Inflammatory markers as predictors of depression and anxiety in adolescents: Statistical model building with component-wise gradient boosting

Identifying predictors of multi-year cannabis vaping in U.S. Young adults using machine learning

INTRODUCTION

Increasing number of current cannabis users report using a vaporized form of cannabis and young adults are most likely to vape cannabis. However, the number of studies on cannabis vaping is limited, and predictors of cannabis vaping among U.S. young adults remain unclear. Previous studies on cannabis vaping have known limitations, as they (1) relied heavily on regression-based approaches that often fail to examine complex and non-linear interactive effects, (2) focused on examining cannabis vaping initiation but not on its use over multiple years, and (3) failed to account for recreational cannabis legalization (RCL) status.

METHODS

This study was a secondary analysis of the restricted use files of the Population Assessment of Tobacco and Health Study, Waves 4-6 (December 2016-November 2021). A two-stage machine learning approach, which included Least Absolute Shrinkage and Selection Operator (LASSO) and Classification and Regression Tree (CART), was used to identify predictors of multi-year cannabis vaping while accounting for state-level RCL status among a representative sample of U.S. young adults.

RESULTS

Stratified CART created a five-terminal-node prediction model for states with RCL (split by cannabis use, cigarette use, bullying behavior, and ethnicity) and a different five-terminal-node prediction model for states without RCL (split by cannabis use, heroin use, nicotine vaping, and hookah use).

CONCLUSIONS

Characteristics predicting multi-year cannabis vaping appear to differ from those of cannabis vaping initiation. Results also highlight the importance of accounting for RCL status because predictors of cannabis vaping may differ for individuals living in states with and without RCL.

Machine Learning for the Prediction of Depression Progression from Inflammation Markers

Major depressive disorder is one of the major contributors to disability worldwide with an estimated prevalence of 4%. Depression is a heterogeneous disease often characterized by an undefined pathogenesis and multifactorial phenotype that complicate diagnosis and follow-up. Translational research and identification of objective biomarkers including inflammation can assist clinicians in diagnosing depression and disease progression. Investigating inflammation markers using machine learning methods combines recent understanding of the pathogenesis of depression associated with inflammatory changes as part of chronic disease progression that aims to highlight complex interactions. In this paper, 721 patients attending a diabetes health screening clinic (DiabHealth) were classified into no depression (none) to minimal depression (none-minimal), mild depression, and moderate to severe depression (moderate-severe) based on the Patient Health Questionnaire (PHQ-9). Logistic Regression, K-nearest Neighbors, Support Vector Machine, Random Forest, Multi-layer Perceptron, and Extreme Gradient Boosting were applied and compared to predict depression level from inflammatory marker data that included C-reactive protein (CRP), Interleukin (IL)-6, IL-1β, IL-10, Complement Component 5a (C5a), D-Dimer, Monocyte Chemoattractant Protein (MCP)-1, and Insulin-like Growth Factor (IGF)-1. MCP-1 and IL-1β were the most significant inflammatory markers for the classification performance of depression level. Extreme Gradient Boosting outperformed the models achieving the highest accuracy and Area Under the Receiver Operator Curve (AUC) of 0.89 and 0.95, respectively.Clinical Relevance- The findings of this study show the potential of machine learning models to aid in clinical practice, leading to a more objective assessment of depression level based on the involvement of MCP-1 and IL-1β inflammatory markers with disease progression.

