, 885 (18.3%) as Hispanic, 106 (2.1%) as Native Hawaiian or other Pacific Islander, 3474 (72.2%) as White, and 430 (8.9%) as other or unknown race or ethnicity; participants could identify as of more than 1 race or ethnicity. A total of 746 participants (15.4%) met PTSD criteria post deployment. In the development phase, models had comparable performance (log loss range, 0.372-0.375; area under the curve range, 0.75-0.76). A gradient-boosting machine with 58 core predictors was selected over an elastic net with 196 predictors and a stacked ensemble of ML models with 801 predictors. In the independent test cohort, the gradient-boosting machine had an area under the curve\u2009of\u20090.74 (95% CI, 0.71-0.77) and low expected calibration error\u2009of 0.032 (95% CI, 0.020-0.046). Approximately one-third of participants with the highest risk accounted for 62.4% (95% CI, 56.5%-67.9%) of the PTSD cases. Core predictors cut across 17 distinct domains: stressful experiences, social network, substance use, childhood or adolescence, unit experiences, health, injuries, irritability or anger, personality, emotional problems, resilience, treatment, anxiety, attention or concentration, family history, mood, and religion.<\/jats:p>\n <\/jats:sec>\n \n Conclusions and Relevance<\/jats:title>\n In this diagnostic\/prognostic study of US Army soldiers, an ML model was developed to predict postdeployment PTSD risk with self-reported information collected before deployment. The optimal model showed good performance in a temporally and geographically distinct validation sample. These results indicate that predeployment stratification of PTSD risk is feasible and may facilitate the development of targeted prevention and early intervention strategies.<\/jats:p>\n <\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2023.21273","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T11:31:38Z","timestamp":1688124698000},"page":"e2321273","source":"Crossref","is-referenced-by-count":33,"title":["Development and Validation of a Machine Learning Prediction Model of Posttraumatic Stress Disorder After Military Deployment"],"prefix":"10.1001","volume":"6","author":[{"given":"Santiago","family":"Papini","sequence":"first","affiliation":[{"name":"Department of Psychiatry, University of California, San Diego, La Jolla"},{"name":"Division of Research, Kaiser Permanente Northern California, Oakland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sonya B.","family":"Norman","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, University of California, San Diego, La Jolla"},{"name":"National Center for PTSD, White River Junction, Vermont"},{"name":"Veterans Affairs Center of Excellence for Stress and Mental Health, San Diego, California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Campbell-Sills","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, University of California, San Diego, La Jolla"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoying","family":"Sun","sequence":"additional","affiliation":[{"name":"Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"He","sequence":"additional","affiliation":[{"name":"Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronald C.","family":"Kessler","sequence":"additional","affiliation":[{"name":"Department of Health Care Policy, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert J.","family":"Ursano","sequence":"additional","affiliation":[{"name":"Center for the Study of Traumatic Stress, Department of Psychiatry, Uniformed Services University of the Health Sciences, Bethesda, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sonia","family":"Jain","sequence":"additional","affiliation":[{"name":"Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Murray B.","family":"Stein","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, University of California, San Diego, La Jolla"},{"name":"Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla"},{"name":"Psychiatry Service, Veterans Affairs San Diego Healthcare System, San Diego, California"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2023,6,30]]},"reference":[{"issue":"3","key":"zoi230627r1","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.cpr.2014.03.002","article-title":"Remission from post-traumatic stress disorder in adults: a systematic review and meta-analysis of long term outcome studies.","volume":"34","author":"Morina","year":"2014","journal-title":"Clin Psychol Rev"},{"key":"zoi230627r2","doi-asserted-by":"publisher","DOI":"10.1037\/tra0001149","article-title":"PTSD, depression, and suicidality among survivors of childhood sexual trauma (CST), military sexual trauma (MST), and sexual revictimization (CST + MST).","author":"Baca","year":"2021","journal-title":"Psychol