检索结果-南通市图书馆

Knowledge Graph Enhanced Transformers for Diagnosis Generation of Chinese Medicine

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Integrative Medicine 2024年第3期30卷 267-276页

作者： WANG Xin-yu YANG tao GAO Xiao-yuan hu Kong-fa School of Artificial Intelligence and Information Technology Nanjing University of Chinese MedicineNanjing210023China School of Information Management Nanjing UniversityNanjing210023China Jiangsu Collaborative Innovation Center of Traditional Chinese Medicine in Prevention and Treatment of Tumor Nanjing210023China Jiangsu Province Engineering Research Center of TCM Intelligence Health Service Nanjing210023China

Chinese medicine(CM)diagnosis intellectualization is one of the hotspots in the research of CM modernization.The traditional CM intelligent diagnosis models transform the CM diagnosis issues into classification issues,however,it is difficult to solve the problems such as excessive or similar categories.With the development of natural language processing techniques,text generation technique has become increasingly mature.In this study,we aimed to establish the CM diagnosis generation model by transforming the CM diagnosis issues into text generation issues.The semantic context characteristic learning capacity was enhanced referring to Bidirectional Long Short-Term Memory(BILSTM)with Transformer as the backbone network.Meanwhile,the CM diagnosis generation model Knowledge Graph Enhanced Transformer(KGET)was established by introducing the knowledge in medical field to enhance the inferential capability.The KGET model was established based on 566 CM case texts,and was compared with the classic text generation models including Long Short-Term Memory sequence-to-sequence(LSTM-seq2seq),Bidirectional and Auto-Regression Transformer(BART),and Chinese Pre-trained Unbalanced Transformer(CPT),so as to analyze the model manifestations.Finally,the ablation experiments were performed to explore the influence of the optimized part on the KGET model.The results of Bilingual Evaluation Understudy(BLEU),Recall-Oriented Understudy for Gisting Evaluation 1(ROUGE1),ROUGE2 and Edit distance of KGET model were 45.85,73.93,54.59 and 7.12,respectively in this study.Compared with LSTM-seq2seq,BART and CPT models,the KGET model was higher in BLEU,ROUGE1 and ROUGE2 by 6.00–17.09,1.65–9.39 and 0.51–17.62,respectively,and lower in Edit distance by 0.47–3.21.The ablation experiment results revealed that introduction of BILSTM model and prior knowledge could significantly increase the model performance.Additionally,the manual assessment indicated that the CM diagnosis results of the KGET model used in this study were highly consistent with the p

关键词： Chinese medicine diagnosis knowledge graph enhanced transformer text generation

Resveratrol combats chronic diseases through enhancing mitochondrial quality

在线全文

学校读者我要写书评

暂无评论

Food Science and human Wellness 2024年第2期13卷 597-610页

作者： Weichu tao hu Zhang Xia Jiang Ning Chen Tianjiu Research and Development Center for Exercise Nutrition and Foods Hubei Key Laboratory of Exercise Training and MonitoringCollege of Sports MedicineWuhan Sports UniversityWuhan 430079China The University Hospital of Wuhan Sports University Wuhan 430079China

Resveratrol(RSV),as a functional food component extracted from natural plants,has been widely studied and recognized in preventing and treating various diseases,with major mechanisms including executing anti-inflammation and anti-oxidation functions,and improving mitochondrial quality.Chronic diseases as non-communicable diseases are mainly caused by multiple factors,such as physiological decline and dysfunction in the body,and have become a significant challenge on public health worldwide.It is worth noting that chronic diseases such as Alzheimer's disease(AD),Parkinson's disease(PD),muscle atrophy,cardiovascular disease,obesity,and cancer are accompanied by abnormal mitochondrial function.Therefore,targeted regulation of mitochondria may be a meaningful way to prevent and treat chronic diseases.Increasing evidence has confirmed that RSV is actively involved in regulating mitochondria,and it has become an essential consideration to prevent and treat chronic diseases through targeting mitochondria and improving corresponding functions.In this article,current studies on RSV to optimize mitochondrial quality for preventing and alleviating chronic disease are systematically summarized,which can provide a theoretical reference for the development of functional foods or drugs to combat chronic diseases.