Cytokine alterations in pediatric internalizing disorders: Systematic review and exploratory multi-variate meta-analysis

Pediatric internalizing disorders are prevalent and characterized by a maladaptive cognitive, emotional response to a perceived stressor. The hypothesized effect of this response is observable changes in behavior mediated by homeostatic inflammatory cytokines. The aim of this study was to synthesize the literature and analyze the effect of cytokines on pediatric internalizing disorders. Influential moderating variables, including mean body mass index, fasting status at blood collection, participant sex, cytokine type, mean age, percentage of sample medicated, and diagnosis, were also assessed. A systematic literature search was performed in electronic databases (Medline, PubMed, and PsycINFO) from January 1, 1980 to June 15, 2022. Case-control studies of pediatric internalizing disorders, specifically anxiety and depression, were reviewed for their association with peripheral cytokine levels. Meta-analyses were performed using a random effects multi-variate model and effect sizes were calculated using Hedge's g for IL-2, CRP, IL-6, TNF-α, IL-1β, IFN-γ, and IL-10. Thirty-three studies were reviewed and 28 studies were included in the meta-analysis (n = 1322 cases and n = 3617 controls). Peripheral cytokine levels were elevated in pediatric internalizing disorders compared to controls (Hedge's g = 0.19, p < 0.001). In the moderator analyses, depression diagnosis (Hedge's g = 0.18, p = 0.009) and non-fasting blood collection (Hedge's g = 0.20, p = 0.006) were significant. The meta-analytic findings are limited by methodological variation between studies, high heterogeneity, and low statistical power. Despite this, the findings suggest that elevated peripheral cytokine levels may play a role in the etiology and/or symptom maintenance of pediatric internalizing disorders.

Depression screening using a non-verbal self-association task: A machine-learning based pilot study

BACKGROUND

Effective screening is important to combat the raising burden of depression and opens a critical time window for early intervention. Clinical use of non-verbal depression screening is nascent, yet a promising and viable candidate to supplement verbal screening. Differential self- and emotion-processing in depression patients were previously reported by non-verbal behavioural assessments, corroborated by neuroimaging findings of distinct neuroanatomical markers. Thus non-verbal validated brain-behaviour based self-emotion-related assessment data reflect physiological differences and may support individual level screening of depression.

METHODS

In this pilot study (n = 84) we collected two longitudinal sessions of behavioural assessment data in a laboratory setting. Depression was assessed using Beck Depression Inventory II (BDI-II), to explore optimal screening methods with machine-learning, and to establish the validity of adapting a novel behavioural assessment focusing on self and emotions for depression screening.

RESULTS

The best machine-learning model achieved high performance in depression screening, 10-Fold cross-validation (CV) Area Under the receiver operating characteristic Curve (AUC) of 0.90 and balanced accuracy of 0.81, using a Gradient Boosting algorithm. Prospective prediction using a model trained with session 1 data to predict session 2 depression status achieved a 10-Fold CV AUC of 0.77 and balanced accuracy of 0.66. We also identified interpretable behavioural signatures for depression patients based on the best model.

CONCLUSION

The study supports the utility of using behavioural data as a viable and cost-effective solution for depression screening, with a potential wide range of applications in clinical settings.

The Importance of CXCL1 in Physiology and Noncancerous Diseases of Bone, Bone Marrow, Muscle and the Nervous System

This review describes the role of CXCL1, a chemokine crucial in inflammation as a chemoattractant for neutrophils, in physiology and in selected major non-cancer diseases. Due to the vast amount of available information, we focus on the role CXCL1 plays in the physiology of bones, bone marrow, muscle and the nervous system. For this reason, we describe its effects on hematopoietic stem cells, myoblasts, oligodendrocyte progenitors and osteoclast precursors. We also present the involvement of CXCL1 in diseases of selected tissues and organs including Alzheimer’s disease, epilepsy, herpes simplex virus type 1 (HSV-1) encephalitis, ischemic stroke, major depression, multiple sclerosis, neuromyelitis optica, neuropathic pain, osteoporosis, prion diseases, rheumatoid arthritis, tick-borne encephalitis (TBE), traumatic spinal cord injury and West Nile fever.

Are pro-inflammatory markers associated with psychological distress in a cross-sectional study of healthy adolescents 15-17 years of age? The Fit Futures study

Background

Inflammatory markers have been associated with depression and anxiety disorder in adolescents. Less is known about the association between inflammation and subclinical symptoms in the form of psychological distress. We investigated prevalence of psychological distress and examined the associations between common pro-inflammatory markers and psychological distress in an adolescent population sample.