Trauma"},{"key":"zoi230627r3","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1016\/j.neubiorev.2021.05.022","article-title":"A unifying translational framework to advance treatment research for comorbid PTSD and substance use disorders.","volume":"127","author":"Hien","year":"2021","journal-title":"Neurosci Biobehav Rev"},{"issue":"2","key":"zoi230627r4","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1111\/sltb.v52.2","article-title":"Risk factors for suicide attempts among US military veterans: a 7-year population-based, longitudinal cohort study.","volume":"52","author":"Nichter","year":"2022","journal-title":"Suicide Life Threat Behav"},{"issue":"7","key":"zoi230627r5","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1037\/tra0001121","article-title":"Advancements in the understanding of PTSD and suicide risk: introduction to a special section.","volume":"13","author":"Stanley","year":"2021","journal-title":"Psychol Trauma"},{"issue":"1","key":"zoi230627r6","doi-asserted-by":"publisher","DOI":"10.1080\/20008198.2020.1824381","article-title":"Prevention and treatment of PTSD: the current evidence base.","volume":"12","author":"Bisson","year":"2021","journal-title":"Eur J Psychotraumatol"},{"key":"zoi230627r7","doi-asserted-by":"publisher","first-page":"29715","DOI":"10.3402\/ejpt.v7.29715","article-title":"Prevention and public health approaches to trauma and traumatic stress: a rationale and a call to action.","volume":"7","author":"Magruder","year":"2016","journal-title":"Eur J Psychotraumatol"},{"key":"zoi230627r8","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.neubiorev.2019.09.013","article-title":"Risk factors for posttraumatic stress disorder: an umbrella review of systematic reviews and meta-analyses.","volume":"107","author":"Tortella-Feliu","year":"2019","journal-title":"Neurosci Biobehav Rev"},{"issue":"2","key":"zoi230627r9","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1002\/jts.2019.32.issue-2","article-title":"Machine learning for prediction of posttraumatic stress and resilience following trauma: an overview of basic concepts and recent advances.","volume":"32","author":"Schultebraucks","year":"2019","journal-title":"J Trauma Stress"},{"issue":"4","key":"zoi230627r10","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1027\/1016-9040\/a000423","article-title":"Artificial intelligence and posttraumatic stress disorder (PTSD): an overview of advances in research and emerging clinical applications.","volume":"25","author":"Malgaroli","year":"2020","journal-title":"Eur Psychol"},{"key":"zoi230627r11","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.jpsychires.2019.12.001","article-title":"The use of machine learning techniques in trauma-related disorders: a systematic review.","volume":"121","author":"Ramos-Lima","year":"2020","journal-title":"J Psychiatr Res"},{"key":"zoi230627r12","doi-asserted-by":"publisher","DOI":"10.1016\/j.expneurol.2020.113526","article-title":"The opportunities and challenges of machine learning in the acute care setting for precision prevention of posttraumatic stress sequelae.","volume":"336","author":"Schultebraucks","year":"2021","journal-title":"Exp Neurol"},{"key":"zoi230627r13","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.jad.2015.05.057","article-title":"Early identification of posttraumatic stress following military deployment: application of machine learning methods to a prospective study of Danish soldiers.","volume":"184","author":"Karstoft","year":"2015","journal-title":"J Affect Disord"},{"issue":"9","key":"zoi230627r14","doi-asserted-by":"publisher","first-page":"5011","DOI":"10.1038\/s41380-020-0789-2","article-title":"Pre-deployment risk factors for PTSD in active-duty personnel deployed to Afghanistan: a machine-learning approach for analyzing multivariate predictors.","volume":"26","author":"Schultebraucks","year":"2021","journal-title":"Mol Psychiatry"},{"key":"zoi230627r15","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2020.113515","article-title":"Using machine learning to predict suicide attempts in military personnel.","volume":"294","author":"Rozek","year":"2020","journal-title":"Psychiatry Res"},{"issue":"3","key":"zoi230627r16","doi-asserted-by":"publisher","first-page":"1631","DOI":"10.1038\/s41380-021-01423-4","article-title":"Predicting suicide attempts among US Army soldiers after leaving active duty using information available before leaving active duty: results from the Study to Assess Risk and Resilience in Servicemembers\u2013Longitudinal Study (STARRS-LS).","volume":"27","author":"Stanley","year":"2022","journal-title":"Mol Psychiatry"},{"key":"zoi230627r17","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/j.jpsychires.2019.12.003","article-title":"Pre-deployment predictors of suicide attempt during and after