Using Data-Driven Algorithms with Large-Scale Plasma Proteomic Data to Discover Novel Biomarkers for Diagnosing Depression.

Given recent technological advances in proteomics, it is now possible to quantify plasma proteomes in large cohorts of patients to screen for biomarkers and to guide the early diagnosis and treatment of depression. Here we used CatBoost machine learning to model and discover biomarkers of depression in UK Biobank data sets (depression n = 4,479, healthy control n = 19,821). CatBoost was employed for model construction, with Shapley Additive Explanations (SHAP) being utilized to interpret the resulting model. Model performance was corroborated through 5-fold cross-validation, and its diagnostic efficacy was evaluated based on the area under the receiver operating characteristic (AUC) curve. A total of 45 depression-related proteins were screened based on the top 20 important features output by the CatBoost model in six data sets. Of the nine diagnostic models for depression, the performance of the traditional risk factor model was improved after the addition of proteomic data, with the best model having an average AUC of 0.764 in the test sets. KEGG pathway analysis of 45 screened proteins showed that the most significant pathway involved was the cytokine-cytokine receptor interaction. It is feasible to explore diagnostic biomarkers of depression using data-driven machine learning methods and large-scale data sets, although the results require validation.

Evaluating Inflammatory Bowel Disease-Related Quality of Life Using an Interpretable Machine Learning Approach: A Multicenter Study in China.

Purpose: Impaired quality of life (QOL) is common in patients with inflammatory bowel disease (IBD). A tool to more quickly identify IBD patients at high risk of impaired QOL improves opportunities for earlier intervention and improves long-term prognosis. The purpose of this study was to use a machine learning (ML) approach to develop risk stratification models for evaluating IBD-related QOL impairments. Patients and Methods: An online questionnaire was used to collect clinical data on 2478 IBD patients from 42 hospitals distributed across 22 provinces in China from September 2021 to May 2022. Eight ML models used to predict the risk of IBD-related QOL impairments were developed and validated. Model performance was evaluated using a set of indexes and the best ML model was explained using a Local Interpretable Model-Agnostic Explanations (LIME) algorithm. Results: The support vector machine (SVM) classifier algorithm-based model outperformed other ML models with an area under the receiver operating characteristic curve (AUC) and an accuracy of 0.80 and 0.71, respectively. The feature importance calculated by the SVM classifier algorithm revealed that glucocorticoid use, anxiety, abdominal pain, sleep disorders, and more severe disease contributed to a higher risk of impaired QOL, while longer disease course and the use of biological agents and immunosuppressants were associated with a lower risk. Conclusion: An ML approach for assessing IBD-related QOL impairments is feasible and effective. This mechanism is a promising tool for gastroenterologists to identify IBD patients at high risk of impaired QOL.

Risk Prediction Model for Non-Suicidal Self-Injury in Chinese Adolescents with Major Depressive Disorder Based on Machine Learning.

Background: Non-suicidal self-injury (NSSI) is a significant social issue, especially among adolescents with major depressive disorder (MDD). This study aimed to construct a risk prediction model using machine learning (ML) algorithms, such as XGBoost and random forest, to identify interventions for healthcare professionals working with adolescents with MDD. Methods: This study investigated 488 adolescents with MDD. Adolescents was randomly divided into 75% training set and 25% test set to testify the predictive value of risk prediction model. The prediction model was constructed using XGBoost and random forest algorithms. We evaluated the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, recall, F Score of the two models for comparing the performance of the two models. Results: There were 161 (33.00%) participants having NSSI. Compared without NSSI, there were statistically significant differences in gender (P=0.035), age (P=0.036), depressive symptoms (P=0.042), sleep quality (P=0.030), dysfunctional attitudes (P=0.048), childhood trauma (P=0.046), interpersonal problems (P=0.047), psychoticism (P) (P=0.049), neuroticism (N) (P=0.044), punishing and Severe (F2) (P=0.045) and Overly-intervening and Protecting (M2) (P=0.047) with NSSI. The AUC values for random forest and XGBoost were 0.780 and 0.807, respectively. The top five most important risk predictors identified by both machine learning methods were dysfunctional attitude, childhood trauma, depressive symptoms, F2 and M2. Conclusion: The study demonstrates the suitability of prediction models for predicting NSSI behavior in Chinese adolescents with MDD based on ML. This model improves the assessment of NSSI in adolescents with MDD by health care professionals working. This provides a foundation for focused prevention and interventions by health care professionals working with these adolescents.

