Molecular Medicine; Psychiatry and Mental Health; Neuroscience (miscellaneous); Biological Psychiatry
Abstract :
[en] In recent years, the application of machine learning (ML) techniques in research on the prediction of post-traumatic stress disorder (PTSD) has increased. However, concerns regarding the clinical relevance and generalizability of ML findings hamper their implementation by clinicians and researchers. Here in this systematic review we examined (1) the extent to which pre-, peri- and post-traumatic risk factors identified using ML approaches coincide with the theoretical understanding of the disorder; (2) whether new insights were gained through ML techniques; and (3) whether ML findings, combined with previous research, enable an integrative model of PTSD risk encompassing both predictor categories and their theoretical relevance. We reviewed ML studies on PTSD risk factors in PubMed, Web of Science and Scopus. Studies were included if they specified when predictors and PTSD symptoms were collected in temporal relation to the traumatic event. A total of 30 studies with 12,908 participants (mean age 36.5 years) were included. After extracting the 15 most important predictors from all studies, we categorized them into pre-, peri- and post-trauma exposure predictors and examined their associations with established theoretical models of PTSD. Many studies exhibited a risk of bias, assessed using the prediction model risk of bias assessment tool (PROBAST). However, we found overlaps in identified predictors across studies, a concordance between data-driven results and theory-driven research, and underexplored predictors identified through ML. We propose an integrative model of PTSD risk that incorporates both data-driven and theory-driven findings and discuss future directions. We emphasize the importance of standards on how to apply and report ML approaches for mental health.
Blekic, Wivine ; Université de Mons - UMONS > Faculté de Psychologie et des Sciences de l'Education > Service de Psychologie cognitive et Neuropsychologie ; Univ. Lille, Inserm, CHU Lille, U1172-LilNCog-Lille Neuroscience & Cognition, Lille, France
D'Hondt, Fabien ; Univ. Lille, Inserm, CHU Lille, U1172-LilNCog-Lille Neuroscience & Cognition, Lille, France ; Centre national de ressources et de résilience Lille-Paris, Lille, France
Shalev, Arieh Y; Department of Psychiatry, NYU Grossman School of Medicine, New York, NY, USA
Schultebraucks, Katharina ; Department of Psychiatry, NYU Grossman School of Medicine, New York, NY, USA ; Department of Population Health, NYU Grossman School of Medicine, New York, NY, USA
Language :
English
Title :
A systematic review of machine learning findings in PTSD and their relationships with theoretical models.
R550 - Institut des Sciences et Technologies de la Santé
Funders :
U.S. Department of Health & Human Services | NIH | National Institute of Mental Health U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute
Funding text :
K.S. received support from the National Institute of Mental Health (R01MH129856) and the National Heart, Lung, and Blood Institute (R01HL156134). The funders had no role in study design, data collection and analysis, decision to publish or preparation of the manuscript.
C. Benjet et al. The epidemiology of traumatic event exposure worldwide: results from the World Mental Health Survey Consortium Psychol. Med. 46 327 343 26511595 10.1017/S0033291715001981
A. Shalev I. Liberzon C. Marmar Post-traumatic stress disorder N. Engl. J. Med. 376 2459 2469 28636846 10.1056/NEJMra1612499
V. Oosterbaan M.L.V. Covers I.A.E. Bicanic R.J.C. Huntjens A. De Jongh Do early interventions prevent PTSD? A systematic review and meta-analysis of the safety and efficacy of early interventions after sexual assault Eur. J. Psychotraumatol. 10 1682932 31762949 6853210 10.1080/20008198.2019.1682932
K.S. Kendler Toward a philosophical structure for psychiatry Am. J. Psychiatry 162 433 440 15741457 10.1176/appi.ajp.162.3.433
Heim, C., Schultebraucks, K., Marmar, C. R. & Nemeroff, C. B. in Post-traumatic Stress Disorder (eds Nemeroff, C. B. & Marmar, C.) 331 (Oxford Medicine Online, 2018).
