IP3R1-mediated MAMs formation contributes to mechanical trauma-induced hepatic injury and the protective effect of melatonin.

INTRODUCTION: There is a high morbidity and mortality rate in mechanical trauma (MT)-induced hepatic injury. Currently, the molecular mechanisms underlying liver MT are largely unclear. Exploring the underlying mechanisms and developing safe and effective medicines to alleviate MT-induced hepatic injury is an urgent requirement. The aim of this study was to reveal the role of mitochondria-associated ER membranes (MAMs) in post-traumatic liver injury, and ascertain whether melatonin protects against MT-induced hepatic injury by regulating MAMs. METHODS: Hepatic mechanical injury was established in Sprague-Dawley rats and primary hepatocytes. A variety of experimental methods were employed to assess the effects of melatonin on hepatic injury, apoptosis, MAMs formation, mitochondrial function and signaling pathways. RESULTS: Significant increase of IP3R1 expression and MAMs formation were observed in MT-induced hepatic injury. Melatonin treatment at the dose of 30 mg/kg inhibited IP3R1-mediated MAMs and attenuated MT-induced liver injury in vivo. In vitro, primary hepatocytes cultured in 20% trauma serum (TS) for 12 h showed upregulated IP3R1 expression, increased MAMs formation and cell injury, which were suppressed by melatonin (100 µmol/L) treatment. Consequently, melatonin suppressed mitochondrial calcium overload, increased mitochondrial membrane potential and improved mitochondrial function under traumatic condition. Melatonin's inhibitory effects on MAMs formation and mitochondrial calcium overload were blunted when IP3R1 was overexpressed. Mechanistically, melatonin bound to its receptor (MR) and increased the expression of phosphorylated ERK1/2, which interacted with FoxO1 and inhibited the activation of FoxO1 that bound to the IP3R1 promoter to inhibit MAMs formation. CONCLUSION: Melatonin prevents the formation of MAMs via the MR-ERK1/2-FoxO1-IP3R1 pathway, thereby alleviating the development of MT-induced liver injury. Melatonin-modulated MAMs may be a promising therapeutic therapy for traumatic hepatic injury.

The association of total pulses with the efficacy of repetitive transcranial magnetic stimulation for treatment-resistant major depression: A dose-response meta-analysis.

AIM: This study aimed to examine dose-effects of total pulses on improvement of depressive symptoms in patients with treatment-resistant depression (TRD) receiving repetitive transcranial magnetic stimulation (rTMS) over the left dorsal lateral prefrontal cortex (DLPFC). MATERIALS AND METHODS: The MEDLINE, Cochrane Central Register of Controlled Trials (CENTRAL), EMBASE, PsycINFO, and ClinicalTrial.gov databases were systematically searched. We included randomized, double-blind, placebo-controlled trials (RCT) that used rTMS over left DLPFC in patients with TRD. Excluded studies were non-TRD, non-RCTs, or combined other brain stimulation interventions. The outcome of interest was the difference between rTMS arms and sham controls in improvement of depressive symptoms in a dose-response manner. A random-effects meta-analysis and dose-response meta-analysis(DRMA) was used to examine antidepressant efficacy of rTMS and association with total pulses. RESULTS: We found that rTMS over left DLPFC is superior to sham controls (reported as standardized mean difference[SMD] with 95% confidence interval: 0.77; 0.56-0.98). The best-fitting model of DRMA was bell-shaped (estimated using restricted cubic spline model; R2 =0.42), indicating that higher doses (>26,660 total pulses) were not associated with increased improvement of depressive symptoms. Stimulation frequency(R2 =0.53) and age(R2 =0.51) were significant moderators for the dose-response curve. Furthermore, 15-20 Hz rTMS was superior to 10 Hz rTMS (0.61, 0.15-1.10) when combining all doses. CONCLUSIONS: Our findings suggest higher doses(total pulses) of rTMS were not always associated with increased improvement of depressive symptoms in patients with TRD, and that the dose-response relationship was moderated by stimulation frequency and age. These associations emphasize the importance of determining dosing parameters to achieve maximum efficacy.

