Quantitative forecasting of PTSD from early trauma responses: a Machine Learning application

Reducing intrusive memories and promoting posttraumatic growth with Traveler: A randomized controlled study

Over recent decades, serious games have become a promising intervention approach for addressing psychological problems by providing users with computerized, engaging, and interactive experiences. An innovative serious game, Traveler, has been developed specifically as an intervention tool for managing posttraumatic responses immediately after trauma. The game incorporates the principle of visuospatial interference, the core elements of Tetris, such as spatial displacement and mental rotation, and the critical phases of eye movement desensitization and reprocessing. To test the intervention efficacy and feasibility of Traveler, we conducted a randomized controlled trial involving 105 young adults. Participants were randomly assigned into three groups: a wait-list control group, a group undergoing five-session written exposure therapy, or a group engaging in one session of Traveler gameplay. Outcome measures included intrusive memories (i.e. vividness of traumatic images, disgust at traumatic images, flashback frequency, and flashback impact) and posttraumatic growth measured by the Posttraumatic Growth Inventory. Traveler significantly outperformed the control and written exposure therapy groups in reducing intrusive memories and enhancing posttraumatic growth, with effects persisting at a 30-day follow-up. Thus, Traveler offers a promising brief and early intervention technique for addressing posttraumatic responses. Yet, its clinical applicability requires further investigation.

Salivary inflammatory biomarkers as a predictor of post-traumatic stress disorder and depressive symptom severity in trauma patients: A prospective study

BACKGROUND

Although post-traumatic stress disorder (PTSD) and depression screening are recommended for traumatic injury patients, routine screening is still uncommon. Salivary inflammatory biomarkers have biological plausibility and potential feasibility and acceptability for screening. This study tested prospective associations between several salivary inflammatory biomarkers (proinflammatory cytokines interleukin-1β, interleukin-6, tumor necrosis factor-α; and C-reactive protein), collected during hospitalization and PTSD and depressive symptoms at 5-month follow-up.

METHODS

Adult traumatic injury patients (N = 696) at a major urban Level 1 trauma center provided salivary samples and completed PTSD and depressive symptom measures during days 0-13 of inpatient hospitalization. At 5-month follow-up, 368 patients (77 % male, 23 % female) completed the Clinician-Administered PTSD Scale for DSM-IV and the Self-rated Inventory of Depressive Symptomatology. Analyses focused on a latent inflammatory cytokine factor and C-reactive protein at baseline predicting 5-month PTSD and depression symptom outcomes and included baseline symptom levels as covariates.

RESULTS

A latent factor representing proinflammatory cytokines was not related to 5-month PTSD or depressive symptom severity. Higher salivary CRP was related to greater PTSD symptom severity (β = .10, p = .03) at 5-month follow-up and more severity in the following depressive symptoms: changes in weight and appetite, bodily complaints, and constipation/diarrhea (β's from .14 to .16, p's from .004 -.03).

CONCLUSION

In a primarily Latine and Black trauma patient sample, salivary CRP measured after traumatic injury was related to greater PTSD symptom severity and severity in several depressive symptom clusters. Our preliminary findings suggest that salivary or systemic CRP may be useful to include in models predicting post-trauma psychopathology.

Trauma-related intrusive memories and anterior hippocampus structural covariance: an ecological momentary assessment study in posttraumatic stress disorder

Trauma-related intrusive memories (TR-IMs) are hallmark symptoms of posttraumatic stress disorder (PTSD), but their neural correlates remain partly unknown. Given its role in autobiographical memory, the hippocampus may play a critical role in TR-IM neurophysiology. The anterior and posterior hippocampi are known to have partially distinct functions, including during retrieval of autobiographical memories. This study aimed to investigate the relationship between TR-IM frequency and the anterior and posterior hippocampi morphology in PTSD. Ninety-three trauma-exposed adults completed daily ecological momentary assessments for fourteen days to capture their TR-IM frequency. Participants then underwent anatomical magnetic resonance imaging to obtain measures of anterior and posterior hippocampal volumes. Partial least squares analysis was applied to identify a structural covariance network that differentiated the anterior and posterior hippocampi. Poisson regression models examined the relationship of TR-IM frequency with anterior and posterior hippocampal volumes and the resulting structural covariance network. Results revealed no significant relationship of TR-IM frequency with hippocampal volumes. However, TR-IM frequency was significantly negatively correlated with the expression of a structural covariance pattern specifically associated with the anterior hippocampus volume. This association remained significant after accounting for the severity of PTSD symptoms other than intrusion symptoms. The network included the bilateral inferior temporal gyri, superior frontal gyri, precuneus, and fusiform gyri. These novel findings indicate that higher TR-IM frequency in individuals with PTSD is associated with lower structural covariance between the anterior hippocampus and other brain regions involved in autobiographical memory, shedding light on the neural correlates underlying this core symptom of PTSD.

Resilience and Disaster: Flexible Adaptation in the Face of Uncertain Threat

Disasters cause sweeping damage, hardship, and loss of life. In this article, we first consider the dominant psychological approach to disasters and its narrow focus on psychopathology (e.g., posttraumatic stress disorder). We then review research on a broader approach that has identified heterogeneous, highly replicable trajectories of outcome, the most common being stable mental health or resilience. We review trajectory research for different types of disasters, including the COVID-19 pandemic. Next, we consider correlates of the resilience trajectory and note their paradoxically limited ability to predict future resilient outcomes. Research using machine learning algorithms improved prediction but has not yet illuminated the mechanism behind resilient adaptation. To that end, we propose a more direct psychological explanation for resilience based on research on the motivational and mechanistic components of regulatory flexibility. Finally, we consider how future research might leverage new computational approaches to better capture regulatory flexibility in real time.

Development and validation of a machine learning model using electronic health records to predict trauma- and stressor-related psychiatric disorders after hospitalization with sepsis

A significant minority of individuals develop trauma- and stressor-related disorders (TSRD) after surviving sepsis, a life-threatening immune response to infections. Accurate prediction of risk for TSRD can facilitate targeted early intervention strategies, but many existing models rely on research measures that are impractical to incorporate to standard emergency department workflows. To increase the feasibility of implementation, we developed models that predict TSRD in the year after survival from sepsis using only electronic health records from the hospitalization (n = 217,122 hospitalizations from 2012-2015). The optimal model was evaluated in a temporally independent prospective test sample (n = 128,783 hospitalizations from 2016-2017), where patients in the highest-risk decile accounted for nearly one-third of TSRD cases. Our approach demonstrates that risk for TSRD after sepsis can be stratified without additional assessment burden on clinicians and patients, which increases the likelihood of model implementation in hospital settings.

TransformEHR: transformer-based encoder-decoder generative model to enhance prediction of disease outcomes using electronic health records

Deep learning transformer-based models using longitudinal electronic health records (EHRs) have shown a great success in prediction of clinical diseases or outcomes. Pretraining on a large dataset can help such models map the input space better and boost their performance on relevant tasks through finetuning with limited data. In this study, we present TransformEHR, a generative encoder-decoder model with transformer that is pretrained using a new pretraining objective-predicting all diseases and outcomes of a patient at a future visit from previous visits. TransformEHR's encoder-decoder framework, paired with the novel pretraining objective, helps it achieve the new state-of-the-art performance on multiple clinical prediction tasks. Comparing with the previous model, TransformEHR improves area under the precision-recall curve by 2% (p < 0.001) for pancreatic cancer onset and by 24% (p = 0.007) for intentional self-harm in patients with post-traumatic stress disorder. The high performance in predicting intentional self-harm shows the potential of TransformEHR in building effective clinical intervention systems. TransformEHR is also generalizable and can be easily finetuned for clinical prediction tasks with limited data.

Predicting non-improvement of symptoms in daily mental healthcare practice using routinely collected patient-level data: a machine learning approach

Objectives

Anxiety and mood disorders greatly affect the quality of life for individuals worldwide. A substantial proportion of patients do not sufficiently improve during evidence-based treatments in mental healthcare. It remains challenging to predict which patients will or will not benefit. Moreover, the limited research available on predictors of treatment outcomes comes from efficacy RCTs with strict selection criteria which may limit generalizability to a real-world context. The current study evaluates the performance of different machine learning (ML) models in predicting non-improvement in an observational sample of patients treated in routine specialized mental healthcare.

Methods

In the current longitudinal exploratory prediction study diagnosis-related, sociodemographic, clinical and routinely collected patient-reported quantitative outcome measures were acquired during treatment as usual of 755 patients with a primary anxiety, depressive, obsessive compulsive or trauma-related disorder in a specialized outpatient mental healthcare center. ML algorithms were trained to predict non-response (< 0.5 standard deviation improvement) in symptomatic distress 6 months after baseline. Different models were trained, including models with and without early change scores in psychopathology and well-being and models with a trimmed set of predictor variables. Performance of trained models was evaluated in a hold-out sample (30%) as a proxy for unseen data.

