MAFNet: A novel adaptive multi-scale model for fine-grained grading of diabetic retinopathy.

Diabetic Retinopathy (DR) is a leading cause of blindness worldwide, and its early detection and accurate grading play a crucial role in clinical intervention. To address the dual limitations of existing methods in multi-scale lesions feature fusion and lesions relation modeling, this study proposes a novel adaptive multi-scale convolutional neural network model for fine-grained grading of DR, called MAFNet (Multi-scale Adaptive Fine-grained Network). The model is constructed through three core modules to establish a multi-scale feature integration framework: the Hierarchical Global Context Module (HGCM) effectively expands the receptive field by employing multi-scale pooling and dynamic feature fusion, capturing lesions features from micro to large-scale areas; the Multi-scale Adaptive Attention Module (MSAM) utilizes an adaptive attention mechanism to dynamically adjust the feature weights at different spatial locations, enhancing the representation of key lesions regions; and the Relational Multi-head Attention Module (RMA) uses a multi-head attention mechanism to model the complex relationships between features in parallel, improving the accuracy of fine-grained lesions identification.

The contrastive learning method in tongue image representation learning and its significance in intelligent diagnosis.

Objective: Tongue diagnosis is crucial in traditional Chinese medicine (TCM). As diagnoses cannot be standardized in TCM, reaching an ideal consensus when labeling TCM syndrome is difficult. This results in the introduction of subjective bias in the representation learning method.

Identification of characteristic genes ofanddeficiency constitutions: an integrated analysis based on bioinformatics and machine learning.

Objective: To utilize the Traditional Chinese Medicine constitution (TCMC) as a complementary and alternative approach for early disease detection and treatment, with a focus on and deficiency constitutions, which serve as key references for disease prevention and management.

Methods: The dataset containing the data of and deficiency constitution was identified through the Gene Expression Omnibus database. This database was used for differential expression genes (DEGs) analysis and weighted gene co-expression network analysis (WGCNA), and the characteristic genes were then obtained in the dataset using a machine learning method.

Machine learning-assisted MALDI-MSI to characterize hippocampal subregion lipid and purine metabolic alterations in depression-related dry eye disease.

Dry eye disease (DED) and depression exhibit high comorbidity, yet lipid and purine diagnostic biomarkers for depression-related DED remain unidentified. In this study, matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) was employed to conduct, for the first time, localization analysis of small-molecule substances, within the CA1, CA2, CA3, and DG subregions of the hippocampal tissue in rats with depression-related DED. Our findings indicate that the 9-aminoacridine (9AA) matrix enabled visualization of over 120 diverse metabolites in each hippocampal region.

Development and validation of potential molecular subtypes and signatures of ocular sarcoidosis based on autophagy-related gene analysis.

Background: Sarcoidosis is characterized by the proliferation of noncaseating granulomas and presents as a complex chronic inflammatory disease. Autophagy plays a crucial role in the initiation, progression, and treatment resistance of various cancers. Despite the recognized importance of autophagy, the involvement of autophagy-related genes (ARGs) in the pathophysiology of ocular sarcoidosis (OS) remains largely unexplored.

Integrated multiple machine learning and Mendelian randomization reveal LTF gene as a prognostic biomarker for nonspecific orbital inflammation.

Background: Nonspecific orbital inflammation (NSOI), also known as idiopathic orbital inflammation, comprises a heterogeneous group of immune-mediated disorders affecting orbital tissues, unified by the absence of a defined etiology. Lactotransferrin (LTF), an iron-binding glycoprotein, exerts potent antimicrobial activity by sequestering iron essential for microbial growth, and demonstrates broad-spectrum antibacterial, antiviral, and antifungal properties.

Methods: LTF was identified through the intersection analysis of common DEGs from datasets GSE58331 and GSE105149 from the GEO database, alongside immune-related gene lists from the ImmPort database, using Multiple Machine learning and WGCNA analysis.

Impact of probiotics on sleep quality and mood states in patients with insomnia: a systematic review and meta-analysis.

Background: Probiotics have garnered increasing attention for their potential role in managing insomnia. This meta-analysis evaluated the effects of probiotics on sleep quality and mood in patients with insomnia.

Methods: Eight public databases were searched to identify relevant randomized controlled trials (RCTs) published before December 2024.

Feasibility analysis of Sinomenine alleviating fibrosis of filtering bleb after glaucoma filtering surgery: a mini review.