D. Borsboom A network theory of mental disorders World Psychiatry 16 5 13 28127906 5269502 10.1002/wps.20375
K. Schultebraucks I.R. Galatzer‐Levy Machine learning for prediction of posttraumatic stress and resilience following trauma: An overview of basic concepts and recent advances J. Trauma. Stress 32 215 225 30892723 10.1002/jts.22384
Kuhn, M. & Johnson, K. Applied Predictive Modeling Vol. 810 (Springer, 2013).
Y. Wu K. Mao L. Dennett Y. Zhang J. Chen Systematic review of machine learning in PTSD studies for automated diagnosis evaluation npj Mental Health Res. 2 16 10.1038/s44184-023-00035-w
Mentis, A.-F. A., Lee, D. & Roussos, P. Applications of artificial intelligence—machine learning for detection of stress: a critical overview. Mol. Psychiatry https://doi.org/10.1038/s41380-023-02047-6 (2023).
L.F. Ramos-Lima V. Waikamp T. Antonelli-Salgado I.C. Passos L.H.M. Freitas The use of machine learning techniques in trauma-related disorders: a systematic review J. Psychiatr. Res. 121 159 172 31830722 10.1016/j.jpsychires.2019.12.001
S. Papini et al. Development and validation of a machine learning model using electronic health records to predict trauma- and stressor-related psychiatric disorders after hospitalization with sepsis Transl. Psychiatry 13 38114475 10730505 10.1038/s41398-023-02699-6 400
J. Watson et al. Overcoming barriers to the adoption and implementation of predictive modeling and machine learning in clinical care: what can we learn from US academic medical centers? JAMIA Open 3 167 172 32734155 7382631 10.1093/jamiaopen/ooz046
Nijdam, M. J. & Wittmann, L. In Evidence-Based Treatments for Trauma-Related Psychological Disorders: A Practical Guide for Clinicians (eds. Schnyder, U. & Cloitre, M.) 41–63 (Springer Nature, 2022).
L.P. Strachan G. Paulik P.M. McEvoy A narrative review of psychological theories of post‐traumatic stress disorder, voice hearing, and other psychotic symptoms Clin. Psychol. Psychother. 29 1791 1811 35578567 10084244 10.1002/cpp.2754
A. Ehlers D.M. Clark A cognitive model of posttraumatic stress disorder Behav. Res. Ther. 38 319 345 10761279 10.1016/S0005-7967(99)00123-0
C.R. Brewin T. Dalgleish S. Joseph A dual representation theory of posttraumatic stress disorder Psychol. Rev. 103 670 8888651 10.1037/0033-295X.103.4.670
T. Dalgleish Cognitive approaches to posttraumatic stress disorder: the evolution of multirepresentational theorizing Psychol. Bull. 130 228 260 14979771 10.1037/0033-2909.130.2.228
Foa, E. B., Huppert, J. D. & Cahill, S. In Pathological Anxiety: Emotional Processing in Etiology and Treatment (ed. Rothbaum, B. O.) 3–24 (Guilford, 2006).
C. Sharp P. Fonagy J.G. Allen Posttraumatic stress disorder: a social‐cognitive perspective Clin. Psychol. Sci. Pract. 19 229 240 10.1111/cpsp.12002
S.C. Hayes J.B. Luoma F.W. Bond A. Masuda J. Lillis Acceptance and commitment therapy: model, processes and outcomes Behav. Res. Ther. 44 1 25 16300724 10.1016/j.brat.2005.06.006
S.C. Hayes M.E. Levin J. Plumb-Vilardaga J.L. Villatte J. Pistorello Acceptance and commitment therapy and contextual behavioral science: examining the progress of a distinctive model of behavioral and cognitive therapy Behav. Ther. 44 180 198 23611068 10.1016/j.beth.2009.08.002
J.J. Gross Emotion regulation: current status and future prospects Psychol. Inquiry 26 1 26 10.1080/1047840X.2014.940781
Wells, A. Metacognitive Therapy for Anxiety and Depression (Guilford, 2009).
