OBJECTIVE: To develop a user-friendly visualization application for the automatic annotation of Human Phenotype Ontology (HPO) terms based on large language models and retrieval-augmented generation (RAG) technology, and to validate its performance in an authoritative case dataset. METHODS: By integrating the domestic open-source large language model DeepSeek-V3 with RAG technology, an interactive web application was deployed on the Streamlit cloud platform. Using only the latest official HPO dataset as the data source, the lightweight sentence-embedding model BAAI/bge-small-en-v1.5 was employed to construct a FAISS vector index. During the online phase, a four-step closed-loop process is automatically completed: multilingual translation, phenotype phrase extraction, RAG candidate retrieval, term mapping, and official database validation. 121 English case reports publicly released by BMJ Case Reports and Oxford Medical Case Reports (with a gold-standard HPO set of 1 794 terms) were selected for application validation. Precision, recall, and F1 score were calculated and compared horizontally with traditional dictionary tools, standalone large language models, and the similar application "RAG-HPO". Finally, replace the model with the more advanced ChatGPT-5 and evaluate its performance on the newly extracted dataset. RESULTS: An HPO term automatic annotation visualization application named PhenoRAG, based on large language models and RAG technology, was successfully developed. Users can access it directly via a web link. Across the 112 cases, a total of 2 150 HPO terms were generated; 2,064 (96.0%) were fully validated by the official database, with a hallucination rate of 1.3% and an HPO ID-name mismatch rate of 2.7%. After deduplication, 1,906 terms remained for testing. The overall precision was 63.65%, recall was 67.34%, and F1 was 65.44%, significantly outperforming traditional annotation tools (F1: 0.45-0.49, P < 0.001). Although PhenoRAG's F1 was lower than that of RAG-HPO (F1 = 0.78, P < 0.001), which relies on a manually constructed synonym database of 54 000 entries plus the HPO dataset, it requires no additional dictionary maintenance and can be used without any background in computer programming. Moreover, after switching to the GPT-5 model, PhenoRAG exhibited no hallucination rate on the new dataset, and its F1 score significantly increased (P = 0.038). CONCLUSION Without constructing a synonym database, the PhenoRAG achieved high-accuracy automatic mapping from clinical text to standard HPO terms. It features a low usage threshold, free access, and a Chinese-language interface, and can directly serve rare disease diagnosis, genetic counseling, and research scenarios in China and worldwide, warranting further clinical promotion and multicenter validation.
Humans ; Phenotype ; Biological Ontologies ; Language ; Software ; Large Language Models

In recent years, cardiovascular disease has become a common disease. With the development of machine learning and big data technologies, the processing ability of electrocardiogram (ECG) signals has been greatly enhanced through new computer technologies, enabling the auxiliary diagnosis technology for cardiovascular disease (CVD) to achieve new improvements. This article discusses the application of machine learning in ECG processing, especially in the auxiliary diagnosis of diseases. Firstly, the conventional signal preprocessing methods are introduced, and then the EEG signal processing methods based on feature extraction and fuzzy classification are explored. Secondly, the application of auxiliary diagnosis in CVD is further summarized. Finally, the advantages and disadvantages of the two methods are analyzed, and based on this, a design of an auxiliary diagnostic system compatible with the two methods is proposed, providing a new perspective for similar applied researches in the future.
Machine Learning ; Cardiovascular Diseases/diagnosis* ; Humans ; Electrocardiography ; Signal Processing, Computer-Assisted ; Diagnosis, Computer-Assisted ; Fuzzy Logic ; Electroencephalography

