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

Decoding chronic stress: From behavioral-molecular dynamics in mice to clinical implications of cortisol and IL-17 in depression severity

BACKGROUNDS

The etiology of depression involves chronic stress, a recognized determinant of onset and severity. This study adopts a translational approach, utilizing a mouse model and a clinical cohort to explore the relationship between chronic stress, molecular changes, and depression severity.

METHODS

In the mouse model, mice were exposed to varying frequencies of chronic stressors over several weeks, followed by behavioral assessments to confirm depressive-like behaviors and measurement of serum indicators to analyze their relationship with stress intensity. In the clinical cohort, we recruited 239 participants, including 137 patients with diagnosed depression and 102 healthy controls, and analyzed their plasma profiles for cortisol and inflammatory cytokines. The clinical cohort revealed distinctive plasma profiles, identifying cortisol and IL-17 as potential markers. Machine learning models were developed using these markers to distinguish depression severity.

RESULTS

The study revealed subtle behavioral-molecular changes in mice subjected to varying chronic stress intensities, confirming dose-response relationships. It identified cortisol and IL-17 as potential biomarkers for distinguishing depression severity and developed machine learning models demonstrating robust diagnostic capabilities.

LIMITATIONS

There is a substantial disparity in the number of individuals among different groups in the clinical participants.

CONCLUSION

The study establishes a correlation between cortisol, IL-17, and chronic stress intensity, suggesting the latter accelerates depression progression. Cortisol and IL-17 exhibit diagnostic potential, providing insights into depression progression and guiding targeted interventions. This research advances our understanding of stressinduced molecular changes in depression, contributing to the comprehension of the intricate relationship between chronic stress, molecular alterations, and depression severity.

Resilience Trajectories Among Older Adults With Disabilities: A Longitudinal Study in Anhui, China

This study applied Richardson's Resiliency Model to measure resilience in depressive symptoms among older adults with disabilities in rural China and examined its association with age-related and cohort-specific temporal effects using the Growth Curve Model to analyze resilience trajectories. We innovatively used propensity score matching to address confounding variables when calculating the resilience score. Data were derived from the Longitudinal Study of Older Adults in Anhui Province, China, with 3,672 observations from 2001 to 2021. The results revealed that 28.30 percent of rural older adults demonstrated resilience by maintaining or improving depressive symptoms post-disability onset. Resilience scores exhibited inverted U-shaped trajectories with increasing age. Similarly, resilience trajectories followed an inverted U-shape from the earlier cohort (born in 1924 or earlier) to the later cohort (born in 1950 or later). These insights into resilience trajectories can inform targeted policies and interventions, crucial as populations age and the prevalence of disability increases.

Exploring the developmental changes in and the relationship between resilience and anxiety and depression in older gastric cancer survivors: A latent growth mixture model and random intercept cross-lagged panel model analysis

OBJECTIVES

This study aims to investigate the independent and joint trajectories of resilience, anxiety, and depression symptoms and research the interaction between older gastric cancer survivors' resilience and anxiety-depression during the period of 1 year after surgery.

METHODS

The participants were 381 older gastric cancer survivors, with a mean age of 69 years. Resilience, anxiety, and depression symptoms were assessed immediately after surgery, and at 3, 6, and 12 months post-surgery, respectively. A longitudinal design was employed to capture the dynamic changes in resilience, anxiety, and depression levels among older gastric cancer survivors post-surgery. Latent growth mixture model and random intercept cross-lagged panel model were used to analyse the trajectories of resilience and anxiety-depression and the interaction between them.

RESULTS

Two latent trajectories were identified for the resilience, four latent trajectories were identified for the anxiety, and five latent trajectories were identified for the depression, respectively, with three joint trajectories identified: gradual-increasing resilience, gradual-decreasing anxiety, and depression group (10.0%); gradual-decreasing resilience, gradual-increasing anxiety, and depression group (21.2%); and rapid-growth resilience, rapid-decline anxiety, and depression group (68.8%). Resilience among older gastric cancer survivors exhibits significant bidirectional and negative predictive effects on anxiety and depression.

CONCLUSIONS

Individual differences in resilience, anxiety, and depression trajectories exist among older gastric cancer survivors, with heterogeneous joint progression patterns, and the relationship between resilience and anxiety-depression appears bidirectional. More sophisticated intervention programmes tailored to the unique characteristics of the relevant trajectories are necessary to enhance resilience and mitigate the risk of anxiety and depression.

Intergenerational continuation of parent-child separation and 1-year telomere length attrition among mother-offspring dyads in rural China: The moderating effects of resilience

BACKGROUND

Although stressor exposure early in life was known risk factor for telomere length (TL) attrition, limited literature explored it across generations. Furthermore, the effects of resilience have rarely been examined. Here, we examined whether the effects of intergenerational parent-child separation on offspring 1-year TL attrition vary by the levels of resilience.

METHOD

In a sample of 342 mother-child dyads living in rural China, the intergenerational continuation of parent-child separation was defined as the two generations both experiencing parent-child separation from both parents for >6 months a year early in life assessed by the parent-reported questionnaire, whereas intergenerational discontinuity refers to parent-child separation exposed in one generation only. TL was measured at baseline (from June to November 2021) and 1-year later with children's buccal mucosa swabs, with resilience polygenic risk scores (PRS) evaluated based on 4 single-nucleotide variations in 4 resilience-related genes (OXTR, FKBP5, NPY, and TNF-α).

RESULTS

Among 342 mother-offspring dyads, 35 (10.2 %) experienced intergenerational continuation of parent-child separation, and 139 (40.6 %) were identified as discontinuous. Remarkably, a 0.12-point reduction in TL attrition was only associated with intergenerational continuation of parent-child separation (95 % CI: 0.04, 0.21, P < 0.01) but not discontinuity. Importantly, the association between intergenerational continuation of parent-child separation with accelerated TL attrition disappeared in offspring with high resilience PRS (β = 0.07, 95%CI: -0.06, 0.21).

CONCLUSION

Our findings highlight the importance of breaking the intergenerational cycle of parent-child separation and the moderating effects of resilience on TL attrition for children exposed to adversity.