Twelve-month efficacy of CGRP monoclonal antibodies and predictive value of short-term response: results of an Australian multicentre study.

Introduction: Clinical trials show that calcitonin gene-related peptide monoclonal antibodies (CGRP mAbs) are effective preventative treatments for chronic migraine. Their efficacy over longer time periods and in cohorts originally excluded from trials remains uncertain. This study aims to explore the impact of CGRP mAbs in an Australian real-life setting. Methods: A multicentre cohort study was performed in the tertiary headache clinics of the Alfred and Austin Hospitals, Melbourne, Australia. Patients were commenced on a CGRP mAb for chronic migraine and asked to keep a headache diary, recorded at 3 monthly appointments for 12 months. Primary outcome was a ≥50% reduction in monthly headache days (MHD). Results: From a population of 105 patients, 90 patients commenced galcanezumab and 15 commenced fremanezumab. The ≥50% responder rate of the cohort was 52.4% after 3 months. Over 12 months follow-up, 25.7% of the cohort ceased due to a lack of efficacy and 16.2% ceased due to an adverse event. There was no difference in response or cessation between medications. There was poor agreement in 3-month and 12-month response rates (Cohen's κ=0.130; p=0.171). On subgroup analysis, continuous headache at baseline and number of trialled preventative treatments were the only factors associated with efficacy. Conclusion: CGRP mAbs were associated with sustained reductions in MHD over 12-month follow-up in patients with resistant migraine in Australia. Further studies are required to determine treatment options for patients with continuous headache. Poor agreement between outcomes at 3 and 12 months highlights the need to assess some patients at later timepoints.

Comparisons of Quality, Correctness, and Similarity Between ChatGPT-Generated and Human-Written Abstracts for Basic Research: Cross-Sectional Study.

BACKGROUND: ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide full-text basic research papers. OBJECTIVE: We aimed to assess the applicability of an artificial intelligence (AI) model in generating abstracts for basic preclinical research. METHODS: We selected 30 basic research papers from Nature, Genome Biology, and Biological Psychiatry. Excluding abstracts, we inputted the full text into ChatPDF, an application of a language model based on ChatGPT, and we prompted it to generate abstracts with the same style as used in the original papers. A total of 8 experts were invited to evaluate the quality of these abstracts (based on a Likert scale of 0-10) and identify which abstracts were generated by ChatPDF, using a blind approach. These abstracts were also evaluated for their similarity to the original abstracts and the accuracy of the AI content. RESULTS: The quality of ChatGPT-generated abstracts was lower than that of the actual abstracts (10-point Likert scale: mean 4.72, SD 2.09 vs mean 8.09, SD 1.03; P<.001). The difference in quality was significant in the unstructured format (mean difference -4.33; 95% CI -4.79 to -3.86; P<.001) but minimal in the 4-subheading structured format (mean difference -2.33; 95% CI -2.79 to -1.86). Among the 30 ChatGPT-generated abstracts, 3 showed wrong conclusions, and 10 were identified as AI content. The mean percentage of similarity between the original and the generated abstracts was not high (2.10%-4.40%). The blinded reviewers achieved a 93% (224/240) accuracy rate in guessing which abstracts were written using ChatGPT. CONCLUSIONS: Using ChatGPT to generate a scientific abstract may not lead to issues of similarity when using real full texts written by humans. However, the quality of the ChatGPT-generated abstracts was suboptimal, and their accuracy was not 100%.

Multimorbidity Pattern and Risk for Mortality Among Patients With Dementia: A Nationwide Cohort Study Using Latent Class Analysis.