Methods

The study was based on data from 458 girls and 473 boys aged 15–17 years from the Fit Futures Study, a large-scale study on adolescent health, conducted in Northern Norway. Psychological distress was measured with the Hopkins Symptom Checklist (HSCL-10). Serum-levels of the following low-grade inflammatory markers were measured: C-reactive protein (CRP), interleukin 6 (IL-6), transforming growth factor-alpha (TGF-α), tumor necrosis factor alpha variant 1 (TRANCE) and tumor necrosis factor alpha variant 2 (TWEAK). Associations between quartiles of inflammatory markers and HSCL-10 were examined by logistic regression and adjusted for potential confounders in sex-stratified analyses.

Results

The proportion of psychological distress above cutoff were 26.9% and 10.8% among girls and boys, respectively. In both girls and boys, crude analysis showed positive associations between all inflammatory markers and HSCL-10, except for TWEAK and TRANCE in boys. However, none of these associations were statistically significant. Further, there were no significant findings in the adjusted analyses.

Conclusion

There was a higher prevalence of psychological distress in girls compared to boys. Pro-inflammatory markers were not significantly associated with psychological distress in data from healthy adolescents aged 15–17 years.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40359-022-00779-8.

C-Reactive Protein and TGF-α Predict Psychological Distress at Two Years of Follow-Up in Healthy Adolescent Boys: The Fit Futures Study

Objective

The scarcity of research on associations between inflammatory markers and symptoms of depression and anxiety during adolescence has yielded inconsistent results. Further, not all studies have controlled for potential confounders. We explored the associations between baseline inflammatory markers and psychological distress including moderators at follow-up in a Norwegian adolescent population sample.

Methods

Data was derived from 373 girls and 294 boys aged 15–18 years at baseline, in the Fit Futures Study, a large-scale 2-year follow-up study on adolescent health. Baseline data was gathered from 2010 to 2011 and follow-up data from 2012 to 2013. Psychological distress was measured with Hopkins Symptom Checklist (HSCL-10). Serum levels of the following inflammatory markers were measured: C-reactive protein (CRP), Interleukin 6 (IL-6), Transforming growth factor alpha (TGF-α), Tumor necrosis factor alpha variant 1 (TRANCE), and variant 2 (TWEAK). Independent associations between baseline inflammatory markers and HSCL-10 at follow-up were explored by linear regressions, in sex-stratified analyses.

Results

In girls, analyses showed positive associations between all inflammatory markers and HSCL-10, except for TRANCE. However, all associations were non-significant in crude as well as in adjusted analyses. In boys, CRP (p = 0.03) and TGF-α (p &lt; 0.01) showed significant associations with HSCL-10, that remained significant after adjustment. Additionally, moderators were found. In boys, CRP was associated with HSCL-10 in those with high body fat and those being physical inactive, and the association between TWEAK and HSCL-10 was dependent upon sleep duration.

Conclusion

There were significant prospective associations between CRP, TFG-α, and HSCL-10 in boys aged 15–18 years at baseline.

Identifying risk profiles for marijuana vaping among U.S. young adults by recreational marijuana legalization status: A machine learning approach

INTRODUCTION

This study attempted to identify risk profiles of marijuana vaping by state-level recreational marijuana legalization (RML) status among U.S. young adults (YA).

METHODS

Data were drawn from the most recent two waves of restricted use files of the Population Assessment of Tobacco and Health Study with state identifiers. We analyzed 6155 young adult (18-24 years) respondents who were naïve to marijuana vaping at Wave 4 and had matched data at Wave 5. We employed a two-stage machine learning approach to predict marijuana vaping initiation at Wave 5 with predictors measured at Wave 4.

