Subjective and objective sleep and circadian parameters as predictors of depression-related outcomes: A machine learning approach in UK Biobank

Non-invasive neurostimulation to improve sleep quality and depressive symptoms in patients with major depressive disorder: A meta-analysis of randomized controlled trials

BACKGROUND

Non-invasive neurostimulation, including bright light therapy (BLT), repetitive transcranial magnetic (rTMS) and transcranial direct current stimulation (tDCS), has been shown to alleviate depressive symptoms in major depressive disorder (MDD). However, the efficacy of these interventions in addressing sleep disturbances in MDD patients remains a subject of debate.

OBJECTIVE

We aimed to conduct a meta-analysis of available randomized controlled trials (RCTs) to assess the effectiveness of non-invasive neurostimulation in improving sleep disturbances and depressive symptoms in MDD patients.

METHODS

Systematic searches for relevant RCTs were conducted in the databases PubMed, Cochrane Library, Web of Science, EMBASE, Wanfang and China National Knowledge Infrastructure up to January 2024. Data on outcomes comparable across the studies were meta-analyzed using Review Manager 5.3 and Stata 14. The pooled results were reported as standardized mean differences (SMD) with their respective 95% confidence intervals (CI).

RESULTS

Our analysis encompassed 15 RCTs involving 1348 patients. Compared to sham or no stimulation, non-invasive neurostimulation significantly improved sleep quality (SMD -0.74, 95%CI -1.15 to -0.33, p = 0.0004) and sleep efficiency (SMD 0.35, 95%CI 0.10 to 0.60, p = 0.006). It also significantly reduced severity of depressive symptoms (SMD -0.62, 95%CI -0.90 to -0.35, p < 0.00001). Subgroup analysis further demonstrated that patients experiencing sleep improvements due to neurostimulation showed a marked decrease in depressive symptoms compared to the control group (SMD = -0.90, 95% CI [-1.26, -0.54], p < 0.0001).

CONCLUSION

Current evidence from RCTs suggests that neurostimulation can enhance sleep quality and efficiency in individuals with MDD, which in turn may be associated with mitigation of depressive symptoms.

PROSPERO REGISTRATION

CRD42023423844.

The gut microbiota and post-traumatic major depression disorder: insights from bidirectional two-sample Mendelian randomization

Background

Exposure to trauma is often associated with an increased incidence of Major Depressive Disorder (MDD), yet the mechanisms underlying MDD development post-trauma remain elusive. The microbiota-gut-brain axis has been implicated in neuropsychiatric disorders, suggesting its potential role in post-traumatic MDD (PTMDD) development. Our study aimed to assess the significance of the gut microbiome-brain interaction in PTMDD.

Methods

We conducted a bidirectional two-sample Mendelian Randomization (MR) analysis to investigate the causal relationship between the gut microbiota and both PTMDD and trauma exposure in MDD. Genome-wide association study (GWAS) summary datasets for PTMDD and trauma exposure in MDD, both derived from the UK Biobank. The PTMDD dataset included 24,090 individuals (13,393 cases and 10,701 controls), while the dataset for trauma exposure in MDD comprised 22,880 participants (13,393 cases and 9,487 controls). Additionally, gut microbiota data from the MiBioGen consortium included 14,306 European individuals across 18 diverse cohorts.

Results

Our research identified a significant negative association between the phylum Verrucomicrobia (odds ratio (OR) [95% confidence interval (CI)] =0.799 [0.684-0.933], P=0.005) and the risk of developing PTMDD, suggesting a protective role for Verrucomicrobia against PTMDD. Conversely, our findings indicate no causal effects of the gut microbiota on trauma exposure in MDD. However, reverse analysis revealed that both PTMDD and MDD influence certain bacterial traits, affecting 5 and 9 bacterial traits, respectively. Moreover, Verrucomicrobia (OR [95% CI] = 1.166 [1.051 - 1.294], P=0.004) was found to be positively impacted by trauma exposure in MDD.

Conclusion

Our findings provide a cause-and-effect relationship between the gut microbiota and PTMDD, contributing to our understanding of the microbiota-gut-brain axis and its role in neuropsychiatric disorder development after trauma. This information provides an opportunity for new treatment and prevention methods which are aimed at the gut-brain interaction.

Machine Learning and Bayesian Network Analyses Identifies Psychiatric Disorders and Symptom Associations with Insomnia in a national sample of 31,285 Treatment-Seeking College Students

Background

A better understanding of the structure of relations among insomnia and anxiety, mood, eating, and alcohol-use disorders is needed, given its prevalence among young adults. Supervised machine learning provides the ability to evaluate the discriminative accuracy of psychiatric disorders associated with insomnia. Combined with Bayesian network analysis, the directionality between symptoms and their associations may be illuminated.