K. Schultebraucks V. Yadav A.Y. Shalev G.A. Bonanno I.R. Galatzer-Levy Deep learning-based classification of posttraumatic stress disorder and depression following trauma utilizing visual and auditory markers of arousal and mood Psychol. Med. 52 957 967 32744201 10.1017/S0033291720002718
M.S. Breen K.G.F. Thomas D.S. Baldwin G. Lipinska Modelling PTSD diagnosis using sleep, memory, and adrenergic metabolites: an exploratory machine‐learning study Hum. Psychopharmacol. Clin. Exp. 34 e2691 10.1002/hup.2691
Q. Gong et al. Using structural neuroanatomy to identify trauma survivors with and without post-traumatic stress disorder at the individual level Psychol. Med. 44 195 203 23551879 10.1017/S0033291713000561
A. Köbach et al. Violent offending promotes appetitive aggression rather than posttraumatic stress—a replication study with burundian ex-combatants Front. Psychol. 6 1755 26696913 4672083 10.3389/fpsyg.2015.01755
P.-F. Kuan et al. Metabolomics analysis of post-traumatic stress disorder symptoms in World Trade Center responders Transl. Psychiatry 12 35484105 9050707 10.1038/s41398-022-01940-y 174
S. Malan-Muller et al. Exploring the relationship between the gut microbiome and mental health outcomes in a posttraumatic stress disorder cohort relative to trauma-exposed controls Eur. Neuropsychopharmacol. 56 24 38 34923209 10.1016/j.euroneuro.2021.11.009
Y.-J. Su Prevalence and predictors of posttraumatic stress disorder and depressive symptoms among burn survivors two years after the 2015 Formosa Fun Coast Water Park explosion in Taiwan Eur. J. Psychotraumatol. 9 30220984 6136356 10.1080/20008198.2018.1512263 1512263
X. Suo et al. Individualized prediction of PTSD symptom severity in trauma survivors from whole-brain resting-state functional connectivity Front. Behav. Neurosci. 14 563152 33408617 7779396 10.3389/fnbeh.2020.563152
Q. Zhang et al. Multimodal MRI-based classification of trauma survivors with and without post-traumatic stress disorder Front. Neurosci. 10 292 27445664 4919361 10.3389/fnins.2016.00292
Q. Gong et al. Quantitative prediction of individual psychopathology in trauma survivors using resting-state fMRI Neuropsychopharmacology 39 681 687 24064470 10.1038/npp.2013.251
Z. Zhu et al. Combining deep learning and graph-theoretic brain features to detect posttraumatic stress disorder at the individual level Diagnostics 11 1416 34441350 8391111 10.3390/diagnostics11081416
Y. Zhang et al. Aberrant white matter microstructure evaluation by automated fiber quantification in typhoon-related post-traumatic stress disorder Brain Imaging Behav. 17 213 222 36576688 10.1007/s11682-022-00755-1
I.R. Galatzer-Levy K.-I. Karstoft A. Statnikov A.Y. Shalev Quantitative forecasting of PTSD from early trauma responses: a machine learning application J. Psychiatr. Res. 59 68 76 25260752 4252741 10.1016/j.jpsychires.2014.08.017
I.R. Galatzer-Levy S. Ma A. Statnikov R. Yehuda A.Y. Shalev Utilization of machine learning for prediction of post-traumatic stress: a re-examination of cortisol in the prediction and pathways to non-remitting PTSD Transl. Psychiatry 7 10.1038/tp.2017.38 e1070–e1070
R. Hinrichs et al. Increased skin conductance response in the immediate aftermath of trauma predicts PTSD risk Chronic Stress 3 10.1177/2470547019844441 247054701984444
K.-I. Karstoft I.R. Galatzer-Levy A. Statnikov Z. Li A.Y. Shalev Bridging a translational gap: using machine learning to improve the prediction of PTSD BMC Psychiatry 15 25886446 4360940 10.1186/s12888-015-0399-8 30
Kim, R. et al. Derivation and validation of risk prediction for posttraumatic stress symptoms following trauma exposure. Psychol. Med.https://doi.org/10.1017/S003329172200191X (2022).
