Faculty Bibliography

Personalized medicine has led to important discoveries and medical innovations. For the successful translation of that progress into precision psychiatry, the complexity of mental illness and its underpinning mechanisms must be considered, and data- driven approaches are needed. Computational approaches such as machine learning are important drivers of innovation and are spurred by recent advances in statistical modeling. (PsycInfo Database Record (c) 2021 APA, all rights reserved)

Women are at higher risk for developing posttraumatic stress disorder (PTSD) compared to men, yet little is known about the biological contributors to this sex difference. One possible mechanism is differential immunological and neuroendocrine responses to traumatic stress exposure. In the current prospective study, we aimed to identify whether sex is indirectly associated with the probability of developing nonremitting PTSD through pro-inflammatory markers and whether steroid hormone concentrations influence this effect. Female (n = 179) and male (n = 197) trauma survivors were recruited from an emergency department and completed clinical assessment within 24 h and blood samples within ∼three hours of trauma exposure. Pro-inflammatory cytokines (IL-6, IL-1

Background: Adverse childhood experiences (ACE) are associated with an increased risk of major depressive disorder (MDD) and hypothalamic-pituitary-adrenal (HPA) axis dysregulation. Within the HPA axis, corticotropin-releasing hormone and vasopressin (AVP) synergistically stimulate the release of adrenocorticotropic hormone, which promotes cortisol release. The cleavage product copeptin is produced during AVP synthesis and is a surrogate marker of AVP release. Children with ACE and young adults with depressive symptoms have higher levels of copeptin than healthy controls. Objective: To uncover the effects of MDD and ACE on copeptin levels in adult females. Methods: We recruited 94 women (mean age: 34.0 ± 3.6 years): 23 with MDD and ACE, 24 with MDD without ACE, 22 with ACE without MDD, and 25 healthy controls. ACE was defined as repeated sexual or physical abuse at least once a month over at least one year before the age of 18 years. MDD was defined by the DSM-IV criteria. Copeptin plasma levels were measured with an immunoluminometric assay. Results: The four groups did not differ in demographic variables. We found a significant negative correlation between body mass index (BMI) and copeptin plasma levels (r = -.21; p = .045). Copeptin plasma levels did not differ between the four groups after controlling for BMI. Conclusion: Neither MDD nor ACE was associated with altered plasma copeptin levels. Thus, copeptin does not seem to play a major role in MDD and ACE in adult females.

BACKGROUND:Visual and auditory signs of patient functioning have long been used for clinical diagnosis, treatment selection, and prognosis. Direct measurement and quantification of these signals can aim to improve the consistency, sensitivity, and scalability of clinical assessment. Currently, we investigate if machine learning-based computer vision (CV), semantic, and acoustic analysis can capture clinical features from free speech responses to a brief interview 1 month post-trauma that accurately classify major depressive disorder (MDD) and posttraumatic stress disorder (PTSD). METHODS:N = 81 patients admitted to an emergency department (ED) of a Level-1 Trauma Unit following a life-threatening traumatic event participated in an open-ended qualitative interview with a para-professional about their experience 1 month following admission. A deep neural network was utilized to extract facial features of emotion and their intensity, movement parameters, speech prosody, and natural language content. These features were utilized as inputs to classify PTSD and MDD cross-sectionally. RESULTS:Both video- and audio-based markers contributed to good discriminatory classification accuracy. The algorithm discriminates PTSD status at 1 month after ED admission with an AUC of 0.90 (weighted average precision = 0.83, recall = 0.84, and f1-score = 0.83) as well as depression status at 1 month after ED admission with an AUC of 0.86 (weighted average precision = 0.83, recall = 0.82, and f1-score = 0.82). CONCLUSIONS:Direct clinical observation during post-trauma free speech using deep learning identifies digital markers that can be utilized to classify MDD and PTSD status.

A better understanding of suicidal behavior is important to detect suicidality in at-risk populations such as patients with borderline personality disorder (BPD), posttraumatic stress disorder (PTSD), and major depressive disorder (MDD). Suicidal tendencies are clinically assessed by verbal thoughts rather than by specifically asking about mental images. This study examines whether imagery and verbal thoughts about suicide occur and differ between patients with BPD with and without comorbid PTSD compared to patients with MDD (clinical controls). All patient groups experienced suicide-related images. Patients with BPD with comorbid PTSD reported significantly more vivid images than patients with MDD. Severity of suicidal ideation, number of previous suicide attempts, and childhood traumata were significantly associated with suicidal imagery across all patient groups. The authors demonstrate for the first time that suicide-related mental imagery occurs in BPD and is associated with suicidal ideation. This finding highlights the importance of assessing mental imagery related to suicide in clinical practice.

