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.

Introduction to the Special Issue on the 39th Annual Meeting of the International Society for Traumatic Stress Studies: Scalable strategies to address the impact of trauma worldwide.

This editorial summary provides an overview of the 39th annual meeting of the International Society for Traumatic Stress Studies (ISTSS) held from November 1-4, 2023. The meeting, themed "Scalable Strategies to Address the Impact of Trauma Worldwide: Innovations and Implementation," encouraged presenters to focus on the scalability of traumatic stress research and practice. The articles presented at the meeting, which form this issue, cover a broad spectrum of topics, from basic biological mechanisms to innovative digital engagement to population-wide treatments. These articles emphasize eliminating biases in research design and psychiatric practice, promoting health equity, and addressing the unique challenges of traumatic stress. This summary underscores the importance of scalability in developing flexible, dynamic, and inclusive mental health care interventions.

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.

Deep learning-based classification of posttraumatic stress disorder and depression following trauma utilizing visual and auditory markers of arousal and mood.

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.

Utilization of machine learning to test the impact of cognitive processing and emotion recognition on the development of PTSD following trauma exposure.

BACKGROUND: Though lifetime exposure to traumatic events is significant, only a minority of individuals develops symptoms of posttraumatic stress disorder (PTSD). Post-trauma alterations in neurocognitive and affective functioning are likely to reflect changes in underlying brain networks that are predictive of PTSD. These constructs are assumed to interact in a highly complex way. The aim of this exploratory study was to apply machine learning models to investigate the contribution of these interactions on PTSD symptom development and identify measures indicative of circuit related dysfunction. METHODS: N = 94 participants admitted to the emergency room of an inner-city hospital after trauma exposure completed a battery of neurocognitive and emotional tests 1 month after the incident. Different machine learning algorithms were applied to predict PTSD symptom severity and clusters after 3 months based. RESULTS: Overall, model accuracy did not differ between PTSD clusters, though the importance of cognitive and emotional domains demonstrated both key differences and overlap. Alterations in higher-order executive functioning, speed of information processing, and processing of emotionally incongruent cues were the most important predictors. CONCLUSIONS: Data-driven approaches are a powerful tool to investigate complex interactions and can enhance the mechanistic understanding of PTSD. The study identifies important relationships between cognitive processing and emotion recognition that may be valuable to predict and understand mechanisms of risk and resilience responses to trauma prospectively.

Machine Learning for Prediction of Posttraumatic Stress and Resilience Following Trauma: An Overview of Basic Concepts and Recent Advances.

Posttraumatic stress responses are characterized by a heterogeneity in clinical appearance and etiology. This heterogeneity impacts the field's ability to characterize, predict, and remediate maladaptive responses to trauma. Machine learning (ML) approaches are increasingly utilized to overcome this foundational problem in characterization, prediction, and treatment selection across branches of medicine that have struggled with similar clinical realities of heterogeneity in etiology and outcome, such as oncology. In this article, we review and evaluate ML approaches and applications utilized in the areas of posttraumatic stress, stress pathology, and resilience research, and present didactic information and examples to aid researchers interested in the relevance of ML to their own research. The examined studies exemplify the high potential of ML approaches to build accurate predictive and diagnostic models of posttraumatic stress and stress pathology risk based on diverse sources of available information. The use of ML approaches to integrate high-dimensional data demonstrates substantial gains in risk prediction even when the sources of data are the same as those used in traditional predictive models. This area of research will greatly benefit from collaboration and data sharing among researchers of posttraumatic stress disorder, stress pathology, and resilience.

