Machine learning methods to predict child posttraumatic stress: a proof of concept study.

BACKGROUND: The care of traumatized children would benefit significantly from accurate predictive models for Posttraumatic Stress Disorder (PTSD), using information available around the time of trauma. Machine Learning (ML) computational methods have yielded strong results in recent applications across many diseases and data types, yet they have not been previously applied to childhood PTSD. Since these methods have not been applied to this complex and debilitating disorder, there is a great deal that remains to be learned about their application. The first step is to prove the concept: Can ML methods - as applied in other fields - produce predictive classification models for childhood PTSD? Additionally, we seek to determine if specific variables can be identified - from the aforementioned predictive classification models - with putative causal relations to PTSD. METHODS: ML predictive classification methods - with causal discovery feature selection - were applied to a data set of 163 children hospitalized with an injury and PTSD was determined three months after hospital discharge. At the time of hospitalization, 105 risk factor variables were collected spanning a range of biopsychosocial domains. RESULTS: Seven percent of subjects had a high level of PTSD symptoms. A predictive classification model was discovered with significant predictive accuracy. A predictive model constructed based on subsets of potentially causally relevant features achieves similar predictivity compared to the best predictive model constructed with all variables. Causal Discovery feature selection methods identified 58 variables of which 10 were identified as most stable. CONCLUSIONS: In this first proof-of-concept application of ML methods to predict childhood Posttraumatic Stress we were able to determine both predictive classification models for childhood PTSD and identify several causal variables. This set of techniques has great potential for enhancing the methodological toolkit in the field and future studies should seek to replicate, refine, and extend the results produced in this study.

Innovations in Practice: Preliminary evidence for effective family engagement in treatment for child traumatic stress-trauma systems therapy approach to preventing dropout.

BACKGROUND: This study aimed to obtain preliminary evidence for the extent to which a novel intervention embedded within a systems-oriented treatment model [trauma systems therapy (TST)] engages and retains traumatized children and their families in treatment. METHOD: Twenty youth who had prominent symptoms of posttraumatic stress were randomly assigned to receive TST or care as usual (CAU). RESULTS: At the 3-month assessment, 90% of TST participants were still in treatment, whereas only 10% of CAU participants remained. Within-group analyses of TST participants demonstrated significant reductions in posttraumatic stress and aggression as well as a slight improvement in home safety. CONCLUSIONS: These preliminary findings point to the need to utilize effective engagement approaches to retain traumatized children and their families in treatment.

Mental health progress requires causal diagnostic nosology and scalable causal discovery.

Nine hundred and seventy million individuals across the globe are estimated to carry the burden of a mental disorder. Limited progress has been achieved in alleviating this burden over decades of effort, compared to progress achieved for many other medical disorders. Progress on outcome improvement for all medical disorders, including mental disorders, requires research capable of discovering causality at sufficient scale and speed, and a diagnostic nosology capable of encoding the causal knowledge that is discovered. Accordingly, the field's guiding paradigm limits progress by maintaining: (a) a diagnostic nosology (DSM-5) with a profound lack of causality; (b) a misalignment between mental health etiologic research and nosology; (c) an over-reliance on clinical trials beyond their capabilities; and (d) a limited adoption of newer methods capable of discovering the complex etiology of mental disorders. We detail feasible directions forward, to achieve greater levels of progress on improving outcomes for mental disorders, by: (a) the discovery of knowledge on the complex etiology of mental disorders with application of Causal Data Science methods; and (b) the encoding of the etiological knowledge that is discovered within a causal diagnostic system for mental disorders.

Computational causal discovery for post-traumatic stress in police officers.