combat deployment: results from the Army Study to Assess Risk and Resilience in Servicemembers.","volume":"121","author":"Zuromski","year":"2020","journal-title":"J Psychiatr Res"},{"issue":"1","key":"zoi230627r18","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1001\/jamapsychiatry.2014.1754","article-title":"Predicting suicides after psychiatric hospitalization in US Army soldiers: the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS).","volume":"72","author":"Kessler","year":"2015","journal-title":"JAMA Psychiatry"},{"issue":"3","key":"zoi230627r19","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1176\/appi.prcp.20200031","article-title":"A machine learning approach to predicting new-onset depression in a military population.","volume":"3","author":"Sampson","year":"2021","journal-title":"Psychiatr Res Clin Pract"},{"key":"zoi230627r20","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.jad.2021.04.010","article-title":"Forecasting military mental health in a complete sample of Danish military personnel deployed between 1992-2013.","volume":"288","author":"Nissen","year":"2021","journal-title":"J Affect Disord"},{"key":"zoi230627r21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpr.2021.102100","article-title":"Pathways to mental health care in active military populations across the Five-Eyes nations: an integrated perspective.","volume":"91","author":"Fikretoglu","year":"2022","journal-title":"Clin Psychol Rev"},{"issue":"4","key":"zoi230627r22","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1002\/mpr.1401","article-title":"Design of the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS).","volume":"22","author":"Kessler","year":"2013","journal-title":"Int J Methods Psychiatr Res"},{"issue":"2","key":"zoi230627r23","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1521\/psyc.2014.77.2.107","article-title":"The Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS).","volume":"77","author":"Ursano","year":"2014","journal-title":"Psychiatry"},{"issue":"2","key":"zoi230627r24","doi-asserted-by":"publisher","DOI":"10.1093\/sleep\/zsy229","article-title":"Pre-deployment insomnia is associated with post-deployment post-traumatic stress disorder and suicidal ideation in US Army soldiers.","volume":"42","author":"Wang","year":"2019","journal-title":"Sleep"},{"issue":"11","key":"zoi230627r25","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1176\/appi.ajp.2015.14121572","article-title":"Prospective longitudinal evaluation of the effect of deployment-acquired traumatic brain injury on posttraumatic stress and related disorders: results from the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS).","volume":"172","author":"Stein","year":"2015","journal-title":"Am J Psychiatry"},{"issue":"11","key":"zoi230627r26","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1002\/da.2018.35.issue-11","article-title":"Predeployment predictors of psychiatric disorder-symptoms and interpersonal violence during combat deployment.","volume":"35","author":"Rosellini","year":"2018","journal-title":"Depress Anxiety"},{"key":"zoi230627r27","doi-asserted-by":"publisher","first-page":"i189","DOI":"10.1136\/bmj.i189","article-title":"Inverse probability weighting.","volume":"352","author":"Mansournia","year":"2016","journal-title":"BMJ"},{"issue":"3","key":"zoi230627r28","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1177\/0962280210395740","article-title":"Review of inverse probability weighting for dealing with missing data.","volume":"22","author":"Seaman","year":"2013","journal-title":"Stat Methods Med Res"},{"issue":"4","key":"zoi230627r29","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1002\/mpr.1399","article-title":"Response bias, weighting adjustments, and design effects in the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS).","volume":"22","author":"Kessler","year":"2013","journal-title":"Int J Methods Psychiatr Res"},{"issue":"4","key":"zoi230627r31","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1002\/mpr.1398","article-title":"Clinical reappraisal of the Composite International Diagnostic Interview Screening Scales (CIDI-SC) in the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS).","volume":"22","author":"Kessler","year":"2013","journal-title":"Int J Methods Psychiatr Res"},{"issue":"2","key":"zoi230627r32","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1002\/(ISSN)1557-0657","article-title":"The World Mental Health (WMH) survey initiative version of the World Health Organization (WHO) Composite International Diagnostic Interview (CIDI).","volume":"13","author":"Kessler","year":"2004","journal-title":"Int J Methods Psychiatr Res"},{"issue":"12","key":"zoi230627r33","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.1176\/appi.ajp.2011.10111704","article-title":"The