Depression is Associated with Treatment Response Trajectories in Adults with Prolonged Grief Disorder: A Machine Learning Analysis

Although evidence-based treatments for Prolonged Grief Disorder (PGD) exist, pretreatment characteristics associated with differential improvement trajectories have not been identified. To identify clinical factors relevant to optimizing PGD treatment outcomes, we used unsupervised and supervised machine learning to study treatment effects from a double-blinded, placebo-controlled, randomized clinical trial. Participants were randomized into four treatment groups for 20 weeks: citalopram with grief-informed clinical management, citalopram with prolonged grief disorder therapy (PGDT), pill placebo with PGDT, or pill placebo with clinical management. The trial included 333 PGD patients aged 18-95 years (M age = 53.9; SD ± 14.4), predominantly female (77.4%) and white (84.4%). Symptom trajectories were assessed using latent growth mixture modeling based on Inventory for Complicated Grief scores collected at six time points every 4 weeks. The relationship between patient-level characteristics and assigned trajectories was examined using logistic regression with elastic net regularization based on the administration of citalopram, PGDT, and risk factors for developing PGD. Three distinct response trajectories were identified: lesser severity responders (60%, n = 200), greater severity responders (18.02%, n = 60), and non-responders (21.92%, n = 73). Differences between greater severity responders and non-responders emerged as statistically significant by Week 8. The elastic net model demonstrated acceptable discrimination between responders and non-responders (AUC = .702; accuracy = .684). Higher baseline depression severity, grief-related functional impairment, and absence of PGDT were associated with reduced treatment response likelihood. These findings underscore the importance of early identification of clinical factors to optimize individualized PGD treatment strategies.

Trial Registration

clinicaltrials.gov Identifier: NCT01179568.

Influences of sex and gender on the associations between risk and protective factors, brain, and behavior

Risk and protective factors for psychiatric illnesses are linked to distinct structural and functional changes in the brain. Further, the prevalence of these factors varies across sexes and genders, yet the distinct and joint effects of sex and gender in this context have not been extensively characterized. This suggests that risk and protective factors may map onto the brain and uniquely influence individuals across sexes and genders. Here, we review how specific risk (childhood maltreatment, the COVID-19 pandemic, experiences of racism), and protective factors (social support and psychological resilience) distinctly influence the brain across sexes and genders. We also discuss the role of sex and gender in the compounding effects of risk factors and in the interdependent influences of risk and protective factors. As such, we call on researchers to consider sex and gender when researching risk and protective factors for psychiatric illnesses, and we provide concrete recommendations on how to account for them in future research. Considering protective factors alongside risk factors in research and acknowledging sex and gender differences will enable us to establish sex- and gender-specific brain-behavior relationships. This will subsequently inform the development of targeted prevention and intervention strategies for psychiatric illnesses, which have been lacking. To achieve sex and gender equality in mental health, acknowledging and researching potential differences will lead to a better understanding of men and women, males and females, and the factors that make them more vulnerable or resilient to psychopathology.

Explainable Machine Learning Models for Brain Diseases: Insights from a Systematic Review

In recent years, Artificial Intelligence (AI) methods, specifically Machine Learning (ML) models, have been providing outstanding results in different areas of knowledge, with the health area being one of its most impactful fields of application. However, to be applied reliably, these models must provide users with clear, simple, and transparent explanations about the medical decision-making process. This systematic review aims to investigate the use and application of explainability in ML models used in brain disease studies. A systematic search was conducted in three major bibliographic databases, Web of Science, Scopus, and PubMed, from January 2014 to December 2023. A total of 133 relevant studies were identified and analyzed out of a total of 682 found in the initial search, in which the explainability of ML models in the medical context was studied, identifying 11 ML models and 12 explainability techniques applied in the study of 20 brain diseases.

Patterns of resilient functioning in early life: Identifying distinct groups and associated factors

Resilience, the capacity to maintain or regain functionality in the face of adversity, is a dynamic process influenced by individual, familial, and community factors. Despite its variability, distinct resilience trajectories can be identified within populations, yet the predictors defining these distinct groups remains largely unclear. Here, using data from the Avon Longitudinal Study of Parents and Children (ages 0-18), we quantify resilience as the remaining variance in psychosocial functioning after taking into account the exposure to adversity. Growth mixture modeling identified seven distinct resilience trajectories, with over half of the study population maintaining resilience throughout early life. Factors increasing the likelihood of resilient trajectory membership included a less emotional temperament, high cognitive abilities, high self-esteem, low levels of autistic social traits, strong sibling relationships, high maternal care, and positive school experiences. Among the socioeconomic factors considered, maternal education - a significant indicator of socioeconomic status - and birth-order were associated with resilient trajectories. Our findings underscore the importance of fostering cognitive abilities, self-esteem, social relationships, positive school experiences, and extracurricular engagement to bolster resilience in adversity-exposed individuals and communities. This research informs resilience-focused interventions in mental health, education, and social policy sectors, and prompts further exploration of socioeconomic influences on resilience trajectories.

The three axioms of resilience

This article summarizes the growing literature on resilience in the face of aversive and potentially traumatic events (PTEs) in three basic axioms: (a) resilience is a common outcome, 2) there are no "key" traits to resilience (resilience is not a type), and (c) resilient outcomes occur through flexible self-regulation. The first axiom highlights the limitation of a traditional, binary view of trauma in terms of the presence-absence of posttraumatic stress disorder, emphasizing instead the heterogeneity of trauma outcomes. Four prototypical trajectories are reviewed: chronic symptoms; delayed symptoms; recovery; and the most common trajectory, resilience. The second axiom reviews the paradoxical inability of known correlates of resilience to adequately predict resilient outcomes. Resilience is instead described as a multifaceted phenomenon with no singular set of key traits, as various factors contribute to resilient outcomes in complex ways. The third axiom provides an explanation of how resilience can emerge from this complex array by introducing the concept of flexible self-regulation. The flexibility mindset is described as providing the motivation for flexible responding. The flexibility sequence is described as explaining the mechanisms underlying flexibility in terms of three serial stages: context sensitivity, strategy repertoire, and feedback adjustment. The final section briefly considers clinical implications.

At-home, telehealth-supported ketamine treatment for depression: Findings from longitudinal, machine learning and symptom network analysis of real-world data

BACKGROUND

Improving safe and effective access to ketamine therapy is of high priority given the growing burden of mental illness. Telehealth-supported administration of sublingual ketamine is being explored toward this goal.

METHODS

In this longitudinal study, moderately-to-severely depressed patients received four doses of ketamine at home over four weeks within a supportive digital health context. Treatment was structured to resemble methods of therapeutic psychedelic trials. Patients receiving a second course of treatment were also examined. Symptoms were assessed using the Patient Health Questionnaire (PHQ-9) for depression. We conducted preregistered machine learning and symptom network analyses to investigate outcomes (osf.io/v2rpx).

RESULTS

A sample of 11,441 patients was analyzed, demonstrating a modal antidepressant response from both non-severe (n = 6384, 55.8 %) and severe (n = 2070, 18.1 %) baseline depression levels. Adverse events were detected in 3.0-4.8 % of participants and predominantly neurologic or psychiatric in nature. A second course of treatment helped extend improvements in patients who responded favorably to initial treatment. Improvement was most strongly predicted by lower depression scores and age at baseline. Symptoms of Depressed mood and Anhedonia sustained depression despite ongoing treatment.

LIMITATIONS

This study was limited by the absence of comparison or control groups and lack of a fixed-dose procedure for ketamine administration.

CONCLUSIONS

At-home, telehealth-supported ketamine administration was largely safe, well-tolerated, and associated with improvement in patients with depression. Strategies for combining psychedelic-oriented therapies with rigorous telehealth models, as explored here, may uniquely address barriers to mental health treatment.