Methods

The current exploratory analyses utilized a national sample of college students across 26 U.S. colleges and universities collected during population-level screening before entering a randomized controlled trial. Firstly, an elastic net regularization model was trained to predict, via repeated 10-fold cross-validation, which psychiatric disorders were associated with insomnia severity. Seven disorders were included: major depressive disorder, generalized anxiety disorder, social anxiety disorder, panic disorder, post-traumatic stress disorder, anorexia nervosa, and alcohol use disorder. Secondly, using a Bayesian network approach, completed partially directed acyclic graphs (CPDAG) built on training and holdout samples were computed via a Bayesian hill-climbing algorithm to determine symptom-level interactions of disorders most associated with insomnia [based on SHAP (SHapley Additive exPlanations) values)] and were evaluated for stability across networks.

Results

Of 31,285 participants, 20,597 were women (65.8%); mean (standard deviation) age was 22.96 (4.52) years. The elastic net model demonstrated clinical significance in predicting insomnia severity in the training sample [R2 = .449 (.016); RMSE = 5.00 [.081]), with comparable performance in accounting for variance explained in the holdout sample [R2 = .33; RMSE = 5.47). SHAP indicated the presence of any psychiatric disorder was associated with higher insomnia severity, with major depressive disorder demonstrated to be the most associated disorder. CPDAGs showed excellent fit in the holdout sample and suggested that depressed mood, fatigue, and self-esteem were the most important depression symptoms that presupposed insomnia.

Conclusion

These findings offer insights into associations between psychiatric disorders and insomnia among college students and encourage future investigation into the potential direction of causality between insomnia and major depressive disorder.

Trial registration

Trial may be found on the National Institute of Health RePORTER website: Project Number: R01MH115128-05.

Evidence for the biopsychosocial model of suicide: a review of whole person modeling studies using machine learning

Background

Traditional approaches to modeling suicide-related thoughts and behaviors focus on few data types from often-siloed disciplines. While psychosocial aspects of risk for these phenotypes are frequently studied, there is a lack of research assessing their impact in the context of biological factors, which are important in determining an individual's fulsome risk profile. To directly test this biopsychosocial model of suicide and identify the relative importance of predictive measures when considered together, a transdisciplinary, multivariate approach is needed. Here, we systematically review the emerging literature on large-scale studies using machine learning to integrate measures of psychological, social, and biological factors simultaneously in the study of suicide.

Methods

We conducted a systematic review of studies that used machine learning to model suicide-related outcomes in human populations including at least one predictor from each of biological, psychological, and sociological data domains. Electronic databases MEDLINE, EMBASE, PsychINFO, PubMed, and Web of Science were searched for reports published between August 2013 and August 30, 2023. We evaluated populations studied, features emerging most consistently as risk or resilience factors, methods used, and strength of evidence for or against the biopsychosocial model of suicide.

Results

Out of 518 full-text articles screened, we identified a total of 20 studies meeting our inclusion criteria, including eight studies conducted in general population samples and 12 in clinical populations. Common important features identified included depressive and anxious symptoms, comorbid psychiatric disorders, social behaviors, lifestyle factors such as exercise, alcohol intake, smoking exposure, and marital and vocational status, and biological factors such as hypothalamic-pituitary-thyroid axis activity markers, sleep-related measures, and selected genetic markers. A minority of studies conducted iterative modeling testing each data type for contribution to model performance, instead of reporting basic measures of relative feature importance.

Conclusion

Studies combining biopsychosocial measures to predict suicide-related phenotypes are beginning to proliferate. This literature provides some early empirical evidence for the biopsychosocial model of suicide, though it is marred by harmonization challenges. For future studies, more specific definitions of suicide-related outcomes, inclusion of a greater breadth of biological data, and more diversity in study populations will be needed.

Major depressive episode with insomnia and excessive daytime sleepiness: A more homogeneous and severe subtype of depression

Previous studies have noted the crucial role of excessive daytime sleepiness (EDS) in the course of depressive illness, and more recently, a few studies documented its strong associations with an increased risk of suicide. While insomnia is associated with heightened emotional reactivity, suicidal behaviors, and increased relapses and recurrence. Our main hypothesis is that major depressive episodes (MDE) with insomnia and EDS are associated with more severe manifestations of depression. However, to date, no study has directly compared MDE with insomnia without EDS (Ins), and MDE with insomnia with EDS (InsEDS) using both subjective biomarkers (administration of self-assessment questionnaires for psychiatric evaluation and sleep complaints) and objective biomarkers (of sleep and circadian rhythms (using actigraphy). The InsEDS group, compared to the Ins group, exhibited significantly increased suicidal ideation, larger seasonal impacts on mood, alterations in sleep duration, weight, appetite, energy levels, and social activities throughout the year. Furthermore, they had significant delayed onset of daily activity measured with actigraphy. These findings provided new insights into the link between suicide, sleep, alertness, and biological clock. They also hold significant implications for identifying individuals with more severe depressive manifestations and for developing tailored and personalized therapeutic strategies.