Columbia-Suicide Severity Rating Scale: initial validity and internal consistency findings from three multisite studies with adolescents and adults.","volume":"168","author":"Posner","year":"2011","journal-title":"Am J Psychiatry"},{"issue":"2","key":"zoi230627r34","doi-asserted-by":"publisher","first-page":"233","DOI":"10.4088\/JCP.09r05072blu","article-title":"Acute stress disorder as a predictor of posttraumatic stress disorder: a systematic review.","volume":"72","author":"Bryant","year":"2011","journal-title":"J Clin Psychiatry"},{"issue":"12","key":"zoi230627r35","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s11920-018-0976-x","article-title":"The current evidence for acute stress disorder.","volume":"20","author":"Bryant","year":"2018","journal-title":"Curr Psychiatry Rep"},{"issue":"2","key":"zoi230627r36","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1111\/acps.v145.2","article-title":"Time course of symptoms in posttraumatic stress disorder with delayed expression: a systematic review.","volume":"145","author":"Bonde","year":"2022","journal-title":"Acta Psychiatr Scand"},{"issue":"11","key":"zoi230627r37","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.4088\/JCP.08r04484","article-title":"Delayed posttraumatic stress disorder: systematic review, meta-analysis, and meta-regression analysis of prospective studies.","volume":"70","author":"Smid","year":"2009","journal-title":"J Clin Psychiatry"},{"issue":"7","key":"zoi230627r38","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1002\/da.v28.7","article-title":"Synthesis of the psychometric properties of the PTSD checklist (PCL) military, civilian, and specific versions.","volume":"28","author":"Wilkins","year":"2011","journal-title":"Depress Anxiety"},{"issue":"5","key":"zoi230627r40","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/s10654-018-0390-z","article-title":"Stacked generalization: an introduction to super learning.","volume":"33","author":"Naimi","year":"2018","journal-title":"Eur J Epidemiol"},{"issue":"1","key":"zoi230627r44","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/s10994-021-06121-4","article-title":"InfoGram and admissible machine learning.","volume":"111","author":"Mukhopadhyay","year":"2022","journal-title":"Mach Learn"},{"issue":"9","key":"zoi230627r45","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0184604","article-title":"Meaningless comparisons lead to false optimism in medical machine learning.","volume":"12","author":"DeMasi","year":"2017","journal-title":"PLoS One"},{"issue":"11","key":"zoi230627r46","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1001\/jamapsychiatry.2021.2427","article-title":"Development and validation of a model to predict posttraumatic stress disorder and major depression after a motor vehicle collision.","volume":"78","author":"Ziobrowski","year":"2021","journal-title":"JAMA Psychiatry"},{"issue":"12","key":"zoi230627r48","doi-asserted-by":"publisher","first-page":"866","DOI":"10.7326\/M18-1990","article-title":"Ensuring fairness in machine learning to advance health equity.","volume":"169","author":"Rajkomar","year":"2018","journal-title":"Ann Intern Med"},{"key":"zoi230627r43","first-page":"785","author":"Chen","year":"2016"},{"key":"zoi230627r30","unstructured":"Army STARRS and STARRS-LS research instruments (questionnaires). Accessed November 1, 2022. https:\/\/starrs-ls.org\/#\/page\/instruments"},{"key":"zoi230627r39","unstructured":"R Core Team. R: a language and environment for statistical computing. 2013. Accessed June 12, 2023. http:\/\/www.r-project.org\/"},{"key":"zoi230627r41","unstructured":"LeDell? E, Poirier? S. H2O AutoML: scalable automatic machine learning. Seventh ICML Workshop on Automated Machine Learning 2020. Accessed June 12, 2023. https:\/\/www.automl.org\/wp-content\/uploads\/2020\/07\/AutoML_2020_paper_61.pdf"},{"key":"zoi230627r42","unstructured":"LeDell? E, Gill? N, Aiello? S, . H2O: R interface for the \u201cH2O\u201d Scalable Machine Learning Platform. R package, version 3.40.0.1. February 28, 2023. Accessed June 12, 2023. https:\/\/cran.r-project.org\/web\/packages\/h2o\/h2o.pdf"},{"key":"zoi230627r47","unstructured":"Barocas? S, Hardt? M, Narayanan? A. Fairness and machine learning: limitations and opportunities. Accessed July 20, 2022. https:\/\/fairmlbook.org\/"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2806713\/papini_2023_oi_230627_1687536381.31721.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T11:31:43Z","timestamp":1688124703000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2806713"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,30]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.21273","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,30]]}}}