OBJECTIVE: Individuals with dementia are at a substantially elevated risk for mortality; however, few studies have examined multimorbidity patterns and determined the inter-relationship between these comorbidities in predicting mortality risk. METHODS: This is a prospective cohort study. Data from 6,556 patients who were diagnosed with dementia between 1997 and 2012 using the Taiwan National Health Insurance Research Database were analyzed. Latent class analysis was performed using 16 common chronic conditions to identify mortality risk among potentially different latent classes. Logistic regression was performed to determine the adjusted association of the determined latent classes with the 5-year mortality rate. RESULTS: With adjustment for age, a three-class model was identified, with 42.7% of participants classified as "low comorbidity class (cluster 1)", 44.2% as "cardiometabolic multimorbidity class (cluster 2)", and 13.1% as "FRINGED class (cluster 3, characterized by FRacture, Infection, NasoGastric feeding, and bleEDing over upper gastrointestinal tract)." The incidence of 5-year mortality was 17.6% in cluster 1, 26.7% in cluster 2, and 59.6% in cluster 3. Compared with cluster 1, the odds ratio for mortality was 9.828 (95% confidence interval [CI]=6.708-14.401; p<0.001) in cluster 2 and 1.582 (95% CI=1.281-1.953; p<0.001) in cluster 3. CONCLUSION: Among patients with dementia, the risk for 5-year mortality was highest in the subpopulation characterized by fracture, urinary and pulmonary infection, upper gastrointestinal bleeding, and nasogastric intubation, rather than cancer or cardiometabolic comorbidities. These findings may improve decision-making and advance care planning for patients with dementia.

MLP-based classification of COVID-19 and skin diseases.

Recent years have witnessed a growing interest in neural network-based medical image classification methods, which have demonstrated remarkable performance in this field. Typically, convolutional neural network (CNN) architectures have been commonly employed to extract local features. However, the transformer, a newly emerged architecture, has gained popularity due to its ability to explore the relevance of remote elements in an image through a self-attention mechanism. Despite this, it is crucial to establish not only local connectivity but also remote relationships between lesion features and capture the overall image structure to improve image classification accuracy. Therefore, to tackle the aforementioned issues, this paper proposes a network based on multilayer perceptrons (MLPs) that can learn the local features of medical images on the one hand and capture the overall feature information in both spatial and channel dimensions on the other hand, thus utilizing image features effectively. This paper has been extensively validated on COVID19-CT dataset and ISIC 2018 dataset, and the results show that the method in this paper is more competitive and has higher performance in medical image classification compared with existing methods. This shows that the use of MLP to capture image features and establish connections between lesions is expected to provide novel ideas for medical image classification tasks in the future.

Composed query image retrieval based on triangle area triple loss function and combining CNN with transformer.

The existing typical combined query image retrieval methods adopt Euclidean distance as sample distance measurement method, and the model trained by triple loss function blindly pursues absolute distance between samples, resulting in unsatisfactory image retrieval performance. Meanwhile, these methods singularly adopt Convolutional Neural Network (CNN) to extract reference image features. However, receptive field of convolution operation has the characteristics of locality, which is easy to cause the loss of edge feature information of reference images. In view of shortcomings of these methods, the following improvements are proposed in this paper: (1) We propose Triangle Area Triple Loss Function (TATLF), which adopts Triangle Area (TA) as measurement of sample distance. TA comprehensively considers the absolute distance and included angle between samples, so that the trained model has better retrieval performance; (2) We combine CNN with Transformer to simultaneously extract local and edge features of reference images, which can effectively reduce the loss of reference images information. Specifically, CNN is adopted to extract local feature information of reference images. Transformer is used to pay attention to the edge feature information of reference images. Extensive experiments on two public datasets, Fashion200k and MIT-States, confirm the excellent performance of our proposed method.

N6-methyladenosine modification governs liver glycogenesis by stabilizing the glycogen synthase 2 mRNA.