RESULTS

Among YA who had never vaped marijuana at Wave 4, 19% of those who lived in the states with RML and 15% of those who lived in the states without RML reported marijuana vaping at Wave 5. Substance-use-related predictors were rarely found as leading predictors in the states with RML. In the states without RML, substance use behaviors, including electronic nicotine delivery systems and smokeless tobacco use, and the presence of externalizing symptoms emerged as predictors for marijuana vaping. Results also revealed that nonlinear interactions between the predictors of marijuana vaping.

CONCLUSIONS

Our results highlight the importance of accounting for the RML status in developing risk profiles of marijuana vaping. Externalizing symptoms may be a behavioral endophenotype of marijuana vaping in the states without RML. Machine learning appears to be a promising analytical approach to identify complex interactions between factors in predicting an emerging risk behavior such as marijuana vaping.

Inflammation and depression in young people: a systematic review and proposed inflammatory pathways

Depression onset peaks during adolescence and young adulthood. Current treatments are only moderately effective, driving the search for novel pathophysiological mechanisms underlying youth depression. Inflammatory dysregulation has been shown in adults with depression, however, less is known about inflammation in youth depression. This systematic review identified 109 studies examining the association between inflammation and youth depression and showed subtle evidence for inflammatory dysregulation in youth depression. Longitudinal studies support the bidirectional association between inflammation and depression in youth. We hypothesise multiple inflammatory pathways contributing to depression. More research is needed on anti-inflammatory treatments, potentially tailored to individual symptom profiles.

The longitudinal associations of inflammatory biomarkers and depression revisited: systematic review, meta-analysis, and meta-regression

The innate immune system is dysregulated in depression; however, less is known about the longitudinal associations of depression and inflammatory biomarkers. We investigated the prospective associations of depression and inflammatory biomarkers [interleukin-6 (IL-6), Tumor Necrosis Factor-Alpha (TNF-α), and C-reactive protein (CRP)] in community samples, both unadjusted and adjusted for covariates. The review, registered with PROSPERO, searched for published and unpublished studies via MEDLINE/PsycINFO/PsycARTICLES/EMBASE/Proquest Dissertation. Standardized Fisher transformations of the correlation/beta coefficients, both unadjusted and adjusted for covariates, were extracted from studies examining the prospective associations of depression and inflammatory biomarkers. Systematic review conducted in January, 2019 included 38 studies representing 58,256 participants, with up to 27 studies included in random-effects meta-analysis. Higher CRP/IL-6 were associated with future depressive symptoms, and higher depressive symptoms were associated with higher future CRP/IL-6 in both unadjusted and adjusted analyses - this is the first meta-analysis reporting an adjusted association of IL-6 with future depression. The adjusted prospective associations of depression with CRP/CRP with depression were substantially attenuated and small in magnitude. No significant associations were observed for TNF-α. No conclusive results were observed in studies of clinical depression. Meta-regression indicated that the association of CRP and future depression was larger in older samples and in studies not controlling for possible infection. Small, prospective associations of depression and inflammatory biomarkers are observed in both directions, particularly for IL-6; however, the strength and importance of this relationship is likely obscured by the heterogeneity in depression and profound study/methodological differences. Implications for future studies are discussed.

Duration of breastmilk feeding of NICU graduates who live with individuals who smoke

BACKGROUND

Breast milk has many benefits for infants, but initiating breastfeeding/pumping can be difficult for mothers of preterm infants, especially those who smoke (or live with individuals who smoke). The primary aim of this study was to identify risks for breastfeeding/pumping cessation with neonatal intensive care unit (NICU) infants' mothers who smoke or live with individuals who smoke, using a novel survival-analytic approach.

METHODS/DESIGN

Mothers (N = 360) were recruited for a secondhand smoke prevention intervention during infants' NICU hospitalizations and followed for ~6 months after infant discharge. Data were obtained from medical records and participant self-report/interviews.