关键词： Resveratrol Functional food Mitochondrial quality Chronic disease Anti-inflammation Anti-oxidation

Impact of next-generation sequencing on antimicrobial treatment in immunocompromised adults with suspected infections

在线全文

学校读者我要写书评

暂无评论

World Journal of Emergency Medicine 2024年第2期15卷 105-110页

作者： Jia Li Jiazhen Luo tao hu Ling Cheng Weiwei Shang Li Yan Department of Intensive Care Unit Tongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030China Department of Emergency Medicine Tongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030China Tongji Medical College Huazhong University of Science and TechnologyWuhan 430030China Department of Geriatrics Tongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030China

BACKGROUND:Prompt pathogen identification can have a substantial impact on the optimization of antimicrobial treatment.The objective of the study was to assess the diagnostic value of next-generation sequencing(NGS)for identifying pathogen and its clinical impact on antimicrobial intervention in immunocompromised patients with suspected infections.METHODS:This was a retrospective study.Between January and August 2020,47 adult immunocompromised patients underwent NGS testing under the following clinical conditions:1)prolonged fever and negative conventional cultures;2)new-onset fever despite empiric antimicrobial treatment;and 3)afebrile with suspected infections on imaging.Clinical data,including conventional microbial test results and antimicrobial treatment before and after NGS,were collected.Data were analyzed according to documented changes in antimicrobial treatment(escalated,no change,or deescalated)after the NGS results.RESULTS:The median time from hospitalization to NGS sampling was 19 d.Clinically relevant pathogens were detected via NGS in 61.7% of patients(29/47),more than half of whom suffered from fungemia(n=17),resulting in an antimicrobial escalation in 53.2% of patients(25/47)and antimicrobial de-escalation in 0.2% of patients(1/47).Antimicrobial changes were mostly due to the identification of fastidious organisms such as Legionella,Pneumocystis jirovecii,and Candida.In the remaining three cases,NGS detected clinically relevant pathogens also detected by conventional cultures a few days later.The antimicrobial treatment was subsequently adjusted according to the susceptibility test results.Overall,NGS changed antimicrobial management in 55.3%(26/47)of patients,and conventional culture detected clinically relevant pathogens in 14.9% of the patients(7/47).CONCLUSION:With its rapid identification and high sensitivity,NGS could be a promising tool for identifying relevant pathogens and enabling rapid appropriate treatment in immunocompromised patients with suspected infections.

关键词： Immunocompromised patients Next-generation sequencing Antimicrobial management

Analysis of Sea Surface Temperature Cooling in Typhoon Events Passing the Kuroshio Current

在线全文

学校读者我要写书评

暂无评论

Journal of Ocean University of China 2024年第2期23卷 287-303页

作者： hu Yuyi SHAO Weizeng SHEN Wei ZUO Juncheng JIANG tao hu Song College of Marine Sciences Shanghai Ocean UniversityShanghai 201306China East China Sea Environment Monitoring Ministry of Natural ResourcesShanghai 201206China China Waterborne Transport Research Institute Ministry of TransportBeijing 100088China

The aim of this study is to investigate the sea surface temperature(SST) cooling as typhoons pass the Kuroshio Current.A numerical circulation model,denoted as the Stony Brook Parallel Ocean Model(sbPOM),was used to simulate the SST,which includes four wave-induced effect terms(i.e.,radiation stress,nonbreaking waves,Stokes drift,and breaking waves) simulated using the third-generation wave model,called WAVEWATCH-Ⅲ(WW3).The significant wave height(SWH) measurements from the Jason-2 altimeter were used to validate the WW3-simulated results,yielding a root mean square error(RMSE) of less than 0.50 m and a correlation coefficient(COR) of approximately 0.93.The water temperature measured from the Advanced Research and Global Observation Satellite was applied to validate the model simulation.Accordingly,the RMSE of the SST is 0.92℃ with a COR of approximately 0.99.As revealed in the sbPOM-simulated SST fields,a reduction in the SST at the Kuroshio Current region was observed as a typhoon passed,although the water temperature of the Kuroshio Current is relatively high.The variation of the SST is consistent with that of the current,whereas the maximum SST lagged behind the occurrence of the peak SWH.Moreover,the Stokes drift plays an important role in the SST cooling after analyzing four wave-induced terms in the background of the Kuroshio Current.The sensitivity experiment also showed that the accuracy of the water temperature was significantly reduced when including breaking waves,which play a negative role in the inside part of the ocean.The variation in the mean mixing layer depth(MLD) showed that a typhoon could enhance the mean MLD in the Kuroshio Current area in September and October,whereas a typhoon has little influence on the mean MLD in the Kuroshio Current area in May.Moreover,the mean MLD rapidly decreased with the weakening of the strong wind force and wave-induced effects when a typhoon crossed the Kuroshio Current.