Hepatic glycogen is the main source of blood glucose and controls the intervals between meals in mammals. Hepatic glycogen storage in mammalian pups is insufficient compared to their adult counterparts; however, the detailed molecular mechanism is poorly understood. Here, we show that, similar to glycogen storage pattern, N6-methyladenosine (m6A) modification in mRNAs gradually increases during the growth of mice in liver. Strikingly, in the hepatocyte-specific Mettl3 knockout mice, loss of m6A modification disrupts liver glycogen storage. On the mechanism, mRNA of Gys2, the liver-specific glycogen synthase, is a substrate of METTL3 and plays a critical role in m6A-mediated glycogenesis. Furthermore, IGF2BP2, a "reader" protein of m6A, stabilizes the mRNA of Gys2. More importantly, reconstitution of GYS2 almost rescues liver glycogenesis in Mettl3-cKO mice. Collectively, a METTL3-IGF2BP2-GYS2 axis, in which METTL3 and IGF2BP2 regulate glycogenesis as "writer" and "reader" proteins respectively, is essential on maintenance of liver glycogenesis in mammals.

Multi-scale feature progressive fusion network for remote sensing image change detection.

Presently, research on deep learning-based change detection (CD) methods has become a hot topic. In particular, feature pyramid networks (FPNs) are widely used in CD tasks to gradually fuse semantic features. However, existing FPN-based CD methods do not correctly detect the complete change region and cannot accurately locate the boundaries of the change region. To solve these problems, a new Multi-Scale Feature Progressive Fusion Network (MFPF-Net) is proposed, which consists of three innovative modules: Layer Feature Fusion Module (LFFM), Multi-Scale Feature Aggregation Module (MSFA), and Multi-Scale Feature Distribution Module (MSFD). Specifically, we first concatenate the features of each layer extracted from the bi-temporal images with their difference maps, and the resulting change maps fuse richer semantic information while effectively representing change regions. Then, the obtained change maps of each layer are directly aggregated, which improves the effective communication and full fusion of feature maps in CD while avoiding the interference of indirect information. Finally, the aggregated feature maps are layered again by pooling and convolution operations, and then a feature fusion strategy with a pyramid structure is used, with layers fused from low to high, to obtain richer contextual information, so that each layer of the layered feature maps has original semantic information and semantic features of other layers. We conducted comprehensive experiments on three publicly available benchmark datasets, CDD, LEVIR-CD, and WHU-CD to verify the effectiveness of the method, and the experimental results show that the method in this paper outperforms other comparative methods.

Migraine management: an update for the 2020s.

Migraine is a common malady cutting across socioeconomic and ethnic divides in Australia. It is typically diagnosed late with significant impact on quality of life. Management options have emerged over the past several years that promise simpler treatment regimens with less potential for side-effects. The development of rationally designed migraine preventives is the most significant advance in treatment since the development of the triptans and delivers significant hope to many headache sufferers.

HARNU-Net: Hierarchical Attention Residual Nested U-Net for Change Detection in Remote Sensing Images.

Change detection (CD) is a particularly important task in the field of remote sensing image processing. It is of practical importance for people when making decisions about transitional situations on the Earth's surface. The existing CD methods focus on the design of feature extraction network, ignoring the strategy fusion and attention enhancement of the extracted features, which will lead to the problems of incomplete boundary of changed area and missing detection of small targets in the final output change map. To overcome the above problems, we proposed a hierarchical attention residual nested U-Net (HARNU-Net) for remote sensing image CD. First, the backbone network is composed of a Siamese network and nested U-Net. We remold the convolution block in nested U-Net and proposed ACON-Relu residual convolution block (A-R), which reduces the missed detection rate of the backbone network in small change areas. Second, this paper proposed the adjacent feature fusion module (AFFM). Based on the adjacency fusion strategy, the module effectively integrates the details and semantic information of multi-level features, so as to realize the feature complementarity and spatial mutual enhancement between adjacent features. Finally, the hierarchical attention residual module (HARM) is proposed, which locally filters and enhances the features in a more fine-grained space to output a much better change map. Adequate experiments on three challenging benchmark public datasets, CDD, LEVIR-CD and BCDD, show that our method outperforms several other state-of-the-art methods and performs excellent in F1, IOU and visual image quality.