Identifying Depression Through Machine Learning Analysis of Omics Data: Scoping Review

BACKGROUND

Depression is one of the most common mental disorders that affects >300 million people worldwide. There is a shortage of providers trained in the provision of mental health care, and the nursing workforce is essential in filling this gap. The diagnosis of depression relies heavily on self-reported symptoms and clinical interviews, which are subject to implicit biases. The omics methods, including genomics, transcriptomics, epigenomics, and microbiomics, are novel methods for identifying the biological underpinnings of depression. Machine learning is used to analyze genomic data that includes large, heterogeneous, and multidimensional data sets.

OBJECTIVE

This scoping review aims to review the existing literature on machine learning methods for omics data analysis to identify individuals with depression, with the goal of providing insight into alternative objective and driven insights into the diagnostic process for depression.

METHODS

This scoping review was reported following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Searches were conducted in 3 databases to identify relevant publications. A total of 3 independent researchers performed screening, and discrepancies were resolved by consensus. Critical appraisal was performed using the Joanna Briggs Institute Critical Appraisal Checklist for Analytical Cross-Sectional Studies.

RESULTS

The screening process identified 15 relevant papers. The omics methods included genomics, transcriptomics, epigenomics, multiomics, and microbiomics, and machine learning methods included random forest, support vector machine, k-nearest neighbor, and artificial neural network.

CONCLUSIONS

The findings of this scoping review indicate that the omics methods had similar performance in identifying omics variants associated with depression. All machine learning methods performed well based on their performance metrics. When variants in omics data are associated with an increased risk of depression, the important next step is for clinicians, especially nurses, to assess individuals for symptoms of depression and provide a diagnosis and any necessary treatment.

Resilience in the Face of Cancer: On the Importance of Defining and Studying Resilience as a Dynamic Process of Adaptation

Resilience is defined as the maintenance or relatively quick recovery of mental health during and after adversity. Rather than focusing on psychopathology and its causes, resilience research aims to understand what protective mechanisms shield individuals against developing such disorders and translate these insights to improve psychosocial care. This resilience approach seems especially promising for the field of oncology because patients face stressor after stressor from diagnosis to survivorship. Helping patients to learn how they can best use the resources and abilities available to them can empower patients to handle subsequent stressors. In the past few decades, resilience has increasingly been considered as a dynamic process of adaptation. While researchers use this definition, resilience has not yet been studied as a dynamic process in the field of oncology. As a result, the potential of resilience research to gain insight into what helps protect cancer patients from developing psychopathology is limited. We discuss conceptual and methodological proposals to advance resilience research in oncology. Most importantly, we propose applying prospective longitudinal designs to capture the dynamic resilience process. By gaining insight in how cancer patients engage in protective factors, resilience research can come to its full potential and help prevent psychopathology.

Distinguishing vulnerability and resilience to posttraumatic stress disorder evaluating traumatic experiences, genetic risk and electronic health records

What distinguishes vulnerability and resilience to posttraumatic stress disorder (PTSD) remains unclear. Levering traumatic experiences reporting, genetic data, and electronic health records (EHR), we investigated and predicted the clinical comorbidities (co-phenome) of PTSD vulnerability and resilience in the UK Biobank (UKB) and All of Us Research Program (AoU), respectively. In 60,354 trauma-exposed UKB participants, we defined PTSD vulnerability and resilience considering PTSD symptoms, trauma burden, and polygenic risk scores. EHR-based phenome-wide association studies (PheWAS) were conducted to dissect the co-phenomes of PTSD vulnerability and resilience. Significant diagnostic endpoints were applied as weights, yielding a phenotypic risk score (PheRS) to conduct PheWAS of PTSD vulnerability and resilience PheRS in up to 95,761 AoU participants. EHR-based PheWAS revealed three significant phenotypes positively associated with PTSD vulnerability (top association "Sleep disorders") and five outcomes inversely associated with PTSD resilience (top association "Irritable Bowel Syndrome"). In the AoU cohort, PheRS analysis showed a partial inverse relationship between vulnerability and resilience with distinct comorbid associations. While PheRSvulnerability associations were linked to multiple phenotypes, PheRSresilience showed inverse relationships with eye conditions. Our study unveils phenotypic differences in PTSD vulnerability and resilience, highlighting that these concepts are not simply the absence and presence 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.

Resilience Phenotypes and Psychological Functioning among Individuals with Opioid Use Disorder

BACKGROUND

Opioid use disorder (OUD) is a heterogeneous disorder. However, there is a lack of deep phenotyping investigations focusing on important psychological constructs such as resilience that may impact OUD. The present study aimed to investigate the relationship between trait resilience and the five-factor model of personality (FFM) among individuals with opioid use disorder (OUD). We also explored whether the FFM and trait resilience form specific phenotypes associated with psychological functioning.

METHODS

This secondary analysis of an epigenetic study included participants of African ancestry (n = 72), an understudied population, who met DSM-5 criteria for OUD. Participants completed measures to assess personality traits, trait resilience, current and previous drug use, and psychological functioning (depression, anxiety, and stress).

RESULTS

Linear regression revealed a significant relationship between resilience (CD-RISC-25 score) and the FFM, R2 = 0.56, F(5,62) = 15.7, p<.001. Further, a two-cluster classification emerged as the optimal solution from the cluster analysis. Cluster 1 (n = 33, 45.8% of the sample) showed lower resilience (CD-RISC-25 score: M = 58.6, SD = 11.2) compared to Cluster 2 (n = 35, 48.6%; CD-RISC-25 score: M = 76.1, SD = 11.9). The "High-Resilience Cluster" (Cluster 2) was characterized by higher FFM traits of: Extraversion, Openness, Agreeableness, and Conscientiousness, and lower Neuroticism versus Cluster 1. Multivariate analysis of variance revealed statistically significant differences between the two resilience clusters concerning other psychological symptoms, Λ = 0.732, F(4, 50) = 7.05, p < 0.003.

CONCLUSIONS

These findings suggest associations between the FFM and trait resilience among individuals with OUD. Two distinct "resilience phenotypes" emerged, with high-resilience individuals displaying less stress, anxiety, and depressive symptoms. Results highlight the clinical importance of resilience as a potential target for intervention in people with OUD.