关键词： typhoon wave sea surface temperature Kuroshio Current

Development of a cell adhesion-based prognostic model for multiple myeloma:Insights into chemotherapy response and potential reversal of adhesion effects

在线全文

学校读者我要写书评

暂无评论

Oncology Research 2024年第4期32卷 753-768页

作者： QIAN hu MENGYAO WANG JINJIN WANG YALI tao TING NIU Department of Hematology West China HospitalSichuan UniversityChengdu610041China

Multiple myeloma(MM)is a hematologic malignancy notorious for its high relapse rate and development of drug resistance,in which cell adhesion-mediated drug resistance plays a critical role.This study integrated four RNA sequencing datasets(CoMMpass,GSE136337,GSE9782,and GSE2658)and focused on analyzing 1706 adhesionrelated genes.Rigorous univariate Cox regression analysis identified 18 key prognosis-related genes,including KIF14,TROAP,FLNA,MSN,LGALS1,PECAM1,and ALCAM,which demonstrated the strongest associations with poor overall survival(OS)in MM patients.To comprehensively evaluate the impact of cell adhesion on MM prognosis,an adhesion-related risk score(ARRS)model was constructed using Lasso Cox regression analysis.The ARRS model emerged as an independent prognostic factor for predicting OS.Furthermore,our findings revealed that a heightened cell adhesion effect correlated with tumor resistance to DNA-damaging drugs,protein kinase inhibitors,and drugs targeting the PI3K/Akt/mTOR signaling pathway.Nevertheless,we identified promising drug candidates,such as tirofiban,pirenzepine,erlotinib,and bosutinib,which exhibit potential in reversing this resistance.In vitro,experiments employing NCIH929,RPMI8226,and AMO1 cell lines confirmed that MM cell lines with high ARRS exhibited poor sensitivity to the aforementioned candidate drugs.By employing siRNA-mediated knockdown of the key ARRS model gene KIF14,we observed suppressed proliferation of NCIH929 cells,along with decreased adhesion to BMSCs and fibronectin.This study presents compelling evidence establishing cell adhesion as a significant prognostic factor in MM.Additionally,potential molecular mechanisms underlying adhesion-related resistance are proposed,along with viable strategies to overcome such resistance.These findings provide a solid scientific foundation for facilitating clinically stratified treatment of MM.

关键词： Cell adhesion Bioinformatics Prognosis Multiple myeloma CAM-DR

Three rare anti-inflammatory sesquiterpene lactones from Magnolia grandiflora

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Natural Medicines 2024年第3期22卷 265-272页

作者： XU Shuangyu ZHANG Feng tao Linlan JIANG Yangming huANG tao LI Yanan hu Zhanxing YANG Jue HAO Xiaojiang YUAN Chunmao State Key Laboratory of Functions and Applications of Medicinal Plants Guizhou Medical UniversityGuiyang 550014China School of Pharmaceutical Sciences Guizhou Medical UniversityGuiyang 550025China Natural Products Research Center of Guizhou Province Guiyang 550014China State Key Laboratory of Phytochemistry and Plant Resources in West China Kunming Institute of BotanyChinese Academy of SciencesKunming 650201China

Four new sesquiterpene lactones(SLs)(1–4),along with a biosynthetically related SL(5),have been isolated from the leaves of Magnolia grandiflora.Magrandate A(1)is notable as the first C18 homogemarane type SL,featuring a unique 1,7-dioxaspiro[4.4]nonan-6-one core.Compounds 2 and 3,representing the first instances of chlorine-substituted gemarane-type SL analogs in natural products,were also identified.The structures of these isolates were elucidated through a combination of spectroscopic data analysis,electronic circular dichroism calculations,and X-ray single-crystal diffraction analysis.All isolates demonstrated anti-inflammatory activity in lipopolysaccharide-stimulated RAW264.7 cells.Notably,3–5 showed a significant inhibitory effect on nitric oxide production,with IC50 values ranging from 0.79 to 4.73μmol·L^(−1).Additionally,4 and 5 exhibited moderate cytotoxic activities against three cancer cell lines,with IC50 values between 3.09 and 11.23μmol·L^(−1).