Results

ML models without early change scores performed poorly in predicting six-month non-response in the hold-out sample with Area Under the Curves (AUCs) < 0.63. Including early change scores slightly improved the models' performance (AUC range: 0.68-0.73). Computationally-intensive ML models did not significantly outperform logistic regression (AUC: 0.69). Reduced prediction models performed similar to the full prediction models in both the models without (AUC: 0.58-0.62 vs. 0.58-0.63) and models with early change scores (AUC: 0.69-0.73 vs. 0.68-0.71). Across different ML algorithms, early change scores in psychopathology and well-being consistently emerged as important predictors for non-improvement.

Conclusion

Accurately predicting treatment outcomes in a mental healthcare context remains challenging. While advanced ML algorithms offer flexibility, they showed limited additional value compared to traditional logistic regression in this study. The current study confirmed the importance of taking early change scores in both psychopathology and well-being into account for predicting longer-term outcomes in symptomatic distress.

Derivation and validation of risk prediction for posttraumatic stress symptoms following trauma exposure

BACKGROUND

Posttraumatic stress symptoms (PTSS) are common following traumatic stress exposure (TSE). Identification of individuals with PTSS risk in the early aftermath of TSE is important to enable targeted administration of preventive interventions. In this study, we used baseline survey data from two prospective cohort studies to identify the most influential predictors of substantial PTSS.

METHODS

Self-identifying black and white American women and men (n = 1546) presenting to one of 16 emergency departments (EDs) within 24 h of motor vehicle collision (MVC) TSE were enrolled. Individuals with substantial PTSS (⩾33, Impact of Events Scale - Revised) 6 months after MVC were identified via follow-up questionnaire. Sociodemographic, pain, general health, event, and psychological/cognitive characteristics were collected in the ED and used in prediction modeling. Ensemble learning methods and Monte Carlo cross-validation were used for feature selection and to determine prediction accuracy. External validation was performed on a hold-out sample (30% of total sample).

RESULTS

Twenty-five percent (n = 394) of individuals reported PTSS 6 months following MVC. Regularized linear regression was the top performing learning method. The top 30 factors together showed good reliability in predicting PTSS in the external sample (Area under the curve = 0.79 ± 0.002). Top predictors included acute pain severity, recovery expectations, socioeconomic status, self-reported race, and psychological symptoms.

CONCLUSIONS

These analyses add to a growing literature indicating that influential predictors of PTSS can be identified and risk for future PTSS estimated from characteristics easily available/assessable at the time of ED presentation following TSE.

Early prediction of mental health problems following military deployment: Integrating pre- and post-deployment factors in neural network models

Military personnel deployed to war zones are at increased risk of mental health problems such as posttraumatic stress disorder (PTSD) or depression. Early pre- or post-deployment identification of those at highest risk of such problems is crucial to target intervention to those in need. However, sufficiently accurate models predicting objectively assessed mental health outcomes have not been put forward. In a sample consisting of all Danish military personnel who deployed to war zones for the first (N = 27,594), second (N = 11,083) and third (N = 5,161) time between 1992 and 2013, we apply neural networks to predict psychiatric diagnoses or use of psychotropic medicine in the years following deployment. Models are based on pre-deployment registry data alone or on pre-deployment registry data in combination with post-deployment questionnaire data on deployment experiences or early post-deployment reactions. Further, we identified the most central predictors of importance for the first, second, and third deployment. Models based on pre-deployment registry data alone had lower accuracy (AUCs ranging from 0.61 (third deployment) to 0.67 (first deployment)) than models including pre- and post-deployment data (AUCs ranging from 0.70 (third deployment) to 0.74 (first deployment)). Age at deployment, deployment year and previous physical trauma were important across deployments. Post-deployment predictors varied across deployments but included deployment exposures as well as early post-deployment symptoms. The results suggest that neural network models combining pre- and early post-deployment data can be utilized for screening tools that identify individuals at risk of severe mental health problems in the years following military deployment.

A computational model for learning from repeated traumatic experiences under uncertainty

Traumatic events can lead to lifelong, inflexible adaptations in threat perception and behavior, which characterize posttraumatic stress disorder (PTSD). This process involves associations between sensory cues and internal states of threat and then generalization of the threat responses to previously neutral cues. However, most formulations neglect adaptations to threat that are not specific to those associations. To incorporate nonassociative responses to threat, we propose a computational theory of PTSD based on adaptation to the frequency of traumatic events by using a reinforcement learning momentum model. Recent threat prediction errors generate momentum that influences subsequent threat perception in novel contexts. This model fits primary data acquired from a mouse model of PTSD, in which unpredictable footshocks in one context accelerate threat learning in a novel context. The theory is consistent with epidemiological data that show that PTSD incidence increases with the number of traumatic events, as well as the disproportionate impact of early life trauma. Because the theory proposes that PTSD relates to the average of recent threat prediction errors rather than the strength of a specific association, it makes novel predictions for the treatment of PTSD.

Machine Learning and the Digital Measurement of Psychological Health

Since its inception, the discipline of psychology has utilized empirical epistemology and mathematical methodologies to infer psychological functioning from direct observation. As new challenges and technological opportunities emerge, scientists are once again challenged to define measurement paradigms for psychological health and illness that solve novel problems and capitalize on new technological opportunities. In this review, we discuss the theoretical foundations of and scientific advances in remote sensor technology and machine learning models as they are applied to quantify psychological functioning, draw clinical inferences, and chart new directions in treatment.

Applications of artificial intelligence-machine learning for detection of stress: a critical overview

Psychological distress is a major contributor to human physiology and pathophysiology, and it has been linked to several conditions, such as auto-immune diseases, metabolic syndrome, sleep disorders, and suicidal thoughts and inclination. Therefore, early detection and management of chronic stress is crucial for the prevention of several diseases. Artificial intelligence (AI) and Machine Learning (ML) have promoted a paradigm shift in several areas of biomedicine including diagnosis, monitoring, and prognosis of disease. Here, our review aims to present some of the AI and ML applications for solving biomedical issues related to psychological stress. We provide several lines of evidence from previous studies highlighting that AI and ML have been able to predict stress and detect the brain normal states vs. abnormal states (notably, in post-traumatic stress disorder (PTSD)) with accuracy around 90%. Of note, AI/ML-driven technology applied to identify ubiquitously present stress exposure may not reach its full potential, unless future analytics focus on detecting prolonged distress through such technology instead of merely assessing stress exposure. Moving forward, we propose that a new subcategory of AI methods called Swarm Intelligence (SI) can be used towards detecting stress and PTSD. SI involves ensemble learning techniques to efficiently solve a complex problem, such as stress detection, and it offers particular strength in clinical settings, such as privacy preservation. We posit that AI and ML approaches will be beneficial for the medical and patient community when applied to predict and assess stress levels. Last, we encourage additional research to bring AI and ML into the standard clinical practice for diagnostics in the not-too-distant future.

Heart and brain traumatic stress biomarker analysis with and without machine learning: A scoping review

The enigma of post-traumatic stress disorder (PTSD) is embedded in a complex array of physiological responses to stressful situations that result in disruptions in arousal and cognitions that characterise the psychological disorder. Deciphering these physiological patterns is complex, which has seen the use of machine learning (ML) grow in popularity. However, it is unclear to what extent ML has been used with physiological data, specifically, the electroencephalogram (EEG) and electrocardiogram (ECG) to further understand the physiological responses associated with PTSD. To better understand the use of EEG and ECG biomarkers, with and without ML, a scoping review was undertaken. A total of 124 papers based on adult samples were identified comprising 19 ML studies involving EEG and ECG. A further 21 studies using EEG data, and 84 studies employing ECG meeting all other criteria but not employing ML were included for comparison. Identified studies indicate classical ML methodologies currently dominate EEG and ECG biomarkers research, with derived biomarkers holding clinically relevant diagnostic implications for PTSD. Discussion of the emerging trends, algorithms used and their success is provided, along with areas for future research.

Derivation and Validation of a Brief Emergency Department-Based Prediction Tool for Posttraumatic Stress After Motor Vehicle Collision

STUDY OBJECTIVE

To derive and initially validate a brief bedside clinical decision support tool that identifies emergency department (ED) patients at high risk of substantial, persistent posttraumatic stress symptoms after a motor vehicle collision.