Predicting acute pancreatitis severity with enhanced computed tomography scans using convolutional neural networks

This study aimed to evaluate acute pancreatitis (AP) severity using convolutional neural network (CNN) models with enhanced computed tomography (CT) scans. Three-dimensional DenseNet CNN models were developed and trained using the enhanced CT scans labeled with two severity assessment methods: the computed tomography severity index (CTSI) and Atlanta classification. Each labeling method was used independently for model training and validation. Model performance was evaluated using confusion matrices, areas under the receiver operating characteristic curve (AUC-ROC), accuracy, precision, recall, F1 score, and respective macro-average metrics. A total of 1,798 enhanced CT scans met the inclusion criteria were included in this study. The dataset was randomly divided into a training dataset (n = 1618) and a test dataset (n = 180) with a ratio of 9:1. The DenseNet model demonstrated promising predictions for both CTSI and Atlanta classification-labeled CT scans, with accuracy greater than 0.7 and AUC-ROC greater than 0.8. Specifically, when trained with CT scans labeled using CTSI, the DenseNet model achieved good performance, with a macro-average F1 score of 0.835 and a macro-average AUC-ROC of 0.980. The findings of this study affirm the feasibility of employing CNN models to predict the severity of AP using enhanced CT scans.

Associations of polygenic risk scores with posttraumatic stress symptom trajectories following combat deployment

BACKGROUND

Identification of genetic risk factors may inform the prevention and treatment of posttraumatic stress disorder (PTSD). This study evaluates the associations of polygenic risk scores (PRS) with patterns of posttraumatic stress symptoms following combat deployment.

METHOD

US Army soldiers of European ancestry (n = 4900) provided genomic data and ratings of posttraumatic stress symptoms before and after deployment to Afghanistan in 2012. Latent growth mixture modeling was used to model posttraumatic stress symptom trajectories among participants who provided post-deployment data (n = 4353). Multinomial logistic regression models tested independent associations between trajectory membership and PRS for PTSD, major depressive disorder (MDD), schizophrenia, neuroticism, alcohol use disorder, and suicide attempt, controlling for age, sex, ancestry, and exposure to potentially traumatic events, and weighted to account for uncertainty in trajectory classification and missing data.

RESULTS

Participants were classified into low-severity (77.2%), increasing-severity (10.5%), decreasing-severity (8.0%), and high-severity (4.3%) posttraumatic stress symptom trajectories. Standardized PTSD-PRS and MDD-PRS were associated with greater odds of membership in the high-severity v. low-severity trajectory [adjusted odds ratios and 95% confidence intervals, 1.23 (1.06-1.43) and 1.18 (1.02-1.37), respectively] and the increasing-severity v. low-severity trajectory [1.12 (1.01-1.25) and 1.16 (1.04-1.28), respectively]. Additionally, MDD-PRS was associated with greater odds of membership in the decreasing-severity v. low-severity trajectory [1.16 (1.03-1.31)]. No other associations were statistically significant.

CONCLUSIONS

Higher polygenic risk for PTSD or MDD is associated with more severe posttraumatic stress symptom trajectories following combat deployment. PRS may help stratify at-risk individuals, enabling more precise targeting of treatment and prevention programs.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Maternal distress and parenting during COVID-19: differential effects related to pre-pandemic distress?

BACKGROUND

Distinguishing whether and how pre-existing characteristics impact maternal responses to adversity is difficult: Does prior well-being decrease the likelihood of encountering stressful experiences? Does it protect against adversity's negative effects? We examine whether the interaction between relatively uniformly experienced adversity (due to COVID-19 experience) and individual variation in pre-existing (i.e., pre-pandemic onset) distress predicted mothers' pandemic levels of distress and insensitive caregiving within a country reporting low COVID-19 death rates, and strict nationwide regulations.

METHOD

Fifty-one Singaporean mothers and their preschool-aged children provided data across two waves. Pre- pandemic onset maternal distress (i.e., psychological distress, anxiety, and parenting stress) was captured via self-reports and maternal sensitivity was coded from videos. Measures were repeated after the pandemic's onset along with questionnaires concerning perceived COVID-19 adversity (e.g., COVID-19's impact upon stress caring for children, housework, job demands, etc.) and pandemic-related objective experiences (e.g., income, COVID-19 diagnoses, etc.). Regression analyses (SPSS v28) considered pre-pandemic onset maternal distress, COVID-19 stress, and their interaction upon post-pandemic onset maternal distress. Models were re-run with appropriate covariates (e.g., objective experience) when significant findings were observed. To rule out alternative models, follow up analyses (PROCESS Model) considered whether COVID-19 stress mediated pre- and post-pandemic onset associations. Models involving maternal sensitivity followed a similar data analytic plan.

RESULTS

Pre-pandemic maternal distress moderated the association between COVID-19 perceived stress and pandemic levels of maternal distress (β = 0.22, p < 0.01) but not pandemic assessed maternal sensitivity. Perceived COVID-19 stress significantly contributed to post-pandemic onset maternal distress for mothers with pre-pandemic onset distress scores above (β = 0.30, p = 0.05), but not below (β = 0.25, p = 0.24), the median. Objective COVID-19 adversity did not account for findings. Post-hoc analyses did not suggest mediation via COVID-19 stress from pre-pandemic to pandemic maternal distress.

CONCLUSIONS

Pre-existing risk may interact with subsequent perceptions of adversity to impact well-being. In combination with existing research, this small study suggests prevention programs should focus upon managing concurrent mental health and may highlight the importance of enhanced screening and proactive coping programs for people entering high stress fields and/or phases of life.

Do the various leisure forms have equal effects on mental health? A longitudinal analysis of self-selected leisure activities

The deteriorating trends of unbalanced income, progressive age-related health problems, and loss of traditional ties necessitate ever-flexible interventions that are helpful to overcome a decline in Chinese adults' mental health. This study aimed to test whether engagement in different domains of leisure is associated with a composite index of mental health, both concurrently and subsequently. Longitudinal data including 10,968 participants (females = 5,804) with a mean age of 46.01 years in the Chinese General Social Survey (CGSS) were analyzed using generalized estimating equations with a logit link. The results showed that face-to-face experiences, such as sports with all ORs of < 1 at the significance level of α = 0.01 and meeting with all ORs of < 1 at the significance level of α = 0.01 except daily in-person meeting frequency, are important for protecting mental health owing to the increasing social support by building close ties. The results also indicate that online leisure with all ORs < 1 at the significance level of α = 0.01 has positive effects on lowering the odds of depression. In addition, receptive cognitive leisure, such as watching television or movies with all ORs < 1 at the significance level of α = 0.05 level, was not consistently associated with depression. However, active cognitive leisure, such as reading with all ORs of < 1 at a significance level of α = 0.01, was associated with lower odds of depression.

Optimal 18F-FDG PET/CT radiomics model development for predicting EGFR mutation status and prognosis in lung adenocarcinoma: a multicentric study

Purpose

To develop and interpret optimal predictive models to identify epidermal growth factor receptor (EGFR) mutation status and subtypes in patients with lung adenocarcinoma based on multicentric ¹⁸F-FDG PET/CT data, and further construct a prognostic model to predict their clinical outcome.