Exploring mechanisms of anhedonia in depression through neuroimaging and data-driven approaches.

BACKGROUND: Anhedonia is a core symptom of depression that is closely related to prognosis and treatment outcomes. However, accurate and efficient treatments for anhedonia are lacking, mandating a deeper understanding of the underlying mechanisms. METHODS: A total of 303 patients diagnosed with depression and anhedonia were assessed by the Snaith-Hamilton Pleasure Scale (SHAPS) and magnetic resonance imaging (MRI). The patients were categorized into a low-anhedonia group and a high-anhedonia group using the K-means algorithm. A data-driven approach was used to explore the differences in brain structure and function with different degrees of anhedonia based on MATLAB. A random forest model was used exploratorily to test the predictive ability of differences in brain structure and function on anhedonia in depression. RESULTS: Structural and functional differences were apparent in several brain regions of patients with depression and high-level anhedonia, including in the temporal lobe, paracingulate gyrus, superior frontal gyrus, inferior occipital gyrus, right insular gyrus, and superior parietal lobule. And changes in these brain regions were significantly correlated with scores of SHAPS. CONCLUSIONS: These brain regions may be useful as biomarkers that provide a more objective assessment of anhedonia in depression, laying the foundation for precision medicine in this treatment-resistant, relatively poor prognosis group.

Fluoxetin suppresses tau phosphorylation and modulates the interaction between tau and tubulin in the hippocampus of CUMS rats.

Depression is considered a crucial psychiatric disease correlated with neuronal-dysfunctions induced by stress-stimuli. This study aimed to investigate effect of Fluoxetine (FL) on chronic unpredictable mild stress (CUMS) and explore the associated mechanisms. CUMS rat model was established by treating with lots of stresses. CUMS rats were administered FL, SB216763 (SB), Wortmannin (WT) alone or in combination. CUMS rats were administered 1 % sugar water to conduct sugar water consumption experiment. Acet-Tub, Tyr-Tub, tau46, p-tau-Ser199/202, p-tau-Ser396, p-tau-Ser231, expression was examined using immunohistochemical assay and western blotassay. Interaction between tau and tubulin was evaluated with immunoprecipitation assay. Double immunohistochemical assay was used to identify interaction between Nestin and Tau. The results indicated that FL treatment only increased sugar consumption of CUMS rats (P < 0.05), but also strengthened effects of SB and WT. FL significantly treatment decreased tau phosphorylation (p-tau) in hippocampal tissues of rats compared to those of rats in CUMS group (P < 0.05). FL treatment markedly decreased Acet-Tub and increased Tyr-Tub expression in hippocampal tissues of rats compared to those of rats in CUMS group (P < 0.05). The effects of FL treatment on p-tau down-regulation and tubulin modulation in hippocampal tissues were independent from PI3K and GSK-3 signaling pathways. FL treatment could also enhance proliferation and total tau of newborn neurons of CUMS rats. FL treatment strengthened interaction between tau and botulin in hippocampal tissues of CUMS rats. In conclusion, Fluoxetin suppressed phosphorylation of tau and modulated the interaction between tau and tubulin in hippocampus of adult CUMS rats.

Executive function impairment is associated with low serum vitamin D levels in children with epilepsy.

PURPOSE: Executive function (EF) impairment and vitamin D deficiency are common clinical features among children with epilepsy (CWE). Recently, vitamin D has become a potential modification factor that affects cognitive status in individuals with neurological disorders. In this study, we investigated the association between EF status and vitamin D levels in patients with CWE. METHODS: In total, 79 CWE patients and 39 healthy controls (HCs) were recruited in this study. Each participant's EF was assessed using the Behavior Rating Inventory of Executive Function-Parent form (Brief-P), and the serum level of 25-OH vitamin D was measured using liquid chromatography-tandem mass spectrometry (LC-MS/MS). RESULTS: Compared with those in the HC group, the CWE group had higher T scores of Brief-P scale, including global executive composite (GEC) (51.01(45.12, 60.69) vs. 44.08(39.24, 49.96), p＜0.001), behavioral regulation index (BRI) (51.29(45.67, 59.13) vs. 45.67(40.06, 51.29), p＜0.001), metacognition index (MI) (51.83(46.77, 59.43) vs. 46.13(40.44, 51.83), p＜0.001), and lower serum vitamin D (14.85(10.24,23.2) vs. 22.5(16.91,30), p＜0.001) levels. After adjustment for covariates, multivariate linear regression models suggested that for every 1 ng/ml increase in vitamin D, the GEC, BRI, and MI would decrease by 0.52 (Coeff = -0.48; 95 % CI = -0.69, -0.26; p = 0.000), 0.45 (Coeff = -0.45; 95 % CI = -0.69, -0.20; p = 0.000), and 0.47 (Coeff = -0.45; 95 % CI = -0.67, -0.22; p = 0.000), respectively. CONCLUSION: There may be an association between decreased vitamin D levels and EF impairment in CWE. Future research should consider longitudinal variations in EF related to improving vitamin D deficiency.