This article reports on a study aimed to elucidate the complex etiology of post-traumatic stress (PTS) in a longitudinal cohort of police officers, by applying rigorous computational causal discovery (CCD) methods with observational data. An existing observational data set was used, which comprised a sample of 207 police officers who were recruited upon entry to police academy training. Participants were evaluated on a comprehensive set of clinical, self-report, genetic, neuroendocrine and physiological measures at baseline during academy training and then were re-evaluated at 12 months after training was completed. A data-processing pipeline-the Protocol for Computational Causal Discovery in Psychiatry (PCCDP)-was applied to this data set to determine a causal model for PTS severity. A causal model of 146 variables and 345 bivariate relations was discovered. This model revealed 5 direct causes and 83 causal pathways (of four steps or less) to PTS at 12 months of police service. Direct causes included single-nucleotide polymorphisms (SNPs) for the Histidine Decarboxylase (HDC) and Mineralocorticoid Receptor (MR) genes, acoustic startle in the context of low perceived threat during training, peritraumatic distress to incident exposure during first year of service, and general symptom severity during training at 1 year of service. The application of CCD methods can determine variables and pathways related to the complex etiology of PTS in a cohort of police officers. This knowledge may inform new approaches to treatment and prevention of critical incident related PTS.

Editorial: In the Causal Labyrinth: Finding the Path From Early Trauma to Neurodevelopment.

Exposure to traumatic events early in life has been associated with significant adverse neurodevelopmental consequences.1,2 Ideally, protecting children from trauma would prevent these consequences. Unfortunately, once a child is exposed to early trauma, the only means of prevention requires implementing effective interventions toward the mechanisms known to have caused the consequences. Therefore, it is imperative to carefully define the true mechanistic pathways from which the neurodevelopmental consequences of early trauma result. The process of determining the correct pathway(s) is not a trivial matter, as is made clear from a valiant effort reported in this issue of the Journal titled, "Early Sexual Trauma Exposure and Neural Response Inhibition in Adolescence and Young Adults: Trajectories of Frontal Theta Oscillations During a Go/No-Go Task."3 This editorial reviews the effort to infer causal mechanism in this article, and introduces a literature that can improve the field's capacity to infer causes from observational data.

Longitudinal association between infant disorganized attachment and childhood posttraumatic stress symptoms.

The purpose of this study was to evaluate whether children with a history of disorganized attachment in infancy were more likely than children without a history of disorganized attachment to exhibit symptoms of posttraumatic stress disorder (PTSD) at school age following trauma exposure. The sample consisted of 78 8.5-year-old children from a larger, ongoing prospective study evaluating the effects of intrauterine cocaine exposure (IUCE) on children's growth and development from birth to adolescence. At the 12-month visit, children's attachment status was scored from videotapes of infant-caregiver dyads in Ainsworth's strange situation. At the 8.5-year visit, children were administered the Violence Exposure Scale-Revised, a child-report trauma exposure inventory, and the Diagnostic Interview for Children and Adolescents by an experienced clinical psychologist masked to children's attachment status and IUCE status. Sixteen of the 78 children (21%) were classified as insecure-disorganized/insecure-other at 12 months. Poisson regressions covarying IUCE, gender, and continuity of maternal care indicated that disorganized attachment status at 12 months, compared with nondisorganized attachment status, significantly predicted both higher avoidance cluster PTSD symptoms and higher reexperiencing cluster PTSD symptoms. These findings suggest that the quality of early dyadic relationships may be linked to differences in children's later development of posttraumatic stress symptoms following a traumatic event.

Brain entropy and human intelligence: A resting-state fMRI study.

Human intelligence comprises comprehension of and reasoning about an infinitely variable external environment. A brain capable of large variability in neural configurations, or states, will more easily understand and predict variable external events. Entropy measures the variety of configurations possible within a system, and recently the concept of brain entropy has been defined as the number of neural states a given brain can access. This study investigates the relationship between human intelligence and brain entropy, to determine whether neural variability as reflected in neuroimaging signals carries information about intellectual ability. We hypothesize that intelligence will be positively associated with entropy in a sample of 892 healthy adults, using resting-state fMRI. Intelligence is measured with the Shipley Vocabulary and WASI Matrix Reasoning tests. Brain entropy was positively associated with intelligence. This relation was most strongly observed in the prefrontal cortex, inferior temporal lobes, and cerebellum. This relationship between high brain entropy and high intelligence indicates an essential role for entropy in brain functioning. It demonstrates that access to variable neural states predicts complex behavioral performance, and specifically shows that entropy derived from neuroimaging signals at rest carries information about intellectual capacity. Future work in this area may elucidate the links between brain entropy in both resting and active states and various forms of intelligence. This insight has the potential to provide predictive information about adaptive behavior and to delineate the subdivisions and nature of intelligence based on entropic patterns.