METHODS

Derivation (n=1,282, 19 ED sites) and validation (n=282, 11 separate ED sites) data were obtained from adults prospectively enrolled in the Advancing Understanding of RecOvery afteR traumA study who were discharged from the ED after motor vehicle collision-related trauma. The primary outcome was substantial posttraumatic stress symptoms at 3 months (Posttraumatic Stress Disorder Checklist for Diagnostic and Statistical Manual of Mental Disorders-5 ≥38). Logistic regression derivation models were evaluated for discriminative ability using the area under the curve and the accuracy of predicted risk probabilities (Brier score). Candidate posttraumatic stress predictors assessed in these models (n=265) spanned a range of sociodemographic, baseline health, peritraumatic, and mechanistic domains. The final model selection was based on performance and ease of administration.

RESULTS

Significant 3-month posttraumatic stress symptoms were common in the derivation (27%) and validation (26%) cohort. The area under the curve and Brier score of the final 8-question tool were 0.82 and 0.14 in the derivation cohort and 0.76 and 0.17 in the validation cohort.

CONCLUSION

This simple 8-question tool demonstrates promise to risk-stratify individuals with substantial posttraumatic stress symptoms who are discharged to home after a motor vehicle collision. Both external validation of this instrument, and work to further develop more accurate tools, are needed. Such tools might benefit public health by enabling the conduct of preventive intervention trials and assisting the growing number of EDs that provide services to trauma survivors aimed at promoting psychological recovery.

Glucocorticoid-based pharmacotherapies preventing PTSD

Posttraumatic stress disorder (PTSD) is a highly disabling psychiatric condition that may arise after exposure to acute and severe trauma. It is a highly prevalent mental disorder worldwide, and the current treatment options for these patients remain limited due to low effectiveness. The time window right after traumatic events provides clinicians with a unique opportunity for preventive interventions against potential deleterious alterations in brain function that lead to PTSD. Some studies pointed out that PTSD patients present an abnormal function of the hypothalamic-pituitary-adrenal axis that may contribute to a vulnerability toward PTSD. Moreover, glucocorticoids have arisen as a promising option for preventing the disorder's development when administered in the aftermath of trauma. The present work compiles the recent findings of glucocorticoid administration for the prevention of a PTSD phenotype, from human studies to animal models of PTSD. Overall, glucocorticoid-based therapies for preventing PTSD demonstrated moderate evidence in terms of efficacy in both clinical and preclinical studies. Although clinical studies point out that glucocorticoids may not be effective for all patients' subpopulations, those with adequate traits might greatly benefit from them. Preclinical studies provide precise insight into the mechanisms mediating this preventive effect, showing glucocorticoid-based prevention to reduce long-lasting behavioral and neurobiological abnormalities caused by traumatic stress. However, further research is needed to delineate the precise mechanisms and the extent to which these interventions can translate into lower PTSD rates and morbidity. This article is part of the Special Issue on 'Fear, Anxiety and PTSD'.

The effect of sleep on intrusive memories in daily life: a systematic review and meta-analysis of trauma film experiments

STUDY OBJECTIVES

To synthesize the literature on the effect of sleep versus wake on the frequency and distress of intrusive memories in everyday life after watching film clips with distressing content as a proxy for traumatic experiences.

METHODS

We conducted a systematic review by searching PubMed and PsychInfo. The last search was conducted on January 31, 2022. We included experimental studies comparing sleep and wake groups on intrusions using ecological diary methods, whereas studies lacking a wake control condition or relying solely on intrusion-triggering tasks or retrospective questionnaires were excluded. Meta-analyses were performed to evaluate the results. Risks of biases were assessed following the Cochrane guidelines.

RESULTS

Across 7 effect sizes from 6 independent studies, sleep (n = 192), as compared to wake (n = 175), significantly reduced the number of intrusive memories (Hedges' g = -0.26, p = .04, 95% CI [-0.50, -0.01]), but not the distress associated with them (Hedges' g = -0.14, p = .25, 95% CI [-0.38, 0.10]).

CONCLUSIONS

Although the results suggest that sleep reduces the number of intrusions, there is a strong need for high-powered pre-registered studies to confirm this effect. Risks of biases in the reviewed work concern the selection of the reported results, measurement of the outcome, and failure to adhere to the intervention. Limitations with the current meta-analysis include the small number of studies, which comprised only English-language articles, and the fact that it was not pre-registered.

Prediction and comparison of psychological health during COVID-19 among Indian population and Rajyoga meditators using machine learning algorithms

Issues of providing mental health support to people with emerging or current mental health disorders are becoming a significant concern throughout the world. One of the biggest effects of digital psychiatry during COVID-19 is its capacity for early identification and forecasting of a person's mental health decline resulting in chronic mental health issues. Therefore, through this study aims at addressing the hological problems by identifying people who are more likely to acquire mental health issues induced by COVID-19 epidemic. To achieve this goal, this study includes 1) Rajyoga practitioners' perceptions of psychological effects, levels of anxiety, stress, and depression are compared to those of the non practitioners 2) Predictions of mental health disorders such as stress, anxiety and depression using machine learning algorithms using the online survey data collected from Rajyoga meditators and general the population. Decision tree, random forest, naive bayeBayespport vector machine and K nearest neighbor algorithms were used for the prediction as they have been shown to be more accurate for predicting psychological disorders. The support vector machine showed the highest accuracy among all other algorithms. The f1 score was also the highest for support vector machine.

Predicting PTSD symptoms in firefighters using a fear-potentiated startle paradigm and machine learning

This study develops a fear-potentiated startle paradigm (FPS) and a machine learning approach to accurately predict PTSD symptoms using electrogram data. A three-phase fear-potentiated startle paradigm was designed to assess the conditioning, generalization, and extinction of fear. Electrooculogram and electrocardiogram signals were collected during the FPS. A total of 1107 Chinese firefighters participated in the study. The Chinese version PCL-C was administered to all subjects. A cutoff of 38 or higher is used to indicate PTSD symptoms. Electrogram features were extracted and selected to build a machine learning model to classify individuals. The machine learning model was 5-fold cross validated. The importance of the selected features was calculated. Classification performance metrics were evaluated for the machine learning model. The machine learning model can identify firefighters with a PCL-C score of 38 or above with sensitivity and specificity both above 0.85 when 5-fold cross validated on a 1107-person sample. The area under the receiver operating characteristic curve of the model is 0.93. Features related to fear generalization are found to be the most important. The proposed fear-potentiated startle paradigm and machine learning approach can accurately predict PTSD symptoms in Chinese firefighters, which can improve the screening and diagnosis of PTSD.

Machine learning prediction of posttraumatic stress disorder trajectories following traumatic injury: Identification and validation in two independent samples

Due to its heterogeneity, the prediction of posttraumatic stress disorder (PTSD) development after traumtic injury is difficult. Recent machine learning approaches have yielded insight into predicting PTSD symptom trajectories. Using data collected within 1 month of traumatic injury, we applied eXtreme Gradient Boosting (XGB) to classify admitted and discharged patients (hospitalized, n = 192; nonhospitalized, n = 214), recruited from a Level 1 trauma center, according to PTSD symptom trajectories. Trajectories were identified using latent class mixed models on PCL-5 scores collected at baseline, 1-3 months posttrauma, and 6 months posttrauma. In both samples, nonremitting, remitting, and resilient PTSD symptom trajectories were identified. In the admitted patient sample, a unique delayed trajectory emerged. Machine learning classifiers (i.e., XGB) were developed and tested on the admitted patient sample and externally validated on the discharged sample with biological and clinical self-report baseline variables as predictors. For external validation sets, prediction was fair for nonremitting versus other trajectories, areas under the curve (AUC = .70); good for nonremitting versus resilient trajectories, AUCs = .73-.76; and prediction failed for nonremitting versus remitting trajectories, AUCs = .46-.48. However, poor precision (< .57) across all models suggests limited generalizability of nonremitting symptom trajectory prediction from admitted to discharged patient samples. Consistency in symptom trajectory identification across samples supports prior studies on the stability of PTSD symptom trajectories following trauma exposure; however, continued work and replication with larger samples are warranted to understand overlapping and unique predictive features of PTSD in different traumatic injury populations.

Acute stress and PTSD among trauma-exposed children and adolescents: Computational prediction and interpretation

BACKGROUND

Youth receiving medical care for injury are at risk of PTSD. Therefore, accurate prediction of chronic PTSD at an early stage is needed. Machine learning (ML) offers a promising approach to precise prediction and interpretation.

AIMS

The study proposes a clinically useful predictive model for PTSD 6-12 months after injury, analyzing the relationship among predictors, and between predictors and outcomes.

METHODS

A ML approach was utilized to train models based on 1167 children and adolescents of nine perspective studies. Demographics, trauma characteristics and acute traumatic stress (ASD) symptoms were used as initial predictors. PTSD diagnosis at six months was derived using DSM-IV PTSD diagnostic criteria. Models were validated on external datasets. Shapley value and partial dependency plot (PDP) were applied to interpret the final model.