This study evaluated the healing-promoting effect and applicability of seven new dressings in chronic wounds. A chronic wound model was established using 48 db/db diabetic mice, which were randomly divided into 8 groups (control, polymer film, alginate, foam, hydrocolloid, hydrogel, carbon fiber, and silver dressing groups). Regular monitoring was conducted on the 5, 10, 15, and 20 days after surgery, and a comprehensive evaluation was performed based on healing rate, characteristic of histopathology, and semi-quantitative scoring. The results showed that, except for the polymer film dressing group, all other dressing groups had significantly better healing-promoting effect than the control group ( P＜0.05), with the hydrocolloid, carbon fiber, and silver dressing groups demonstrated particularly outstanding efficacy. This study systematically compared the efficacy differences of seven dressings, and combined them with the adhesion, exudate volume and infection risks to provide a scientific basis for clinical dressing selection.
Animals ; Mice ; Wound Healing ; Bandages ; Male ; Diabetes Mellitus, Experimental ; Disease Models, Animal

Medical robotic arm often encounters multi-source and nonlinear errors during the calibration process, making it difficult for traditional mathematical modeling methods to fully characterize system error features, thereby limiting further improvement in calibration accuracy. In this study, a robotic arm parameter error identification model is established, and a calibration method based on an adaptive long short-term memory (ALSTM) neural network is proposed. The method incorporates a particle swarm optimization (PSO) algorithm to optimize the weights of each layer of the LSTM neural network, enabling more effective fitting of robotic arm kinematic errors and ultimately yielding more accurate Denavit-Hartenberg (D-H) parameters. To validate the proposed approach, 110 sets of experimental data are collected using the HSR-JR680 robotic arm calibration system. Experimental results demonstrate that the ALSTM model reduces the root mean square error (RMSE) by 23.07%-80.39% compared to traditional calibration methods, and shortens the convergence time by 32.44% compared to a standard LSTM model. The optimized D-H parameters obtained meet the high-precision calibration requirements of medical robotic arm, confirming the effectiveness of the proposed method.
Calibration ; Neural Networks, Computer ; Algorithms ; Robotics ; Robotic Surgical Procedures ; Models, Theoretical

OBJECTIVE: To enhance the reliability of medical equipment, this study aims to develop a failure cause diagnosis model and provide rational suggestions for efficient equipment use. METHODS: Combine fault tree analysis (FTA) to identify basic events causing equipment failure and calculate their prior probabilities. Obtain conditional probability tables for each node through expert assessment. Integrate triangular fuzzy number theory with Bayesian network (BN) to construct a fuzzy Bayesian network (FBN) for posterior probability inference and sensitivity analysis. RESULTS: Using endoscopes as the subject, the analysis shows that the model accurately calculates the endoscope failure probability at 0.385%, and identifies the key causes: improper cleaning ( X5, posterior probability 0.36064), untimely fault detection ( X8, posterior probability 0.23571), irregular transportation ( X6, posterior probability 0.11344), and natural aging ( X10, posterior probability 0.11377). Sensitivity analysis also confirms their influence weights (mutual information values are 0.00749, 0.00591, 0.00202, 0.00174). CONCLUSION The model can accurately perform quantitative analysis and rapid fault location of medical equipment failures, enabling effective preventive measures.
Bayes Theorem ; Fuzzy Logic ; Equipment Failure Analysis/methods* ; Equipment Failure ; Algorithms

