IntroductionDepression is a prevalent mental disorder with a severe global impact. Traditional interview-based assessments are limited by subjectivity, lengthy procedures, and unequal access to care. Although advances in AI have facilitated multimodal models for depression detection—using audiovisual data as an accessible alternative to biosignals—current approaches remain challenged by inefficient long-term temporal modeling and superficial multimodal fusion. Moreover, biosignal-based methods are constrained by high costs and narrow applicability. These challenges underscore the urgent need for optimized multimodal solutions.MethodsThis paper proposes ASYM (Attentive Synergy Mamba), a novel multimodal architecture for depression recognition, comprising three core modules: a Cross-Modal Interactive Mamba, a Multi-Scale Gated Parallel Fusion, and a Multimodal Enhanced Mamba. First, features from each modality are interactively enhanced using convolutional neural network and Bi-Mamba blocks. Cross-modal complementary information is then extracted via a cross-attention mechanism. A dual-path fusion module subsequently augments multi-scale representations and integrates cross-modal features through dynamic weighting. Finally, the feature representations are refined by a series of Bi-Mamba blocks.ResultsEvaluations on the D-Vlog and LMVD datasets using accuracy, precision, recall, and F1-score showed that ASYM achieved an accuracy of 70.91% and an F1-score of 77.13% on D-Vlog, and 74.68% accuracy with a 74.90% F1-score on LMVD. The macro-average performance across both datasets surpassed all compared mainstream methods. Ablation studies confirmed the necessity of each component, as removing any module significantly degraded performance, underscoring the efficacy and critical contribution of the proposed architecture.DiscussionWhile multimodal depression detection has improved upon single-modality approaches, issues such as computational inefficiency in long-sequence processing and inadequate fusion strategies persist. Our model addresses these limitations through multimodal interaction and multi-scale feature fusion. Future work will focus on clinical validation across diverse populations to bridge computational psychiatry and clinical practice.
The associations of systemic inflammation and insulin resistance-related indicators with psychopathology and BDNF in patients with chronic schizophrenia
BackgroundThe triglyceride-glucose (TyG) index and C-reactive protein-triglyceride-glucose index (CTI) are innovative indicators for assessing insulin resistance (IR) and inflammation, yet research on them in patients with schizophrenia remains limited. This study aimed to explore TyG index and CTI levels and their associations with psychopathology and brain-derived neurotrophic factor (BDNF) in patients with chronic schizophrenia (CS).MethodsThis cross-sectional study was conducted across one general hospital and two psychiatric hospitals in Anhui Province, China. Socio-demographic information and hematological parameters were collected from participants, and their psychiatric and depressive symptoms were assessed using the Positive and Negative Syndrome Scale (PANSS) and the Calgary Depression Scale for Schizophrenia (CDSS), respectively.ResultsA total of 324 patients with CS and 150 healthy controls (HCs) were enrolled in the study. Compared with HCs, patients had higher TyG index and CTI levels (all P < 0.001). Binary logistic regression analyses revealed that among patients, a high TyG index level was significantly associated with higher BDNF levels and lower negative factor scores of the PANSS, while a high CTI level was significantly associated with higher depression-hopelessness factor scores of the CDSS and lower negative factor scores of the PANSS (all P < 0.05).ConclusionPatients with CS had higher levels of TyG index and CTI, which were significantly associated with the severity of negative and depressive symptoms, as well as BDNF levels. It is suggested that the integration of the TyG index and CTI into clinical monitoring for patients with CS is necessary.
