Objective To discuss the method of constructing TCM word network and the subsequent optimization method;To solve the problems of natural language processing in the TCM-clinical decision support system using TCM terminology.Methods This study was based on several national standards and terminology dictionaries of TCM,such as Zhong Yi Lin Chuang Zhen Liao Shu Yu Ji Bing Part and Zhong Yi Yao Xue Zhu Ti Ci Biao,supplemented with related corpus on the Internet,and the framework of TCM word network was constructed with ontology as the guide.Word2Vec was used to load pre-trained models for similarity calculation,statistical and rule-based new word discovery,bibliometric analysis,and other methods to add or delete concept words and synonyms such as symptom terms and prescription terms.Results The TCM word network contained 55 semantic types and 13 semantic relationships,more than 110 000 concept words,and more than 300 000 synonyms.In addition to classifying concept words by semantic types,more detailed semantic classification was carried out in the upper and lower tree structures,in which more than 30 000 concept words had superordinate words,and nearly 2 600 concept words had subordinate words.At the same time,a process-based terminology supplementation mechanism,update review mechanism and cleaning mechanism were created.Conclusion TCM word network can not only be applied to the natural language processing process of TCM-clinical decision support system,but also can be applied to the normalization of data and the automatic construction of knowledge graph.

Objective To discuss the method of constructing TCM word network and the subsequent optimization method;To solve the problems of natural language processing in the TCM-clinical decision support system using TCM terminology.Methods This study was based on several national standards and terminology dictionaries of TCM,such as Zhong Yi Lin Chuang Zhen Liao Shu Yu Ji Bing Part and Zhong Yi Yao Xue Zhu Ti Ci Biao,supplemented with related corpus on the Internet,and the framework of TCM word network was constructed with ontology as the guide.Word2Vec was used to load pre-trained models for similarity calculation,statistical and rule-based new word discovery,bibliometric analysis,and other methods to add or delete concept words and synonyms such as symptom terms and prescription terms.Results The TCM word network contained 55 semantic types and 13 semantic relationships,more than 110 000 concept words,and more than 300 000 synonyms.In addition to classifying concept words by semantic types,more detailed semantic classification was carried out in the upper and lower tree structures,in which more than 30 000 concept words had superordinate words,and nearly 2 600 concept words had subordinate words.At the same time,a process-based terminology supplementation mechanism,update review mechanism and cleaning mechanism were created.Conclusion TCM word network can not only be applied to the natural language processing process of TCM-clinical decision support system,but also can be applied to the normalization of data and the automatic construction of knowledge graph.

Alzheimer's disease (AD), a chronic degenerative disease of the central nervous system, is more prevalent in the elderly population and its incidence is increasing every year. It is important to pay attention to new methods of AD prevention and treatment for clinical treatment of AD, improving the quality of life of patients . This article analyzed the association between the theory and the etiology and pathogenesis of AD and the research basis of moxibustion for the prevention and treatment of AD based on the theory of "thought of emphasizing yang", in order to provide a broader idea for the TCM treatment of AD.

Objective:To screen out the differentially regulated metabolites by the analysis of serum metabolic fingerprints, and to provide potential biomarkers for diagnosis of lung cancer.Methods:A total of 228 subjects were enrolled in Changhai Hospital from January 27, 2021 to June 4, 2021, including 97 newly diagnosed lung cancer patients and 131 healthy individuals. Serum samples were collected from the enrolled cohort according to a standard procedure, and the enrolled cohort was divided into a training set and a completely independent validation set by stratified random sampling. The metabolic fingerprints of serum samples were collected by previously developed nano-assisted laser desorption/ionization mass spectrometry (nano-LDI MS). After age and gender matching of the training set, a diagnostic model based on serum metabolic fingerprints was established by machine learning algorithm, and the classification performance of the model was evaluated by receiver operating characteristic (ROC) curve.Results:Serum metabolic fingerprint for each sample was obtained in 1 minute using a novel nano-LDI MS, with consumption of only 1 μl original serum sample. For the training set, the area under ROC curve (AUC) of the constructed classifier for diagnosis of lung cancer was 0.92 (95% CI 0.87-0.97), with a sensitivity of 89% and specificity of 89%. For the independent validation set, the AUC reached 0.96 (95% CI 0.90-1.00) with a sensitivity of 91% and specificity of 94%, which showed no significant decrease compared to training set. We also identified a biomarker panel of 5 metabolites, demonstrating a unique metabolic fingerprint of lung cancer patients. Conclusion:Serum metabolic fingerprints and machine learning were combined to establish a diagnostic model, which can be used to distinguish between lung cancer patients and healthy controls. This work sheds lights on the rapid metabolic analysis for clinical application towards in vitro diagnosis.