S. Papini et al. Ensemble machine learning prediction of posttraumatic stress disorder screening status after emergency room hospitalization J. Anxiety Disord. 60 35 42 30419537 6777842 10.1016/j.janxdis.2018.10.004
K. Schultebraucks et al. Forecasting individual risk for long-term posttraumatic stress disorder in emergency medical settings using biomedical data: a machine learning multicenter cohort study Neurobiol. Stress 14 33553513 7843920 10.1016/j.ynstr.2021.100297 100297
K. Schultebraucks et al. A validated predictive algorithm of post-traumatic stress course following emergency department admission after a traumatic stressor Nat. Med. 26 1084 1088 32632194 10.1038/s41591-020-0951-z
S. Wshah C. Skalka M. Price Predicting posttraumatic stress disorder risk: a machine learning approach JMIR Ment. Health 6 31333201 6681635 10.2196/13946 e13946
M. Augsburger I.R. Galatzer-Levy Utilization of machine learning to test the impact of cognitive processing and emotion recognition on the development of PTSD following trauma exposure BMC Psychiatry 20 32576245 7310383 10.1186/s12888-020-02728-4 325
M.C. Morris et al. Predicting posttraumatic stress disorder among survivors of recent interpersonal violence J. Interpers. Viol. 37 NP11460 NP11489 10.1177/0886260520978195
K. Schultebraucks et al. Assessment of early neurocognitive functioning increases the accuracy of predicting chronic PTSD risk Mol. Psychiatry 27 2247 2254 35082440 11129320 10.1038/s41380-022-01445-6
K.-I. Karstoft I. Tsamardinos K. Eskelund S.B. Andersen L.R. Nissen Applicability of an automated model and parameter selection in the prediction of screening-level PTSD in danish soldiers following deployment: development study of transferable predictive models using automated machine learning JMIR Med. Inform. 8 e17119 32706722 7407253 10.2196/17119
K. Schultebraucks et al. Pre-deployment risk factors for PTSD in active-duty personnel deployed to Afghanistan: a machine-learning approach for analyzing multivariate predictors Mol. Psychiatry 26 5011 5022 32488126 10.1038/s41380-020-0789-2
K.-I. Karstoft A. Statnikov S.B. Andersen T. Madsen I.R. Galatzer-Levy Early identification of posttraumatic stress following military deployment: application of machine learning methods to a prospective study of Danish soldiers J. Affect. Disord. 184 170 175 26093830 10.1016/j.jad.2015.05.057
S. Rousseau I.S. Polachek T.I. Frenkel A machine learning approach to identifying pregnant women’s risk for persistent post-traumatic stress following childbirth J. Affect. Disord. 296 136 149 34601301 10.1016/j.jad.2021.09.014
S. Papini et al. Development and validation of a machine learning prediction model of posttraumatic stress disorder after military deployment JAMA Netw. Open 6 e2321273–e2321273 10.1001/jamanetworkopen.2023.21273
A.H. Wani et al. The impact of psychopathology, social adversity and stress-relevant DNA methylation on prospective risk for post-traumatic stress: a machine learning approach J. Affect. Disord. 282 894 905 33601733 10.1016/j.jad.2020.12.076
I.R. Galatzer-Levy R.A. Bryant 636,120 ways to have posttraumatic stress disorder Perspect. Psychol. Sci. 8 651 662 26173229 10.1177/1745691613504115
I.R. Galatzer-Levy S.H. Huang G.A. Bonanno Trajectories of resilience and dysfunction following potential trauma: a review and statistical evaluation Clin. Psychol. Rev. 63 41 55 29902711 10.1016/j.cpr.2018.05.008
E.T. Beierl I. Böllinghaus D.M. Clark E. Glucksman A. Ehlers Cognitive paths from trauma to posttraumatic stress disorder: a prospective study of Ehlers and Clark's model in survivors of assaults or road traffic collisions Psychol. Med. 50 2172 2181 31507261 10.1017/S0033291719002253
K.W. Samuelson et al. Predeployment neurocognitive functioning predicts postdeployment posttraumatic stress in Army personnel Neuropsychology 34 276 287 31789568 10.1037/neu0000603