Spanish Abstracts by Asociación Chilena de Estrés Traumático (ACET) Aprendizaje de Máquinas para la Predicción del Estrés Postraumático y Resiliencia después del Trauma: Una Visión General de los Conceptos Básicos y Avances Recientes APRENDIZAJE DE MAQUINAS Y ESTRÉS POSTRAUMÁTICO Las respuestas al estrés postraumático se caracterizan por una heterogeneidad en el aspecto clínico y etiología. Esta heterogeneidad afecta la capacidad del campo para caracterizar, predecir y remediar respuestas desadaptativas al trauma. Los enfoques de aprendizaje maquinas (AM) son cada vez más utilizados para superar este problema fundamental en la caracterización, predicción y selección de tratamiento a través de las ramas de la medicina que han luchado con realidades clínicas similares de heterogeneidad en la etiología y resultados, como la oncología. En este artículo, revisamos y evaluamos los enfoques y las aplicaciones de AM utilizados en las áreas de estrés postraumático, patología del estrés, e investigación en resiliencia y presenta información didáctica y ejemplos para ayudar a investigadores interesados ​​en la relevancia del AM para su propia investigación. Los estudios examinados ejemplifican el alto potencial de los enfoques de AM para construir modelos predictivos y de diagnóstico precisos de estrés postraumático y riesgo de estrés patológico basados ​​en diversas fuentes de Información disponible. El uso de enfoques de AM para integrar datos multidimensionales demuestran ganancias sustanciales en la predicción del riesgo, incluso cuando las fuentes de datos son las mismas que las utilizadas en los modelos predictivos tradicionales. Esta área de investigación se beneficiará enormemente de la colaboración y el intercambio de datos entre los investigadores del trastorno de estrés postraumático, la patología del estrés y resiliencia.

Marijuana and other cannabinoids as a treatment for posttraumatic stress disorder: A literature review.

Posttraumatic stress disorder (PTSD) is common in the general population, yet there are limitations to the effectiveness, tolerability, and acceptability of available first-line interventions. We review the extant knowledge on the effects of marijuana and other cannabinoids on PTSD. Potential therapeutic effects of these agents may largely derive from actions on the endocannabinoid system and we review major animal and human findings in this area. Preclinical and clinical studies generally support the biological plausibility for cannabinoids' potential therapeutic effects, but underscore heterogeneity in outcomes depending on dose, chemotype, and individual variation. Treatment outcome studies of whole plant marijuana and related cannabinoids on PTSD are limited and not methodologically rigorous, precluding conclusions about their potential therapeutic effects. Reported benefits for nightmares and sleep (particularly with synthetic cannabinoid nabilone) substantiate larger controlled trials to determine effectiveness and tolerability. Of concern, marijuana use has been linked to adverse psychiatric outcomes, including conditions commonly comorbid with PTSD such as depression, anxiety, psychosis, and substance misuse. Available evidence is stronger for marijuana's harmful effects on the development of psychosis and substance misuse than for the development of depression and anxiety. Marijuana use is also associated with worse treatment outcomes in naturalistic studies, and with maladaptive coping styles that may maintain PTSD symptoms. Known risks of marijuana thus currently outweigh unknown benefits for PTSD. Although controlled research on marijuana and other cannabinoids' effects on PTSD remains limited, rapid shifts in the legal landscape may now enable such studies, potentially opening new avenues in PTSD treatment research.

Bridging a translational gap: using machine learning to improve the prediction of PTSD.

BACKGROUND: Predicting Posttraumatic Stress Disorder (PTSD) is a pre-requisite for targeted prevention. Current research has identified group-level risk-indicators, many of which (e.g., head trauma, receiving opiates) concern but a subset of survivors. Identifying interchangeable sets of risk indicators may increase the efficiency of early risk assessment. The study goal is to use supervised machine learning (ML) to uncover interchangeable, maximally predictive combinations of early risk indicators. METHODS: Data variables (features) reflecting event characteristics, emergency department (ED) records and early symptoms were collected in 957 trauma survivors within ten days of ED admission, and used to predict PTSD symptom trajectories during the following fifteen months. A Target Information Equivalence Algorithm (TIE*) identified all minimal sets of features (Markov Boundaries; MBs) that maximized the prediction of a non-remitting PTSD symptom trajectory when integrated in a support vector machine (SVM). The predictive accuracy of each set of predictors was evaluated in a repeated 10-fold cross-validation and expressed as average area under the Receiver Operating Characteristics curve (AUC) for all validation trials. RESULTS: The average number of MBs per cross validation was 800. MBs' mean AUC was 0.75 (95% range: 0.67-0.80). The average number of features per MB was 18 (range: 12-32) with 13 features present in over 75% of the sets. CONCLUSIONS: Our findings support the hypothesized existence of multiple and interchangeable sets of risk indicators that equally and exhaustively predict non-remitting PTSD. ML's ability to increase prediction versatility is a promising step towards developing algorithmic, knowledge-based, personalized prediction of post-traumatic psychopathology.