RESULTS

A random forest model with 13 predictors (age, ethnicity, trauma type, intrusive memories, nightmares, reliving, distress, dissociation, cognitive avoidance, sleep, irritability, hypervigilance and startle) yielded F-scores of.973,0.902 and.961 with training and two external datasets. Shapley values were calculated for individual and grouped predictors. A cumulative effect for intrusion symptoms was observed. PDP showed a non-linear relationship between age and PTSD, and between ASD symptom severity and PTSD. A 43 % difference in the risk between non-minority and minority ethnic groups was detected.

CONCLUSIONS

A ML model demonstrated excellent classification performance and good potential for clinical utility, using a few easily obtainable variables. Model interpretation gave a comprehensive quantitative analysis on the operations among predictors, in particular ASD symptoms.

Sex-dependent risk factors for PTSD: a prospective structural MRI study

Female individuals are more likely to be diagnosed with PTSD following trauma exposure than males, potentially due, in part, to underlying neurobiological factors. Several brain regions underlying fear learning and expression have previously been associated with PTSD, with the hippocampus, amygdala, dorsal anterior cingulate cortex (dACC), and rostral ACC (rACC) showing altered volume and function in those with PTSD. However, few studies have examined how sex impacts the predictive value of subcortical volumes and cortical thickness in longitudinal PTSD studies. As part of an emergency department study completed at the Grady Trauma Project in Atlanta, GA, N = 93 (40 Female) participants were enrolled within 24 h following a traumatic event. Multi-echo T1-weighted MRI images were collected one-month post-trauma exposure. Bilateral amygdala and hippocampal volumes and rACC and dACC cortical thickness were segmented. To assess the longitudinal course of PTSD, the PTSD Symptom Scale (PSS) was collected 6 months post-trauma. We investigated whether regional volume/thickness interacted with sex to predict later PTSD symptom severity, controlling for PSS score at time of scan, age, race, and trauma type, as well as intracranial volume (ICV) for subcortical volumes. There was a significant interaction between sex and rACC for 6-month PSS, such that right rACC thickness was positively correlated with 6-month PSS scores in females, but not in males. In examining PTSD symptom subtypes and depression symptoms, greater rACC thickness in females predicted greater avoidance symptoms, while smaller rACC thickness in males predicted greater depression symptoms. Amygdala and hippocampus volume and dACC thickness showed no main effect or interaction with sex. The current findings provide evidence for sex-based differences in how brain volume predicts future PTSD severity and symptoms and supports the rACC as being a vital region regarding PTSD. Gender differences should be assessed in future longitudinal PTSD MRI studies for more accurate identification of future PTSD risk following trauma.

Subpopulation-specific machine learning prognosis for underrepresented patients with double prioritized bias correction

Background

Many clinical datasets are intrinsically imbalanced, dominated by overwhelming majority groups. Off-the-shelf machine learning models that optimize the prognosis of majority patient types (e.g., healthy class) may cause substantial errors on the minority prediction class (e.g., disease class) and demographic subgroups (e.g., Black or young patients). In the typical one-machine-learning-model-fits-all paradigm, racial and age disparities are likely to exist, but unreported. In addition, some widely used whole-population metrics give misleading results.

Methods

We design a double prioritized (DP) bias correction technique to mitigate representational biases in machine learning-based prognosis. Our method trains customized machine learning models for specific ethnicity or age groups, a substantial departure from the one-model-predicts-all convention. We compare with other sampling and reweighting techniques in mortality and cancer survivability prediction tasks.

Results

We first provide empirical evidence showing various prediction deficiencies in a typical machine learning setting without bias correction. For example, missed death cases are 3.14 times higher than missed survival cases for mortality prediction. Then, we show DP consistently boosts the minority class recall for underrepresented groups, by up to 38.0%. DP also reduces relative disparities across race and age groups, e.g., up to 88.0% better than the 8 existing sampling solutions in terms of the relative disparity of minority class recall. Cross-race and cross-age-group evaluation also suggests the need for subpopulation-specific machine learning models.

Conclusions

Biases exist in the widely accepted one-machine-learning-model-fits-all-population approach. We invent a bias correction method that produces specialized machine learning prognostication models for underrepresented racial and age groups. This technique may reduce potentially life-threatening prediction mistakes for minority populations.

Positive Cognitive Reappraisal in Stress Resilience, Mental Health, and Well-Being: A Comprehensive Systematic Review

Stress-related psychopathology is on the rise, and there is a pressing need for improved prevention strategies. Positive appraisal style, the tendency to appraise potentially threatening situations in a positive way, has been proposed to act as a key resilience mechanism and therefore offers a potential target for preventive approaches. In this article, we review n  =  99 studies investigating associations of positive cognitive reappraisal, an important sub-facet of positive appraisal style, with outcome-based resilience and relevant other outcomes, which are considered resilience-related. According to the studies reviewed, positive cognitive reappraisal moderates the relation between stressors and negative outcomes and is positively related to several resilience-related outcomes. It also mediates between other resilience factors and resilience, suggesting it is a proximal resilience factor.

Predicting Posttraumatic Stress Disorder Among Survivors of Recent Interpersonal Violence

A substantial minority of women who experience interpersonal violence will develop posttraumatic stress disorder (PTSD). One critical challenge for preventing PTSD is predicting whose acute posttraumatic stress symptoms will worsen to a clinically significant degree. This 6-month longitudinal study adopted multilevel modeling and exploratory machine learning (ML) methods to predict PTSD onset in 58 young women, ages 18 to 30, who experienced an incident of physical and/or sexual assault in the three months prior to baseline assessment. Women completed baseline assessments of theory-driven cognitive and neurobiological predictors and interview-based measures of PTSD diagnostic status and symptom severity at 1-, 3-, and 6-month follow-ups. Higher levels of self-blame, generalized anxiety disorder severity, childhood trauma exposure, and impairment across multiple domains were associated with a pattern of high and stable posttraumatic stress symptom severity over time. Predictive performance for PTSD onset was similarly strong for a gradient boosting machine learning model including all predictors and a logistic regression model including only baseline posttraumatic stress symptom severity. The present findings provide directions for future work on PTSD prediction among interpersonal violence survivors that could enhance early risk detection and potentially inform targeted prevention programs.

Identifying posttraumatic stress disorder staging from clinical and sociodemographic features: a proof-of-concept study using a machine learning approach

This proof-of-concept study aimed to investigate the viability of a predictive model to support posttraumatic stress disorder (PTSD) staging. We performed a naturalistic, cross-sectional study at two Brazilian centers: the Psychological Trauma Research and Treatment (NET-Trauma) Program at Universidade Federal of Rio Grande do Sul, and the Program for Research and Care on Violence and PTSD (PROVE), at Universidade Federal of São Paulo. Five supervised machine-learning algorithms were tested: Elastic Net, Gradient Boosting Machine, Random Forest, Support Vector Machine, and C5.0, using clinical (Clinician-Administered PTSD Scale version 5) and sociodemographic features. A hundred and twelve patients were enrolled (61 from NET-Trauma and 51 from PROVE). We found a model with four classes suitable for the PTSD staging, with best performance metrics using the C5.0 algorithm to CAPS-5 15-items plus sociodemographic features, with an accuracy of 65.6% for the train dataset and 52.9% for the test dataset (both significant). The number of symptoms, CAPS-5 total score, global severity score, and presence of current/previous trauma events appear as main features to predict PTSD staging. This is the first study to evaluate staging in PTSD with machine learning algorithms using accessible clinical and sociodemographic features, which may be used in future research.

Early pharmacological interventions for universal prevention of post-traumatic stress disorder (PTSD)

BACKGROUND

Post-traumatic stress disorder (PTSD) is a severe and debilitating condition. Several pharmacological interventions have been proposed with the aim to prevent or mitigate it. These interventions should balance efficacy and tolerability, given that not all individuals exposed to a traumatic event will develop PTSD. There are different possible approaches to preventing PTSD; universal prevention is aimed at individuals at risk of developing PTSD on the basis of having been exposed to a traumatic event, irrespective of whether they are showing signs of psychological difficulties.

OBJECTIVES

To assess the efficacy and acceptability of pharmacological interventions for universal prevention of PTSD in adults exposed to a traumatic event.

SEARCH METHODS

We searched the Cochrane Common Mental Disorders Controlled Trial Register (CCMDCTR), CENTRAL, MEDLINE, Embase, two other databases and two trials registers (November 2020). We checked the reference lists of all included studies and relevant systematic reviews. The search was last updated on 13 November 2020.

SELECTION CRITERIA

We included randomised clinical trials on adults exposed to any kind of traumatic event. We considered comparisons of any medication with placebo or with another medication. We excluded trials that investigated medications as an augmentation to psychotherapy.

