Risk analysis of re⁃fracture after percutaneous kyphoplasty in elderly patients with osteoporotic thoracolumbar compression fractures and construction of a columnar graph prediction model / 解剖学报

Objective To investigate the risk factors for re-fracture after percutaneous kyphoplasty (PKP) in elderly patients with osteoporotic thoracolumbar compression fractures and to construct a line graph prediction model. Methods One hundred and eighty-two elderly patients with osteoporotic thoracolumbar compression fractures treated with PKP from January 2016 to November 2019 were selected for the study‚ and the patients were continuously followed up for 3 years after surgery. Clinical data were collected from both groups; Receiver operating characteristic (ROC) curve analysis was performed on the measures; Logistic regression analysis was performed to determine the independent risk factors affecting postoperative re-fracture in PKP; the R language software 4. 0 “rms” package was used to construct a predictive model for the line graph‚ and the calibration and decision curves were used to internally validate the predictive model for the line graph and for clinical evaluation of predictive performance. Results The differences between the two groups were statistically significant (P0. 22‚ which could provide a net clinical benefit‚ and the net clinical benefit was higher than the independent predictors. Conclusion BMD‚ number of injured vertebrae‚ single-segment cement injection‚ cement leakage‚ pre-and post-PKP vertebral height difference‚ and posterior convexity angle change are independent risk factors affecting the recurrent fracture after PKP in elderly patients with osteoporotic thoracolumbar compression fracture‚ and this study constructs a column line graph model to predict the recurrent fracture after PKP in elderly patients with osteoporotic thoracolumbar compression fracture as a predictor for clinical. This study provides an important reference for clinical prevention and treatment‚ and has clinical application value.

Transfer learning enhanced graph neural network for aldehyde oxidase metabolism prediction and its experimental application

Aldehyde oxidase (AOX) is a molybdoenzyme that is primarily expressed in the liver and is involved in the metabolism of drugs and other xenobiotics. AOX-mediated metabolism can result in unexpected outcomes, such as the production of toxic metabolites and high metabolic clearance, which can lead to the clinical failure of novel therapeutic agents. Computational models can assist medicinal chemists in rapidly evaluating the AOX metabolic risk of compounds during the early phases of drug discovery and provide valuable clues for manipulating AOX-mediated metabolism liability. In this study, we developed a novel graph neural network called AOMP for predicting AOX-mediated metabolism. AOMP integrated the tasks of metabolic substrate/non-substrate classification and metabolic site prediction, while utilizing transfer learning from 13C nuclear magnetic resonance data to enhance its performance on both tasks. AOMP significantly outperformed the benchmark methods in both cross-validation and external testing. Using AOMP, we systematically assessed the AOX-mediated metabolism of common fragments in kinase inhibitors and successfully identified four new scaffolds with AOX metabolism liability, which were validated through in vitro experiments. Furthermore, for the convenience of the community, we established the first online service for AOX metabolism prediction based on AOMP, which is freely available at https://aomp.alphama.com.cn.

Construction of Knowledge Graph Based on Literature Data by Taking Treatment of Diabetic Peripheral Neuropathy with Traditional Chinese Medicine as An Example / 中国实验方剂学杂志

ObjectiveTo systematically sort out the knowledge framework and conceptual logic relationship of "disease-syndrome-treatment-prescription-medicine" in the existing literature on traditional Chinese medicine（TCM） treatment of diabetic peripheral neuropathy（DPN）， to construct of the knowledge map of TCM treatment of DPN， and to promote the explicitation of the implicit knowledge in the literature on the treatment of DPN with TCM. MethodTaking the literature of China National Knowledge Infrastructure about TCM treatment of DPN as the main data source， TCM-related concepts and entities were constructed by manual citation， and the corresponding relationships between the entities were established. Structured data were formed by processing with Python 3.7， and the knowledge graph was constructed based on Neo4j 3.5.34 graph database. ResultThe resulting knowledge graph with TCM diagnosis and treatment logic， defined 12 node labels such as prescriptions， Chinese medicines and syndrome types at the schema layer， as well as 4 types of relationships， such as inclusion， correspondence， selection and composition. It could support the query and discovery of nodes（syndrome elements， syndrome types and treatment methods）， as well as the relationship between each node. ConclusionBased on the literature data， this study constructed a knowledge map for TCM treatment of DPN， which brought together various methods of TCM treatment of DPN， including internal and external treatment. The whole chain knowledge structure of syndrome differentiation and classification for DPN treatment is formed from syndrome element analysis， syndrome type composition to treatment method selection， which can provide new ideas and methods for literature data to serve clinical and scientific research work， as well as reference for visualization of TCM literature knowledge， intellectualization of TCM knowledge services and the standardization of TCM diagnosis and treatment.