Appreciating methodological complexity and integrating neurobiological perspectives to advance the science of resilience.

Kalisch and colleagues identify several routes to a better understanding of mechanisms underlying resilience and highlight the need to integrate findings from neuroscience and animal learning. We argue that appreciating methodological complexity and integrating neurobiological perspectives will advance the science of resilience and ultimately help improve the lives of those exposed to stress and adversity.

Optimism and death: predicting the course and consequences of depression trajectories in response to heart attack.

The course of depression in relation to myocardial infarction (MI), commonly known as heart attack, and the consequences for mortality are not well characterized. Further, optimism may predict both the effects of MI on depression as well as mortality secondary to MI. In the current study, we utilized a large population-based prospective sample of older adults (N=2,147) to identify heterogeneous trajectories of depression from 6 years prior to their first-reported MI to 4 years after. Findings indicated that individuals were at significantly increased risk for mortality when depression emerged after their first-reported MI, compared with resilient individuals who had no significant post-MI elevation in depression symptomatology. Individuals with chronic depression and those demonstrating pre-event depression followed by recovery after MI were not at increased risk. Further, optimism, measured before MI, prospectively differentiated all depressed individuals from participants who were resilient.

Patterns of lifetime PTSD comorbidity: a latent class analysis.

BACKGROUND: Posttraumatic stress disorder (PTSD) is associated with high rates of psychiatric comorbidity, most notably substance use disorders, major depression, and other anxiety disorders. However, little is known about how these disorders cluster together among people with PTSD, if disorder clusters have distinct etiologies in terms of trauma type, and if they confer greater burden over and above PTSD alone. METHOD: Utilizing Latent Class Analysis, we tested for discrete patterns of lifetime comorbidity with PTSD following trauma exposure (n = 409). Diagnoses were based on the Structured Clinical Interview for DSM-IV (SCID). Next, we examined if gender, trauma type, symptom frequency, severity, and interference with everyday life were associated with the latent classes. RESULTS: Three patterns of lifetime comorbidity with PTSD emerged: a class characterized by predominantly comorbid mood and anxiety disorders; a class characterized by predominantly comorbid mood, anxiety, and substance dependence; and a relatively pure low-comorbidity PTSD class. Individuals in both high comorbid classes had nearly two and a half times the rates of suicidal ideation, endorsed more PTSD symptom severity, and demonstrated a greater likelihood of intimate partner abuse compared to the low comorbidity class. Men were most likely to fall into the substance dependent class. CONCLUSION: PTSD comorbidity clusters into a small number of common patterns. These patterns may represent an important area of study, as they confer distinct differences in risk and possibly etiology. Implications for research and treatment are discussed.

Heterogeneous patterns of stress over the four years of college: associations with anxious attachment and ego-resiliency.

OBJECTIVE: A growing body of literature suggests that college students display alarming rates of psychological distress. However, studies of responses to significant life stressors in other contexts have found that people respond in heterogeneous ways and that attachment style and ego-resiliency mitigate the effects of stressors on mental health. METHOD: Individual differences in distress among a cohort of students (N = 157; Mean age = 18.8 years, 62.6% female) across the four years of college were analyzed using latent class growth analysis. Trajectories were then regressed on levels of anxious and avoidant attachment and ego-resiliency. RESULTS: Four discrete patterns emerged characterized by healthy and maladaptive patterns of stress response, indicating that students respond to college in heterogeneous ways. Several patterns showed significant variability in distress by semester. Low levels of anxious but not avoidant attachment predicted membership in the stable-low distress or resilient class while ego-resiliency predicted membership in both the resilient and moderate distress classes. CONCLUSIONS: Findings indicate that low levels of anxious attachment and the ability to flexibly cope with adversity may be associated with better mental health throughout college. Implications from stress response and developmental perspectives are discussed.

Positron emission tomography shows elevated cannabinoid CB1 receptor binding in men with alcohol dependence.