DATA COLLECTION AND ANALYSIS

We used standard Cochrane methodological procedures. In a random-effects model, we analysed dichotomous data as risk ratios (RR) and number needed to treat for an additional beneficial/harmful outcome (NNTB/NNTH). We analysed continuous data as mean differences (MD) or standardised mean differences (SMD).

MAIN RESULTS

We included 13 studies which considered eight interventions (hydrocortisone, propranolol, dexamethasone, omega-3 fatty acids, gabapentin, paroxetine, PulmoCare enteral formula, Oxepa enteral formula and 5-hydroxytryptophan) and involved 2023 participants, with a single trial contributing 1244 participants. Eight studies enrolled participants from emergency departments or trauma centres or similar settings. Participants were exposed to a range of both intentional and unintentional traumatic events. Five studies considered participants in the context of intensive care units with traumatic events consisting of severe physical illness. Our concerns about risk of bias in the included studies were mostly due to high attrition and possible selective reporting. We could meta-analyse data for two comparisons: hydrocortisone versus placebo, but limited to secondary outcomes; and propranolol versus placebo. No study compared hydrocortisone to placebo at the primary endpoint of three months after the traumatic event. The evidence on whether propranolol was more effective in reducing the severity of PTSD symptoms compared to placebo at three months after the traumatic event is inconclusive, because of serious risk of bias amongst the included studies, serious inconsistency amongst the studies' results, and very serious imprecision of the estimate of effect (SMD -0.51, 95% confidence interval (CI) -1.61 to 0.59; I² = 83%; 3 studies, 86 participants; very low-certainty evidence). No study provided data on dropout rates due to side effects at three months post-traumatic event. The evidence on whether propranolol was more effective than placebo in reducing the probability of experiencing PTSD at three months after the traumatic event is inconclusive, because of serious risk of bias amongst the included studies, and very serious imprecision of the estimate of effect (RR 0.77, 95% CI 0.31 to 1.92; 3 studies, 88 participants; very low-certainty evidence). No study assessed functional disability or quality of life.  Only one study compared gabapentin to placebo at the primary endpoint of three months after the traumatic event, with inconclusive evidence in terms of both PTSD severity and probability of experiencing PTSD, because of imprecision of the effect estimate, serious risk of bias and serious imprecision (very low-certainty evidence). We found no data on dropout rates due to side effects, functional disability or quality of life. For the remaining comparisons, the available data are inconclusive or missing in terms of PTSD severity reduction and dropout rates due to adverse events. No study assessed functional disability.

AUTHORS' CONCLUSIONS

This review provides uncertain evidence only regarding the use of hydrocortisone, propranolol, dexamethasone, omega-3 fatty acids, gabapentin, paroxetine, PulmoCare formula, Oxepa formula, or 5-hydroxytryptophan as universal PTSD prevention strategies. Future research might benefit from larger samples, better reporting of side effects and inclusion of quality of life and functioning measures.

The Italian Version of the International Trauma Questionnaire: Symptom and Network Structure of Post-Traumatic Stress Disorder and Complex Post-Traumatic Stress Disorder in a Sample of Late Adolescents Exposed to a Natural Disaster

The 11th revision of the International Classification of Diseases has endorsed substantial changes in Post-Traumatic Stress Disorder (PTSD) and has introduced Complex PTSD (cPTSD). The objective of this study was to assess the symptom and network structure of PTSD and cPTSD using the International Trauma Questionnaire- Italian version (ITQ) and the prevalence of PTSD and cPTSD in a community sample of late adolescents enriched with exposure to a destructive earthquake. A 1,010 high school students participated to the study. Confirmatory Factor Analysis supports that a six first-order correlated factors was the best fitting model of ICD-11 PTSD/cPTSD. The network analysis supports a clear separation between core PTSD symptoms and disturbances in self-organization (DSO) symptoms, avoidance, and negative self-concept were the most central items. The prevalence of PTSD and cPTSD was 9.11 and 4.06%, respectively. Female participants reported higher rates of both PTSD and cPTSD. This is the first study to report on ICD-11 PTSD and cPTSD rates on an Italian adolescence community sample. Consistent with other community samples, we found higher rates of PTSD compared to cPTSD. The results confirmed the factorial validity of the ITQ. The network structure highlights the importance of negative self-concept in cPTSD and avoidance in PTSD.

A systematic literature review of AI-based digital decision support systems for post-traumatic stress disorder

OBJECTIVE

Over the last decade, an increase in research on medical decision support systems has been observed. However, compared to other disciplines, decision support systems in mental health are still in the minority, especially for rare diseases like post-traumatic stress disorder (PTSD). We aim to provide a comprehensive analysis of state-of-the-art digital decision support systems (DDSSs) for PTSD.

METHODS

Based on our systematic literature review of DDSSs for PTSD, we created an analytical framework using thematic analysis for feature extraction and quantitative analysis for the literature. Based on this framework, we extracted information around the medical domain of DDSSs, the data used, the technology used for data collection, user interaction, decision-making, user groups, validation, decision type and maturity level. Extracting data for all of these framework dimensions ensures consistency in our analysis and gives a holistic overview of DDSSs.

RESULTS

Research on DDSSs for PTSD is rare and primarily deals with the algorithmic part of DDSSs (n = 17). Only one DDSS was found to be a usable product. From a data perspective, mostly checklists or questionnaires were used (n = 9). While the median sample size of 151 was rather low, the average accuracy was 82%. Validation, excluding algorithmic accuracy (like user acceptance), was mostly neglected, as was an analysis concerning possible user groups.

CONCLUSION

Based on a systematic literature review, we developed a framework covering all parts (medical domain, data used, technology used for data collection, user interaction, decision-making, user groups, validation, decision type and maturity level) of DDSSs. Our framework was then used to analyze DDSSs for post-traumatic stress disorder. We found that DDSSs are not ready-to-use products but are mostly algorithms based on secondary datasets. This shows that there is still a gap between technical possibilities and real-world clinical work.

AI-Based Prediction and Prevention of Psychological and Behavioral Changes in Ex-COVID-19 Patients

The COVID-19 pandemic has adverse consequences on human psychology and behavior long after initial recovery from the virus. These COVID-19 health sequelae, if undetected and left untreated, may lead to more enduring mental health problems, and put vulnerable individuals at risk of developing more serious psychopathologies. Therefore, an early distinction of such vulnerable individuals from those who are more resilient is important to undertake timely preventive interventions. The main aim of this article is to present a comprehensive multimodal conceptual approach for addressing these potential psychological and behavioral mental health changes using state-of-the-art tools and means of artificial intelligence (AI). Mental health COVID-19 recovery programs at post-COVID clinics based on AI prediction and prevention strategies may significantly improve the global mental health of ex-COVID-19 patients. Most COVID-19 recovery programs currently involve specialists such as pulmonologists, cardiologists, and neurologists, but there is a lack of psychiatrist care. The focus of this article is on new tools which can enhance the current limited psychiatrist resources and capabilities in coping with the upcoming challenges related to widespread mental health disorders. Patients affected by COVID-19 are more vulnerable to psychological and behavioral changes than non-COVID populations and therefore they deserve careful clinical psychological screening in post-COVID clinics. However, despite significant advances in research, the pace of progress in prevention of psychiatric disorders in these patients is still insufficient. Current approaches for the diagnosis of psychiatric disorders largely rely on clinical rating scales, as well as self-rating questionnaires that are inadequate for comprehensive assessment of ex-COVID-19 patients' susceptibility to mental health deterioration. These limitations can presumably be overcome by applying state-of-the-art AI-based tools in diagnosis, prevention, and treatment of psychiatric disorders in acute phase of disease to prevent more chronic psychiatric consequences.

Diagnosing post-traumatic stress disorder using electronic medical record data

This study proposes a predictive model that uses structured data and unstructured narrative notes from Electronic Medical Records to accurately identify patients diagnosed with Post-Traumatic Stress Disorder (PTSD). We utilize data from primary care clinicians participating in the Manitoba Primary Care Research Network (MaPCReN) representing 154,118 patients. A reference sample of 195 patients that had their PTSD diagnosis confirmed using a manual chart review of structured data and narrative notes, and PTSD negative patients is used as the gold standard data for model training, validation and testing. We assess structured and unstructured data from eight tables in the MaPCReN namely, patient demographics, disease case, examinations, medication, billing records, health condition, risk factors, and encounter notes. Feature engineering is applied to convert data into proper representation for predictive modeling. We explore serial and parallel mixed data models that are trained on both structured and unstructured data to identify PTSD. Model performances were calculated based on a highly skewed hold-out test dataset. The serial model that uses both structured and text data as input, yielded the highest values in sensitivity (0.77), F-measure (0.76), and AUC (0.88) and the parallel model that uses both structured and text data as the input obtained the highest positive predicted value (PPV) (0.75). Diseases such as PTSD are difficult to diagnose. Information recorded in the chart note over multiple visits of the patients with the primary care physicians has higher predictive power than structured data and combining these two data types can increase the predictive capabilities of machine learning models in diagnosing PTSD. While the deep-learning model outperformed the traditional ensemble model in processing text data, the ensemble classifier obtained better results in ingesting a combination of features obtained from both data types in the serial mixed model. The study demonstrated that unstructured encounter notes enhance a model's ability to identify patients diagnosed with PTSD. These findings can enhance quality improvement, research, and disease surveillance related to PTSD in primary care populations.