Excesso de peso pré-gestacional e ácidos graxos poli-insaturados no leite humano: modelo teórico de causalidade / Pre-gestational overweight and polyunsaturated fatty acids in human milk: theoretical causality model

Resumo Inúmeros estudos têm se detido na avaliação da associação entre o excesso de peso pré-gestacional e os ácidos graxos poli-insaturados no leite humano. Todavia, diante da complexidade de fatores de risco potencialmente confundidores, é recomendável a utilização de ferramentas gráficas para identificar possíveis vieses. O objetivo deste artigo é propor um modelo teórico de causalidade utilizando o gráfico acíclico direcionado entre o excesso de peso pré-gestacional e os ácidos graxos poli-insaturados no leite humano. Foi realizada ampla revisão da literatura para identificar as variáveis com relações causais com a exposição e/ou desfecho. A escolha das variáveis para ajuste seguiu o algoritmo gráfico que compreende seis critérios para a seleção de um conjunto mínimo de variáveis potencialmente confundidoras. Condições socioeconômicas, intervalo interpartal, idade materna e padrão de consumo alimentar foram as variáveis ajustadas a fim de se estimar o efeito total do excesso de peso pré-gestacional sobre o conteúdo dos ácidos graxos poli-insaturados no leite humano. O conjunto mínimo de variáveis encontrado pelo presente estudo pode ser utilizado na análise de outros estudos que avaliem essa associação.

Abstract A number of studies have focused on the evaluation of the relationship between pre-pregnancy overweight and polyunsaturated fatty acids content in human milk. However, given the complexity of potentially confounding risk factors, the use of graphical tools is recommended to identify possible biases. This article aims to propose a theoretical model of causality using the directed acyclic graph between pre-pregnancy overweight and polyunsaturated fatty acids content in human milk. Methods: An extensive literature review was performed to identify variables with causal relationships with exposure and/or outcome. The choice of variables for adjustment followed the graphic algorithm that comprises six criteria for selecting a minimum set of potentially confounding variables. Socioeconomic conditions, interpartum interval, maternal age and food consumption pattern were the variables that would have to be adjusted in order to estimate the total effect of pre-pregnancy overweight on polyunsaturated fatty acids content in human milk. The minimum set of variables found in the present study can be used in the analysis of other studies that evaluate this association.

Knowledge Graph Enhanced Transformers for Diagnosis Generation of Chinese Medicine / 中国结合医学杂志

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 practical diagnosis results. In conclusion, text generation technology can be effectively applied to CM diagnostic modeling. It can effectively avoid the problem of poor diagnostic performance caused by excessive and similar categories in traditional CM diagnostic classification models. CM diagnostic text generation technology has broad application prospects in the future.

Overview of the application of knowledge graphs in the medical field / 生物医学工程学杂志

With the booming development of medical information technology and computer science, the medical services industry is gradually transiting from information technology to intelligence. The medical knowledge graph plays an important role in intelligent medical applications such as knowledge questions and answers and intelligent diagnosis, and is a key technology for promoting wise medical care and the basis for intelligent management of medical information. In order to fully exploit the great potential of knowledge graphs in the medical field, this paper focuses on five aspects: inter-drug relationship discovery, assisted diagnosis, personalized recommendation, decision support and intelligent prediction. The latest research progress on medical knowledge graphs is introduced, and relevant suggestions are made in light of the current challenges and problems faced by medical knowledge graphs to provide reference for promoting the wide application of medical knowledge graphs.