Dose adjustment of paroxetine based on CYP2D6 activity score inferred metabolizer status in Chinese Han patients with depressive or anxiety disorders: a prospective study and cross-ethnic meta-analysis.

BACKGROUND: Understanding the impact of CYP2D6 metabolism on paroxetine, a widely used antidepressant, is essential for precision dosing. METHODS: We conducted an 8-week, multi-center, single-drug, 2-week wash period prospective cohort study in 921 Chinese Han patients with depressive or anxiety disorders (ChiCTR2000038462). We performed CYP2D6 genotyping (single nucleotide variant and copy number variant) to derive the CYP2D6 activity score and evaluated paroxetine treatment outcomes including steady-state concentration, treatment efficacy, and adverse reaction. CYP2D6 metabolizer status was categorized into poor metabolizers (PMs), intermediate metabolizers (IMs), extensive metabolizers (EMs), and ultrarapid metabolizers (UMs). The influence of CYP2D6 metabolic phenotype on paroxetine treatment outcomes was examined using multiple regression analysis and cross-ethnic meta-analysis. The therapeutic reference range of paroxetine was estimated by receiver operating characteristic (ROC) analyses. FINDINGS: After adjusting for demographic factors, the steady-state concentrations of paroxetine in PMs, IMs, and UMs were 2.50, 1.12, and 0.39 times that of EMs, with PM and UM effects being statistically significant (multiple linear regression, P = 0.03 and P = 0.04). Sex and ethnicity influenced the comparison between IMs and EMs. Moreover, poor efficacy of paroxetine was associated with UM, and a higher risk of developing adverse reactions was associated with lower CYP2D6 activity score. Lastly, cross-ethnic meta-analysis suggested dose adjustments for PMs, IMs, EMs, and UMs in the East Asian population to be 35%, 40%, 143%, and 241% of the manufacturer's recommended dose, and 62%, 68%, 131%, and 159% in the non-East Asian population. INTERPRETATION: Our findings advocate for precision dosing based on the CYP2D6 metabolic phenotype, with sex and ethnicity being crucial considerations in this approach. FUNDING: National Natural Science Foundation of China; Academy of Medical Sciences Research Unit.

Common gastrointestinal symptoms and their impact on psychological state and quality of life in patients with inflammatory bowel disease: a cross-sectional multicenter study in China.

Objective: To explore the impact of common gastrointestinal (GI) symptoms on psychological symptoms, sleep quality, and quality of life in patients with inflammatory bowel disease (IBD). Methods: A unified questionnaire was developed to collect clinical data on the mental psychology and quality of life of IBD patients from 42 hospitals in 22 provinces in P. R. China from September 2021 to May 2022. The general clinical characteristics, psychological symptoms, sleep quality, and quality of life of IBD patients with different numbers of GI symptoms were analyzed by descriptive statistical analysis. Results: A total of 2,478 IBD patients were finally analysed in this study, including 365 without GI symptoms (14.7%), 752 with single symptoms (30.4%), 841 with double symptoms (33.9%), and 520 with three symptoms (21.0%). Compared with patients without GI symptoms, patients with only simple abdominalgia or diarrhea or hematochezia showed significantly higher levels of anxiety and depression and worse quality of life (all P < 0.05). Compared with asymptomatic patients, patients with double symptoms (e.g. abdominalgia plus hematochezia, diarrhea plus hematochezia, abdominalgia plus diarrhea) and patients with three symptoms (abdominalgia, diarrhea, and hematochezia) showed significantly higher levels of anxiety and depression and worse sleep quality and quality of life (all P < 0.05). Conclusion: Compared with IBD patients without gastrointestinal symptoms, patients with gastrointestinal symptoms were more likely to experience anxiety, depression, sleep disturbances, and poorer quality of life.