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

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.

Combining Deep Learning and Graph-Theoretic Brain Features to Detect Posttraumatic Stress Disorder at the Individual Level

Previous studies using resting-state functional MRI (rs-fMRI) have revealed alterations in graphical metrics in groups of individuals with posttraumatic stress disorder (PTSD). To explore the ability of graph measures to diagnose PTSD and capture its essential features in individual patients, we used a deep learning (DL) model based on a graph-theoretic approach to discriminate PTSD from trauma-exposed non-PTSD at the individual level and to identify its most discriminant features. Our study was performed on rs-fMRI data from 91 individuals with PTSD and 126 trauma-exposed non-PTSD patients. To evaluate our DL method, we used the traditional support vector machine (SVM) classifier as a reference. Our results showed that the proposed DL model allowed single-subject discrimination of PTSD and trauma-exposed non-PTSD individuals with higher accuracy (average: 80%) than the traditional SVM (average: 57.7%). The top 10 DL features were identified within the default mode, central executive, and salience networks; the first two of these networks were also identified in the SVM classification. We also found that nodal efficiency in the left fusiform gyrus was negatively correlated with the Clinician Administered PTSD Scale score. These findings demonstrate that DL based on graphical features is a promising method for assisting in the diagnosis of PTSD.

Prediction of eating disorder treatment response trajectories via machine learning does not improve performance versus a simpler regression approach

OBJECTIVE

Patterns of response to eating disorder (ED) treatment are heterogeneous. Advance knowledge of a patient's expected course may inform precision medicine for ED treatment. This study explored the feasibility of applying machine learning to generate personalized predictions of symptom trajectories among patients receiving treatment for EDs, and compared model performance to a simpler logistic regression prediction model.

METHOD

Participants were adolescent girls and adult women (N = 333) presenting for residential ED treatment. Self-report progress assessments were completed at admission, discharge, and weekly throughout treatment. Latent growth mixture modeling previously identified three latent treatment response trajectories (Rapid Response, Gradual Response, and Low-Symptom Static Response) and assigned a trajectory type to each patient. Machine learning models (support vector, k-nearest neighbors) and logistic regression were applied to these data to predict a patient's response trajectory using data from the first 2 weeks of treatment.

RESULTS

The best-performing machine learning model (evaluated via area under the receiver operating characteristics curve [AUC]) was the radial-kernel support vector machine (AUCRADIAL = 0.94). However, the more computationally-intensive machine learning models did not improve predictive power beyond that achieved by logistic regression (AUCLOGIT = 0.93). Logistic regression significantly improved upon chance prediction (MAUC[NULL] = 0.50, SD = .01; p <.001).

DISCUSSION

Prediction of ED treatment response trajectories is feasible and achieves excellent performance, however, machine learning added little benefit. We discuss the need to explore how advance knowledge of expected trajectories may be used to plan treatment and deliver individualized interventions to maximize treatment effects.

Prediction of Task Performance From Physiological Features of Stress Resilience

In this paper, we investigate the potential of generic physiological features of stress resilience in predicting air traffic control (ATC) candidates' performance in a highly-stressful low-fidelity ATC simulator scenario. Stress resilience is highlighted as an important occupational factor that influences the performance and well-being of air traffic control officers (ATCO). Poor stress management, besides the lack of skills, can be a direct cause of poor performance under stress, both in the selection process of ATCOs and later in the workplace. 40 ATC candidates, within the final stages of their selection process, underwent a stimulation paradigm for elicitation and assessment of various generic task-unrelated physiological features, related to resting heart rate variability (HRV) and respiratory sinus arrhythmia (RSA), acoustic startle response (ASR) and the physiological allostatic response, which are all recognized as relevant psychophysiological markers of stress resilience. The multimodal approach included analysis of electrocardiography, electromyography, electrodermal activity and respiration. We make advances in computational methodology for assessment of physiological features of stress resilience, and investigate the predictive power of the obtained feature space in a binary classification problem: prediction of high- vs. low-performance on the developed ATC simulator. Our novel approach yields a relatively high 78.16% classification accuracy. These results are discussed in the context of prior work, while considering study limitations and proposing directions for future work.

Predicting suicidal behavior and self-harm after general hospitalization of adults with serious mental illness

Individuals with psychiatric disorders are vulnerable to adverse mental health outcomes following physical illness. This longitudinal cohort study defined risk profiles for readmission for suicidal behavior and self-harm after general hospitalization of adults with serious mental illness. Structured electronic health record data were analyzed from 15,644 general non-psychiatric index hospitalizations of individuals with depression, bipolar, and psychotic disorders admitted to an urban health system in the southwestern United States between 2006 and 2017. Using data from one-year prior to and including index hospitalization, supervised machine learning was implemented to predict risk of readmission for suicide attempt and self-harm in the following year. The Classification and Regression Tree algorithm produced a classification prediction with an area under the receiver operating curve (AUC) of 0.86 (95% confidence interval (CI) 0.74-0.97). Incidence of suicide-related behavior was highest after general non-psychiatric hospitalizations of individuals with prior suicide attempt or self-harm (18%; 69 cases/389 hospitalizations) and lowest after hospitalizations associated with very high medical morbidity burden (0 cases/3090 hospitalizations). Predictor combinations, rather than single risk factors, explained the majority of risk, including concomitant alcohol use disorder with moderate medical morbidity, and age ≤55-years-old with low medical morbidity. Findings suggest that applying an efficient and highly interpretable machine learning algorithm to electronic health record data may inform general hospital clinical decision support, resource allocation, and preventative interventions for medically ill adults with serious mental illness.

Demanding and effective: participants' experiences of internet-delivered prolonged exposure provided within two months after exposure to trauma

Background: The use of remotely delivered early intervention after trauma may prevent and/or reduce symptoms of post-traumatic stress. Our research group evaluated a novel three-week therapist-guided internet-delivered intervention based on prolonged exposure (Condensed Internet-Delivered Prolonged Exposure; CIPE) in a pilot trial. The results indicated that the intervention was feasible, acceptable and reduced symptoms of post-traumatic stress at post-intervention compared to a waiting-list condition. Exposure to traumatic memories can be emotionally demanding and there is a need for detailed investigation of participants' experiences in receiving this type of intervention remotely. Objective: Investigate participants' experiences of receiving CIPE early after trauma. Method: In this study, qualitative thematic analysis was used and semi-structured interviews with 11 participants six months after intervention completion were conducted. All interviews were audio-recorded and transcribed verbatim. Results: One overarching theme labelled as 'demanding and effective' was identified. Participants expressed that treatment effects could only be achieved by putting in a lot of effort and by being emotionally close to the trauma memory during exposure exercises. Participants reported CIPE to be a highly credible- and educative intervention that motivated them to fully engage in exposure exercises. The most distressing parts of the intervention was perceived as tolerable and important to do to heal psychologically after trauma. For many participants, the possibility to engage in the intervention whenever and where it suited them was helpful, although some participants described it as challenging to find a balance between their own responsibility and when to expect therapist support. The internet-based format was perceived as a safe forum for self-disclosure that helped some participants overcome avoidance due to shame during imaginal exposure. Conclusion: CIPE was considered demanding, yet effective by the interviewed participants. The most distressing parts of the intervention was perceived to be the most important and were tolerable and feasible to provide online.

Physiological parameters of mental health predict the emergence of post-traumatic stress symptoms in physicians treating COVID-19 patients

Lack of established knowledge and treatment strategies, and change in work environment, may altogether critically affect the mental health and functioning of physicians treating COVID-19 patients. Thus, we examined whether treating COVID-19 patients affect the physicians' mental health differently compared with physicians treating non-COVID-19 patients. In this cohort study, an association was blindly computed between physiologically measured anxiety and attention vigilance (collected from 1 May 2014 to 31 May 31 2016) and self-reports of anxiety, mental health aspects, and sleep quality (collected from 20 April to 30 June 2020, and analyzed from 1 July to 1 September 2020), of 91 physicians treating COVID-19 or non-COVID-19 patients. As a priori hypothesized, physicians treating COVID-19 patients showed a relative elevation in both physiological measures of anxiety (95% CI: 2317.69-2453.44 versus 1982.32-2068.46; P < 0.001) and attention vigilance (95% CI: 29.85-34.97 versus 22.84-26.61; P < 0.001), compared with their colleagues treating non-COVID-19 patients. At least 3 months into the pandemic, physicians treating COVID-19 patients reported high anxiety and low quality of sleep. Machine learning showed clustering to the COVID-19 and non-COVID-19 subgroups with a high correlation mainly between physiological and self-reported anxiety, and between physiologically measured anxiety and sleep duration. To conclude, the pattern of attention vigilance, heightened anxiety, and reduced sleep quality findings point the need for mental intervention aimed at those physicians susceptible to develop post-traumatic stress symptoms, owing to the consequences of fighting at the forefront of the COVID-19 pandemic.