R.A. Bryant A critical review of mechanisms of adaptation to trauma: implications for early interventions for posttraumatic stress disorder Clin. Psychol. Rev. 85 33588312 10.1016/j.cpr.2021.101981 101981
P.R. Zoladz D.M. Diamond Current status on behavioral and biological markers of PTSD: a search for clarity in a conflicting literature Neurosci. Biobehav. Rev. 37 860 895 23567521 10.1016/j.neubiorev.2013.03.024
S. Wilker et al. Genetic variation is associated with PTSD risk and aversive memory: evidence from two trauma-exposed African samples and one healthy European sample Transl Psychiatry 8 30467376 6250662 10.1038/s41398-018-0297-1 251
A.M. Sbisa et al. Potential peripheral biomarkers associated with the emergence and presence of posttraumatic stress disorder symptomatology: a systematic review Psychoneuroendocrinology 147 36308820 10.1016/j.psyneuen.2022.105954 105954
V. Michopoulos S.D. Norrholm T. Jovanovic Diagnostic biomarkers for posttraumatic stress disorder: promising horizons from translational neuroscience research Biol. Psychiatry 78 344 353 25727177 4520791 10.1016/j.biopsych.2015.01.005
S.A. McLean et al. The AURORA Study: a longitudinal, multimodal library of brain biology and function after traumatic stress exposure Mol. Psychiatry 25 283 296 31745239 10.1038/s41380-019-0581-3
J.P. Hayes M.B. VanElzakker L.M. Shin Emotion and cognition interactions in PTSD: a review of neurocognitive and neuroimaging studies Front. Integr. Neurosci. 6 89 23087624 3466464 10.3389/fnint.2012.00089
S. Lee et al. Distinctively different human neurobiological responses after trauma exposure and implications for posttraumatic stress disorder subtyping Mol. Psychiatry 28 2964 2974 36854717 10.1038/s41380-023-01995-3
J. Slatman Bio-psycho-social interaction: an enactive perspective Int. Rev. Psychiatry 33 471 477
G.L. Engel The clinical application of the biopsychosocial model Am. J. Psychiatry 137 535 544 7369396 10.1176/ajp.137.5.535
G. Engel The need for a new medical model: a challenge for biomedicine Science 196 129 136 847460 10.1126/science.847460
C.D. Calhoun et al. The role of social support in coping with psychological trauma: an integrated biopsychosocial model for posttraumatic stress recovery Psychiatr. Q 93 949 970 36199000 9534006 10.1007/s11126-022-10003-w
J.N. Crawford A.M. Talkovsky J.E. Bormann A.J. Lang Targeting hyperarousal: Mantram Repetition Program for PTSD in US veterans Eur. J. Psychotraumatol. 10 1665768 31632617 6781252 10.1080/20008198.2019.1665768
T.L. Schell G.N. Marshall L.H. Jaycox All symptoms are not created equal: the prominent role of hyperarousal in the natural course of posttraumatic psychological distress J. Abnorm. Psychol. 113 189 197 15122939 10.1037/0021-843X.113.2.189
C.J. Ruggero et al. Posttraumatic stress disorder in daily life among World Trade Center responders: temporal symptom cascades J. Psychiatr. Res. 138 240 245 33866052 10.1016/j.jpsychires.2021.04.002
J. Difede M. Olden J. Cukor Evidence-based treatment of post-traumatic stress disorder Annu. Rev. Med. 65 319 332 24422573 10.1146/annurev-med-051812-145438
M.H. Afzali et al. A network approach to the comorbidity between posttraumatic stress disorder and major depressive disorder: the role of overlapping symptoms J. Affect. Disord. 208 490 496 27810269 10.1016/j.jad.2016.10.037
E.I. Fried et al. Replicability and generalizability of posttraumatic stress disorder (PTSD) networks: a cross-cultural multisite study of PTSD symptoms in four trauma patient samples Clin. Psychol. Sci. 6 335 351 29881651 5974702 10.1177/2167702617745092
R.A. Bryant Post‐traumatic stress disorder: a state‐of‐the‐art review of evidence and challenges World Psychiatry 18 259 269 31496089 6732680 10.1002/wps.20656
Bardeen, J. R. In Emotion in Posttraumatic Stress Disorder: Etiology, Assessment, Neurobiology, and Treatment (eds. Tull, M. T. & Kimbrel, N. A.) 311–341 (Elsevier Academic, 2020).