Entity extraction and graph construction based on Chinese medical text / 中国药科大学学报

@#Knowledge graph technology has promoted the progress of new drug research and development, but domestic research starts late and domain knowledge is mostly stored in text, resulting in low rate of knowledge graph reuse.Based on multi-source and heterogeneous medical texts, this paper designed a Chinese named entity recognition model based on Bert-wwm-ext pre-training model and also integrated cascade thought, which reduced the complexity of traditional single classification and further improved the efficiency of text recognition.The experimental results showed that the model achieved the best performance with an F1-score of 0.903, a precision of 89.2%, and a recall rate of 91.5% on the self-built dataset.At the same time, the model was applied to the public dataset CCKS2019, and the results showed that the model had better performance and recognition effect.Using this model, this paper constructed a Chinese medical knowledge graph, involving 13 530 entities, 10 939 attributes and 39 247 relationships of them in total.The Chinese medical entity extraction and graph construction method proposed in this paper is expected to help researchers accelerate the new discovery of medical knowledge, and shorten the process of new drug discovery.

Drug repurposing for Alzheimer''s disease using knowledge graph embedding / 中国药科大学学报

@#Alzheimer''s disease (AD) has brought to us huge medical and economic burdens, and so discovery of its therapeutic drugs is of great significance.In this paper, we utilized knowledge graph embedding (KGE) models to explore drug repurposing for AD on the publicly available drug repurposing knowledge graph (DRKG).Specifically, we applied four KGE models, namely TransE, DistMult, ComplEx, and RotatE, to learn the embedding vectors of entities and relations on DRKG.By using three classical knowledge graph evaluation metrics, we then evaluated and compared the performance of these models as well as the quality of the learned embedded vectors.Based on our results, we selected the RotatE model for link prediction and identified 16 drugs that might be repurposed for the treatment of AD.Previous studies have confirmed the potential therapeutic effects of 12 drugs against AD, i.e., glutathione, haloperidol, capsaicin, quercetin, estradiol, glucose, disulfire, adenosine, paroxetine, paclitaxel, glybride and amitriptyline.Our study demonstrates that drug repurposing based on KGE may provide new ideas and methods for AD drug discovery.Moreover, the RotatE model effectively integrates multi-source information of DRKG, enabling promising AD drug repurposing.The source code of this paper is available at https://github.com/LuYF-Lemon-love/AD-KGE.

Artificial intelligence-based drug development: current progress and future challenges / 中国药科大学学报

@#In recent years, artificial intelligence (AI) has been widely applied in the field of drug discovery and development.In particular, natural language processing technology has been significantly improved after the emergence of the pre-training model.On this basis, the introduction of graph neural network has also made drug development more accurate and efficient.In order to help drug developers more systematically and comprehensively understand the application of artificial intelligence in drug discovery, this article introduces cutting-edge algorithms in AI, and elaborates on the various applications of AI in drug development, including drug small molecule design, virtual screening, drug repurposing, and drug property prediction, finally discusses the opportunities and challenges of AI in future drug development.

Abnormal topology of cortical thickness covariance network and altered functional connectivity in patients with anti-N-methyl-D-aspartate receptor encephalitis / 中华行为医学与脑科学杂志

Objective:To explore the changes in topological attributes of structural covariance network based on cortical thickness and the brain functional activities in patients with anti-N-methyl-D-aspartate receptor (NMDAR) encephalitis by graph theory and functional connectivity (FC) analyses, and to investigate whether these changes were correlated to cognitive impairment.Methods:A total of 33 patients with anti-NMDAR encephalitis from Department of Neurology of the First Affiliated Hospital of Guangxi Medical University(patient group) and 35 healthy controls(control group) with matched gender, age, and education were included from July 2018 to November 2021.All subjects received cognitive function assessments, structural and functional magnetic resonance imaging scans.Structural covariance networks were constructed in the two groups based on cortical thickness values and topological characteristics of networks were computed.A non-parametric permutation test which repeated 1 000 times was used to compare the characteristics of the networks between the two groups.Brain regions with abnormal topology were defined as region of interest(ROI), and FC values in global brain level were calculated.SPM 12 and RESTplus were used to identify the brain regions with significant differences in FC values between the two groups.Finally, Spearman correlation analysis between FC values of significant brain regions and cognitive scores were performed by SPSS 24.0.Results:The cognitive score of patients with anti-NMDAR encephalitis (27.0(23.5, 28.0)) was lower than that in control group(29.0(27.0, 30.0)) ( Z=-3.029, P=0.002). Graph theory analysis found that the patients showed significantly increased clustering coefficients ( P=0.004) and decreased global efficiency ( P=0.004) compared with healthy controls.Moreover, the nodal efficiency of left ventral posterior cingulate cortex (vPCC) and right dorsal posterior cingulate cortex (dPCC), as well as the nodal degree centrality of left vPCC and left polar planum of superior temporal gyrus (ppSTG) in patient group were significantly decreased ( P<0.05, FDR corrected) compared with control group.FC analysis showed the increased FC values between left vPCC and posterior cerebellum (MNI: x=6, y=-66, z=-21), as well as between left ppSTG and anterior cerebellum (MNI: x=6, y=-54, z=-12) (GRF corrected, voxel level P<0.001, cluster level P<0.05) in patient grooup.The FC values between left vPCC and posterior cerebellum were negatively correlated with the cognitive scores ( r=-0.403, P=0.020). Conclusion:Patients with anti-NMDAR encephalitis show abnormal topology of structural covariance network based on cortical thickness and altered FC values, some of which are correlated to cognition and may be the underlying neural mechanism of cognitive impairment in patients with anti-NMDAR encephalitis.