Mfn2-mediated mitochondrial fusion alleviates doxorubicin-induced cardiotoxicity with enhancing its anticancer activity through metabolic switch.

Imbalanced mitochondrial dynamics including inhibited mitochondrial fusion is associated with cardiac dysfunction as well as tumorigenesis. This study sought to explore the effects of promoting mitochondrial fusion on doxorubicin(Dox)-induced cardiotoxicity and its antitumor efficacy, with a focus on the underlying metabolic mechanisms. Herein, the inhibition of Mfn2-mediated mitochondrial fusion was identified as a key phenotype in Dox-induced cardiotoxicity. Restoration of Mfn2-mediated mitochondrial fusion enhanced mitochondrial oxidative metabolism, reduced cellular injury/apoptosis and inhibited mitochondria-derived oxidative stress in the Dox-treated cardiomyocytes. Application of lentivirus expressing Drp1 (mitochondrial fusion inhibitor) or Rote/Anti A (mitochondrial complex I/III inhibitors) blunted the above protective effects of Mfn2. Cardiac-specific Mfn2 transgenic mice showed preserved mitochondrial fusion and attenuated myocardial injury upon Dox exposure in vivo. The suppression of Mfn2-mediated mitochondrial fusion was induced by Dox-elicited upregulation of FoxO1, which inhibited the transcription of Mfn2 by binding to its promoter sites. In the B16 melanoma, Mfn2 upregulation not only attenuated tumor growth alone but also further delayed tumor growth in the presence of Dox. Mechanistically, Mfn2 synergized with the inhibitory action of Dox on glycolysis metabolism in the tumor cells. One common feature in both cardiomyocytes and tumor cells was that Mfn2 increased the ratio of oxygen consumption rate to extracellular acidification rate, suggesting Mfn2 triggered a shift from aerobic glycolysis to mitochondrial oxidative metabolism. In conclusion, targeting Mfn2-mediated mitochondrial fusion may provide a dual therapeutic advantage in Dox-based chemotherapy by simultaneously defending against Dox-induced cardiotoxicity and boosting its antitumor potency via metabolic shift.

Image Super-Resolution via Dual-Level Recurrent Residual Networks.

Recently, the feedforward architecture of a super-resolution network based on deep learning was proposed to learn the representation of a low-resolution (LR) input and the non-linear mapping from these inputs to a high-resolution (HR) output, but this method cannot completely solve the interdependence between LR and HR images. In this paper, we retain the feedforward architecture and introduce residuals to a dual-level; therefore, we propose the dual-level recurrent residual network (DLRRN) to generate an HR image with rich details and satisfactory vision. Compared with feedforward networks that operate at a fixed spatial resolution, the dual-level recurrent residual block (DLRRB) in DLRRN utilizes both LR and HR space information. The circular signals in DLRRB enhance spatial details by the mutual guidance between two directions (LR to HR and HR to LR). Specifically, the LR information of the current layer is generated by the HR and LR information of the previous layer. Then, the HR information of the previous layer and LR information of the current layer jointly generate the HR information of the current layer, and so on. The proposed DLRRN has a strong ability for early reconstruction and can gradually restore the final high-resolution image. An extensive quantitative and qualitative evaluation of the benchmark dataset was carried out, and the experimental results proved that our network achieved good results in terms of network parameters, visual effects and objective performance metrics.

Deep parameter-free attention hashing for image retrieval.