RESULTS

The sample was predominantly ethnic/racial minorities; mean age was 26.8 (SD = 5.9) years. One-fifth never initiated breastfeeding/pumping (n = 67; 18.9%) and mean time-to-breastfeeding cessation was 48.1 days (SD = 57.2; median = 30.4 [interquartile range: 6.0-60.9]). Education, length of stay, employment, race/ethnicity, number of household members who smoke, and readiness-to-protect infants from tobacco smoke were significantly associated with breastfeeding cessation. Further, infants fed breast milk for ≥4 months had 42.7% more well-child visits (p < 0.001) and 50.0% fewer respiratory-related clinic visits (p < 0.05).

CONCLUSIONS

One-quarter of infants admitted to NICUs will be discharged to households where individuals who smoke live; we demonstrated that smoking-related factors were associated with mothers' breastfeeding practices. Infants who received breast milk longer had fewer respiratory-related visits.

IMPACT

One-quarter of NICU infants will be discharged to households where smokers live. Initiating/sustaining breastfeeding can be difficult for mothers of preterm NICU infants, especially mothers who smoke or live with others who smoke. Education, employment, race/ethnicity, length of stay, household member smoking, and readiness-to-protect infants from tobacco smoke were significantly associated with time-to-breastfeeding cessation. Infants fed breast milk for ≥4 months had 42.7% more well-child visits and 50.0% fewer respiratory-related clinic visits, compared to infants fed breast milk <4 months. Data support intervention refinements for mothers from smoking households and making NICU-based healthcare workers aware of risk factors for early breastfeeding cessation.

Using machine learning to identify predictors of imminent drinking and create tailored messages for at-risk drinkers experiencing homelessness

Adults experiencing homelessness are more likely to have an alcohol use disorder compared to adults in the general population. Although shelter-based treatments are common, completion rates tend to be poor, suggesting a need for more effective approaches that are tailored to this understudied and underserved population. One barrier to developing more effective treatments is the limited knowledge of the triggers of alcohol use among homeless adults. This paper describes the use of ecological momentary assessment (EMA) to identify predictors of “imminent drinking” (i.e., drinking within the next 4 h), among a sample of adults experiencing homelessness and receiving health services at a homeless shelter. A total of 78 mostly male (84.6%) adults experiencing homelessness (mean age = 46.6) who reported hazardous drinking completed up to five EMAs per day over 4 weeks (a total of 4557 completed EMAs). The study used machine learning techniques to create a drinking risk algorithm that predicted 82% of imminent drinking episodes within 4 h of the first drink of the day, and correctly identified 76% of nondrinking episodes. The algorithm included the following 7 predictors of imminent drinking: urge to drink, having alcohol easily available, feeling confident that alcohol would improve mood, feeling depressed, lower commitment to being alcohol free, not interacting with someone drinking alcohol, and being indoors. The research team used the results to develop intervention content (e.g., brief tailored messages) that will be delivered when imminent drinking is detected in an upcoming intervention phase. Specifically, we created three theoretically grounded message tracks focused on urge/craving, social/availability, and negative affect/mood, which are further tailored to a participant’s current drinking goal (i.e., stay sober, drink less, no goal) to support positive change. To our knowledge, this is the first study to develop tailored intervention messages based on likelihood of imminent drinking, current drinking triggers, and drinking goals among adults experiencing homelessness.

Personalized Medicine Using Neuroimmunological Biomarkers in Depressive Disorders

Major depressive disorder (MDD) is associated with increased suicidal risk and reduced productivity at work. Neuroimmunology, the study of the immune system and nervous system, provides further insight into the pathogenesis and outcome of MDD. Cytokines are the main modulators of neuroimmunology, and their levels are somewhat entangled in depressive disorders as they affect depressive symptoms and are affected by antidepressant treatment. The use of cytokine-derived medication as a treatment option for MDD is currently a topic of interest. Although not very promising, cytokines are also considered as possible prognostic or diagnostic markers for depression. The machine learning approach is a powerful tool for pattern recognition and has been used in psychiatry for finding useful patterns in data that have translational meaning and can be incorporated in daily clinical practice. This review focuses on the current knowledge of neuroimmunology and depression and the possible use of machine learning to widen our understanding of the topic.