Effects of autotaxin and lysophosphatidic acid deficiencies on depression-like behaviors in mice exposed to chronic unpredictable mild stress.

The involvement of lipids in the mechanism of depression has triggered extensive discussions. Earlier studies have identified diminished levels of lysophosphatidic acid (LPA) and autotaxin (ATX) in individuals experiencing depression. However, the exact significance of this phenomenon in relation to depression remains inconclusive. This study seeks to explore the deeper implications of these observations. We assessed alterations in ATX and LPA in both the control group and the chronic unpredictable mild stress (CUMS) model group. Additionally, the impact of ATX adeno-associated virus (AAV-ATX) injection into the hippocampus was validated through behavioral tests in CUMS-exposed mice. Furthermore, we probed the effects of LPA on synapse-associated proteins both in HT22 cells and within the mouse hippocampus. The mechanisms underpinning the LPA-triggered shifts in protein expression were further scrutinized. Hippocampal tissues were augmented with ATX to assess its potential to alleviate depression-like behavior by modulating synaptic-related proteins. Our findings suggest that the decrement in ATX and LPA levels alters the expression of proteins associated with synaptic plasticity in vitro and in vivo, such as synapsin-I (SYN), synaptophysin (SYP), and brain-derived neurotrophic factor (BDNF). Moreover, we discerned a role for the ERK/CREB signaling pathway in mediating the effects of ATX and LPA. Importantly, strategic supplementation of ATX effectively mitigated depression-like behaviors. This study indicates that the ATX-LPA pathway may influence depression-like behaviors by modulating synaptic plasticity in the brains of CUMS-exposed mice. These insights augment our understanding of depression's potential pathogenic mechanism in the context of lipid metabolism and propose promising therapeutic strategies for ameliorating the disease.

Oligodendrocyte-derived exosomes-containing SIRT2 ameliorates depressive-like behaviors and restores hippocampal neurogenesis and synaptic plasticity via the AKT/GSK-3ß pathway in depressed mice.

AIMS: To investigate the antidepressant role of oligodendrocyte-derived exosomes (ODEXs)-containing sirtuin 2 (SIRT2) and the underlying mechanism both in vivo and in vitro. METHODS: Oligodendrocyte-derived exosomes isolated from mouse serum were administered to mice with chronic unpredictable mild stress (CUMS)-induced depression via the tail vein. The antidepressant effects of ODEXs were assessed through behavioral tests and quantification of alterations in hippocampal neuroplasticity. The role of SIRT2 was confirmed using the selective inhibitor AK-7. Neural stem/progenitor cells (NSPCs) were used to further validate the impact of overexpressed SIRT2 and ODEXs on neurogenesis and synapse formation in vitro. RESULTS: Oligodendrocyte-derived exosome treatment alleviated depressive-like behaviors and restored neurogenesis and synaptic plasticity in CUMS mice. SIRT2 was enriched in ODEXs, and blocking SIRT2 with AK-7 reversed the antidepressant effects of ODEXs. SIRT2 overexpression was sufficient to enhance neurogenesis and synaptic protein expression. Mechanistically, ODEXs mediated transcellular delivery of SIRT2, targeting AKT deacetylation and AKT/GSK-3ß signaling to regulate neuroplasticity. CONCLUSION: This study establishes how ODEXs improve depressive-like behaviors and hippocampal neuroplasticity and might provide a promising therapeutic approach for depression.

Environmental enrichment attenuates depressive-like behavior in maternal rats by inhibiting neuroinflammation and apoptosis and promoting neuroplasticity.

Gestational stress can exacerbate postpartum depression (PPD), for which treatment options remain limited. Environmental enrichment (EE) may be a therapeutic intervention for neuropsychiatric disorders, including depression, but the specific mechanisms by which EE might impact PPD remain unknown. Here we examined the behavioral, molecular, and cellular impact of EE in a stable PPD model in rats developed through maternal separation (MS). Maternal rats subjected to MS developed depression-like behavior and cognitive dysfunction together with evidence of significant neuroinflammation including microglia activation, neuronal apoptosis, and impaired synaptic plasticity. Expanding the duration of EE to throughout pregnancy and lactation, we observed an EE-associated reversal of MS-induced depressive phenotypes, inhibition of neuroinflammation and neuronal apoptosis, and improvement in synaptic plasticity in maternal rats. Thus, EE effectively alleviates neuroinflammation, neuronal apoptosis, damage to synaptic plasticity, and consequent depression-like behavior in mother rats experiencing MS-induced PPD, paving the way for new preventive and therapeutic strategies for PPD.