OBJECTIVE: To explore the key target molecules and potential mechanisms of oridonin against non-small cell lung cancer (NSCLC). METHODS: The target molecules of oridonin were retrieved from SEA, STITCH, SuperPred and TargetPred databases; target genes associated with the treatment of NSCLC were retrieved from GeneCards, DisGeNET and TTD databases. Then, the overlapping target molecules between the drug and the disease were identified. The protein-protein interaction (PPI) was constructed using the STRING database according to overlapping targets, and Cytoscape was used to screen for key targets. Molecular docking verification were performed using AutoDockTools and PyMOL software. Using the DAVID database, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis were conducted. The impact of oridonin on the proliferation and apoptosis of NSCLC cells was assessed using cell counting kit-8, cell proliferation EdU image kit, and Annexin V-FITC/PI apoptosis kit respectively. Moreover, real-time quantitative PCR and Western blot were used to verify the potential mechanisms. RESULTS: Fifty-six target molecules and 12 key target molecules of oridonin involved in NSCLC treatment were identified, including tumor protein 53 (TP53), Caspase-3, signal transducer and activator of transcription 3 (STAT3), mitogen-activated protein kinase kinase 8 (MAPK8), and mammalian target of rapamycin (mTOR). Molecular docking showed that oridonin and its key target molecules bind spontaneously. GO and KEGG enrichment analyses revealed cancer, apoptosis, phosphoinositide-3 kinase/protein kinase B (PI3K/Akt), and other signaling pathways. In vitro experiments showed that oridonin inhibited the proliferation, induced apoptosis, downregulated the expression of Bcl-2 and Akt, and upregulated the expression of Caspase-3. CONCLUSION Oridonin can act on multiple targets and pathways to exert its inhibitory effects on NSCLC, and its mechanism may be related to upregulating the expression of Caspase-3 and downregulating the expressions of Akt and Bcl-2.
Diterpenes, Kaurane/chemistry* ; Carcinoma, Non-Small-Cell Lung/pathology* ; Humans ; Network Pharmacology ; Lung Neoplasms/pathology* ; Cell Proliferation/drug effects* ; Apoptosis/drug effects* ; Molecular Docking Simulation ; Protein Interaction Maps/drug effects* ; Cell Line, Tumor ; Signal Transduction/drug effects* ; Gene Expression Regulation, Neoplastic/drug effects* ; Reproducibility of Results ; Gene Ontology

OBJECTIVE: To investigate the therapeutic effect of Xiangshao Granules (XSG) on post-stroke depression (PSD) and explore the underlying mechanisms. METHODS: Forty-three C57BL/6J mice were divided into 3 groups: sham (n=15), PSD+vehicle (n=14), and PSD+XSG (n=14) groups according to a random number table. The PSD models were constructed using chronic unpredictable mild stress (CUMS) after middle cerebral artery occlusion (MCAO). The sham group only experienced the same surgical operation, but without MACO and CUMS stimulation. The XSG group received XSG (60 mg/kg per day) by gavage for 4 weeks. The mice in the sham and vehicle groups were given the same volume of 0.9% saline at the same time. The body weight and behavior tests including open field test, sucrose preference test, tail suspension test, and elevated plus-maze test, were used to validate the PSD mouse model. Real-time fluorescence quantitative polymerase chain reaction (RT-qPCR), enzyme-linked immunosorbent assay (ELISA), and immunofluorescence staining were used to evaluate the anti-inflammatory effects of XSG. The potential molecular mechanisms were explored and verified through network pharmacology analysis, Nissl staining, Western blot, ELISA, and RT-qPCR, respectively. RESULTS: The body weight and behavior tests showed that MCAO combined with CUMS successfully established the PSD models. XSG alleviated neuronal damage, reduced the expressions of pro-apoptotic proteins Caspase-3 and B-cell lymphoma-2 (BCL-2)-associated X (BAX), and increased the expression of anti-apoptotic protein BCL-2 in PSD mice (P<0.05 or P<0.01). XSG inhibited microglial activation and the expressions of pro-inflammatory cytokines including tumor necrosis factor-α, interleukin (IL)-1 β, and IL-6 via the toll-like receptor 4/nuclear factor kappa-B signaling pathway in PSD mice (P<0.05 or P<0.01). Furthermore, XSG decreased the expression of indoleamine 2,3-dioxygenase1 (IDO1) and increased the concentration of 5-hydroxytryptamine in PSD mice (P<0.05 or P<0.01). CONCLUSION XSG could reverse the anxiety/depressionlike behaviors and reduce the neuronal injury in the hippocampus and prefrontal cortex of PSD mice, which may be a potential therapeutic agent for PSD.
Animals ; Indoleamine-Pyrrole 2,3,-Dioxygenase/metabolism* ; Depression/etiology* ; Drugs, Chinese Herbal/therapeutic use* ; Hippocampus/metabolism* ; Male ; Mice, Inbred C57BL ; Prefrontal Cortex/pathology* ; Microglia/metabolism* ; Stroke/drug therapy* ; Disease Models, Animal ; Mice ; Behavior, Animal/drug effects*