BACKGROUND: Several lines of evidence link cannabinoid (CB) type 1 (CB (1) ) receptor-mediated endogenous CB (eCB) signaling to the etiology of alcohol dependence (AD). However, to date, only peripheral measures of eCB function have been collected in living humans with AD and no human in vivo data on the potentially critical role of the brain CB (1) receptor in AD have been published. This is an important gap in the literature, because recent therapeutic developments suggest that these receptors could be targeted for the treatment for AD. METHODS: Medication-free participants were scanned during early abstinence 4 weeks after their last drink. Using positron emission tomography (PET) with a high-resolution research tomograph and the CB (1) receptor selective radiotracer [(11) C]OMAR, we determined [(11) C]OMAR volume of distribution ( V (T) ) values, a measure of CB (1) receptor density, in a priori selected brain regions in men with AD (n = 8, age 37.4 ± 7.9 years; 5 smokers) and healthy control (HC) men (n = 8, age 32.5 ± 6.9 years; all nonsmokers). PET images reconstructed using the MOLAR algorithm with hardware motion correction were rigidly aligned to the subject-specific magnetic resonance (MR) image, which in turn was warped to an MR template. Time-activity curves (TACs) were extracted from the dynamic PET data using a priori selected regions of interest delineated in the MR template space. RESULTS: In AD relative to HC, [(11) C]OMAR V (T) values were elevated by approximately 20% (p = 0.023) in a circuit, including the amygdala, hippocampus, putamen, insula, anterior and posterior cingulate cortices, and orbitofrontal cortex. Age, body mass index, or smoking status did not influence the outcome. CONCLUSIONS: These findings agree with preclinical evidence and provide the first, albeit still preliminary in vivo evidence suggesting a role for brain CB (1) receptors in AD. The current study design does not answer the important question of whether elevated CB (1) receptors are a preexisting vulnerability factor for AD or whether elevations develop as a consequence of AD.

Modern views of machine learning for precision psychiatry.

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

Facial and Vocal Markers of Schizophrenia Measured Using Remote Smartphone Assessments: Observational Study.

BACKGROUND: Machine learning-based facial and vocal measurements have demonstrated relationships with schizophrenia diagnosis and severity. Demonstrating utility and validity of remote and automated assessments conducted outside of controlled experimental or clinical settings can facilitate scaling such measurement tools to aid in risk assessment and tracking of treatment response in populations that are difficult to engage. OBJECTIVE: This study aimed to determine the accuracy of machine learning-based facial and vocal measurements acquired through automated assessments conducted remotely through smartphones. METHODS: Measurements of facial and vocal characteristics including facial expressivity, vocal acoustics, and speech prevalence were assessed in 20 patients with schizophrenia over the course of 2 weeks in response to two classes of prompts previously utilized in experimental laboratory assessments: evoked prompts, where subjects are guided to produce specific facial expressions and speech; and spontaneous prompts, where subjects are presented stimuli in the form of emotionally evocative imagery and asked to freely respond. Facial and vocal measurements were assessed in relation to schizophrenia symptom severity using the Positive and Negative Syndrome Scale. RESULTS: Vocal markers including speech prevalence, vocal jitter, fundamental frequency, and vocal intensity demonstrated specificity as markers of negative symptom severity, while measurement of facial expressivity demonstrated itself as a robust marker of overall schizophrenia symptom severity. CONCLUSIONS: Established facial and vocal measurements, collected remotely in schizophrenia patients via smartphones in response to automated task prompts, demonstrated accuracy as markers of schizophrenia symptom severity. Clinical implications are discussed.

Peritraumatic and trait dissociation differentiate police officers with resilient versus symptomatic trajectories of posttraumatic stress symptoms.