Dysregulated cerebral blood flow, rather than gray matter Volume, exhibits stronger correlations with blood inflammatory and lipid markers in depression.

Arterial spin labeling (ASL) can be used to detect differences in perfusion for multiple brain regions thought to be important in major depressive disorder (MDD). However, the potential of cerebral blood flow (CBF) to predict MDD and its correlations between the blood lipid levels and immune markers, which are closely related to MDD and brain function change, remain unclear. The 451 individuals - 298 with MDD and 133 healthy controls who underwent MRI at a single time point with arterial spin labelling and a high resolution T1-weighted structural scan. A proportion of MDD also provided blood samples for analysis of lipid and immune markers. We performed CBF case-control comparisons, random forest model construction, and exploratory correlation analyses. Moreover, we investigated the relationship between gray matter volume (GMV), blood lipids, and the immune system within the same sample to assess the differences in CBF and GMV. We found that the left inferior parietal but supramarginal and angular gyrus were significantly different between the MDD patients and HCs (voxel-wise P < 0.001, cluster-wise FWE correction). And bilateral inferior temporal (ITG), right middle temporal gyrus and left precentral gyrus CBF predict MDD (the area under the receiver operating characteristic curve of the random forest model is 0.717) and that CBF is a more sensitive predictor of MDD than GMV. The left ITG showed a positive correlation trend with immunoglobulin G (r = 0.260) and CD4 counts (r = 0.283). The right ITG showed a correlation trend with Total Cholesterol (r = -0.249) and tumour necrosis factor-alpha (r = -0.295). Immunity and lipids were closely related to CBF change, with the immunity relationship potentially playing a greater role. The interactions between CBF, plasma lipids and immune index could therefore represent an MDD pathophysiological mechanism. The current findings provide evidence for targeted regulation of CBF or immune properties in MDD.

Psychological symptoms and quality of life in patients with inflammatory bowel disease in China: A multicenter study.

AIMS: To investigate the current situation of mental psychology and quality of life (QoL) in patients with inflammatory bowel disease (IBD) in China, and analyze the influencing factors. METHODS: A unified questionnaire was developed to collect clinical data on IBD patients from 42 hospitals in 22 provinces from September 2021 to May 2022. Multivariate Logistic regression analysis was conducted, and independent influencing factors were screened out to construct nomogram. The consistency index (C-index), receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), calibration curve, and decision curve analysis (DCA) were used to evaluate the discrimination, accuracy, and clinical utility of the nomogram model. RESULTS: A total of 2478 IBD patients were surveyed, including 1371 patients with ulcerative colitis (UC) and 1107 patients with Crohn's disease (CD). Among them, 25.5%, 29.7%, 60.2%, and 37.7% of IBD patients had anxiety, depression, sleep disturbance and poor QoL, respectively. The proportion of anxiety, depression, and poor QoL in UC patients was significantly higher than that in CD patients (all p < 0.05), but there was no difference in sleep disturbance between them (p = 0.737). Female, higher disease activity and the first visit were independent risk factors for anxiety, depression and sleep disturbance in IBD patients (all p < 0.05). The first visit, higher disease activity, abdominal pain and diarrhea symptoms, anxiety, depression and sleep disturbance were independent risk factors for the poor QoL of patients (all p < 0.05). The AUC value of the nomogram prediction model for predicting poor QoL was 0.773 (95% CI: 0.754-0.792). The calibration diagram of the model showed that the calibration curve fit well with the ideal curve, and DCA showed that the nomogram model could bring clinical benefits. CONCLUSION: IBD patients have higher anxiety, depression, and sleep disturbance, which affect their QoL. The nomogram prediction model we constructed has high accuracy and performance when predicting QoL.

Distinct resting-state functional connectivity of the anterior cingulate cortex subregions in first-episode schizophrenia.