Impaired cognitive functioning constitutes an important symptom of major depressive disorder (MDD), potentially associated with elevated cortisol levels. Adverse childhood experiences (ACE) enhance the risk for MDD and can contribute to disturbances in the stress systems, including cortisol and cognitive functions. In healthy participants, cortisol administration as well as acute stress can affect cognitive performance. In the current study, we tested cognitive performance in MDD patients with (N = 32) and without (N = 52) ACE and healthy participants with (N = 22) and without (N = 37) ACE after psychosocial stress induction (Trier Social Stress Test, TSST) and a control condition (Placebo-TSST). MDD predicted lower performance in verbal learning and both selective and sustained attention, while ACE predicted lower performance in psychomotoric speed and working memory. There were no interaction effects of MDD and ACE. After stress, MDD patients were more likely to show lower performance in working memory as well as in selective and sustained attention compared with participants without MDD. Individuals with ACE were more likely to show lower performance in verbal memory after stress compared with individuals without ACE. Our results indicate negative effects of MDD and ACE on distinct cognitive domains. Furthermore, MDD and/or ACE seem to enhance susceptibility for stress-related cognitive impairments.

Annually, approximately 30 million patients are discharged from the emergency department (ED) after a traumatic event¹. These patients are at substantial psychiatric risk, with approximately 10-20% developing one or more disorders, including anxiety, depression or post-traumatic stress disorder (PTSD)^2-4. At present, no accurate method exists to predict the development of PTSD symptoms upon ED admission after trauma⁵. Accurate risk identification at the point of treatment by ED services is necessary to inform the targeted deployment of existing treatment^6-9 to mitigate subsequent psychopathology in high-risk populations^10,11. This work reports the development and validation of an algorithm for prediction of post-traumatic stress course over 12 months using two independently collected prospective cohorts of trauma survivors from two level 1 emergency trauma centers, which uses routinely collectible data from electronic medical records, along with brief clinical assessments of the patient's immediate stress reaction. Results demonstrate externally validated accuracy to discriminate PTSD risk with high precision. While the predictive algorithm yields useful reproducible results on two independent prospective cohorts of ED patients, future research should extend the generalizability to the broad, clinically heterogeneous ED population under conditions of routine medical care.

Diagnosing autism spectrum disorders (ASD) is a complicated, time-consuming process which is particularly challenging in older individuals. One of the most widely used behavioral diagnostic tools is the Autism Diagnostic Observation Schedule (ADOS). Previous work using machine learning techniques suggested that ASD detection in children can be achieved with substantially fewer items than the original ADOS. Here, we expand on this work with a specific focus on adolescents and adults as assessed with the ADOS Module 4. We used a machine learning algorithm (support vector machine) to examine whether ASD detection can be improved by identifying a subset of behavioral features from the ADOS Module 4 in a routine clinical sample of N = 673 high-functioning adolescents and adults with ASD (n = 385) and individuals with suspected ASD but other best-estimate or no psychiatric diagnoses (n = 288). We identified reduced subsets of 5 behavioral features for the whole sample as well as age subgroups (adolescents vs. adults) that showed good specificity and sensitivity and reached performance close to that of the existing ADOS algorithm and the full ADOS, with no significant differences in overall performance. These results may help to improve the complicated diagnostic process of ASD by encouraging future efforts to develop novel diagnostic instruments for ASD detection based on the identified constructs as well as aiding clinicians in the difficult question of differential diagnosis.

OBJECTIVE:The Fort Campbell Cohort study was designed to assess predeployment biological and behavioral markers and build predictive models to identify risk and resilience for posttraumatic stress disorder (PTSD) following deployment. This article addresses neurocognitive functioning variables as potential prospective predictors. METHOD/METHODS:In a sample of 403 soldiers, we examined whether PTSD symptom severity (using the PTSD Checklist) as well as posttraumatic stress trajectories could be prospectively predicted by measures of executive functioning (using two web-based tasks from WebNeuro) assessed predeployment. RESULTS:Controlling for age, gender, education, prior number of deployments, childhood trauma exposure, and PTSD symptom severity at Phase 1, linear regression models revealed that predeployment sustained attention and inhibitory control performance were significantly associated with postdeployment PTSD symptom severity. We also identified two posttraumatic stress trajectories utilizing latent growth mixture models. The "resilient" group consisted of 90.9% of the soldiers who exhibited stable low levels of PTSD symptoms from pre- to postdeployment. The "increasing" group consisted of 9.1% of the soldiers, who exhibited an increase in PTSD symptoms following deployment, crossing a threshold for diagnosis based on PTSD Checklist scores. Logistic regression models predicting trajectory revealed a similar pattern of findings as the linear regression models, in which predeployment sustained attention (95% CI of odds ratio: 1.0109, 1.0558) and inhibitory control (95% CI: 1.0011, 1.0074) performance were significantly associated with postdeployment PTSD trajectory. CONCLUSIONS:These findings have clinical implications for understanding the pathogenesis of PTSD and building preventative programs for military personnel. (PsycINFO Database Record (c) 2019 APA, all rights reserved).