Research has consistently demonstrated that stress reactions to potentially traumatic events do not represent a unified phenomenon. Instead, individuals tend to cluster into prototypical response patterns over time including chronic symptoms, recovery, and resilience. We examined heterogeneity in a posttraumatic stress disorder (PTSD) symptom course in a sample of 178 active-duty police officers following exposure to a life-threatening event using latent growth mixture modeling (LGMM). This analysis revealed 3 discrete PTSD symptom trajectories: resilient (88%), distressed-improving (10%), and distressed-worsening (2%). We further examined whether trait and peritraumatic dissociation distinguished these symptom trajectories. Findings indicate that trait and peritraumatic dissociation differentiated the resilient from the distressed-improving trajectory (trait, p < .05; peritraumatic, p < .001), but only peritraumatic dissociation differentiated the resilient from the distressed-worsening trajectory (p < .001). It is essential to explore heterogeneity in symptom course and its predictors among active-duty police officers, a repeatedly exposed group. These findings suggest that police officers may be a highly resilient group overall. Furthermore, though there is abundant evidence that dissociation has a positive linear relationship with PTSD symptoms, this study demonstrates that degree of dissociation can distinguish between resilient and symptomatic groups of individuals.

Utilization of Machine Learning-Based Computer Vision and Voice Analysis to Derive Digital Biomarkers of Cognitive Functioning in Trauma Survivors.

BACKGROUND: Alterations in multiple domains of cognition have been observed in individuals who have experienced a traumatic stressor. These domains may provide important insights in identifying underlying neurobiological dysfunction driving an individual's clinical response to trauma. However, such assessments are burdensome, costly, and time-consuming. To overcome barriers, efforts have emerged to measure multiple domains of cognitive functioning through the application of machine learning (ML) models to passive data sources. METHODS: We utilized automated computer vision and voice analysis methods to extract facial, movement, and speech characteristics from semi-structured clinical interviews in 81 trauma survivors who additionally completed a cognitive assessment battery. A ML-based regression framework was used to identify variance in visual and auditory measures that relate to multiple cognitive domains. RESULTS: Models derived from visual and auditory measures collectively accounted for a large variance in multiple domains of cognitive functioning, including motor coordination (R2 = 0.52), processing speed (R2 = 0.42), emotional bias (R2 = 0.52), sustained attention (R2 = 0.51), controlled attention (R2 = 0.44), cognitive flexibility (R2 = 0.43), cognitive inhibition (R2 = 0.64), and executive functioning (R2 = 0.63), consistent with the high test-retest reliability of traditional cognitive assessments. Face, voice, speech content, and movement have all significantly contributed to explaining the variance in predicting functioning in all cognitive domains. CONCLUSIONS: The results demonstrate the feasibility of automated measurement of reliable proxies of cognitive functioning through low-burden passive patient evaluations. This makes it easier to monitor cognitive functions and to intervene earlier and at a lower threshold without requiring a time-consuming neurocognitive assessment by, for instance, a licensed psychologist with specialized training in neuropsychology.

Discriminating Heterogeneous Trajectories of Resilience and Depression After Major Life Stressors Using Polygenic Scores.

Importance: Major life stressors, such as loss and trauma, increase the risk of depression. It is known that individuals show heterogeneous trajectories of depressive symptoms following major life stressors, including chronic depression, recovery, and resilience. Although common genetic variation has been associated with depression risk, genomic factors that could help discriminate trajectories of risk vs resilience following adversity have not been identified. Objective: To assess the discriminatory accuracy of a deep neural net combining joint information from 21 psychiatric and health-related multiple polygenic scores (PGSs) for discriminating resilience vs other longitudinal symptom trajectories with use of longitudinal, genetically informed data on adults exposed to major life stressors. Design, Setting, and Participants: The Health and Retirement Study is a longitudinal panel cohort study in US citizens older than 50 years, with data being collected once every 2 years between 1992 and 2010. A total of 2071 participants who were of European ancestry with available depressive symptom trajectory information after experiencing an index depressogenic major life stressor were included. Latent growth mixture modeling identified heterogeneous trajectories of depressive symptoms before and after major life stressors, including stable low symptoms (ie, resilience), as well as improving, emergent, and preexisting/chronic symptom patterns. Twenty-one PGSs were examined as factors distinctively associated with these heterogeneous trajectories. Local interpretable model-agnostic explanations were applied to examine PGSs associated with each trajectory. Data were analyzed using the DNN model from June to July 2020. Exposures: Development of depression and resilience were examined in older adults after a major life stressor, such as bereavement, divorce, and job loss, or major health events, such as myocardial infarction and cancer. Main Outcomes and Measures: Discriminatory accuracy of a deep neural net model trained for the multinomial classification of 4 distinct trajectories of depressive symptoms (Center for Epidemiologic Studies-Depression scale) based on 21 PGSs using supervised machine learning. Results: Of the 2071 participants, 1329 were women (64.2%); mean (SD) age was 55.96 (8.52) years. Of these, 1638 (79.1%) were classified as resilient, 160 (7.75) in recovery (improving), 159 (7.7%) with emerging depression, and 114 (5.5%) with preexisting/chronic depression symptoms. Deep neural nets distinguished these 4 trajectories with high discriminatory accuracy (multiclass micro-average area under the curve, 0.88; 95% CI, 0.87-0.89; multiclass macro-average area under the curve, 0.86; 95% CI, 0.85-0.87). Discriminatory accuracy was highest for preexisting/chronic depression (AUC 0.93), followed by emerging depression (AUC 0.88), recovery (AUC 0.87), resilience (AUC 0.75). Conclusions and Relevance: The results of the longitudinal cohort study suggest that multivariate PGS profiles provide information to accurately distinguish between heterogeneous stress-related risk and resilience phenotypes.