Methods

The ¹⁸F-FDG PET/CT imaging and clinical characters of 767 patients with lung adenocarcinoma from 4 cohorts were collected. Seventy-six radiomics candidates using cross-combination method to identity EGFR mutation status and subtypes were built. Further, Shapley additive explanations and local interpretable model-agnostic explanations were used for optimal models' interpretation. Moreover, in order to predict the overall survival, a multivariate Cox proportional hazard model based on handcrafted radiomics features and clinical characteristics was constructed. The predictive performance and clinical net benefit of the models were evaluated via area under receiver operating characteristic (AUC), C-index and decision curve analysis.

Results

Among the 76 radiomics candidates, light gradient boosting machine classifier (LGBM) combined with recursive feature elimination wrapped LGBM feature selection method achieved best performance in predicting EGFR mutation status (AUC reached 0.80, 0.61, 0.71 in the internal test cohort and two external test cohorts, respectively). And extreme gradient boosting classifier combined with support vector machine feature selection method achieved best performance in predicting EGFR subtypes (AUC reached 0.76, 0.63, 0.61 in the internal test cohort and two external test cohorts, respectively). The C-index of the Cox proportional hazard model achieved 0.863.

Conclusions

The integration of cross-combination method and the external validation from multi-center data achieved a good prediction and generalization performance in predicting EGFR mutation status and its subtypes. The combination of handcrafted radiomics features and clinical factors achieved good performance in predicting prognosis. With the urgent needs of multicentric ¹⁸F-FDG PET/CT trails, robust and explainable radiomics models have great potential in decision making and prognosis prediction of lung adenocarcinoma.

Relationship between anxiety and depressive trajectories of women who conceived through assisted reproductive technology and their children's emotional and behavioral problems: A prospective cohort study

OBJECTIVE

This study aimed to examine the relationship between the anxiety and depressive trajectory of women conceived through assisted reproductive technology (ART) and their children's emotional and behavioral problems.

METHODS

This prospective cohort study including 18,711 women, was conducted between July 2014 and December 2017. Self-rating scales for anxiety and depression were used before treatment, during the first trimester, and two to three years postpartum. A latent class growth analysis identified their maternal anxiety and depressive symptom trajectories. Multiple comparison and linear regression models were performed to assess the relationships between maternal trajectories and their offspring's emotional and behavioral problems.

RESULTS

Three longitudinal heterogeneous trajectories of maternal anxiety and depressive symptoms were identified: resilient, recurrent, and emergent. After adjusting for covariates, children with mothers in the recurrent and emergent trajectory groups had higher Child Behavior Checklist/2-3 scores. Additionally, the participants with a recurrent trajectory had lower education and employment levels and younger maternal age at delivery. They also had a history of ovarian surgery, primipara, secondary infertility, polycystic ovary syndrome, and more embryo transferred cycles, including intracytoplasmic sperm injections. Those with resilient trajectories had higher antral follicle counts and GnRH antagonist protocol. Finally, the participants with emergent trajectories had a lower monthly income, primipara, ectopic pregnancy, and fresh embryo transfers.

CONCLUSIONS

Infertile women's psychological stress was not alleviated by the ART-sociodemographic, infertility-related and treatment-related characteristics determined three mental health trajectories. Children with mothers in recurrent and emergent trajectories showed higher odds of experiencing emotional and behavioral problems.

Genetic predisposition to depression and inflammation impacts symptom burden and survival in patients with head and neck cancer: A longitudinal study

OBJECTIVE

The primary purpose of this study was to investigate the contribution of genetic predispositions to depression and inflammation, as measured through polygenic risk scores, on symptom burden (physical and psychological) in patients with head and neck cancer in the immediate post-treatment period (i.e., at three months post-diagnosis), as well as on 3-, 6-, 12-, 24- and 36-month survival.

METHODS

Prospective longitudinal study of 223 adults (72 % participation) newly diagnosed with a first occurrence of primary head and neck cancer, paired with genetic data (Illumina PsychArray), validated psychometric measures, Structured Clinical Interviews for DSM Disorders (SCID-I), and medical chart reviews.

RESULTS

Symptom burden at 3 months was predicted by (R² adj. = 0.38, p < 0.001): a baseline SCID-I Anxiety Disorder (b = 1.69, B = 0.23, 95%CI = 0.43-2.94; p = 0.009), baseline levels of HADS anxiety (b = 0.20, B = 0.29, 95%CI = 0.07-0.34; p = 0.003), the polygenic risk score (PRS) for depression (b = 0.66, B = 0.18, 95%CI = 0.003-1.32; p = 0.049), and cumulated dose of radiotherapy (b = 0.002, B = 0.46, 95%CI = 0.001-0.003; p < 0.001). When controlling for factors known to be associated with cancer survival, patients with a higher PRS associated with depression and inflammation, respectively, presented higher risk of death within 36 months (b = 1.75, Exp(B) = 5.75, 95%CI = 1.55-21.27, p = 0.009 and b = 0.14, Exp(B) = 1.15, 95%CI = 1.01-1.30, p = 0.03).

CONCLUSIONS

Our results outline three potential pathways of symptom burden in patients with head and neck cancer: a genetic predisposition towards depression; an initial anxiety disorder upon being diagnosed with cancer or high levels of anxiety upon diagnosis; and a dose-related response to radiotherapy. One may want to investigate early interventions in these areas to alleviate symptom burden in patients faced with a life-threatening disease, as well as consider targeting genetic predisposition towards depression and inflammation implicated in survival. The high prevalence of distress in patients with head and neck cancer is an opportunity to study genetic predispositions, which could potentially be broadly generalized to other cancers and diseases.

Latent patterns of depression trajectory among adolescents during the covid-19 pandemic

Present study aimed to explore adolescent depression trajectory during the COVID-19 pandemic, and the impact of parental style on it. Five-wave data of adolescent sample in China mainland were collected, and the group-based trajectory modeling was used to examine the theory constructs. Findings showed that, during the COVID-19 pandemic, there are four distinct patterns of change in depression symptoms over time, namely, resistance (72.3 %), recovery (15.3 %), increasing (6.7 %), chronic (5.7 %). Differences about the impact of parental style and grade on depression trajectory were found. Findings contribute to the knowledge of the impact of the COVID-19 pandemic on depression trajectory among general population, and parental style and grade should be considered in adolescent psychological intervention in the pandemic.