Fibrosis of the filtering bleb remains the predominant cause of glaucoma filtering surgery failure, mediated by interconnected pathological processes including postoperative local inflammation, aberrant fibroblast proliferation, and deposition of the extracellular matrix (ECM). The antimetabolite drugs 5-fluorouracil (5-FU) and mitomycin C (MMC) are effective in preventing filtering bleb fibrosis, but their non-specific cytotoxic effects necessitate the development of targeted therapeutic alternatives. Fibrosis is a group of diseases with similar pathological mechanisms and molecular features.

Deciphering the angiogenic potential of Zhishi Xiebai Guizhi decoction in coronary heart disease: an in-depth network pharmacology and experimental investigation.

ZXGD Decoction, a traditional Chinese formulation historically used for cardiovascular ailments, was evaluated for its efficacy in coronary heart disease (CHD) through an integrated network pharmacology and randomized controlled trial (RCT) approach. Its selection was rooted in documented therapeutic benefits for blood stasis and endothelial dysfunction, with modern pharmacology identifying active compounds (e.g.

Meta-analysis of acupuncture combined therapies for amblyopia: efficacy and safety insights.

Background: Acupuncture, a traditional Chinese medicine therapy, is widely used for the management of amblyopia. This study aimed to perform a meta-analysis of the efficacy and safety of acupuncture combined with conventional treatments for amblyopia.

Methods: We searched eight databases for relevant studies published before December 31, 2024.

Immune Regulation and ECM-Related Pathway Enrichment Reveal ATP2A3 as a Prognostic Biomarker for Nonspecific Orbital Inflammation: An Integrated Machine Learning and Mendelian Randomization Analysis.

Nonspecific orbital inflammation (NSOI) is a heterogeneous inflammatory disorder of the orbit with an unclear etiology. ATP2A3, a key regulator of calcium homeostasis in the endoplasmic reticulum (ER), may play a pivotal role in NSOI pathogenesis. Its potential as a diagnostic biomarker merits thorough investigation.

Chlorogenic acid attenuates oxidative damage in rat lacrimal gland epithelial cells via PI3K/AKT/FoxO3 signaling: network pharmacology and experimental evidence.

Oxidative stress and inflammation are crucial in dry eye pathogenesis. The antioxidant and anti-inflammatory activities of chlorogenic acid (CGA) have been studied in various fields, including ophthalmology. However, its therapeutic effects on dry eye remain unclear.

Application of Metabolomics and the Discovery of Potential Serum Biomarkers for Diuretic Resistance in Heart Failure.

Background: Diuretic resistance (DR) is characterized by insufficient fluid and sodium excretion enhancement despite maximum loop diuretic doses, indicating a phenotype of refractory heart failure (HF). Recently, metabolomics has emerged as a crucial tool for diagnosing and understanding the pathogenesis of various diseases. This study aimed to differentiate diuretic-resistant patients from non-resistant HF to identify biomarkers linked to the emergence of DR.

L.: a potential botanical drug for preventing and treating retinal cell apoptosis.

Retinal cell apoptosis is the primary pathological process in many retinal diseases, including retinitis pigmentosa and age-related macular degeneration, which can cause severe visual impairment and blindness. , a traditional Chinese medicinal botanical drug, has a long history and extensive application in ophthalmic disease prevention and treatment. This study systematically reviewed the key active metabolites in including polysaccharides, carotenoids, and flavonoids, that exert retinal protective effects.

Sinomenine alleviates experimental autoimmune uveitis in rats: Possible involvement of PI3K/AKT and NF-κB signaling pathways.

Uveitis is an inflammatory ocular condition characterized by an autoimmune etiology. Sinomenine (SIN), the main active constituent of the rhizome of Sinomenium acutum (Thunb.) Rehd.

Unveiling the therapeutic effects of traditional Chinese patent medicines: A network meta-analysis on chronic atrophic gastritis.

Background: The study aimed to conduct a network meta-analysis of randomized controlled trials (RCTs) to examine the effectiveness and safety of traditional Chinese patent medicine (TCPM), either used alone or combined with conventional treatment (CT) of chemical drugs, for treating chronic atrophic gastritis (CAG).

Methods: We searched the literature from database creation to December 2023; our primary endpoint was clinical response rate. Secondary outcome measures were the inhibition rate of Helicobacter pylori and clinical symptom score, including pain and noisy scores for the stomach, score for belch and acid reflux, score for the bitter taste and the dry throat, and safety according to total adverse events.

A Novel Approach for Suprachoroidal Space Injection: An Experimental Evaluation.

Purpose: This study aims to describe an innovative suprachoroidal space injection technique using a combination of 30 G and 22 G needles attached to a 1 ml injector. The efficacy and applicability of this technique in suprachoroidal injections are evaluated.