Remote Digital Measurement of Facial and Vocal Markers of Major Depressive Disorder Severity and Treatment Response: A Pilot Study.

Objectives: Multiple machine learning-based visual and auditory digital markers have demonstrated associations between major depressive disorder (MDD) status and severity. The current study examines if such measurements can quantify response to antidepressant treatment (ADT) with selective serotonin reuptake inhibitors (SSRIs) and serotonin-norepinephrine uptake inhibitors (SNRIs). Methods: Visual and auditory markers were acquired through an automated smartphone task that measures facial, vocal, and head movement characteristics across 4 weeks of treatment (with time points at baseline, 2 weeks, and 4 weeks) on ADT (n = 18). MDD diagnosis was confirmed using the Mini-International Neuropsychiatric Interview (MINI), and the Montgomery-Åsberg Depression Rating Scale (MADRS) was collected concordantly to assess changes in MDD severity. Results: Patient responses to ADT demonstrated clinically and statistically significant changes in the MADRS [F (2, 34) = 51.62, p < 0.0001]. Additionally, patients demonstrated significant increases in multiple digital markers including facial expressivity, head movement, and amount of speech. Finally, patients demonstrated significantly decreased frequency of fear and anger facial expressions. Conclusion: Digital markers associated with MDD demonstrate validity as measures of treatment response.

Computer Vision-Based Assessment of Motor Functioning in Schizophrenia: Use of Smartphones for Remote Measurement of Schizophrenia Symptomatology.

INTRODUCTION: Motor abnormalities have been shown to be a distinct component of schizophrenia symptomatology. However, objective and scalable methods for assessment of motor functioning in schizophrenia are lacking. Advancements in machine learning-based digital tools have allowed for automated and remote "digital phenotyping" of disease symptomatology. Here, we assess the performance of a computer vision-based assessment of motor functioning as a characteristic of schizophrenia using video data collected remotely through smartphones. METHODS: Eighteen patients with schizophrenia and 9 healthy controls were asked to remotely participate in smartphone-based assessments daily for 14 days. Video recorded from the smartphone front-facing camera during these assessments was used to quantify the Euclidean distance of head movement between frames through a pretrained computer vision model. The ability of head movement measurements to distinguish between patients and healthy controls as well as their relationship to schizophrenia symptom severity as measured through traditional clinical scores was assessed. RESULTS: The rate of head movement in participants with schizophrenia (1.48 mm/frame) and those without differed significantly (2.50 mm/frame; p = 0.01), and a logistic regression demonstrated that head movement was a significant predictor of schizophrenia diagnosis (p = 0.02). Linear regression between head movement and clinical scores of schizophrenia showed that head movement has a negative relationship with schizophrenia symptom severity (p = 0.04), primarily with negative symptoms of schizophrenia. CONCLUSIONS: Remote, smartphone-based assessments were able to capture meaningful visual behavior for computer vision-based objective measurement of head movement. The measurements of head movement acquired were able to accurately classify schizophrenia diagnosis and quantify symptom severity in patients with schizophrenia.