MF-SuP-pKa: Multi-fidelity modeling with subgraph pooling mechanism for pKa prediction

Acid-base dissociation constant (pKa) is a key physicochemical parameter in chemical science, especially in organic synthesis and drug discovery. Current methodologies for pKa prediction still suffer from limited applicability domain and lack of chemical insight. Here we present MF-SuP-pKa (multi-fidelity modeling with subgraph pooling for pKa prediction), a novel pKa prediction model that utilizes subgraph pooling, multi-fidelity learning and data augmentation. In our model, a knowledge-aware subgraph pooling strategy was designed to capture the local and global environments around the ionization sites for micro-pKa prediction. To overcome the scarcity of accurate pKa data, low-fidelity data (computational pKa) was used to fit the high-fidelity data (experimental pKa) through transfer learning. The final MF-SuP-pKa model was constructed by pre-training on the augmented ChEMBL data set and fine-tuning on the DataWarrior data set. Extensive evaluation on the DataWarrior data set and three benchmark data sets shows that MF-SuP-pKa achieves superior performances to the state-of-the-art pKa prediction models while requires much less high-fidelity training data. Compared with Attentive FP, MF-SuP-pKa achieves 23.83% and 20.12% improvement in terms of mean absolute error (MAE) on the acidic and basic sets, respectively.

Diagnosis and Treatment Reasoning of Integrated Traditional Chinese and Western Medicine Against Acute Abdomen Based on Knowledge Graph / 中国实验方剂学杂志

ObjectiveIn view of the standardization of clinical diagnosis and treatment of the acute abdomen and the inheritance of diagnosis and treatment experience of prestigious veteran traditional Chinese medicine（TCM） doctors， a diagnosis and treatment reasoning algorithm based on association rule mining under incomplete evidence（AMIE）+ random walk was proposed to provide information services and technical support for primary doctors by recommending personalized diagnosis and treatment plans based on medical records. MethodThe experience of diagnosis and treatment of acute abdomen of prestigious veteran TCM doctors and the text data of clinical diagnosis and treatment guidelines of integrated TCM and western medicine were collected to complete the task of knowledge extraction and construct acute abdomen knowledge graph based on Neo4j. On the basis of ontology-supported rule-based reasoning， the rule reasoning based on similar syndromes was used to expand the syndrome combinations whose Jaccard similarity was greater than the threshold in the syndrome recommendation results. The semantic path coverage algorithm was used to calculate the semantic similarity between the symptom nodes. The symptom nodes were divided into 10 categories， and the symptom nodes in the same category were extended. The random walk algorithm was used to search the symptom nodes connected with the syndrome， and the connection rules between the syndrome and symptom nodes were extended to realize the knowledge reasoning of AMIE+ random walk. ResultThe acute abdomen knowledge graph included 1 320 nodes and 2 464 relationships. According to the link prediction evaluation index of knowledge reasoning， the reasoning results of the three algorithms in the auxiliary diagnosis and treatment of acute abdomen were compared. The AMIE+ random walk algorithm complemented the knowledge graph by extending the similar syndrome connection rules and the syndrome-symptom connection rules. Compared with the knowledge reasoning algorithm based on ontology rules， the area under the curve （AUC） was 15.18% higher and the accuracy was 30.36% higher， which achieved more accurate and effective knowledge inference. ConclusionThis study used knowledge graph technology to visualize the diagnosis and treatment of acute abdomen with TCM and western medicine， assisting primary clinicians in intuitively viewing the diagnosis and treatment process and data relationship. The proposed diagnosis and treatment reasoning algorithm can realize the personalized diagnosis and treatment plan recommendation at the level of "disease-syndrome-diagnosis-treatment-prescription"， which can assist primary doctors in disease diagnosis and treatment and clinical decision-making， contribute to the knowledge sharing and application of diagnosis and treatment experience and clinical guidelines of prestigious veteran TCM doctors， improve the level of primary clinical diagnosis and treatment， and promote the normalization and standardization of the diagnosis and treatment process of acute abdomen with integrated TCM and western medicine.