Predicting the first smoking lapse during a quit attempt: A machine learning approach

BACKGROUND

Just-in-time adaptive interventions (JITAI) aim to prevent smoking lapse using tailored support delivered via mobile technology in the moments when it is most needed. Effective smoking cessation JITAI rely on the development of accurate decision rules that determine when someone is most likely to lapse. The primary goal of the present study was to identify the strongest predictors of first lapse among smokers undergoing a quit attempt.

METHODS

Smokers attending a clinic-based smoking cessation program (n = 74) were asked to complete ecological momentary assessments five times daily on study-provided smartphones for 4 weeks post-quit. A three-stage modeling process utilized Cox proportional hazards regression to examine time to lapse a function of 31 predictors. First, univariate models evaluated the relationship between each predictor and time to lapse. Second, the elastic net machine learning algorithm was used to select the best predictors. Third, backwards elimination further reduced the set of predictors to optimize parsimony.

RESULTS

Univariate models identified seven predictors significantly related to time to lapse. The elastic net algorithm retained five: perceived odds of smoking today, confidence in ability to avoid smoking, motivation to avoid smoking, urge to smoke, and cigarette availability. The reduced model demonstrated inadequate approximation to the non-penalized baseline model.

CONCLUSIONS

Accurate estimation of moments of high risk for smoking lapse remains an important goal in the development of JITAI. These results demonstrate the utility of exploratory data-driven approaches to variable selection. The results of this study can inform future JITAI by highlighting targets for intervention.

Predicting Daily Sheltering Arrangements among Youth Experiencing Homelessness Using Diary Measurements Collected by Ecological Momentary Assessment

Youths experiencing homelessness (YEH) often cycle between various sheltering locations including spending nights on the streets, in shelters and with others. Few studies have explored the patterns of daily sheltering over time. A total of 66 participants completed 724 ecological momentary assessments that assessed daily sleeping arrangements. Analyses applied a hypothesis-generating machine learning algorithm (component-wise gradient boosting) to build interpretable models that would select only the best predictors of daily sheltering from a large set of 92 variables while accounting for the correlated nature of the data. Sheltering was examined as a three-category outcome comparing nights spent literally homeless, unstably housed or at a shelter. The final model retained 15 predictors. These predictors included (among others) specific stressors (e.g., not having a place to stay, parenting and hunger), discrimination (by a friend or nonspecified other; due to race or homelessness), being arrested and synthetic cannabinoids use (a.k.a., “kush”). The final model demonstrated success in classifying the categorical outcome. These results have implications for developing just-in-time adaptive interventions for improving the lives of YEH.

Inflammatory Response and Treatment-Resistant Mental Disorders: Should Immunotherapy Be Added to Pharmacotherapy?

Treatment resistance continues to challenge and frustrate mental health clinicians and provoke psychiatric researchers to seek additional explanatory theories for psychopathology. Because the inflammatory process activates symptoms of depression, anxiety, and psychosis, it is a reasonable route to follow for primary and/or indirect contribution to mental disorders. The current article reviews the research literature regarding the role the inflammatory process and immune system play in mental disorders as well as novel treatments under investigation for resistant depression, anxiety, substance use, and psychotic disorders. [Journal of Psychosocial Nursing and Mental Health Services, 58(1), 11-16.].

Low-dose alcohol ameliorated homocysteine-induced anxiety-related behavior via attenuating oxidative stress in mice