Deep hashing method is widely applied in the field of image retrieval because of its advantages of low storage consumption and fast retrieval speed. There is a defect of insufficiency feature extraction when existing deep hashing method uses the convolutional neural network (CNN) to extract images semantic features. Some studies propose to add channel-based or spatial-based attention modules. However, embedding these modules into the network can increase the complexity of model and lead to over fitting in the training process. In this study, a novel deep parameter-free attention hashing (DPFAH) is proposed to solve these problems, that designs a parameter-free attention (PFA) module in ResNet18 network. PFA is a lightweight module that defines an energy function to measure the importance of each neuron and infers 3-D attention weights for feature map in a layer. A fast closed-form solution for this energy function proves that the PFA module does not add any parameters to the network. Otherwise, this paper designs a novel hashing framework that includes the hash codes learning branch and the classification branch to explore more label information. The like-binary codes are constrained by a regulation term to reduce the quantization error in the continuous relaxation. Experiments on CIFAR-10, NUS-WIDE and Imagenet-100 show that DPFAH method achieves better performance.

Comparing the relative and absolute effect of erenumab: is a 50% response enough? Results from the ESTEEMen study.

BACKGROUND: Monoclonal antibodies acting on the calcitonin gene-related peptide (CGRP) or its receptor have changed migraine preventive treatment. Those treatments have led to reconsidering the outcomes of migraine prevention. Available data mostly considered benefits in terms of relative efficacy (percent or absolute decrease in monthly migraine days [MMDs] or headache days compared with baseline). However, not enough attention has been paid to residual MMDs and/or migraine-related disability in treated patients. In the present study, we aimed at comparing the relative and absolute efficacy of erenumab. METHODS: ESTEEMen was a collaborative project among 16 European headache centers which already performed real-life data collections on patients treated with erenumab for at least 12 weeks. For the present study, we performed a subgroup analysis on patients with complete data on MMDs at baseline and at weeks 9-12 of treatment. Starting from efficacy thresholds proposed by previous literature, we classified patients into 0-29%, 30-49%, 50-74%, and ≥75% responders according to MMD decrease from baseline to weeks 9-12 of treatment. For each response category, we reported the median MMDs and Headache Impact test-6 (HIT-6) scores at baseline and at weeks 9-12. We categorized the number of residual MMDs at weeks 9-12 as follows: 0-3, 4-7, 8-14, ≥15. We classified HIT-6 score into four categories: ≤49, 50-55, 56-59, and ≥60. To keep in line with the original scope of the ESTEEMen study, calculations were performed in men and women. RESULTS: Out of 1215 patients, at weeks 9-12, 381 (31.4%) had a 0-29% response, 186 (15.3%) a 30-49% response, 396 (32.6%) a 50-74% response, and 252 (20.7%) a ≥75% response; 246 patients (20.2%) had 0-3 residual MMDs, 443 (36.5%) had 4-7 MMDs, 299 (24.6%) had 8-14 MMDs, and 227 (18.7%) had ≥15 MMDs. Among patients with 50-74% response, 246 (62.1%) had 4-7 and 94 (23.7%) 8-14 residual MMDs, while among patients with ≥75% response 187 (74.2%) had 0-3 and 65 (25.8%) had 4-7 residual MMDs. CONCLUSIONS: The present study shows that even patients with good relative response to erenumab may have a clinically non-negligible residual migraine burden. Relative measures of efficacy cannot be enough to thoroughly consider the efficacy of migraine prevention.

Intravenous Lidocaine and Ketamine Infusions for Headache Disorders: A Retrospective Cohort Study.

Introduction: The use of lidocaine (lignocaine) and ketamine infusion in the inpatient treatment of patients with headache disorders is supported by small case series. We undertook a retrospective cohort study in order to assess the efficacy, duration and safety of lidocaine and ketamine infusions. Methods: Patients admitted between 01/01/2018 and 31/07/2021 were identified by ICD code and electronic prescription. Efficacy of infusion was determined by reduction in visual analog score (VAS), and patient demographics were collected from review of the hospital electronic medical record. Results: Through the study period, 83 infusions (50 lidocaine, 33 ketamine) were initiated for a headache disorder (77 migraine, three NDPH, two SUNCT, one cluster headache). In migraine, lidocaine infusion achieved a ≥50% reduction in pain in 51.1% over a mean 6.2 days (SD 2.4). Ketamine infusion was associated with a ≥50% reduction in pain in 34.4% over a mean 5.1 days (SD 1.5). Side effects were observed in 32 and 42.4% respectively. Infusion for medication overuse headache (MOH) led to successful withdrawal of analgesia in 61.1% of lidocaine, and 41.7% of ketamine infusions. Conclusion: Lidocaine and ketamine infusions are an efficacious inpatient treatment for headache disorders, however associated with prolonged length-of-stay and possible side-effects.

