A5012982867- Traditional Chinese Medicine Studies
- Biomedical Text Mining and Ontologies
- Metabolomics and Mass Spectrometry Studies
- Bioinformatics and Genomic Networks
- Machine Learning in Healthcare
- Traditional Chinese Medicine Analysis
- Computational Drug Discovery Methods
- Botanical Studies and Applications
- Gene expression and cancer classification
- Topic Modeling
- Pharmacological Effects of Natural Compounds
- Acupuncture Treatment Research Studies
- Medical Research and Treatments
- Sleep and related disorders
- Plant-based Medicinal Research
- Spectroscopy and Chemometric Analyses
- Mental Health Research Topics
- Machine Learning in Bioinformatics
- Image Retrieval and Classification Techniques
- Advanced Chemical Sensor Technologies
- Sensory Analysis and Statistical Methods
- Advanced Text Analysis Techniques
- Chronic Disease Management Strategies
- Natural Language Processing Techniques
- Complementary and Alternative Medicine Studies
Chinese Academy of Medical Sciences & Peking Union Medical College
2015-2024
Guang’anmen Hospital
2015-2024
Dongguan People’s Hospital
2024
China Academy of Chinese Medical Sciences
2011-2022
Xiyuan Hospital
2021
Harbin Institute of Technology
2011
Beijing Jiaotong University
2010
Abstract Objective The recent surge in large language models (LLMs) across various fields has yet to be fully realized traditional Chinese medicine (TCM). This study aims bridge this gap by developing a model tailored TCM knowledge, enhancing its performance and accuracy clinical reasoning tasks such as diagnosis, treatment, prescription recommendations. Materials Methods harnessed wide array of data resources, including ancient books, textbooks, data, create 3 key datasets: the Pre-trained...
The discovery of disease-causing genes is a critical step towards understanding the nature disease and determining possible cure for it. In recent years, many computational methods to identify have been proposed. However, making full use disease-related (e.g., symptoms) gene-related gene ontology protein-protein interactions) information improve performance prediction still an issue. Here, we develop heterogeneous disease-gene-related network (HDGN) embedding representation framework (called...
Traditional Chinese medicine (TCM) is a clinical‐based discipline in which real‐world clinical practice plays significant role for both the development of therapy and theoretical research. The large‐scale data generated during daily operations TCM provide highly valuable knowledge source decision making. Secondary analysis these would be vital task studies before randomised controlled trials are conducted. In this article, we discuss challenges issues, such as structured curation,...
Abstract Background Disease comorbidity is popular and has significant indications for disease progress management. We aim to detect the general patterns in Chinese populations using a large-scale clinical data set. Methods extracted diseases from anonymized set derived 8,572,137 inpatients 453 hospitals across China. built Comorbidity Network (DCN) correlation analysis detected topological of both complex network mining methods. The were further validated by shared molecular mechanisms...
Traditional Chinese Medicine (TCM) has received increasing attention as a complementary approach or alternative to modern medicine. However, experimental methods for identifying novel targets of TCM herbs heavily relied on the current available herb-compound-target relationships. In this work, we present an Herb-Target Interaction Network (HTINet) approach, network integration pipeline herb-target prediction mainly relying symptom related associations. HTINet focuses capturing...
Investigating the molecular mechanisms of symptoms is a vital task in precision medicine to refine disease taxonomy and improve personalized management chronic diseases. Although there are abundant experimental studies computational efforts obtain candidate genes diseases, identification symptom rarely addressed. We curated high-quality benchmark dataset symptom-gene associations proposed heterogeneous network embedding for identifying genes.
Abstract As one of the most vital methods in drug development, repositioning emphasizes further analysis and research approved drugs based on existing large amount clinical experimental data to identify new indications drugs. However, didn’t achieve enough prediction performance, these do not consider effectiveness information drugs, which make it difficult obtain reliable valuable results. In this study, we proposed a framework termed DRONet, full use comparative relationships (ECR) among...
Abstract Media convergence is a media change led by technological innovation. Applying technology to the study of clustering in Chinese medicine can significantly exploit advantages fusion. Obtaining consistent and complementary information among multiple modalities through provide technical support for clustering. This article presents an approach based on Convergence Graph convolution Encoder Clustering (MCGEC) traditional (TCM) clinical data. It feeds modal graph structure from into...
The efficacy of a traditional Chinese medicine medication derives from the complex interactions herbs or Materia Medica in formula. aim this paper is to propose new approach systematically generate combinations interacting that might lead good outcome. Our was tested on data set prescriptions for diabetic patients verify effectiveness detected herbs. This able detect effective higher orders herb-herb with statistical validation. We present an exploratory analysis clinical records using...
Traditional Chinese medicine (TCM) can provide important complementary medical care to modern medicine, and is widely practiced in China many other countries. Unfortunately, due its empirical nature history of trial error, effective diagnosis prescription methods are not well-defined. This setback results a significant challenge retaining, sharing, inheriting knowledge among physicians. In this paper, we propose new asymmetric probabilistic model for the joint analysis symptoms, diseases,...
As a well-established multidrug combinations schema, traditional Chinese medicine (herbal prescription) has been used for thousands of years in real-world clinical settings. This paper uses complex network approach to investigate the regularities underlying herbal prescriptions. Using five collected large-scale prescription datasets, we construct weighted combination networks with herb as nodes and combinational use links. We found that weight distribution displays clear power law, which...
Background . Symptoms and signs (symptoms in brief) are the essential clinical manifestations for individualized diagnosis treatment traditional Chinese medicine (TCM). To gain insights into molecular mechanism of symptoms, we develop a computational approach to identify candidate genes symptoms. Methods This paper presents network-based integrated analysis multiple phenotype-genotype data sources prediction prioritizing associated The method first calculates similarities between symptoms...
Abstract Background Chinese herbal medicine is one of the most popular (CM) therapies for primary insomnia. One important characteristics CM that different clinicians give prescriptions even same patient. However, there must be some fixed drug patterns in every clinician’s prescriptions. This study aims to screen effective core insomnia treatment three prestigious clinicians. Methods/design A triple-blind, randomized, placebo-controlled, parallel-group clinical trial will performed. Three...
Background. The characteristics of treatment based on syndrome differentiation (TBSD) cause great challenges to evaluate the effectiveness clinical methods. Objectives. This paper aims influence physician personalized medicine in process TBSD. Methods. We performed a randomized, triple-blind trial involving patients primary insomnia treated by 3 physicians individually and independently. (n = 30) were randomly assigned receive treatments for every visit. However, they always received...
Background . Traditional Chinese medicine (TCM) is an individualized by observing the symptoms and signs (symptoms in brief) of patients. We aim to extract meaningful herb-symptom relationships from large scale TCM clinical data. Methods To investigate correlations between herbs held for patients, we use four data sets collected outpatient settings calculate similarities patient pairs terms herb constituents their prescriptions manifesting cosine measure. address large-scale multiple testing...