Background: The medical records of traditional Chinese medicine（TCM） contain numerous synonymous terms with different descriptions,which is not conducive to computer-aided data mining of TCM. However, there is a lack of models available to normalize synonymous TCM terms. Therefore, construction of a synonymous term conversion（STC） model for normalizing synonymous TCM terms is necessary.Methods: Based on the neural networks of bidirectional encoder representations from transformers（BERT）, four types of TCM STC models were designed: Models based on BERT and text classification, text sequence generation, named entity recognition, and text matching. The superior STC model was selected on the basis of its performance in converting synonymous terms. Moreover, three misjudgment inspection methods for the conversion results of the STC model based on inconsistency were proposed to find incorrect term conversion: Neuron random deactivation, output comparison of multiple isomorphic models, and output comparison of multiple heterogeneous models（OCMH）.Results: The classification-based STC model outperformed the other STC task models. It achieved F1 scores of 0.91, 0.91, and 0.83 for performing symptoms, patterns, and treatments STC tasks, respectively. The OCMH method showed the best performance in misjudgment inspection, with wrong detection rates of 0.80, 0.84, and 0.90 in the term conversion results for symptoms, patterns, and treatments, respectively.Conclusion: The TCM STC model based on classification achieved superior performance in converting synonymous terms for symptoms,patterns, and treatments. The misjudgment inspection method based on OCMH showed superior performance in identifying incorrect outputs.

目的 在辨证论治思想指导下构建中医主题词自动标引模型,为相关研究提供参考.方法 收集2019年12月-2020年12月中国中医科学院"名医名家传承"项目管理平台记录的22位名老中医电子病历,在辨证论治思想指导下对病历中的症状和证候进行主题词标引,并采用Tensorflow人工智能模型构建工具、双向编码表示(BERT)语言处理模型、Sigmoid函数及统一计算架构(CUDA)技术构建中医主题词自动标引模型,以准确率、精确率、召回率、F1得分为指标对模型进行评价.结果 在对症状和证候的主题词标引中,基于BERT的中医主题词自动标引模型各项指标表现最优,精确率与召回率均达87％以上.结论 本研究在辨证论治思想指导下构建的中医主题词自动标引模型可高效自动提取电子病历中的症状和证候信息,可为大数据背景下的中医数据挖掘及辨证论治规律研究提供有效工具.

目的:探索构建适用于中医学领域的分词模型.方法:采用基于SentencePiece的无监督学习分词方法,提出利用出版教材、名家著作及中医临床病历这3种不同类型的文献构建中医学分词模型;选择中医临床病历、名医医案作为测试集进行模型测试.结果:中医学分词模型在测试集中的Kappa系数为0.79(一致性程度很高),准确率为0.84,宏观精确率为0.84,宏观召回率为0.83,宏观f1得分为0.83.结论:所构建的分词模型对于中医学专业术语有着较好的切分效果,表明该方法可运用于中医学领域的分词模型的构建,可为进一步地研究中医学分词提供方法学参考.

Background The modernization of traditional Chinese medicine (TCM) demands systematic data mining using medical records. However, this process is hindered by the fact that many TCM symptoms have the same meaning but different literal expressions (i.e., TCM synonymous symptoms). This problem can be solved by using natural language processing algorithms to construct a high-quality TCM symptom normalization model for normalizing TCM synonymous symptoms to unified literal expressions. Methods Four types of TCM symptom normalization models, based on natural language processing, were constructed to find a high-quality one: (1) a text sequence generation model based on a bidirectional long short-term memory (Bi-LSTM) neural network with an encoder-decoder structure; (2) a text classification model based on a Bi-LSTM neural network and sigmoid function; (3) a text sequence generation model based on bidirectional encoder representation from transformers (BERT) with sequence-to-sequence training method of unified language model (BERT-UniLM); (4) a text classification model based on BERT and sigmoid function (BERT-Classification). The performance of the models was compared using four metrics: accuracy, recall, precision, and F1-score. Results The BERT-Classification model outperformed the models based on Bi-LSTM and BERT-UniLM with respect to the four metrics. Conclusions The BERT-Classification model has superior performance in normalizing expressions of TCM synonymous symptoms.

目的 探讨冠心病不稳定型心绞痛病人中医证型、血脂、血尿酸(UA)三者之间的相关性.方法 分析411例冠心病不稳定型心绞痛病人的中医证型、血脂、血尿酸等相关指标,分析三者之间的关系.结果 血瘀证高密度脂蛋白胆固醇(HDL-C)水平低于非血瘀证(P＜0.05),气虚证HDL-C水平高于非气虚证(P＜0.05);痰浊证UA正常率明显低于非痰浊证(P＜0.05),而血瘀证和非血瘀证、气虚证和非气虚证UA正常率比较差异无统计学意义(P＞0.05);UA与三酰甘油(TG)呈正相关(r=0.275,P＜0.05);UA与HDL-C呈负相关(r=-0.239,P＜0.05).结论 冠心病不稳定型心绞痛病人的中医证型与HDL-C异常、UA水平有一定的相关性,而UA与HDL-C、TG具有一定的相关性.

Objective:Using Meta-analysis to access the efficacy and safety of Shenling Baizhu San for the treatment of nonalcoholic fatty liver disease (NAFLD).Methods:We searched CBM,CNKI,VIP,Wanfang and Pubmed database.We assess and bring into randomized controlled trials (RCT) comparing Shenling Baizhu San with no treatment,placebo,or medications for NAFLD.We assessed the quality of included studies using the Jadad rating scale.The RevMan 5.0 software was used for Meta-analysis.Results:Six studies were included and made a Meta-analysis.The Meta-analysis results showed that when Shenling Baizhu San treatment group compared with control group,the clinical total efficiency rate's odds ratio (OR) was 4.41 and 95％CI was (2.48,7.84),P＜0.00001,and the difference was statistically significant.ALT MD was-30.00 and 95％ CI (-36.54,-23.45) (P＜0.00001).AST MD was-9.40 and 95％CI (-12.96,-5.85),P＜0.00001.TC MD was-0.59 and 95％CI (-0.83,-0.34),P＜0.00001;TG MD was-0.35,95％CI (-0.55,-0.15),P＜0.00001.All studies included did not report adverse reactions.Conclusion:Shenling Baizhu San in the treatment of NAFLD has significant clinical curative effect.However,the number and the study sample size are small and the methodological quality is low.To further evaluate the effect and safety of Shenling Baizhu San for NAFLD,more rationally designed and strictly executed RCTs with large samples need to be made.