Physical activity may buffer against depression and promote resilience after major life stressors

As many individuals experience potentially traumatic or stressful life events, understanding factors that are likely to promote resilience is imperative. Given the demonstrated efficacy of exercise for depression treatment, we examined if exercise buffers against the risk of developing psychiatric symptoms following life stressors. 1405 participants (61% female) from a longitudinal panel cohort experienced disability onset (43%), bereavement (26%), heart attack (20%), divorce (11%), and job loss (3%). They reported time spent exercising and depressive symptoms (Center for Epidemiologic Studies Depression scale) across three time points collected in two-year intervals: T0 (pre-stressor), T1 (acutely post-stressor), and T2 (post-stressor). Participants were classified in previously identified heterogeneous depression trajectories pre- to post-life stressor: resilient (69%), emerging (11.5%), chronic (10%), and improving (9.5%). Multinomial logistic regression found that more T0 exercise predicted likelihood of classification in resilient versus other groups (all p<.02). Controlling for covariates, only the higher likelihood of classification in resilient versus improving remained (p=.03). Follow-up repeated measures general linear model (GLM) assessed whether trajectory was associated with exercise at each time, controlling for covariates. GLM indicated significant within-subjects effects for time (p=.016, partial η2=.003) and time*trajectory (p=.020, partial η2=.005) on exercise and significant between-subjects effects of trajectory (p<.001, partial η2=.016) and all covariates. The resilient group showed consistent high exercise levels. The improving group had consistent moderate exercise. The emerging and chronic groups were associated with lower exercise post-stressor. Pre-stressor exercise may buffer against depression and ongoing exercise may be associated with lower depression levels following a major life stressor.

Resilient phenotypes among bereaved youth: a comparison of trajectory, relative, and cross-domain approaches

BACKGROUND

Bereavement is a common traumatic event associated with adverse health outcomes across the life course. Despite these risks, not all bereaved individuals experience these negative effects. Limited scientific consensus exists on how to define resilience in individuals who have experienced the death of a loved one.

METHODS

Using a sample of N = 3766 youth from the Avon Longitudinal Study of Parents and Children birth cohort, we identified bereavement of a family member between ages 7 and 8.5. We derived and compared three different approaches to assess resilience among bereaved youth. Trajectory-based psychological resilience identified sub-groups with similar psychological symptom profiles between ages 6 and 16 using latent growth mixture models. Relative psychological resilience at age 16 leveraged standardized residuals from a model regressing psychological symptoms on bereavement to determine better-than-expected psychological functioning relative to bereavement status. Relative cross-domain resilience around age 16 was a sum score of the residuals approach applied to eight unique domains of health. Predictive validity of each approach was assessed using depressive symptoms at age 17.5 RESULTS: Overall, N = 877 (23%) youth were bereaved of a family member between ages 7 and 8.5. Using latent growth mixture models, a three-class solution described 84% of bereaved youth with low and stable psychological symptoms over time, 8% with worsening symptoms, and 8% with improving yet elevated symptoms. Each relative resilience score was largely concordant with the trajectory-based approach in identifying individuals as resilient or not, though relative psychological resilience demonstrated a stronger degree of concordance than the cross-domain score. Relative psychological and cross-domain resilience exhibited moderate to low correlation, depending on the domains included (r = 0.14-0.43). For each approach, resilience significantly predicted lower depressive symptoms at age 17.5, highlighting predictive validity of these measures.

CONCLUSIONS

Psychological symptom trajectories among bereaved youth aligned with those previously identified among bereaved adults. The residual-based approach to defining resilience exhibited limited utility in the context of bereavement. When identifying risk and resilience after bereavement, researchers and clinicians must address the interplay across psychosocial and physical health domains, as bereaved youth considered resilient from a mental health perspective may benefit from intervention in other domains.

Methodological and Quality Flaws in the Use of Artificial Intelligence in Mental Health Research: Systematic Review

BACKGROUND

Artificial intelligence (AI) is giving rise to a revolution in medicine and health care. Mental health conditions are highly prevalent in many countries, and the COVID-19 pandemic has increased the risk of further erosion of the mental well-being in the population. Therefore, it is relevant to assess the current status of the application of AI toward mental health research to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

This study aims to perform a systematic overview of AI applications in mental health in terms of methodologies, data, outcomes, performance, and quality.

METHODS

A systematic search in PubMed, Scopus, IEEE Xplore, and Cochrane databases was conducted to collect records of use cases of AI for mental health disorder studies from January 2016 to November 2021. Records were screened for eligibility if they were a practical implementation of AI in clinical trials involving mental health conditions. Records of AI study cases were evaluated and categorized by the International Classification of Diseases 11th Revision (ICD-11). Data related to trial settings, collection methodology, features, outcomes, and model development and evaluation were extracted following the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) guideline. Further, evaluation of risk of bias is provided.

RESULTS

A total of 429 nonduplicated records were retrieved from the databases and 129 were included for a full assessment-18 of which were manually added. The distribution of AI applications in mental health was found unbalanced between ICD-11 mental health categories. Predominant categories were Depressive disorders (n=70) and Schizophrenia or other primary psychotic disorders (n=26). Most interventions were based on randomized controlled trials (n=62), followed by prospective cohorts (n=24) among observational studies. AI was typically applied to evaluate quality of treatments (n=44) or stratify patients into subgroups and clusters (n=31). Models usually applied a combination of questionnaires and scales to assess symptom severity using electronic health records (n=49) as well as medical images (n=33). Quality assessment revealed important flaws in the process of AI application and data preprocessing pipelines. One-third of the studies (n=56) did not report any preprocessing or data preparation. One-fifth of the models were developed by comparing several methods (n=35) without assessing their suitability in advance and a small proportion reported external validation (n=21). Only 1 paper reported a second assessment of a previous AI model. Risk of bias and transparent reporting yielded low scores due to a poor reporting of the strategy for adjusting hyperparameters, coefficients, and the explainability of the models. International collaboration was anecdotal (n=17) and data and developed models mostly remained private (n=126).

CONCLUSIONS

These significant shortcomings, alongside the lack of information to ensure reproducibility and transparency, are indicative of the challenges that AI in mental health needs to face before contributing to a solid base for knowledge generation and for being a support tool in mental health management.

Resilience in older adults with cancer: A scoping literature review

INTRODUCTION

Resilience, the ability to respond to stressors by maintaining or rapidly returning to normal homeostasis, serves as a new paradigm to improve the care of older adults. However, resilience research in oncology is nascent. We aimed to describe the current research landscape on physical, cognitive, and psychosocial resilience in older cancer patients.

MATERIALS AND METHODS

We searched PubMed/MEDLINE from inception to January 28, 2022 for records with the terms "resilient OR resilience OR resiliency." We included studies that focused on persons over age 65 with cancer and assessed physical, cognitive, or psychological resilience. We excluded studies that did not report original data; did not have the full text available; assessed resilience on fewer than three time points; and published in non-English languages. Definitions and measures of resilience were extracted and categorized using qualitative analysis.

RESULTS

Of 473 articles screened, we found 29 articles that met criteria for inclusion in our review. There was a high degree of heterogeneity in the definitions and measures of resilience. Resilience was defined as robustness/resistance to decline (n = 11), recovery from trauma/stressor (n = 7), and adaptive and proactive coping behaviors (n = 6). Ten papers did not define resilience. 21 studies utilized longitudinal analysis, five studies used randomized and nonrandomized control trials, and four studies assessed pre-post analysis. Stressors included cancer diagnosis (n = 18), chemotherapy (n = 3), radiation (n = 3), acute illness (n = 3), surgery (n = 2), and hematopoietic cell transplant (n = 1).