Efficient Image Super-Resolution via Self-Calibrated Feature Fuse.

Recently, many super-resolution reconstruction (SR) feedforward networks based on deep learning have been proposed. These networks enable the reconstructed images to achieve convincing results. However, due to a large amount of computation and parameters, SR technology is greatly limited in devices with limited computing power. To trade-off the network performance and network parameters. In this paper, we propose the efficient image super-resolution network via Self-Calibrated Feature Fuse, named SCFFN, by constructing the self-calibrated feature fuse block (SCFFB). Specifically, to recover the high-frequency detail information of the image as much as possible, we propose SCFFB by self-transformation and self-fusion of features. In addition, to accelerate the network training while reducing the computational complexity of the network, we employ an attention mechanism to elaborate the reconstruction part of the network, called U-SCA. Compared with the existing transposed convolution, it can greatly reduce the computation burden of the network without reducing the reconstruction effect. We have conducted full quantitative and qualitative experiments on public datasets, and the experimental results show that the network achieves comparable performance to other networks, while we only need fewer parameters and computational resources.

Efficacy and safety of Xiaoyao pills for mild to moderate depression: study protocol for a randomized controlled trial.

BACKGROUND: Depression is one of the most frequent and severe psychiatric conditions. Many chemical drugs to treat depression are associated with adverse reactions and have shortcomings. Traditional Chinese medicine is of great significance in the prevention and treatment of depression. Xiaoyao pills has achieved good results in clinical application, which has the advantages of quick effect and no obvious adverse reactions. The aim of our study is to evaluate the efficacy and safety of Xiaoyao pills on mild to moderate depression patients. METHODS: This study is a multi-centre, double-blinded, randomized and placebo-controlled clinical trial. A total of 108 participants are assigned to three groups: Xiaoyao pill group taking Xiaoyao pills twice daily for 4 weeks, placebo group taking placebos twice daily for 4 weeks and normal group without taking any drug. The primary and secondary outcome measures are the Hamilton Depression Scale (HAMD) and Traditional Chinese Medicine (TCM) Syndrome Scale. The assessment is at baseline (before treatment initiation), 1 week, 2 weeks 4 weeks after the first treatment. Exploratory outcome is also assessed to explore the mechanism of Xiaoyao pills at baseline and 4 weeks. DISCUSSION: The results from this study will provide clinical evidence on the efficacy and safety of Xiaoyao pills in patients with mild to moderate depression with syndrome of liver stagnation and spleen deficiency. TRIAL REGISTRATION: ClinicalTrials.gov ISRCTN12746343. Registered on September 25, 2020.

MHANet: A hybrid attention mechanism for retinal diseases classification.

With the increase of patients with retinopathy, retinopathy recognition has become a research hotspot. In this article, we describe the etiology and symptoms of three kinds of retinal diseases, including drusen(DRUSEN), choroidal neovascularization(CNV) and diabetic macular edema(DME). In addition, we also propose a hybrid attention mechanism to classify and recognize different types of retinopathy images. In particular, the hybrid attention mechanism proposed in this paper includes parallel spatial attention mechanism and channel attention mechanism. It can extract the key features in the channel dimension and spatial dimension of retinopathy images, and reduce the negative impact of background information on classification results. The experimental results show that the hybrid attention mechanism proposed in this paper can better assist the network to focus on extracting thr fetures of the retinopathy area and enhance the adaptability to the differences of different data sets. Finally, the hybrid attention mechanism achieved 96.5% and 99.76% classification accuracy on two public OCT data sets of retinopathy, respectively.