Recent studies showed that homocysteine (Hcy) levels were obviously elevated in patients with anxiety, furthermore, oxidative stress and inflammation were closely linked with Hcy-related damage. Despite alcohol exposure has differential effects on different forms of anxiety, the role of alcohol on anxiety-related behavior induced by high Hcy levels is still not entirely clear. The present study investigated the protective potential of low-dose alcohol against homocysteine-induced anxiety-related behavior and explored the possible underlying mechanisms. Mice were administered intragastrically with methionine (2.0 g/kg/day) or alcohol (0.6 g/kg/day). After 21 days of administration, the anxiety-related behavior was evaluated through open field (OF) and elevated plus maze (EPM) tests, and the variations of oxidative stress and inflammation levels were measured. The results of OF and EPM tests showed that the anxiety-related behavior in mice was prevented by alcohol treatment. Alcohol lowered the elevated serum Hcy levels and alleviated the damage of hippocampal tissues in hyperhomocysteinemia (HHcy) mice. Meanwhile, the superoxide dismutase (SOD) activity of the hippocampal tissues enhanced, and the malondialdehyde (MDA) concentration of the hippocampal tissues and the serum interleukin-1β (IL-1β) level decreased. In addition, after administering alcohol, the increase of superoxide dismutase 1 (SOD1), heme oxygenase 1 (HO-1) protein expression and the decrease of IL-1β protein expression were also detected in HHcy mice hippocampal tissues. Taken together, low-dose alcohol significantly ameliorated the Hcy-induced anxiety-related behavior in mice, which might be related to SOD1 and HO-1 upregulation and IL-1β downregulation.

Reduced CXCL1/GRO chemokine plasma levels are a possible biomarker of elderly depression

BACKGROUND

Depression is the single largest contributor to non-fatal health loss worldwide. A role of inflammation in major depressive disorder (MDD) was suggested, and we sought to determine if cytokine levels predict the severity of depressive symptomatology or distinguish MDD patients from healthy controls (HCs).

METHODS

The severity of depressive symptoms and cognitive impairment were assessed by the Korean version of the Geriatric Depression Scale (GDS-K) and Mini-Mental State Examination (MMSE-KC) in 152 elderly subjects (76 with MDD). Plasma levels of 28 cytokines were measured and analysed as continuous predictors or dichotomized using the median value. The association between individual cytokines, MDD risk and depressive symptoms severity was investigated using multiple logistic and linear regressions that included the relevant covariates. A Cytokine Weighted Score (CWS) was calculated by weighting cytokines according to previously reported effect sizes on MDD risk. Sensitivity analyses were performed excluding subjects with significant cognitive impairment.

RESULTS

CXCL10/IP-10 levels were higher in subjects with MDD vs. HCs while the opposite was observed for CXCL1/GRO. Only the second association survived after adjusting for possible confounders and excluding subjects with severe cognitive impairment. Using dichotomized cytokine levels, CXCL1/GRO and TNF-α were negatively associated with MDD. The CWS was also negatively associated with MDD. Cytokine levels did not predict the severity of depressive symptoms.

LIMITATIONS

Our cross-sectional approach was not able to longitudinally evaluate any temporal fluctuations in the considered cytokine levels.

CONCLUSIONS

This study found significantly lower CXCL1/GRO chemokine plasma levels in elderly subjects with MDD compared to HCs.

The use of component-wise gradient boosting to assess the possible role of cognitive measures as markers of vulnerability to pediatric bipolar disorder

BACKGROUND AND AIMS

Cognitive impairments are primary hallmarks symptoms of bipolar disorder (BD). Whether these deficits are markers of vulnerability or symptoms of the disease is still unclear. This study used a component-wise gradient (CGB) machine learning algorithm to identify cognitive measures that could accurately differentiate pediatric BD, unaffected offspring of BD parents, and healthy controls.

METHODS

59 healthy controls (HC; 11.19 ± 3.15 yo; 30 girls), 119 children and adolescents with BD (13.31 ± 3.02 yo, 52 girls) and 49 unaffected offspring of BD parents (UO; 9.36 ± 3.18 yo; 22 girls) completed the CANTAB cognitive battery.

RESULTS

CGB achieved accuracy of 73.2% and an AUROC of 0.785 in classifying individuals as either BD or non-BD on a dataset held out for validation for testing. The strongest cognitive predictors of BD were measures of processing speed and affective processing. Measures of cognition did not differentiate between UO and HC.