A machine learning approach to modeling PTSD and difficulties in emotion regulation

Despite evidence for the association between emotion regulation difficulties and posttraumatic stress disorder (PTSD), less is known about the specific emotion regulation abilities that are most relevant to PTSD severity. This study examined both item-level and subscale-level models of difficulties in emotion regulation in relation to PTSD severity using supervised machine learning in a sample of U.S. adults (N=570). Participants were recruited via Amazon's Mechanical Turk (MTurk) and completed self-report measures of emotion regulation difficulties and PTSD severity. We used five different machine learning algorithms separately to train each statistical model. Using ridge and elastic net regression results in the testing sample, emotion regulation predictor variables accounted for approximately 28% and 27% of the variance in PTSD severity in the item- and subscale-level models, respectively. In the item-level model, four predictor variables had notable relative importance values for PTSD severity. These items captured secondary emotional responding, experiencing emotions as out-of-control, difficulties modulating emotional arousal, and low emotional granularity. In the subscale-level model, lack of access to effective emotion regulation strategies, lack of emotional clarity, and emotional nonacceptance subscales had the highest relative importance to PTSD severity. Results from analyses modeling a probable diagnosis of PTSD based on DERS items and subscales are presented in supplemental findings. Findings have implications for developing more efficient, targeted emotion regulation interventions for PTSD.

A survey on Machine learning based Medical Assistive systems in Current Oncological Sciences

BACKGROUND

Cancer is one of the life threatening disease which is affecting a large number of population worldwide. The cancer cells multiply inside the body without showing much symptoms on the surface of the skin thereby making it difficult to predict and detect at the onset of disease. Many organizations are working towards automating the process of cancer detection with minimal false detection rates.

INTRODUCTION

The machine learning algorithms serve to be a promising alternative to support health care practitioners to rule out the disease and predict the growth with various imaging and statistical analysis tools. The medical practitioners are utilizing the output of these algorithms to diagnose and design the course of treatment. These algorithms are capable of finding out the risk level of the patient and can reduce the mortality rate concerning to cancer disease.

METHOD

This article presents the existing state of art techniques for identifying cancer affecting human organs based on machine learning models. The supported set of imaging operations are also elaborated for each type of Cancer.

CONCLUSION

The CAD tools are the aid for the diagnostic radiologists for preliminary investigations and detecting the nature of tumor cells.

The opportunities and challenges of machine learning in the acute care setting for precision prevention of posttraumatic stress sequelae

Personalized medicine is among the most exciting innovations in recent clinical research, offering the opportunity for tailored screening and management at the individual level. Biomarker-enriched clinical trials have shown increased efficiency and informativeness in cancer research due to the selective exclusion of patients unlikely to benefit. In acute stress situations, clinically significant decisions are often made in time-sensitive manners and providers may be pressed to make decisions based on abbreviated clinical assessments. Up to 30% of trauma survivors admitted to the Emergency Department (ED) will develop long-lasting posttraumatic stress psychopathologies. The long-term impact of those survivors with posttraumatic stress sequelae are significant, impacting both long-term psychological and physiological recovery. An accurate prognostic model of who will develop posttraumatic stress symptoms does not exist yet. Additionally, no scalable and cost-effective method that can be easily integrated into routine care exists, even though especially the acute care setting provides a critical window of opportunity for prevention in the so-called golden hours when preventive measures are most effective. In this review, we aim to discuss emerging machine learning (ML) applications that are promising for precisely risk stratification and targeted treatments in the acute care setting. The aim of this narrative review is to present examples of digital health innovations and to discuss the potential of these new approaches for treatment selection and prevention of posttraumatic sequelae in the acute care setting. The application of artificial intelligence-based solutions have already had great success in other areas and are rapidly approaching the field of psychological care as well. New ways of algorithm-based risk predicting, and the use of digital phenotypes provide a high potential for predicting future risk of PTSD in acute care settings and to go new steps in precision psychiatry.

Machine Learning to Differentiate Risk of Suicide Attempt and Self-harm After General Medical Hospitalization of Women With Mental Illness

BACKGROUND

Suicide prevention is a public health priority, but risk factors for suicide after medical hospitalization remain understudied. This problem is critical for women, for whom suicide rates in the United States are disproportionately increasing.

OBJECTIVE

To differentiate the risk of suicide attempt and self-harm following general medical hospitalization among women with depression, bipolar disorder, and chronic psychosis.

METHODS

We developed a machine learning algorithm that identified risk factors of suicide attempt and self-harm after general hospitalization using electronic health record data from 1628 women in the University of California Los Angeles Integrated Clinical and Research Data Repository. To assess replicability, we applied the algorithm to a larger sample of 140,848 women in the New York City Clinical Data Research Network.

RESULTS

The classification tree algorithm identified risk groups in University of California Los Angeles Integrated Clinical and Research Data Repository (area under the curve 0.73, sensitivity 73.4, specificity 84.1, accuracy 0.84), and predictor combinations characterizing key risk groups were replicated in New York City Clinical Data Research Network (area under the curve 0.71, sensitivity 83.3, specificity 82.2, and accuracy 0.84). Predictors included medical comorbidity, history of pregnancy-related mental illness, age, and history of suicide-related behavior. Women with antecedent medical illness and history of pregnancy-related mental illness were at high risk (6.9%-17.2% readmitted for suicide-related behavior), as were women below 55 years old without antecedent medical illness (4.0%-7.5% readmitted).

CONCLUSIONS

Prevention of suicide attempt and self-harm among women following acute medical illness may be improved by screening for sex-specific predictors including perinatal mental health history.

Forecasting individual risk for long-term Posttraumatic Stress Disorder in emergency medical settings using biomedical data: A machine learning multicenter cohort study

The necessary requirement of a traumatic event preceding the development of Posttraumatic Stress Disorder, theoretically allows for administering preventive and early interventions in the early aftermath of such events. Machine learning models including biomedical data to forecast PTSD outcome after trauma are highly promising for detection of individuals most in need of such interventions. In the current study, machine learning was applied on biomedical data collected within 48 h post-trauma to forecast individual risk for long-term PTSD, using a multinominal approach including the full spectrum of common PTSD symptom courses within one prognostic model for the first time. N = 417 patients (37.2% females; mean age 46.09 ± 15.88) admitted with (suspected) serious injury to two urban Academic Level-1 Trauma Centers were included. Routinely collected biomedical information (endocrine measures, vital signs, pharmacotherapy, demographics, injury and trauma characteristics) upon ED admission and subsequent 48 h was used. Cross-validated multi-nominal classification of longitudinal self-reported symptom severity (IES-R) over 12 months and bimodal classification of clinician-rated PTSD diagnosis (CAPS-IV) at 12 months post-trauma was performed using extreme Gradient Boosting and evaluated on hold-out sets. SHapley Additive exPlanations (SHAP) values were used to explain the derived models in human-interpretable form. Good prediction of longitudinal PTSD symptom trajectories (multiclass AUC = 0.89) and clinician-rated PTSD at 12 months (AUC = 0.89) was achieved. Most relevant prognostic variables to forecast both multinominal and dichotomous PTSD outcomes included acute endocrine and psychophysiological measures and hospital-prescribed pharmacotherapy. Thus, individual risk for long-term PTSD was accurately forecasted from biomedical information routinely collected within 48 h post-trauma. These results facilitate future targeted preventive interventions by enabling future early risk detection and provide further insights into the complex etiology of PTSD.