Effect of transcranial magnetic stimulation on prognosis in patients with postherpetic neuralgia and comorbid depression undergoing interventional neuromodulation therapy: protocol for a randomized double-blind placebo-controlled trial
BackgroundPostherpetic neuralgia (PHN) is often accompanied by depression, creating a vicious cycle that exacerbates symptoms and contributes to suboptimal treatment outcomes, even with interventional therapies. Repetitive transcranial magnetic stimulation (rTMS) has demonstrated potential in alleviating both pain and mood disturbances. However, its efficacy in enhancing prognosis when used alongside interventional neuromodulation therapy for PHN accompanied by depression remains inadequately explored and requires further investigation.ObjectiveThis study aims to generate preliminary evidence on the efficacy and safety of rTMS in enhancing prognosis and alleviating pain in patients with PHN and mild to moderate depression undergoing interventional neuromodulation therapy.MethodsThis study is a single-center, randomized, double-blind, placebo-controlled trial involving 174 adult patients with PHN. Participants will be randomly assigned, stratified by interventional neuromodulation therapy, to either the rTMS group (n=87) or the control group (n=87). Both groups will undergo either 10 Hz rTMS or sham stimulation for five consecutive days. The primary outcome is the incidence of poor prognosis at 3 months post-discharge. Secondary outcomes include the incidence of poor prognosis at 6 months post-discharge; Visual Analog Scale (VAS) sleep scores; short-form McGill Pain Questionnaire (SF-MPQ) scores; Self-Rating Depression Scale (SDS) scores; patient satisfaction; Pain Disability Index (PDI) scores; Multidimensional Fatigue Inventory-20 (MFI-20) scores; pregabalin oral doses; and the need for tramadol or antidepressants. Safety outcomes will include assessments of headache, pain at the stimulation site, neck pain, insomnia, muscle soreness, dizziness, nausea, tinnitus, irritability, tachycardia (heart rate > 100 bpm), and epilepsy. Data will be analyzed using a modified intention-to-treat approach.DiscussionThis study aims to provide preliminary evidence on the efficacy and safety of 10 Hz rTMS in improving prognosis and alleviating pain in PHN patients with mild to moderate depression undergoing interventional pain management.Trial registrationhttps://www.chictr.org.cn/bin/project/edit?pid=261070, identifier ChiCTR2500096978.
From work-related trauma to suicidal ideation: a serial mediation model of posttraumatic stress and depression in rescue workers
ObjectivesRescue workers face frequent occupational trauma, increasing their risk for posttraumatic stress symptoms (PTSS), depression, and suicidal ideation. However, pathways linking trauma to suicidality remain poorly understood. This study investigated these mechanisms by testing a serial mediation model.MethodsFrom a larger survey of Swiss rescue workers, participants reporting suicidal ideation (n = 44) were matched by age, sex, and profession with a control group without suicidal ideation (n = 44). Symptomatology was assessed using validated questionnaires such as the Posttraumatic Stress Scale-10 (PTSS-10) for posttraumatic stress and the Brief Symptom Inventory (BSI) for depressive symptoms. Structural Equation Modeling (SEM) was employed to test a serial two-mediator model: Trauma Exposure – PTSS – Depressive Symptoms – Suicidal Ideation.ResultsParticipants with suicidal ideation had significantly higher levels of trauma, PTSS, and depressive symptoms. SEM confirmed an excellent model fit (χ² = 1.925, CFI = 1.000, RMSEA <.001) and a full mediation effect: trauma exposure was associated with PTSS, which in turn related to depressive symptoms, which were subsequently linked to suicidal ideation. The specific serial indirect pathway was significant (B = 0.143, p = .011), while the direct path from trauma to suicidal ideation was non-significant. The model explained 69.4% of the variance in suicidal ideation.ConclusionThe findings suggest a developmental pathway in which trauma exposure is associated with suicidal ideation through the sequential roles of PTSS and depressive symptoms. Consequently, suicide prevention for rescue workers should prioritize the management of post-traumatic and depressive symptoms to potentially disrupt this symptomatic progression.
Peer Mentor Training and Supervision for a Digital Adolescent Depression Treatment in South Africa and Uganda: Mixed Methods Evaluation
Background: Blended digital mental health interventions combining technology with human support are more effective than stand-alone treatments. However, limited research has examined how to train and supervise personnel delivering human support components. The Kuamsha app, a gamified digital intervention for adolescent depression based on behavioral activation, was designed to be paired with low-intensity telephone-based peer support. A structured training and supervision program for peer supporters was codeveloped through workshops with mental health professionals and youth with lived experience of mental health challenges in South Africa and Uganda. To the best of our knowledge, this is the first study to evaluate a structured peer mentor model within a digital mental health intervention in low- and middle-income countries. Objective: This study assessed the feasibility, acceptability, and fidelity of a training and supervision program for peer supporters delivering a digital mental health intervention in South Africa