DISCUSSION

Evidence for predictors and determinants of resilience in older adults with cancer is limited by the absence of standardized definitions and measurements. There is a fundamental need for a more precise definition, measures, and understanding of the physiologic mechanisms underlying the response to the physical, cognitive, and psychosocial stressors of cancer and its treatments.

Air pollution, genetic factors and the risk of depression

Both genetics and ambient air pollutants contribute to depression, but the degree to which genetic susceptibility modifies the effect of air pollution on depression remains unknown. We aimed to investigate the effect of the modification of genetic susceptibility on depression. Notably, 490,780 participants who were free of depression at baseline in the UK Biobank study were recruited from 2006 to 2010. A land use regression (LUR) model was performed to estimate the concentrations of particulate matter with diameters ranging from ≤2.5-≤10 μm (PM_2.5, PM_2.5-10 and PM₁₀), nitrogen dioxide (NO₂), and nitrogen oxides (NO_x). The International Classification of Diseases 10th Revision (ICD-10) code was used to identify depression cases. Cox proportional hazard models adjusted for covariates were used to investigate the association between ambient air pollutants and depression. Moreover, the polygenic risk score (PRS) was calculated to evaluate cumulative genetic effects, and additive interaction models were established to explore whether genetic susceptibility modified the effects of air pollutants on depression. PM_2.5, PM₁₀, NO₂ and NO_x exposure were significantly positively associated with the risk of depression, and the hazard ratios and 95 % confidence intervals for a 10-μg/m³ increase in PM_2.5, PM₁₀, NO₂ and NO_x concentrations were 2.12 (1.82, 2.47), 1.12 (1.03, 1.23), 1.07 (1.05, 1.10) and 1.04 (1.03, 1.05), respectively. Air pollutants and genetic variants exerted significant additive effects on the risk of depression (relative excess risk due to the interaction [RERI]: 0.15 for PM_2.5, 0.12 for PM₁₀, 0.10 for NO₂, and 0.12 for NO_x; attributable proportion due to the interaction [AP]: 0.12 for PM_2.5, 0.10 for PM₁₀, 0.08 for NO₂, and 0.09 for NO_x). Air pollution exposure was significantly associated with the risk of depression, and participants with a higher genetic risk were more likely to develop depression when exposed to high levels of air pollution.

Trajectories of resilience and mental distress to global major disruptions

The COVID-19 pandemic has resulted in a major societal disruption, raising the question of how people can maintain or quickly regain their mental health (i.e., be resilient) during such times. Researchers have used the pandemic as a use case for studying resilience in response to a global, synchronously starting, and chronic set of stressors on the individual and societal level. Our review of this recent literature reveals that mental distress trajectories during the pandemic largely resemble mental distress responses to individual-level macro-stressors, except for a lower prevalence of recovery trajectories. Results suggest more resilient responses in older adults, but trajectories are less consistent for younger and older ages compared with middle-aged adults. We call for more research integrating state-of-the-art operationalizations of resilience and using these to study resilience over the lifespan.

Traumatic stress symptoms in family caregivers of patients with acute leukaemia: protocol for a multisite mixed methods, longitudinal, observational study

INTRODUCTION

The diagnosis, progression or recurrence of cancer is often highly traumatic for family caregivers (FCs), but systematic assessments of distress and approaches for its prevention and treatment are lacking. Acute leukaemia (AL) is a life-threatening cancer of the blood, which most often presents acutely, requires intensive treatment and is associated with severe physical symptoms. Consequently, traumatic stress may be common in the FCs of patients with AL. We aim to determine the prevalence, severity, longitudinal course and predictors of traumatic stress symptoms in FCs of patients with AL in the first year after diagnosis, and to understand their lived experience of traumatic stress and perceived support needs.

METHODS AND ANALYSIS

This two-site longitudinal, observational, mixed methods study will recruit 223 adult FCs of paediatric or adult patients newly diagnosed with AL from two tertiary care centres. Quantitative data will be collected from self-report questionnaires at enrolment, and 1, 3, 6, 9 and 12 months after admission to hospital for initial treatment. Quantitative data will be analysed using descriptive and machine learning approaches and a multilevel modelling (MLM) approach will be used to confirm machine learning findings. Semi-structured qualitative interviews will be conducted at 3, 6 and 12 months and analysed using a grounded theory approach.

ETHICS AND DISSEMINATION

This study is funded by the Canadian Institutes of Health Research (CIHR number PJT 173255) and has received ethical approval from the Ontario Cancer Research Ethics Board (CTO Project ID: 2104). The data generated have the potential to inform the development of targeted psychosocial interventions for traumatic stress, which is a public health priority for high-risk populations such as FCs of patients with haematological malignancies. An integrated and end-of-study knowledge translation strategy that involves FCs and other stakeholders will be used to interpret and disseminate study results.

Association of polygenic risk scores and hair cortisol with mental health trajectories during COVID lockdown

The COVID-19 pandemic is a global stressor with inter-individually differing influences on mental health trajectories. Polygenic Risk Scores (PRSs) for psychiatric phenotypes are associated with individual mental health predispositions. Elevated hair cortisol concentrations (HCC) and high PRSs are related to negative mental health outcomes. We analyzed whether PRSs and HCC are related to different mental health trajectories during the first COVID lockdown in Germany. Among 523 participants selected from the longitudinal resilience assessment study (LORA), we previously reported three subgroups (acute dysfunction, delayed dysfunction, resilient) based on weekly mental health (GHQ-28) assessment during COVID lockdown. DNA from blood was collected at the baseline of the original LORA study (n = 364) and used to calculate the PRSs of 12 different psychopathological phenotypes. An explorative bifactor model with Schmid-Leiman transformation was calculated to extract a general genetic factor for psychiatric disorders. Hair samples were collected quarterly prior to the pandemic for determining HCC (n = 192). Bivariate logistic regressions were performed to test the associations of HCC and the PRS factors with the reported trajectories. The bifactor model revealed 1 general factor and 4 sub-factors. Results indicate a significant association between increased values on the general risk factor and the allocation to the acute dysfunction class. The same was found for elevated HCC and the exploratorily tested sub-factor "childhood-onset neurodevelopmental disorders". Genetic risk and long-term cortisol secretion as a potential indicator of stress, indicated by PRSs and HCC, respectively, predicted different mental health trajectories. Results indicate a potential for future studies on risk prediction.

Prediction of the trajectories of depressive symptoms among children in the adolescent brain cognitive development (ABCD) study using machine learning approach

BACKGROUND

Depression often first emerges during adolescence and evidence shows that the long-term patterns of depressive symptoms over time are heterogeneous. It is meaningful to predict the trajectory of depressive symptoms in adolescents to find early intervention targets.

METHODS

Based on the Adolescent Brain Cognitive Development Study, we included 4962 participants aged 9-10 who were followed-up for 2 years. Trajectories of depressive symptoms were identified by Latent Class Growth Analyses (LCGA). Four types of machine learning models were built to predict the identified trajectories and to obtain variables with predictive value based on the best performance model.