Kinome-wide polypharmacology profiling of small molecules by multi-task graph isomorphism network approach

Prediction of the interactions between small molecules and their targets play important roles in various applications of drug development, such as lead discovery, drug repurposing and elucidation of potential drug side effects. Therefore, a variety of machine learning-based models have been developed to predict these interactions. In this study, a model called auxiliary multi-task graph isomorphism network with uncertainty weighting (AMGU) was developed to predict the inhibitory activities of small molecules against 204 different kinases based on the multi-task Graph Isomorphism Network (MT-GIN) with the auxiliary learning and uncertainty weighting strategy. The calculation results illustrate that the AMGU model outperformed the descriptor-based models and state-of-the-art graph neural networks (GNN) models on the internal test set. Furthermore, it also exhibited much better performance on two external test sets, suggesting that the AMGU model has enhanced generalizability due to its great transfer learning capacity. Then, a naïve model-agnostic interpretable method for GNN called edges masking was devised to explain the underlying predictive mechanisms, and the consistency of the interpretability results for 5 typical epidermal growth factor receptor (EGFR) inhibitors with their structure‒activity relationships could be observed. Finally, a free online web server called KIP was developed to predict the kinome-wide polypharmacology effects of small molecules (http://cadd.zju.edu.cn/kip).

Current status and trend of acupuncture-moxibustion for myofascial pain syndrome: a visual analysis of knowledge graph based on CiteSpace and VOSviewer / 中国针灸

Bibliometric and scientific knowledge graph methods were used to analyze the research status and hot spots of acupuncture-moxibustion in treatment of myofascial pain syndrome (MPS) and explore its development trend. The articles of both Chinese and English versions relevant to MPS treated by acupuncture-moxibustion were searched in CNKI, VIP, Wanfang, SinoMed and WOS from the database inception to March 20, 2023. Using Excel2016, CiteSpace6.2.R2 and VOSviewer1.6.18, the visual analysis was conducted by means of the cooperative network, keyword co-occurrence, keyword timeline, keyword emergence, etc. From Chinese databases and WOS database, 910 Chinese articles and 300 English articles were included, respectively. The annual publication volume showed an overall rising trend. Literature output of English articles was concentrated in Spain, China, and the United States, of which, there was less cross-regional cooperation. In the keyword analysis, regarding acupuncture-moxibustion therapy, Chinese articles focused on "acupuncture", "electroacupuncture" and "acupotomy"; while, "dry needling" and "injection" were dominated for English one. Clinical study was the current hot spot in Chinese databases, in comparison, the randomized controlled double-blind clinical trial was predominant in WOS. Both Chinese and English articles were limited in the report of mechanism research. The cooperation among research teams should be strengthened to conduct comparative research, dose-effect research and effect mechanism research with different methods of acupuncture-moxibustion involved so that the evidences can be provided for deeper exploration.

Knowledge graph analysis of pyroptosis research in traditional Chinese medicine based on VOSviewer and CiteSpace / 中国中药杂志