Condensed internet-delivered prolonged exposure provided soon after trauma: A randomised pilot trial

Exposure to trauma is common and may have detrimental psychological consequences. Brief exposure therapy provided early after trauma has shown encouraging results in promoting recovery. To scale up treatment availability, we developed a 3-week internet-delivered intervention comprised of four modules based on prolonged exposure (condensed internet-delivered prolonged exposure; CIPE) with therapist support. In this pilot study, we assessed the feasibility, acceptability, and preliminary efficacy of CIPE delivered within 2 months after the index event. Thirty-three participants were randomised to CIPE or a waiting list (WL). The frequency, vividness and distress of intrusive recollections or flashback memories of the traumatic event were assessed using an intrusive memory smartphone app. Symptoms of post-traumatic stress were assessed by the PTSD Symptom Checklist for DSM-5 (PCL-5). The most common index traumas in the sample were rape, interpersonal violence and life-threatening accidents. A majority of participants (82%) randomised to CIPE completed all modules, and the number of logins per participant to the Internet platform was high during the three-week intervention (M = 19.6, SD = 11.8). At post-treatment, the CIPE participants had a more favourable reduction than the WL group on the vividness and distress ratings, as well as on the PCL-5 sum score (bootstrapped d = 0.85; 95% CI [0.25-1.45]). Treatment effects were sustained at 6-months follow up and no severe adverse events associated with the intervention were found. CIPE seems to be a feasible and possibly efficacious early intervention after trauma. Large-scale trials are needed to assess its efficacy and long-term benefits.

Virtual Reality-Based Treatment for Military Members and Veterans With Combat-Related Posttraumatic Stress Disorder: Protocol for a Multimodular Motion-Assisted Memory Desensitization and Reconsolidation Randomized Controlled Trial

Background

Military members are at elevated risk of operational stress injuries, including posttraumatic stress disorder (PTSD) and moral injury. Although psychotherapy can reduce symptoms, some military members may experience treatment-resistant PTSD. Multimodular motion-assisted memory desensitization and reconsolidation (3MDR) has been introduced as a virtual reality (VR) intervention for military members with PTSD related to military service. The 3MDR intervention incorporates exposure therapy, psychotherapy, eye movement desensitization and reconsolidation, VR, supportive counselling, and treadmill walking.

Objective

The objective of this study is to investigate whether 3MDR reduces PTSD symptoms among military members with combat-related treatment-resistant PTSD (TR-PTSD); examine the technology acceptance and usability of the Computer Assisted Rehabilitation ENvironment (CAREN) and 3MDR interventions by Canadian Armed Forces service members (CAF-SMs), veterans, 3MDR clinicians, and operators; and evaluate the impact on clinicians and operators of delivering 3MDR.

Methods

This is a mixed-methods waitlist controlled crossover design randomized controlled trial. Participants include both CAF-SMs and veterans (N=40) aged 18-60 years with combat-related TR-PTSD (unsuccessful experience of at least 2 evidence-based trauma treatments). Participants will also include clinicians and operators (N=12) who have been trained in 3MDR and subsequently utilized this intervention with patients. CAF-SMs and veterans will receive 6 weekly 90-minute 3MDR sessions. Quantitative and qualitative data will be collected at baseline and at 1, 3, and 6 months postintervention. Quantitative data collection will include multiomic biomarkers (ie, blood and salivary proteomic and genomic profiles of neuroendocrine, immune-inflammatory mediators, and microRNA), eye tracking, electroencephalography, and physiological data. Data from outcome measures will capture self-reported symptoms of PTSD, moral injury, resilience, and technology acceptance and usability. Qualitative data will be collected from audiovisual recordings of 3MDR sessions and semistructured interviews. Data analysis will include univariate and multivariate approaches, and thematic analysis of treatment sessions and interviews. Machine learning analysis will be included to develop models for the prediction of diagnosis, symptom severity, and treatment outcomes.

Results

This study commenced in April 2019 and is planned to conclude in April 2021. Study results will guide the further evolution and utilization of 3MDR for military members with TR-PTSD and will have utility in treating other trauma-affected populations.

Conclusions

The goal of this study is to utilize qualitative and quantitative primary and secondary outcomes to provide evidence for the effectiveness and feasibility of 3MDR for treating CAF-SMs and veterans with combat-related TR-PTSD. The results will inform a full-scale clinical trial and stimulate development and adaptation of the protocol to mobile VR apps in supervised clinical settings. This study will add to knowledge of the clinical effectiveness of 3MDR, and provide the first comprehensive analysis of biomarkers, technology acceptance and usability, moral injury, resilience, and the experience of clinicians and operators delivering 3MDR.

Trial Registration

ISRCTN Registry 11264368; http://www.isrctn.com/ISRCTN11264368.

International Registered Report Identifier (IRRID)

DERR1-10.2196/20620

Artificial Intelligence and Posttraumatic Stress Disorder (PTSD)

Abstract. Posttraumatic stress disorder (PTSD) is a debilitating disease that can occur after experiencing a traumatic event. Despite recent progress in computational research, it has not yet been possible to identify precise and reliable risk factors that enable predictive models of individual risk for posttraumatic stress after trauma. In this overview, we discuss recent advances in the use of Machine Learning (ML) and Artificial Intelligence (AI) for risk stratification and targeted treatment allocation in the context of stress pathologies and we critically review the benefits and challenges of emerging approaches. The vast heterogeneity in the manifestation and the etiology of PTSD is discussed as one major reason for the need to deploy ML-based computational models to better account for individual differences between patients. Striving for personalized medicine is one of the most important goals of current clinical research and is of great potential for the field of posttraumatic stress research. The use of ML is a promising and necessary approach for reaching more personalized treatments and to make further progress in the field of precision psychiatry.

Implementing Precision Psychiatry: A Systematic Review of Individualized Prediction Models for Clinical Practice

BACKGROUND

The impact of precision psychiatry for clinical practice has not been systematically appraised. This study aims to provide a comprehensive review of validated prediction models to estimate the individual risk of being affected with a condition (diagnostic), developing outcomes (prognostic), or responding to treatments (predictive) in mental disorders.

METHODS

PRISMA/RIGHT/CHARMS-compliant systematic review of the Web of Science, Cochrane Central Register of Reviews, and Ovid/PsycINFO databases from inception until July 21, 2019 (PROSPERO CRD42019155713) to identify diagnostic/prognostic/predictive prediction studies that reported individualized estimates in psychiatry and that were internally or externally validated or implemented. Random effect meta-regression analyses addressed the impact of several factors on the accuracy of prediction models.

FINDINGS

Literature search identified 584 prediction modeling studies, of which 89 were included. 10.4% of the total studies included prediction models internally validated (n = 61), 4.6% models externally validated (n = 27), and 0.2% (n = 1) models considered for implementation. Across validated prediction modeling studies (n = 88), 18.2% were diagnostic, 68.2% prognostic, and 13.6% predictive. The most frequently investigated condition was psychosis (36.4%), and the most frequently employed predictors clinical (69.5%). Unimodal compared to multimodal models (β = .29, P = .03) and diagnostic compared to prognostic (β = .84, p < .0001) and predictive (β = .87, P = .002) models were associated with increased accuracy.

INTERPRETATION

To date, several validated prediction models are available to support the diagnosis and prognosis of psychiatric conditions, in particular, psychosis, or to predict treatment response. Advancements of knowledge are limited by the lack of implementation research in real-world clinical practice. A new generation of implementation research is required to address this translational gap.

Literature review and methodological considerations for understanding circulating risk biomarkers following trauma exposure

Exposure to traumatic events is common. While many individuals recover following trauma exposure, a substantial subset develop adverse posttraumatic neuropsychiatric sequelae (APNS) such as posttraumatic stress, major depression, and regional or widespread chronic musculoskeletal pain. APNS cause substantial burden to the individual and to society, causing functional impairment and physical disability, risk for suicide, lost workdays, and increased health care costs. Contemporary treatment is limited by an inability to identify individuals at high risk of APNS in the immediate aftermath of trauma, and an inability to identify optimal treatments for individual patients. Our purpose is to provide a comprehensive review describing candidate blood-based biomarkers that may help to identify those at high risk of APNS and/or guide individual intervention decision-making. Such blood-based biomarkers include circulating biological factors such as hormones, proteins, immune molecules, neuropeptides, neurotransmitters, mRNA, and noncoding RNA expression signatures, while we do not review genetic and epigenetic biomarkers due to other recent reviews of this topic. The current state of the literature on circulating risk biomarkers of APNS is summarized, and key considerations and challenges for their discovery and translation are discussed. We also describe the AURORA study, a specific example of current scientific efforts to identify such circulating risk biomarkers and the largest study to date focused on identifying risk and prognostic factors in the aftermath of trauma exposure.

Supervised Machine Learning: A Brief Primer

Machine learning is increasingly used in mental health research and has the potential to advance our understanding of how to characterize, predict, and treat mental disorders and associated adverse health outcomes (e.g., suicidal behavior). Machine learning offers new tools to overcome challenges for which traditional statistical methods are not well-suited. This paper provides an overview of machine learning with a specific focus on supervised learning (i.e., methods that are designed to predict or classify an outcome of interest). Several common supervised learning methods are described, along with applied examples from the published literature. We also provide an overview of supervised learning model building, validation, and performance evaluation. Finally, challenges in creating robust and generalizable machine learning algorithms are discussed.