RESULTS

Of all participants, 536 (10.80%) were classified as increasing, 269 (5.42%) as persistently high, 433 (8.73%) as decreasing, and 3724 (75.05%) as persistently low by LCGA. Gradient Boosting Machine (GBM) model got the highest discriminant performance. Sleep quality, parental emotional state and family financial adversities were the most important predictors and three resting state functional magnetic resonance imaging functional connectivity data were also helpful to distinguish trajectories.

LIMITATION

We only have depressive symptom scores at three time points. Some valuable predictors are not specific to depression. External validation is an important next step. These predictors should not be interpreted as etiology and some variables were reported by parents/caregivers.

CONCLUSION

Using GBM combined with baseline characteristics, the trajectories of depressive symptoms with two years among adolescents aged 9-10 years can be well predicted, which might further facilitate the identification of adolescents at high risk of depressive symptoms and development of effective early interventions.

Variation in depressive symptom trajectories in a large sample of couples

The occurrence of depression is influenced by social relationships, however, most studies focus on individuals, not couples. We aimed to study how depressive symptoms of couples evolve over time and determine, which characteristics are associated with their distinct trajectories. A multi-centric cohort sample of 11,136 heterosexual couples (mean age = 60.76) from 16 European countries was followed for up to 12 years (SHARE study). Information on depressive symptoms measured by EURO-D scale was collected every 2 years. Dyadic growth mixture modeling extracted four distinct classes of couples: both non-depressed (76.91%); only women having consistently high depressive symptoms while men having consistently low depressive symptoms (8.08%); both having increasing depressive symptoms (7.83%); and both having decreasing depressive symptoms (7.18%). Couples with increasing depressive symptoms had the highest prevalence of relationship dissolution and bereavement. In comparison to the nondepressed class, individuals with any depressive symptoms were less psychologically and physically well. Our results suggest that distinct mechanisms are responsible for couples' various longitudinal trajectories of depressive symptoms.

Intranasal oxytocin administration impacts the acquisition and consolidation of trauma-associated memories: a double-blind randomized placebo-controlled experimental study in healthy women

Intrusive memories are a hallmark symptom of post-traumatic stress disorder (PTSD) and oxytocin has been implicated in the formation of intrusive memories. This study investigates how oxytocin influences the acquisition and consolidation of trauma-associated memories and whether these effects are influenced by individual neurobiological and genetic differences. In this randomized, double-blind, placebo-controlled study, 220 healthy women received either a single dose of intranasal 24IU oxytocin or a placebo before exposure to a trauma film paradigm that solicits intrusive memories. We used a "general random forest" machine learning approach to examine whether differences in the noradrenergic and hypothalamic-pituitary-adrenal axis activity, polygenic risk for psychiatric disorders, and genetic polymorphism of the oxytocin receptor influence the effect of oxytocin on the acquisition and consolidation of intrusive memories. Oxytocin induced significantly more intrusive memories than placebo did (t(188.33) = 2.12, p = 0.035, Cohen's d = 0.30, 95% CI 0.16-0.44). As hypothesized, we found that the effect of oxytocin on intrusive memories was influenced by biological covariates, such as salivary cortisol, heart rate variability, and PTSD polygenic risk scores. The five factors that were most relevant to the oxytocin effect on intrusive memories were included in a Poisson regression, which showed that, besides oxytocin administration, higher polygenic loadings for PTSD and major depressive disorder were directly associated with a higher number of reported intrusions after exposure to the trauma film stressor. These results suggest that intranasal oxytocin amplifies the acquisition and consolidation of intrusive memories and that this effect is modulated by neurobiological and genetic factors. Trial registration: NCT03031405.

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.

Identification of transdiagnostic psychiatric disorder subtypes using unsupervised learning

Psychiatric disorders show heterogeneous symptoms and trajectories, with current nosology not accurately reflecting their molecular etiology and the variability and symptomatic overlap within and between diagnostic classes. This heterogeneity impedes timely and targeted treatment. Our study aimed to identify psychiatric patient clusters that share clinical and genetic features and may profit from similar therapies. We used high-dimensional data clustering on deep clinical data to identify transdiagnostic groups in a discovery sample (N = 1250) of healthy controls and patients diagnosed with depression, bipolar disorder, schizophrenia, schizoaffective disorder, and other psychiatric disorders. We observed five diagnostically mixed clusters and ordered them based on severity. The least impaired cluster 0, containing most healthy controls, showed general well-being. Clusters 1-3 differed predominantly regarding levels of maltreatment, depression, daily functioning, and parental bonding. Cluster 4 contained most patients diagnosed with psychotic disorders and exhibited the highest severity in many dimensions, including medication load. Depressed patients were present in all clusters, indicating that we captured different disease stages or subtypes. We replicated all but the smallest cluster 1 in an independent sample (N = 622). Next, we analyzed genetic differences between clusters using polygenic scores (PGS) and the psychiatric family history. These genetic variables differed mainly between clusters 0 and 4 (prediction area under the receiver operating characteristic curve (AUC) = 81%; significant PGS: cross-disorder psychiatric risk, schizophrenia, and educational attainment). Our results confirm that psychiatric disorders consist of heterogeneous subtypes sharing molecular factors and symptoms. The identification of transdiagnostic clusters advances our understanding of the heterogeneity of psychiatric disorders and may support the development of personalized treatments.

Machine yearning: How advances in computational methods lead to new insights about reactions to loss

The loss of a loved one is a potentially traumatic event that can result in disparate outcomes and symptom patterns. Machine learning methods offer computational tools to probe this heterogeneity and understand grief psychopathology in its complexity. In this article, we examine the latest contributions to the scientific study of bereavement reactions garnered through the use of computational methods. We focus on findings originating from trajectory modeling studies, as well as the recent insights originating from the network analysis of prolonged grief symptoms. We also discuss applications of artificial intelligence for the accurate identification of major depression and post-traumatic stress, as examples for their potential applications to the study of loss reactions.

The resilience paradox

Decades of research have consistently shown that the most common outcome following potential trauma is a stable trajectory of healthy functioning, or resilience. However, attempts to predict resilience reveal a paradox: the correlates of resilient outcomes are generally so modest that it is not possible accurately identify who will be resilient to potential trauma and who not. Commonly used resilience questionnaires essentially ignore this paradox by including only a few presumably key predictors. However, these questionnaires show virtually no predictive utility. The opposite approach, capturing as many predictors as possible using multivariate modelling or machine learning, also fails to fully address the paradox. A closer examination of small effects reveals two primary reasons for these predictive failures: situational variability and the cost-benefit tradeoffs inherent in all behavioural responses. Together, these considerations indicate that behavioural adjustment to traumatic stress is an ongoing process that necessitates flexible self-regulation. To that end, recent research and theory on flexible self-regulation in the context of resilience are discussed and next steps are considered.