The anterior cingulate cortex (ACC) is a heterogeneous region of the brain's limbic system that regulates cognitive and emotional processing, and is frequently implicated in schizophrenia. This study aims to characterize resting-state functional connectivity (rsFC) profiles of three subregions of ACC in patients with first-episode schizophrenia and healthy controls. Resting-state functional magnetic resonance imaging (rs-fMRI) scans were collected from 60 first-episode schizophrenia (FES) patients and 60 healthy controls (HC), and the subgenual ACC (sgACC), pregenual ACC (pgACC), and dorsal ACC (dACC) were selected as seed regions from the newest automated anatomical labeling atlas 3 (AAL3). Seed-based rsFC maps for each ACC subregion were generated and compared between the two groups. The results revealed that compared to the HC group, the FES group showed higher rsFC between the pgACC and bilateral lateral orbitofrontal cortex (lOFC), and lower rsFC between the dACC and right posterior OFC (pOFC), the medial prefrontal gyrus (MPFC), and the precuneus cortex (PCu). These findings point to a selective functional dysconnectivity of pgACC and dACC in schizophrenia and provide more accurate information about the functional role of the ACC in this disorder.

The Neuroprotective Effects of BMSC-Derived Exosomes against Glutamate-Induced HT22 Cell Cytotoxicity.

Many central nervous system diseases are closely related to nerve damage caused by dysregulation of the endogenous neurotransmitter glutamate. Exosomes derived from bone marrow mesenchymal stem cells (BMSC-Exos) play an important role in improving injury and regeneration functions. However, its mechanism remains unknown. Therefore, the aim of this study is to investigate whether and how BMSC-Exos improve neurotoxicity caused by glutamate and to fill the gap in the literature. In this study, glutamate-treated HT22 cells were first exposed to mouse-derived BMSC-Exos at different concentrations to observe their effects on HT22 apoptosis. Next, we treated glutamate-treated HT22 cells with mouse-derived BMSC-Exos. We then inhibited the PI3K/Akt/mTOR signaling pathways using the PI3K/Akt inhibitor and the mTOR inhibitor, respectively, and observed the protective effect of mouse-derived BMSC-Exos on HT22 cells treated with glutamate. Our results show that BMSC-Exos reduced apoptosis triggered by glutamate stimulation, increased cell vitality, and decreased the levels of proapoptotic proteins while increasing the levels of anti-apoptotic proteins. The protective effect of BMSC-Exos was weakened when PI3K/Akt inhibitor and mTOR inhibitor were added. To sum up, we draw the following conclusions: BMSC-Exos can reduce neuronal apoptosis and apoptosis-related protein expression after glutamate stimulation by regulating the PI3K/Akt/mTOR signaling pathway.

The relationship between childhood maltreatment and non-suicidal self-injury in adolescents with depressive disorders.

This study aims to explore the core symptoms of Non-Suicidal Self-Injury (NSSI) in adolescents with depressive disorders and the relationship between childhood maltreatment (CM) and NSSI symptoms by using network analysis. A total of 689 adolescents with depressive disorders participated in the survey. The Chinese version of the Adolescent Non-Suicidal Self-Injury Assessment Questionnaire (ANSAQ) and the Short Form of the Childhood Trauma Questionnaire (CTQ-SF) were employed to measure NSSI and the symptoms of CM, respectively. Using network analysis, the NSSI network and the CM-NSSI network were constructed to identify the most central symptoms and the bridge symptoms within the networks. Within the NSSI network, "Intentional scratches", " Intentionally hitting hard objects with your head ", " Intentionally hitting oneself with fists or harder objects ", and " Intentional pinching " were identified as the primary symptoms of NSSI. "emotional abuse", "sexual abuse", and " Intentionally cut yourself " emerged as three key bridge symptoms linking CM with NSSI. This research is the first to investigate the symptom network of CM-NSSI in a sample of adolescents with depressive disorders, providing a foundation for subsequent NSSI prevention and the development of targeted intervention strategies.

A neuroimaging-based precision medicine framework for depression.