The long-term consequences of early childhood trauma: a case study and discussion.

There is a great need to better understand the impact of traumatic events very early in life on the course of children's future development. This report focuses on the intriguing case of a girl who witnessed the murder of her mother by her father at the age of 19 months and seemed to have no recollection of this incident until the age of 11, when she began to exhibit severe symptoms of posttraumatic stress disorder (PTSD) in response to a traumatic reminder. The case presentation serves as the basis for a discussion regarding pertinent issues involved in early childhood trauma. This case and accompanying discussion were originally presented at the 19th Annual Meeting of the International Society for Traumatic Stress Studies and were transcribed and revised for use in this article. Specific topics include early childhood memory and trauma, learning and the appraisal of danger, and PTSD and traumatic grief in early childhood. Clinical and public health implications are also discussed. This case illustrates the dramatic impact that "preverbal" traumatic memories can have on children's later functioning and speaks to the importance of assisting very young children in the immediate aftermath of traumatic events.

A Complex Systems Approach to Causal Discovery in Psychiatry.

Conventional research methodologies and data analytic approaches in psychiatric research are unable to reliably infer causal relations without experimental designs, or to make inferences about the functional properties of the complex systems in which psychiatric disorders are embedded. This article describes a series of studies to validate a novel hybrid computational approach--the Complex Systems-Causal Network (CS-CN) method-designed to integrate causal discovery within a complex systems framework for psychiatric research. The CS-CN method was first applied to an existing dataset on psychopathology in 163 children hospitalized with injuries (validation study). Next, it was applied to a much larger dataset of traumatized children (replication study). Finally, the CS-CN method was applied in a controlled experiment using a 'gold standard' dataset for causal discovery and compared with other methods for accurately detecting causal variables (resimulation controlled experiment). The CS-CN method successfully detected a causal network of 111 variables and 167 bivariate relations in the initial validation study. This causal network had well-defined adaptive properties and a set of variables was found that disproportionally contributed to these properties. Modeling the removal of these variables resulted in significant loss of adaptive properties. The CS-CN method was successfully applied in the replication study and performed better than traditional statistical methods, and similarly to state-of-the-art causal discovery algorithms in the causal detection experiment. The CS-CN method was validated, replicated, and yielded both novel and previously validated findings related to risk factors and potential treatments of psychiatric disorders. The novel approach yields both fine-grain (micro) and high-level (macro) insights and thus represents a promising approach for complex systems-oriented research in psychiatry.

Pathways to PTSD, part II: Sexually abused children.

OBJECTIVE: The goal of this research was to develop and test a prospective model of posttraumatic stress symptoms in sexually abused children that includes pretrauma, trauma, and disclosure-related pathways. METHOD: At time 1, several measures were used to assess pretrauma variables, trauma variables, and stress reactions upon disclosure for 156 sexually abused children ages 8 to 13 years. At the time 2 follow-up (7 to 36 months following the initial interview), the children were assessed for posttraumatic stress disorder (PTSD) symptoms. RESULTS: A path analysis involving a series of hierarchically nested ordinary least squares multiple regression analyses indicated three direct paths to PTSD symptoms: avoidant coping, anxiety/arousal, and dissociation, all measured during or immediately after disclosure of sexual abuse. Additionally, age and gender predicted avoidant coping, while life stress and age at abuse onset predicted symptoms of anxiety/arousal. Taken together, these pathways accounted for approximately 57% of the variance in PTSD symptoms. CONCLUSIONS: Symptoms measured at the time of disclosure constitute direct, independent pathways by which sexually abused children are likely to develop later PTSD symptoms. These findings speak to the importance of assessing children during the disclosure of abuse in order to identify those at greatest risk for later PTSD symptoms.

Pathways to PTSD, part I: Children with burns.