To explore the research hotspots and frontier directions of pyroptosis in the field of traditional Chinese medicine(TCM), the authors searched CNKI and Web of Science for literature related to pyroptosis in TCM, screened literature according to the search strategy and inclusion criteria, and analyzed the publication trend of the included literature. VOSviewer was used to draw author cooperation and keyword co-occurrence network diagrams, and CiteSpace was employed for keyword clustering, emergence, and timeline view. Finally, 507 Chinese literature and 464 English literature were included, and it was found that the number of Chinese and English literature was increasing rapidly year by year. The co-occurrence of the authors showed that in terms of Chinese literature, there was a representative research team composed of DU Guan-hua, WANG Shou-bao and FANG Lian-hua, and for English literature, the representative research team was composed of XIAO Xiao-he, BAI Zhao-fang and XU Guang. The network visualization of Chinese and English keywords revealed that inflammation, apoptosis, oxidative stress, autophagy, organ damage, fibrosis, atherosclerosis, and ischemia-reperfusion injury were the primary research diseases and pathological processes in TCM; berberine, resveratrol, puerarin, na-ringenin, astragaloside Ⅳ, and baicalin were the representative active ingredients; NLRP3/caspase-1/GSDMD, TLR4/NF-κB/NLRP3, and p38/MAPK signaling pathways were the main research pathways. Keyword clustering, emergence, and timeline analysis indicated that the pyroptosis research in TCM focused on the mechanism of TCM monomers and compounds intervening in diseases and pathological processes. Pyroptosis is a research hotspot in the area of TCM, and the current discussion mainly focuses on the mechanism of the therapeutic effect of TCM.

Advances in multimodal MRI-based study of brain networks in patients with carotid artery stenosis / 中国辐射卫生

@#Stenosis and occlusion caused by carotid atherosclerosis is an important cause of ischemic stroke. In recent years, with the continuous development of magnetic resonance imaging (MRI) technology and the introduction of complex network theory, brain network analysis can be used not only to explain the clinical symptoms and cognitive dysfunction in patients with carotid stenosis caused by changes in network topological properties of different brain regions, but also to explore the imaging markers of carotid stenosis, thus providing important reference data for the diagnosis of early asymptomatic carotid stenosis, the selection of individualized intervention programs, and the assessment of efficacy. Brain network analysis has been used as a powerful tool. In this paper, we review the studies of structural and functional brain networks in patients with carotid stenosis, and introduce the definitions of brain network nodes and edges and important topological properties of complex networks. We also analyze the current research on brain network in patients with carotid stenosis, and discuss the challenges and outlook of existing imaging techniques and network construction methodologies in this field.

Knowledge Graph Construction of Coronary Heart Disease Based on Traditional Chinese Medicine Diagnosis and Treatment Guidelines / 中国实验方剂学杂志

ObjectiveTo construct the syndrome differentiation and treatment process in the diagnosis and treatment guideline into a visual knowledge graph using knowledge graph technology， and visualize the process from the input of clinical manifestations to the output of corresponding traditional Chinese medicine （TCM） diagnosis and prescriptions through programs， to visually display the diagnosis and treatment process as well as the data relationship for TCM practitioners. This paper facilitated the standardized and normalized TCM diagnosis and treatment of coronary heart disease， and provided technical support for the inheritance and promotion of TCM diagnosis and treatment. MethodNeo4j and py2neo were used to construct a knowledge graph based on the Guideline for Diagnosis and Treatment of Coronary Heart Disease with Stable Angina Pectoris published by China Association of Chinese Medicine Cardiovascular Disease Branch. A knowledge graph regarding the input of clinical manifestations was built through programs， visually displaying the standardized TCM diagnosis and treatment process of coronary heart disease with stable angina pectoris. ResultThe structured data were extracted from the guideline by py2neo connecting to Neo4j and imported into Neo4j to construct the knowledge graph of TCM diagnosis and treatment of coronary heart disease with stable angina pectoris， which had graph database query function. ConclusionAiming at the problems existing in the inheritance of TCM diagnosis and treatment， this paper proposed a diagnosis and treatment guideline integrating the experience of TCM experts and evidence-based evidence for coronary heart disease with stable angina pectoris， and realized the visualization process of knowledge graph based on TCM diagnosis and treatment guideline and the experience of TCM experts. It is helpful to intuitively display the whole TCM diagnosis and treatment process from symptom input to prescriptions and inherit TCM experience， providing a new paradigm for standardized and normalized TCM diagnosis and treatment.