OBJECTIVE: To explore the mechanism of action of asperosaponin VI (AVI) in the treatment of rheumatoid arthritis (RA) and validate it in ex vivo experiments using network pharmacology and molecular docking methods. METHODS: The predicted targets of AVI were obtained from PharmMaper, UniProt and SwissTarget Prediction platforms, the disease targets were collected from Online Mendelian Inheritance in Man, Therapeutic Target Database and GeneCards databases, the intersection targets of AVI and RA were obtained from Venny 2.1.0, and the protein-protein interaction (PPI) network was obtained from STRING database, which was analyzed by Cytoscape software and screened to obtain the core targets. Cytoscape software was used to analyze PPI network and screen the core targets. Based on the Database for Annotation, Visualization and Integrated Discovery database, Gene Ontology functional and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis were performed, and Cytoscape software was used to construct the "Disease-Pathway-Target-Drug" network, which was finally verified by molecular docking and animal experiments. RESULTS: Network pharmacological studies showed that AVI was able to modulate 289 targets, with 102 targets for the potential treatment of RA, with the core pathway being the AKT/PI3K signaling pathway, and the core targets being the epidermal growth factor receptor (EGFR) and matrix metalloproteinase 9 (MMP9). Molecular docking results showed that AVI could produce strong binding with both of the 2 core targets. In vitro cellular experiments showed that AVI reduced nitric oxide, prostaglandin E₂, tumor necrosis factor-alpha (TNF-α), interleukin-6 (IL-6), and IL-1 β levels (P<0.05) and inhibited cyclooxygenase-2, nitric oxide synthase, EGFR, MMP9, phosphorylated phosphoinositide 3-kinase (p-PI3K), and phosphorylated serine-threonine kinase (p-AKT) proteins (P<0.05). The results of in vivo studies showed that AVI improved RA score and foot swelling thickness and decreased TNF-α, IL-6, p-PI3K and p-AKT levels in RA rats (P<0.05). CONCLUSION AVI exerts anti-inflammatory and anti-RA effects which might be related to the EGFR/MMP9/AKT/PI3K pathway.
Saponins/chemistry* ; ErbB Receptors/metabolism* ; Phosphatidylinositol 3-Kinases/metabolism* ; Signal Transduction/drug effects* ; Molecular Docking Simulation ; Animals ; Arthritis, Rheumatoid/drug therapy* ; Proto-Oncogene Proteins c-akt/metabolism* ; Matrix Metalloproteinase 9/metabolism* ; Protein Interaction Maps/drug effects* ; Humans ; Network Pharmacology ; Male ; Rats