OBJECTIVE: The goal of this study was to develop a model of risk factors for posttraumatic stress disorder (PTSD) in a group of acutely burned children. METHOD: Seventy-two children between the ages of 7 and 17 who were admitted to the hospital for an acute burn were eligible for study. Members of families who consented completed the Child PTSD Reaction Index, the Multidimensional Anxiety Scale for Children, and other self-report measures of psychopathology and environmental stress both during the hospitalization and 3 months following the burn. A path analytic strategy was used to build a model of risk factors for PTSD. RESULTS: Two pathways to PTSD were discerned: 1) from the size of the burn and level of pain following the burn to the child's level of acute separation anxiety, and then to PTSD, and 2) from the size of the burn to the child's level of acute dissociation following the burn, and then to PTSD. Together these pathways accounted for almost 60% of the variance in PTSD symptoms and constituted a model with excellent fit indices. CONCLUSIONS: These findings support a model of complex etiology for childhood PTSD in which two independent pathways may be mediated by different biobehavioral systems.

Review of child and adolescent refugee mental health.

OBJECTIVE: To review stressful experiences and stress reactions among child and adolescent refugees, as well as interventions and ethical considerations in research and clinical work, within the framework of the chronological experiences of child refugees; namely, the phases of preflight, flight, and resettlement. Highlighted are special refugee populations such as unaccompanied minors, asylum seekers, and former child soldiers. Pertinent medical findings are summarized. METHOD: The authors reviewed articles from 1990 to 2003 addressing the topics above. Literature was gathered from databases including PsycINFO, Medline, and SocioFile. Pertinent earlier papers and those from other disciplines cited in database-identified articles were also included. RESULTS: Child and adolescent refugees suffer from significant conflict-related exposures. Reactions to stress may be mediated by coping strategies, belief systems, and social relations. CONCLUSIONS: More research is needed on interventions, specifically on efficacy and cultural relevance. Interventions that have an impact on multiple ecological levels need further development and evaluation.

Self-destructive behavior in patients with dissociative disorders.

Highrates of self-injury have been reported in patients with dissociative disorders, yet no prior study has directly compared these patients with other psychiatric patients. The present study assesses self-destructive behavior in a group of inpatients who have dissociative disorders compared to those who report few dissociative symptoms. These patients more frequently engage in self-destructive behaviors, use more methods of self-injury, and begin to injure themselves at an earlier age then patients who do not dissociate. Results have important implications for understanding the relationship between dissociation, childhood trauma, and self-injury and for assessment and treatment of patients with dissociative disorders.

Posttraumatic stress responses in children with life-threatening illnesses.

Posttraumatic stress symptoms have been reported in response to various serious medical illnesses in adults and children. Not surprisingly, posttraumatic stress is probably more common in response to acute, life-threatening, events that are related to the illness. Emerging data suggest that children often experience life-saving medical procedures as traumatic, which puts caretakers and medical personnel in the role of perpetrators for the children. Trauma symptoms are also reported as common and severe in caregivers. Both of these issues have been previously poorly understood and should be addressed in assessment and treatment. As with other traumatic events, developmental considerations, the nature and severity of the event itself, social supports, and premorbid exposure to negative life events are also important issues to consider in developing appropriate interventions. The importance of developing prevention and treatment for PTSD in medically ill children and adults includes increased morbidity and mortality (e.g., nonadherence to medications) and psychiatric sequelae and decreased quality of life. Obstacles to systematic study of a psychiatric intervention for this group include difficulties assessing multidrug regimens and cognitive treatment effects in this group. The relative stability of social supports and the potential use of preventive measures make this an attractive population for intervention. Clinicians and researchers are encouraged to work together to develop and use uniform screening and assessment methods that will help to identify cases and facilitate the multicenter trials that are vital to increasing knowledge in this patient population.

Testimonial psychotherapy for adolescent refugees: a case series.

Adolescent refugees are a traumatized, vulnerable group of arrivals to America who lack experience with or interest in psychiatric care. Testimonial psychotherapy's unique focus on transcribing personal, traumatic events for the altruistic purpose of education and advocacy make it an acceptable interaction by which to bridge the cultural gap that prevents young refugees from seeking psychiatric care. The theoretical basis for testimony is discussed. Testimonial psychotherapy has been used with adult refugees, but not with adolescents. This article describes the testimonial process with three Sudanese adolescents (the so-called 'Lost Boys'), which appeared feasible and safe. An efficacy study is underway.