A method of mental disorder recognition based on visibility graph / 生物医学工程学杂志

The causes of mental disorders are complex, and early recognition and early intervention are recognized as effective way to avoid irreversible brain damage over time. The existing computer-aided recognition methods mostly focus on multimodal data fusion, ignoring the asynchronous acquisition problem of multimodal data. For this reason, this paper proposes a framework of mental disorder recognition based on visibility graph (VG) to solve the problem of asynchronous data acquisition. First, time series electroencephalograms (EEG) data are mapped to spatial visibility graph. Then, an improved auto regressive model is used to accurately calculate the temporal EEG data features, and reasonably select the spatial metric features by analyzing the spatiotemporal mapping relationship. Finally, on the basis of spatiotemporal information complementarity, different contribution coefficients are assigned to each spatiotemporal feature and to explore the maximum potential of feature so as to make decisions. The results of controlled experiments show that the method in this paper can effectively improve the recognition accuracy of mental disorders. Taking Alzheimer's disease and depression as examples, the highest recognition rates are 93.73% and 90.35%, respectively. In summary, the results of this paper provide an effective computer-aided tool for rapid clinical diagnosis of mental disorders.

Research on classification method of multimodal magnetic resonance images of Alzheimer's disease based on generalized convolutional neural networks / 生物医学工程学杂志

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. Neuroimaging based on magnetic resonance imaging (MRI) is one of the most intuitive and reliable methods to perform AD screening and diagnosis. Clinical head MRI detection generates multimodal image data, and to solve the problem of multimodal MRI processing and information fusion, this paper proposes a structural and functional MRI feature extraction and fusion method based on generalized convolutional neural networks (gCNN). The method includes a three-dimensional residual U-shaped network based on hybrid attention mechanism (3D HA-ResUNet) for feature representation and classification for structural MRI, and a U-shaped graph convolutional neural network (U-GCN) for node feature representation and classification of brain functional networks for functional MRI. Based on the fusion of the two types of image features, the optimal feature subset is selected based on discrete binary particle swarm optimization, and the prediction results are output by a machine learning classifier. The validation results of multimodal dataset from the AD Neuroimaging Initiative (ADNI) open-source database show that the proposed models have superior performance in their respective data domains. The gCNN framework combines the advantages of these two models and further improves the performance of the methods using single-modal MRI, improving the classification accuracy and sensitivity by 5.56% and 11.11%, respectively. In conclusion, the gCNN-based multimodal MRI classification method proposed in this paper can provide a technical basis for the auxiliary diagnosis of Alzheimer's disease.

Study on the explicitation of implicit knowledge and the construction of knowledge graph on moxibustion in medical case records of ZHOU Mei-sheng's Jiusheng / 中国针灸

To explore the methods of the explicitation of implicit knowledge and the construction of knowledge graph on moxibustion in medical case records of ZHOU Mei-sheng's Jiusheng. The medical case records data of Jiusheng was collected, the frequency statistic was analyzed based on Python3.8.6, complex network analysis was performed using Gephi9.2 software, community analysis was performed by the ancient and modern medical case cloud platform V2.3.5, and analysis and verification of correlation graph and weight graph were proceed by Neo4j3.5.25 image database. The disease systems with frequency≥10 % were surgery, ophthalmology and otorhinolaryngology, locomotor, digestive and respiratory systems. The diseases under the disease system were mainly carbuncle, arthritis, lumbar disc herniation and headache. The commonly used moxibustion methods were fumigating moxibustion, blowing moxibustion, direct moxibustion and warming acupuncture. The core prescription of points obtained by complex network analysis included Yatong point, Zhiyang(GV 9), Sanyinjiao(SP 6), Dazhui(GV 14), Zusanli(ST 36), Lingtai(GV 10), Xinshu(BL 15), Zhijian point and Hegu(LI 4), which were basically consistent with high-frequency points. A total of 6 communities were obtained by community analysis, corresponding to different diseases. Through the analysis of correlation graph, 13 pairs of strong association rule points were obtained. The correlation between Zhiyang(GV 9)-Dazhui(GV 14) and Yatong point-Lingtai(GV 10) was the strongest. The acupoints with high correlation with Yatong point were Zhiyang(GV 9), Lingtai(GV 10), Dazhui(GV 14), Zusanli(ST 36) and Sanyinjiao(SP 6). In the weight graph of the high-frequency disease system, the relationship of the first weight of the surgery system disease was fumigating moxibustion-carbuncle-Yatong point, and the relationship of the first weight of the ophthalmology and otorhinolaryngology system disease was blowing moxibustion-laryngitis-Hegu (LI 4). The results of correlation graph and weight graph are consistent with the results of data mining, which can be used as an effective way to study the knowledge base of moxibustion diagnosis and treatment in the future.