OBJECTIVE: To explore the potential effects and mechanisms of Liang-Ge-San (LGS) for the treatment of acute respiratory distress syndrome (ARDS) through network pharmacology analysis and to verify LGS activity through biological experiments. METHODS: The key ingredients of LGS and related targets were obtained from the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform. ARDS-related targets were selected from GeneCards and DisGeNET databases. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes enrichment analyses were performed using the Metascape Database. Molecular docking analysis was used to confirm the binding affinity of the core compounds with key therapeutic targets. Finally, the effects of LGS on key signaling pathways and biological processes were determined by in vitro and in vivo experiments. RESULTS: A total of LGS-related targets and 496 ARDS-related targets were obtained from the databases. Network pharmacological analysis suggested that LGS could treat ARDS based on the following information: LGS ingredients luteolin, wogonin, and baicalein may be potential candidate agents. Mitogen-activated protein kinase 14 (MAPK14), recombinant V-Rel reticuloendotheliosis viral oncogene homolog A (RELA), and tumor necrosis factor alpha (TNF-α) may be potential therapeutic targets. Reactive oxygen species metabolic process and the apoptotic signaling pathway were the main biological processes. The p38MAPK/NF-κ B signaling pathway might be the key signaling pathway activated by LGS against ARDS. Moreover, molecular docking demonstrated that luteolin, wogonin, and baicalein had a good binding affinity with MAPK14, RELA, and TNF α. In vitro experiments, LGS inhibited the expression and entry of p38 and p65 into the nucleation in human bronchial epithelial cells (HBE) cells induced by LPS, inhibited the inflammatory response and oxidative stress response, and inhibited HBE cell apoptosis (P<0.05 or P<0.01). In vivo experiments, LGS improved lung injury caused by ligation and puncture, reduced inflammatory responses, and inhibited the activation of p38MAPK and p65 (P<0.05 or P<0.01). CONCLUSION LGS could reduce reactive oxygen species and inflammatory cytokine production by inhibiting p38MAPK/NF-κ B signaling pathway, thus reducing apoptosis and attenuating ARDS.
Drugs, Chinese Herbal/pharmacology* ; Respiratory Distress Syndrome/enzymology* ; p38 Mitogen-Activated Protein Kinases/metabolism* ; NF-kappa B/metabolism* ; Animals ; Signal Transduction/drug effects* ; Molecular Docking Simulation ; Humans ; Male ; Network Pharmacology ; Apoptosis/drug effects* ; Mice

OBJECTIVE: To illustrate the role of dehydrocorydaline (DHC) in chronic constriction injury (CCI)-induced neuropathic pain and the underlying mechanism. METHODS: C57BL/6J mice were randomly divided into 3 groups by using a random number table, including sham group (sham operation), CCI group [intrathecal injection of 10% dimethyl sulfoxide (DMSO)], and CCI+DHC group (intrathecal injection of DHC), 8 mice in each group. A CCI mouse model was conducted to induce neuropathic pain through ligating the right common sciatic nerve. On day 14 after CCI modeling or sham operation, mice were intrathecal injected with 5 µL of 10% DMSO or 10 mg/kg DHC (5 µL) into the 5th to 6th lumbar intervertebral space (L5-L6). Pregnant ICR mice were sacrificed for isolating primary spinal neurons on day 14 of embryo development for in vitro experiment. Pain behaviors were evaluated by measuring the paw withdrawal mechanical threshold (PWMT) of mice. Immunofluorescence was used to observe the activation of astrocytes and microglia in mouse spinal cord. Protein expressions of inducible nitric oxide synthase (iNOS), tumor necrosis factor alpha (TNF-α), interleukin 6 (IL-6), phosphorylation of N-methyl-D-aspartate receptor subunit 2B (p-NR2B), and NR2B in the spinal cord or primary spinal neurons were detected by Western blot. RESULTS: In CCI-induced neuropathic pain model, mice presented significantly decreased PWMT, activation of glial cells, overexpressions of iNOS, TNF-α, IL-6, and higher p-NR2B/NR2B ratio in the spinal cord (P<0.05 or P<0.01), which were all reversed by a single intrathecal injection of DHC (P<0.05 or P<0.01). The p-NR2B/NR2B ratio in primary spinal neurons were also inhibited after DHC treatment (P<0.05). CONCLUSION An intrathecal injection of DHC relieved CCI-induced neuropathic pain in mice by inhibiting the neuroinflammation and neuron hyperactivity.
Animals ; Neuralgia/etiology* ; Mice, Inbred C57BL ; Analgesics/pharmacology* ; Neuroinflammatory Diseases/pathology* ; Constriction ; Male ; Receptors, N-Methyl-D-Aspartate/metabolism* ; Nitric Oxide Synthase Type II/metabolism* ; Mice, Inbred ICR ; Microglia/pathology* ; Spinal Cord/drug effects* ; Female ; Mice ; Tumor Necrosis Factor-alpha/metabolism* ; Disease Models, Animal ; Constriction, Pathologic/complications* ; Interleukin-6/metabolism* ; Astrocytes/metabolism* ; Chronic Disease ; Neurons/metabolism*