Trauma Systems Therapy in Residential Settings: Improving Emotion Regulation and the Social Environment of Traumatized Children and Youth in Congregate Care.

Although abundant evidence exists indicating the prevalence of trauma exposure among youth in residential care, few models exist for creating trauma-informed milieu treatment. This article outlines the problem and describes the implementation of Trauma Systems Therapy (TST) in three residential centers. TST is unique in emphasizing youth emotions and behaviors as well as the role a distressed or threatening social environment may play in keeping a traumatized youth in a dysregulated state. This dual emphasis makes TST specifically appropriate to implementation in congregate care, focusing assessment and intervention strategies on both clinical treatment and the functioning of the therapeutic milieu itself. Data are reported on incidents of the use of physical restraint; numbers of disrupted foster care placements following discharge from residential treatment; and scores on psychometric measures of children's functioning and emotion regulation capacity. Knowledge gained through TST implementation in these three residential centers has important implications for developing a model of trauma-informed congregate care.

A randomized controlled trial of sertraline to prevent posttraumatic stress disorder in burned children.

BACKGROUND: This study evaluated the potential benefits of a centrally acting selective serotonin reuptake inhibitor, sertraline, versus placebo for prevention of symptoms of posttraumatic stress disorder (PTSD) and depression in burned children. This is the first controlled investigation based on our review of the early use of a medication to prevent PTSD in children. METHODS: Twenty-six children aged 6-20 were assessed in a 24-week double-blind placebo-controlled design. Each child received either flexibly dosed sertraline between 25-150 mg/day or placebo. At each reassessment, information was collected in compliance with the study medication, parental assessment of the child's symptomatology and functioning, and the child's self-report of symptomatology. The protocol was approved by the Human Studies Committees of Massachusetts General Hospital and Shriners Hospitals for Children. RESULTS: The final sample was 17 subjects who received sertraline versus 9 placebo control subjects matched for age, severity of injury, and type of hospitalization. There was no significant difference in change from baseline with child-reported symptoms; however, the sertraline group demonstrated a greater decrease in parent-reported symptoms over 8 weeks (-4.1 vs. -0.5, p=0.005), over 12 weeks (-4.4 vs. -1.2, p=.008), and over 24 weeks (-4.0 vs. -0.2, p=0.017). CONCLUSIONS: Sertraline was a safe drug, and it was somewhat more effective in preventing PTSD symptoms than placebo according to parent report but not child report. Based on this study, sertraline may prevent the emergence of PTSD symptoms in children.

Pretrauma problems, prior stressor exposure, and gender as predictors of change in posttraumatic stress symptoms among physically injured children and adolescents.

OBJECTIVE: This study addressed predictors of change in posttraumatic stress symptoms (PTSS) among youths who had experienced physical injuries. The influences of pretrauma internalizing and externalizing problems, prior stressor exposure, and gender were investigated. Additionally, gender was examined as a moderator of the associations between internalizing problems and PTSS, externalizing problems and PTSS, and prior stressor exposure and PTSS. METHOD: Participants were 157 children and adolescents (75% male; age M = 13.30 years, SD = 3.60; 44% Caucasian, 39% African American, 13% Hispanic, and 4% other) admitted to 2 hospitals for physical injuries. Youths and their parents completed measures of PTSS (Child Posttraumatic Stress Reaction Index), internalizing and externalizing problems (Child Behavior Checklist), and prior stressor exposure (Coddington Life Events Scale, Child) during the hospital stay; youths completed up to 3 additional PTSS assessments targeted at 3, 6, and 12 months postinjury. RESULTS: Multilevel regression analyses revealed a significant average decline in PTSS over time (p < .05) that followed a curvilinear trajectory. Externalizing problems, prior stressor exposure, and female gender predicted higher initial PTSS levels (p < .05). Gender moderated the influence of internalizing problems, externalizing problems, and prior stressor exposure on decline in PTSS over time (p < .05). Patterns of recovery for those with high and low levels of each characteristic differed for girls and boys. CONCLUSIONS: Findings suggest targets for clinical consideration, both with respect to identifying subgroups of children and adolescents that may warrant early assessment and monitoring and timing of more directed PTSS treatment intervention.