CONCLUSIONS

Alterations in processing speed and affective processing are markers of BD in pediatric populations. Longitudinal studies should determine whether UO with a cognitive profile similar to that of HC are at less or equal risk for mood disorders. Future studies should include relevant measures for BD such as verbal memory and genetic risk scores.

PET radioligand binding to translocator protein (TSPO) is increased in unmedicated depressed subjects

BACKGROUND

Inflammation is associated with major depressive disorder (MDD). Translocator protein 18 kDa (TSPO), a putative biomarker of neuroinflammation, is quantified using positron emission tomography (PET) and 11C-PBR28, a TSPO tracer. We sought to (1) investigate TSPO binding in MDD subjects currently experiencing a major depressive episode, (2) investigate the effects of antidepressants on TSPO binding, and (3) determine the relationship of peripheral and central inflammatory markers to cerebral TSPO binding. Twenty-eight depressed MDD subjects (unmedicated (n = 12) or medicated (n = 16)) and 20 healthy controls (HC) underwent PET imaging using 11C-PBR28. Total distribution volume (VT, proportional to Bmax/Kd) was measured and corrected with the free fraction in plasma (fp). The subgenual prefrontal cortex (sgPFC) and anterior cingulate cortex (ACC) were the primary regions of interest. Peripheral blood samples and cerebrospinal fluid were analyzed to investigate the relationship between TSPO binding and peripheral and central inflammatory markers, including interleukins and neurotrophic factors previously linked to depression.

RESULTS

TSPO binding was higher in MDD versus HC in the sgPFC (Cohen's d = 0.64, p = .038, 95% CI 0.04-1.24) and ACC (d = 0.60, p = .049, 95% CI 0.001-1.21), though these comparisons missed the corrected threshold for statistical significance (α = .025). Exploratory analyses demonstrated that unmedicated MDD subjects had the highest level of TSPO binding, followed by medicated MDD subjects, who did not differ from HC. TSPO binding correlated with interleukin-5 in cerebrospinal fluid but with no other central inflammatory markers.

CONCLUSIONS

This study found a trend towards increased TSPO binding in the brains of MDD subjects, and post hoc analysis extended these findings by demonstrating that this abnormality is significant in unmedicated (but not medicated) MDD subjects.

Genetic and Psychosocial Predictors of Aggression: Variable Selection and Model Building With Component-Wise Gradient Boosting

Rationale: Given datasets with a large or diverse set of predictors of aggression, machine learning (ML) provides efficient tools for identifying the most salient variables and building a parsimonious statistical model. ML techniques permit efficient exploration of data, have not been widely used in aggression research, and may have utility for those seeking prediction of aggressive behavior.

Objectives: The present study examined predictors of aggression and constructed an optimized model using ML techniques. Predictors were derived from a dataset that included demographic, psychometric and genetic predictors, specifically FK506 binding protein 5 (FKBP5) polymorphisms, which have been shown to alter response to threatening stimuli, but have not been tested as predictors of aggressive behavior in adults.

Methods: The data analysis approach utilized component-wise gradient boosting and model reduction via backward elimination to: (a) select variables from an initial set of 20 to build a model of trait aggression; and then (b) reduce that model to maximize parsimony and generalizability.

Results: From a dataset of N = 47 participants, component-wise gradient boosting selected 8 of 20 possible predictors to model Buss-Perry Aggression Questionnaire (BPAQ) total score, with R² = 0.66. This model was simplified using backward elimination, retaining six predictors: smoking status, psychopathy (interpersonal manipulation and callous affect), childhood trauma (physical abuse and neglect), and the FKBP5_13 gene (rs1360780). The six-factor model approximated the initial eight-factor model at 99.4% of R².

Conclusions: Using an inductive data science approach, the gradient boosting model identified predictors consistent with previous experimental work in aggression; specifically psychopathy and trauma exposure. Additionally, allelic variants in FKBP5 were identified for the first time, but the relatively small sample size limits generality of results and calls for replication. This approach provides utility for the prediction of aggression behavior, particularly in the context of large multivariate datasets.