and Uganda. Methods: We conducted a mixed methods evaluation of the peer mentor program. Quantitative metrics assessed the feasibility of recruitment, retention, and attendance among peer mentors (n=13, South Africa; n=4, Uganda), as well as training acceptability. Fidelity, adherence, and competence were scored at the session level and converted to percentages of the maximum possible score. Linear mixed-effects regression models with a random intercept for provider and site estimated adjusted marginal means (95% CI). In-depth interviews and focus group discussions explored program acceptability and implementation factors. Results: The peer mentor training and supervision program was feasible and acceptable in both settings, with high recruitment (South Africa: n=13/19, 68%; Uganda: 4/4, 100%), retention (South Africa: 9/13, 69%; Uganda: 4/4, 100%), and training attendance rates (89%‐92% in South Africa and 100% in Uganda), alongside qualitative reports of high satisfaction. All peer mentors met a minimum posttraining competency threshold (≥50%), with median competency scores of 70.7% (IQR 45.8%‐78.2%) in South Africa and 75.4% (IQR 73.8%‐77.3%) in Uganda. Independent ratings of recorded calls indicated high overall fidelity in South Africa (84.7%, 95% CI 80.3%‐89.0%) and Uganda (87.7%, 95% CI 83.4%‐92.1%). Adherence was higher in Uganda than South Africa (adjusted mean difference [AMD] 13.30 percentage points, 95% CI 8.99‐17.61; <.001), as was competence (AMD 4.88 percentage points, 95% CI 1.23‐8.53; =.009). The AMD in overall fidelity (3.06 percentage points, 95% CI −0.98 to 7.10) was not statistically significant (=.14). The qualitative findings emphasized the value of ongoing supervision and capacity development, interactive training approaches, and blended delivery models. Conclusions: Locally adapted training and supervision models can strengthen peer mentor capabilities to support digital interventions. Adequate supervisory capacity and incentive structures are critical to sustain engagement, retention, and fidelity. In settings with frequent network disruptions, periodic in-person contact between peer mentors and supervisors may enhance fidelity. Future research should examine how peer mentor fidelity influences user engagement and mental health outcomes. Trial Registration: Pan African Clinical Trials Registry PACTR202206574814636; https://pactr.samrc.ac.za/TrialDisplay.aspx?TrialID=23792 International Registered Report Identifier (IRRID): RR2-10.1136/bmjopen-2022-065977
<![CDATA[Deep intracranial frequency stimulation 77.5 Hz high-gamma approach was associated with statistically significant reductions in self-injury behaviors and depressive symptoms in female adolescents with nonsuicidal self-injury.]]>
<![CDATA[BPL-003 phase 2a part 2 results show reductions in depression symptoms.]]>
<![CDATA[Explore glutamate-based depression treatments—esketamine and dextromethorphan-bupropion—boost synaptogenesis and deliver fast relief when monoamines fail.]]>
<![CDATA[Why settle for “less bad”? Clinicians urge aggressive depression care aimed at true remission, balancing side effects and patient priorities.]]>
Prefrontal and hippocampal microstructural gray matter following cognitive training under moderate hypoxia in mood disorders: a randomized controlled trial
BackgroundCognitive impairment persists during partial or full remission in 50–70% of individuals with mood disorders and impacts daily functioning and clinical prognosis. Preclinical evidence suggests that extended exposure to moderate hypoxia, combined with motor-cognitive learning, may elevate neuroplasticity and improve cognition. In these individuals with remitted mood disorders, we found that cognitive training under repeated moderate normobaric hypoxia improved executive function, and here investigate neurobiological mechanisms.MethodsParticipants with major depressive disorder (MDD) or bipolar disorder (BD) in partial or full remission were randomized to 3 weeks of 3.5-h daily normobaric hypoxia (12% O2) combined with cognitive training five to 6 days per week or treatment-as-usual (TAU). Participants were assessed with cognitive tests and diffusion-weighted MRI at baseline and 1 month after treatment completion (week 8) as part of the ALTIBRAIN trial (ClinicalTrials.gov: NCT06121206). Prefrontal and hippocampal gray matter microstructure were modelled with Neurite Orientation Dispersion and Density Imaging (NODDI).ResultsFifty-seven participants (mean age 39 years, SD: 13, 70% female) with baseline MRI data were included. No significant effects of hypoxia-cognition training vs. TAU on neurite density index (NDI) or orientation dispersion index (ODI) were observed in either the prefrontal cortex or hippocampus (all p-FDR ≥ 0.832). No significant associations were observed between microstructural changes and changes in cognitive function in either region (all p-FDR ≥ 0.721). At baseline, microstructure in both regions was not associated with executive function or global cognition (all p > 0.40).ConclusionThe absence of detectable microstructural changes, despite selective improvements in executive function, indicates that NODDI-derived metrics did not capture structural correlates of the cognitive response to hypoxia-cognition training. Whether this reflects functional neural mechanisms, measurement insensitivity, or the timing of the single follow-up assessment remains to be determined. Future studies should incorporate multiple imaging time points to capture the dynamic trajectories of putative microstructural brain changes.