BACKGROUND: Symptom-based diagnostic criteria of depression leads to notorious heterogeneity and subjectivity. METHODS: The study was conducted in two stages at two sites: development of a neuroimaging-based subtyping and precise repetitive transcranial magnetic stimulation (rTMS) strategy for depression at Center 1 and its clinical application at Center 2. Center 1 identified depression subtypes and subtype-specific rTMS targets based on amplitude of low frequency fluctuation (ALFF) in a cohort of 238 major depressive disorder patients and 66 healthy controls (HC). Subtypes were identified using a Gaussian Mixture Model, and subtype-specific rTMS targets were selected based on dominant brain regions prominently differentiating depression subtypes from HC. Subsequently, one classifier was employed and 72 hospitalized, depressed youths at Center 2 received two-week precise rTMS. MRI and clinical assessments were obtained at baseline, midpoint, and treatment completion for evaluation. RESULTS: Two neuroimaging subtypes of depression, archetypal and atypical depression, were identified based on distinct frontal-posterior functional imbalance patterns as measured by ALFF. The dorsomedial prefrontal cortex was identified as the rTMS target for archetypal depression, and the occipital cortex for atypical depression. Following precise rTMS, ALFF alterations were normalized in both archetypal and atypical depressed youths, corresponding with symptom response of 90.00% in archetypal depression and 70.73% in atypical depression. CONCLUSIONS: A precision medicine framework for depression was developed based on objective neurobiomarkers and implemented with promising results, actualizing a subtyping-treatment-evaluation closed loop in depression. Future randomized controlled trials are warranted.

A Machine Learning Analysis of Big Metabolomics Data for Classifying Depression: Model Development and Validation.

BACKGROUND: Many metabolomics studies of depression have been performed, but these have been limited by their scale. A comprehensive in silico analysis of global metabolite levels in large populations could provide robust insights into the pathological mechanisms underlying depression and candidate clinical biomarkers. METHODS: Depression-associated metabolomics was studied in 2 datasets from the UK Biobank database: participants with lifetime depression (N = 123,459) and participants with current depression (N = 94,921). The Whitehall II cohort (N = 4744) was used for external validation. CatBoost machine learning was used for modeling, and Shapley additive explanations were used to interpret the model. Fivefold cross-validation was used to validate model performance, training the model on 3 of the 5 sets with the remaining 2 sets for validation and testing, respectively. Diagnostic performance was assessed using the area under the receiver operating characteristic curve. RESULTS: In the lifetime depression and current depression datasets and sex-specific analyses, 24 significantly associated metabolic biomarkers were identified, 12 of which overlapped in the 2 datasets. The addition of metabolic features slightly improved the performance of a diagnostic model using traditional (nonmetabolomics) risk factors alone (lifetime depression: area under the curve 0.655 vs. 0.658 with metabolomics; current depression: area under the curve 0.711 vs. 0.716 with metabolomics). CONCLUSIONS: The machine learning model identified 24 metabolic biomarkers associated with depression. If validated, metabolic biomarkers may have future clinical applications as supplementary information to guide early and population-based depression detection.

Altered in vivo early neurogenesis traits in patients with depression: Evidence from neuron-derived extracellular vesicles and electroconvulsive therapy.

BACKGROUND: The neurogenesis hypothesis is a promising candidate etiologic hypothesis for depression, and it is associated with electroconvulsive therapy (ECT). However, human in vivo molecular-level evidence is lacking. OBJECTIVE: We used neuron-derived extracellular vesicles (NDEVs) as a "window to the neurons" to explore the in vivo neurogenesis status associated with ECT in patients with treatment-resistant depression (TRD). METHODS: In this study, we enrolled 40 patients with TRD and 35 healthy controls (HCs). We isolated NDEVs from the plasma of each participant to test the levels of doublecortin (DCX), a marker of neurogenesis, and cluster of differentiation (CD) 81, a marker of EVs. We also assessed the plasma levels of brain-derived neurotrophic factor (BDNF), a protein that is known to be associated with ECT and neuroplastic processes. RESULTS: Our findings indicated that both the levels of DCX in NDEVs and BDNF in plasma were significantly lower in TRD patients compared to HCs at baseline, but increased following ECTs. Conversely, levels of CD81 in NDEVs were found higher in TRD patients at baseline, but did not change after the ECT treatments. Exploratory analyses revealed that lower levels of BDNF in plasma and DCX in NDEVs, along with higher CD81 levels in NDEVs, were associated with more severe depressive symptoms and reduced cognitive function at baseline. Furthermore, higher baseline CD81 concentrations in NDEVs were correlated with greater decreases in depression symptoms. CONCLUSIONS: We first present human in vivo evidence of early neurogenesis using DCX through NDEVs: decreased in TRD patients, increased after ECTs.