Multi-View Graph Contrastive Learning via Adaptive Channel Optimization for Depression Detection in EEG Signals.

Automated detection of depression using Electroencephalogram (EEG) signals has become a promising application in advanced bioinformatics technology. Although current methods have achieved high detection performance, several challenges still need to be addressed: (1) Previous studies do not consider data redundancy when modeling multi-channel EEG signals, resulting in some unrecognized noise channels remaining. (2) Most works focus on the functional connection of EEG signals, ignoring their spatial proximity. The spatial topological structure of EEG signals has not been fully utilized to capture more fine-grained features. (3) Prior depression detection models fail to provide interpretability. To address these challenges, this paper proposes a new model, Multi-view Graph Contrastive Learning via Adaptive Channel Optimization (MGCL-ACO) for depression detection in EEG signals. Specifically, the proposed model first selects the critical channels by maximizing the mutual information between tracks and labels of EEG signals to eliminate data redundancy. Then, the MGCL-ACO model builds two similarity metric views based on functional connectivity and spatial proximity. MGCL-ACO constructs the feature extraction module by graph convolutions and contrastive learning to capture more fine-grained features of different perspectives. Finally, our model provides interpretability by visualizing a brain map related to the significance scores of the selected channels. Extensive experiments have been performed on public datasets, and the results show that our proposed model outperforms the most advanced baselines. Our proposed model not only provides a promising approach for automated depression detection using optimal EEG signals but also has the potential to improve the accuracy and interpretability of depression diagnosis in clinical practice.

[Effects of modified Xiaoyao San on TLR4/NF-κB pathway in hippocampal microglia of LPS-induced depression model rats].

OBJECTIVE: To investigate the effects of modified Xiaoyao San on TLR4/NF-κB pathway in hippocampal microglia of LPS-induced depression model rats, and to explore its antidepressant mechanism. METHODS: SD rats were randomly divided into control, model, fluoxetine (10 mg·kg-1), low and high dose of modified Xiaoyao San (3.64, 7.28g·kg-1) group. The depression model was established by chronic LPS injection (ip, 0.5 mg·kg-1) and rats were treated by intragastric administration for 14 days. After the model was established, the depression-like behavior of rats was evaluated by open field and forced swimming test. The expression of microglia marker protein Iba-1 was detected by immunohistochemistry. The levels of TNF-α and IL-6 in hippocampal homogenate were detected by ELISA method and the expressions of TLR4 and NF-κB protein in hippocampus were detected by Western blot. RESULTS: Compared with control group, the depression-like behavior was significant in model group rats (P＜0.01), the microglia in the brain was activated (P＜0.01), the contents of TNF-α and IL-6 in the hippocampus were increased (P＜0.01), and the expression levels of TLR4 and NF-κB proteins were up-regulated (P＜0.01). Compared with model group, the depression-like behavior of the rats in the fluoxetine and high-dose modified Xiaoyao San group was significantly alleviated (P＜0.05), the expression of Iba-1 in microglia returned to normal (P＜0.01), the contents of TNF-α and IL-6 were decreased (P＜0.01), and the expression levels of TLR4 and NF-κB protein were decreased (P＜0.05). Compared with fluoxetine group, the high-dose modified Xiaoyao San group had no statistically significant difference in each index, suggesting that there was no significant difference in the antidepressant effect between the two groups. CONCLUSION: Modified Xiaoyao San can significantly improve the depression-like behavior in rats, and its mechanism may be related to inhibiting the TLR4/NF-κB pathway of microglia and down-regulating the expression of inflammatory factors.

[Effects of Ganmai Dazao Tang on synaptic structure of hippocampal neurons in depression model rats].

Objective: To investigate the effects of Ganmai Dazao Tang on behavior and monoamine neurotransmitters in rats with depression, and to explore its potential mechanism from synaptic structure. Methods: Sixty SD rats were randomly divided into 5 groups: normal control group, model group, fluoxetine group (10.8 mg/kg), Ganmai Dazao Tang high and low dose group (9.72, 4.86 g/kg), 12 rats in each group. Except the control group, the rats in the other groups were all chronically unpredictable mild stress (CUMS) to establish a depression model, and were treated by intragastric administration for 21 days. The depression-like behaviors of rats were evaluated by sucrose consumption test and open field test. The contents of serotonin (5-HT) and norepinephrine (NE) in hippocampus were detected by ELISA. The synaptic damage of neurons was observed by Golgi staining. The synaptic structure protein expression levels of MAP-2 and GAP-43 of hippocampus were detected by Immunohistochemistry and Western blot. Results: Compared with control group, the sucrose preference and autonomic activity scores of the depression model rats were decreased significantly (P＜0.01), the levels of 5-HT and NE in hippocampus were decreased significantly (P＜0.01), and the dendritic spines were absent, and the expressions of MAP-2 and GAP-43 were down-regulated significantly (P＜0.01). After treated with Ganmai Dazao Tang, the depression-like behavior of the model rats was significantly relieved (P＜0.01), and the levels of 5-HT and NE were increased (P＜ 0.05). Dendritic spine density, length and branching were increased, the expressions of MAP-2 and GAP-43 were increased (P＜ 0.01). Conclusion: Ganmai Dazao Tang can improve the depression-like behavior of depression model rats and increase the monoamine neurotransmitter content in hippocampus, which may be related to up-regulation of synaptic structural proteins and relief of synaptic damage in neurons.

[TIE's flying acupuncture for acute cerebral infarction hemiplegia: a randomized controlled trial].

OBJECTIVE: To compare the efficacy difference between TIE 's flying acupuncture combined with conventional treatment and conventional treatment alone on acute cerebral infarction hemiplegia. METHODS: A total of 120 patients were randomly divided into an observation group and a control group, 60 cases in each one. The control group was treated with conventional treatment, including anti-platelet aggregation, lipid-lowering, formula of traditional Chinese medicine which could promote circulation and remove stasis, neurotrophic medication and symptomatic treatment; mannitol was used for cerebral infarction with large area or increased intracranial pressure. Based on the conventional treatment applied in the control group, the observation group was treated with flying acupuncture at the affected Jianyu (LI 15), Quchi (LI 11), Shousanli (LI 10), Waiguan (TE 5), Hegu (LI 4), Huantiao (GB 30), Biguan (ST 31), Futu (ST 32), Zusanli (ST 36), etc. The treatment was given once a day, six days per week, for totally 2 weeks. The simplified Fugl-Meyer score, National Institute of Health Stroke Scale (NIHSS) and ADL-Bathel index (BI) score were evaluated before and after treatment in the two groups. RESULTS: After the treatment, the simplified Fugl-Meyer and BI were significantly increased in both groups (all P<0.05), which was significantly higher in the observation group (both P<0.05); after the treatment, the NIHSS was significantly lowered in both groups (both P<0.05), which was significantly lower in the observation group (P<0.05). CONCLUSION: TIE 's flying acupuncture combined with conventional treatment were effective for acute cerebral infarction hemiplegia, which have better efficacy than conventional treatment on improving motor function, neurological deficit and daily living ability, and the pain is mild.