关键词： Magnolia grandiflora Sesquiterpene lactones Isolation and identification Anti-inflammatory activity

Low-molecular-weight heparin and preeclampsia—does the sword cut both ways?Three case reports and review of literature

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Clinical Cases 2024年第9期12卷 1634-1643页

作者： Dan Shan tao Li Xi Tan Ya-Yi hu Department of Obstetrics and Gynecology West China Second University HospitalSichuan UniversityChengdu 610000Sichuan ProvinceChina Key Laboratory of Birth Defects and Related Diseases of Women and Children Sichuan UniversityMinistry of EducationChengdu 610000SichuanChina

BACKGROUND Low-molecular-weight heparins(LMWH)are the most commonly used anticoagulants during pregnancy.It is considered to be the drug of choice due to its safety in not crossing placenta.Considering the beneficial effect in the improvement of microcirculation,prophylactic application of LMWH in patients with preeclampsia became a trend.However,the bleeding risk related with LMWH in preeclampsia patients has seldomly been evaluated.This current study aimed to identify the potential risks regarding LMWH application in patients with preeclampsia.CASE SUMMARY Herein we present a case series of three pregnant women diagnosed with preeclampsia on LMWH therapy during pregnancy.All the cases experienced catastrophic hemorrhagic events.After reviewing the twenty-one meta-analyses,the bleeding risk related with LMWH seems ignorable.Only one study analyzed the bleeding risk of LMWH and found a significantly higher risk of developing PPH in women receiving LMWH.Other studies reported minor bleeding risks,none of these were serious enough to stop LMWH treatment.Possibilities of bleeding either from uterus or from intrabdominal organs in preeclampsia patients on LMWH therapy should not be ignored.Intensive management of blood pressure even after delivery and homeostasis suture in surgery are crucial.CONCLUSION Consideration should be given to the balance between benefits and risks of LMWH in patients with preeclampsia.

关键词： Pregnancy Preeclampsia Low-molecular-weight heparin Hemorrhage Case report

The joint knowledge reasoning model based on knowledge representation learning for aviation assembly domain

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第1期67卷 143-156页

作者： LIU PeiFeng QIAN Lu LU hu XUE Lei ZHAO XingWei tao Bo State Key Laboratory of Digital Manufacturing Equipment and Technology Department of MechanicalHuazhong University of Science and TechnologyWuhan 430074China School of Transportation and Logistics Engineering Wuhan University of Technology(WHUT)Wuhan 430063China Shanghai Aircraft Manufacturing Co. Ltd.Shanghai 201324China

Knowledge graph technology is widely applied in the domain of general knowledge reasoning with an excellent performance.For fine-grained professional fields,professional knowledge graphs can provide more accurate information in practical industrial scenarios.Based on an aviation assembly domain-specific knowledge graph,the article constructs a joint knowledge reasoning model,which combines a named entity recognition model and a subgraph embedding learning model.When performing knowledge reasoning tasks,the two models vectorize entities,relationships and entity attributes in the same space,so as to share parameters and optimize learning efficiency.The knowledge reasoning model,which provides intelligent question answering services,is able to reduce the assembly error rate and improve the assembly efficiency.The system can accurately solve general knowledge reasoning problems in the assembly process in actual industrial scenarios of general assembly and component assembly under interference-free conditions.Finally,this paper compares the proposed knowledge reasoning model based on knowledge representation learning and the question-answering system based on large-scale pre-trained models.In the application scenario of system functional testing in general assembly,the joint model attains an accuracy rate of 95%,outperforming GPT with 78%accuracy and enhanced representation through knowledge integration with 71%accuracy.

关键词： intelligent manufacturing knowledge graph aviation assembly knowledge representation knowledge-based question an-swering

Feature extraction and learning approaches for cancellable biometrics:A survey

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 4-25页

作者： Wencheng Yang Song Wang Jiankun hu Xiaohui tao Yan Li School of Mathematics Physics and ComputingUniversity of Southern QueenslandToowoombaQueenslandAustralia School of Computing Engineering and Mathematical SciencesLa Trobe UniversityMelbourneVictoriaAustralia School of Engineering and Information Technology University of New South Wales at the Australian Defence Force Academy(UNSW@ADFA)CanberraAustralian Capital TerritoryAustralia

Biometric recognition is a widely used technology for user authentication.In the application of this technology,biometric security and recognition accuracy are two important issues that should be considered.In terms of biometric security,cancellable biometrics is an effective technique for protecting biometric data.Regarding recognition accuracy,feature representation plays a significant role in the performance and reliability of cancellable biometric systems.How to design good feature representations for cancellable biometrics is a challenging topic that has attracted a great deal of attention from the computer vision community,especially from researchers of cancellable biometrics.Feature extraction and learning in cancellable biometrics is to find suitable feature representations with a view to achieving satisfactory recognition performance,while the privacy of biometric data is protected.This survey informs the progress,trend and challenges of feature extraction and learning for cancellable biometrics,thus shedding light on the latest developments and future research of this area.

关键词： biometrics feature extraction