Methods: In this study, we conducted both and injection experiments using isolated porcine eyes and live SD rats, respectively.

Development and validation of potential molecular subtypes and signatures of thyroid eye disease based on angiogenesis-related gene analysis.

Background: Thyroid eye disease (TED) is an autoimmune inflammatory disorder of the orbit, associated with a range of potential clinical sequelae. Tumor cells in TED overexpress pro-angiogenic factors, driving the formation of heterogeneous and immature neovascularization. This dysregulated angiogenesis often leads to a hypoxic microenvironment due to insufficient perfusion.

Tuck-KGC: based on tensor decomposition for diabetes knowledge graph completion model integrating Chinese and Western medicine.

The medical knowledge graph is essential for intelligent medical services, encompassing personalized diagnostics, precision therapies, and intelligent consultations, among others. However, medical knowledge graphs frequently suffer from incompleteness, primarily due to the absence of certain entities or relationships. The incomplete nature of knowledge graphs poses substantial challenges to these tasks.

Molecular insights into ulcerative colitis and orbital inflammation.

Ulcerative colitis (UC) is an increasingly prevalent inflammatory condition affecting the intestinal mucosa, while nonspecific orbital inflammation (NSOI) is a common non-neoplastic orbital disorder. Exploring the molecular interplay between UC and NSOI may help physicians make earlier diagnoses and enhance treatment approaches. We analyzed gene expression datasets (GSE58331, GSE105149, GSE206285, and GSE179285) for UC and NSOI from the GEO database.

Analysis of dominant microorganisms and core enzymes in Qingke Baijiu Daqu by high-throughput sequencing and proteomics.

Daqu plays a crucial role in Qingke Baijiu production by providing essential raw materials, microorganisms, and enzymes for fermentation. In order to further investigate the impact of microorganisms and enzymes in Qingke Baijiu Daqu, the physicochemical properties, dominant microorganisms, as well as enzyme system composition of Qingke Baijiu Daqu were studied. The results revealed 8 dominant bacterial genera and 4 dominant fungal genera in Daqu.

One lung ventilation during thoracoscopic lobectomy alters lung microbiome miversity and composition.

Current research indicates that the lungs are not sterile and maintain their own unique microecological balance, which can be disrupted by mechanical ventilation.One-lung ventilation (OLV) induces ischemia-reperfusion (IR) injury in the non-ventilated lung, a common contributor to acute lung injury during the perioperative period. This study investigates alterations in the pulmonary microbiome following one-lung ventilation during thoracoscopic lobectomy and evaluates the impact of differential microbiota on inflammatory responses.

A comparison of the efficacy and safety of Chinese patent medicine combined with Western medicine for Helicobacter pylori-related gastric ulcer: A systematic review and network meta-analysis.

Background: The aim of this network meta-analysis (NMA) was to compare the effectiveness and safety of different Chinese patent medicines (CPMs) combined with Western medicines (WMs) regimen versus WMs alone in the treatment of Helicobacter pylori-related gastric ulcer (GU).

Methods: A comprehensive search was conducted on databases from their inception to May 31, 2023, to identify all randomized controlled trials (RCTs) that investigated the efficacy of CPMs in combination with conventional WMs in the treatment of patients with H pylori-related GU. Using Cochrane risk of bias assessment tool, we evaluated the methodological quality of RCTs.

Left T7 paravertebral nerve blockade activate the α7nAChR-Dependent CAP in patients undergoing thoracoscopic lobectomy: a prospective controlled study.

Objective: This study aimed to observe the impact of Tthoracic paravertebral nerve blockade(TPVB) at left T7 level on the α7nAChR-dependent cholinergic anti-inflammatory pathway in patients undergoing thoracoscopic lobectomy.

Methods: Scheduled thoracoscopic lung surgery patients at the First Affiliated Hospital of Nanchang University from August to September 2023 were divided into two groups according to the surgical site. The experimental group underwent left T7 paravertebral nerve blockade (LTPVB group), while the control group underwent right T7 paravertebral nerve blockade (RTPVB group).

Risk prediction of integrated traditional Chinese and western medicine for diabetes retinopathy based on optimized gradient boosting classifier model.

In order to take full advantage of traditional Chinese medicine (TCM) and western medicine, combined with machine learning technology, to study the risk factors and better risk prediction model of diabetic retinopathy (DR), and provide basis for the screening and treatment of it. Through a retrospective study of DR cases in the real world, the electronic medical records of patients who met screening criteria were collected. Moreover, Recursive Feature Elimination with Cross-Validation (RFECV) was used for feature selection.