S. Van Liempt M. Van Zuiden H. Westenberg A. Super E. Vermetten Impact of sleep on PTSD symptom development of PTSD symptoms in combat veteerans: a prospective longitudinal cohort study Depress. Anxiety 30 469 474 23389990 10.1002/da.22054
V.I. Spoormaker et al. The neural correlates and temporal sequence of the relationship between shock exposure, disturbed sleep and impaired consolidation of fear extinction J. Psychiatr. Res. 44 1121 1128 20471033 10.1016/j.jpsychires.2010.04.017
Tan, J., Yang, J., Wu, S., Chen, G. & Zhao, J. A critical look at the current train/test split in machine learning. Preprint at https://doi.org/10.48550/arXiv.2106.04525 (2021).
A. Vabalas E. Gowen E. Poliakoff A.J. Casson Machine learning algorithm validation with a limited sample size PLoS ONE 14 31697686 6837442 10.1371/journal.pone.0224365 e0224365
X. Teng et al. Improving radiomic model reliability using robust features from perturbations for head-and-neck carcinoma Front. Oncol. 12 974467 36313629 9614273 10.3389/fonc.2022.974467
M. Malgaroli K. Schultebraucks Artificial intelligence and posttraumatic stress disorder (PTSD) Eur. Psychol. 25 272 282 10.1027/1016-9040/a000423
Steyerberg, E. In Clinical Prediction Models. Statistics for Biology and Health https://doi.org/10.1007/978-0-387-77244-8_2 (Springer, 2009).
A. Bartal K.M. Jagodnik S.J. Chan M.S. Babu S. Dekel Identifying women with postdelivery posttraumatic stress disorder using natural language processing of personal childbirth narratives Am. J. Obstet. Gynecol. MFM 5 100834 36509356 10.1016/j.ajogmf.2022.100834
C. Panigutti et al. Co-design of human-centered, explainable AI for clinical decision support ACM Trans. Interact. Intell. Syst. 13 1 35 10.1145/3587271
D. Moher A. Liberati J. Tetzlaff D. Altman Preferred Reporting Items for Systematic Reviews and Meta-analyses: the PRISMA statement PLoS Med. 6 19621072 2707599 10.1371/journal.pmed.1000097 e1000097
K.G.M. Moons et al. PROBAST: a tool to assess risk of bias and applicability of prediction model studies: explanation and elaboration Ann. Intern. Med. 170 W1 30596876 10.7326/M18-1377
J.J. Gross The extended process model of emotion regulation: elaborations, applications, and future directions Psychol. Inquiry 26 130 137 10.1080/1047840X.2015.989751
A. Wells S. Sembi Metacognitive therapy for PTSD: a core treatment manual Cogn. Behav. Pract. 11 365 377 10.1016/S1077-7229(04)80053-1
M. Garcia N. Bruno S. Grunenwald É. Bui P. Birmes Cortisol et état de stress post-traumatique: Conséquences endocriniennes et métaboliques du stress Corresp. Métab. Hor m. Diabetes Nutr. 16 26 30
I. Fragkaki K. Thomaes M. Sijbrandij Posttraumatic stress disorder under ongoing threat: a review of neurobiological and neuroendocrine findings Eur. J. Psychotraumatol. 7 30915 27511448 10.3402/ejpt.v7.30915
J.S. Stevens et al. Amygdala reactivity and anterior cingulate habituation predict posttraumatic stress disorder symptom maintenance after acute civilian trauma Biol. Psychiatry 81 1023 1029 28117048 10.1016/j.biopsych.2016.11.015
D.G. Andrewes L.M. Jenkins The role of the amygdala and the ventromedial prefrontal cortex in emotional regulation: Implications for post-traumatic stress disorder Neuropsychol. Rev. 29 220 243 30877420 10.1007/s11065-019-09398-4
