As an advanced data science technology,the knowledge graph systematically integrates and displays the knowledge framework within the field of traditional Chinese medicine(TCM).This not only contributes to a deeper com...As an advanced data science technology,the knowledge graph systematically integrates and displays the knowledge framework within the field of traditional Chinese medicine(TCM).This not only contributes to a deeper comprehension of traditional Chinese medical theories but also provides robust support for the intelligent decision systems and medical applications of TCM.Against this backdrop,this paper aims to systematically review the current status and development trends of TCM knowledge graphs,offering theoretical and technical foundations to facilitate the inheritance,innovation,and integrated development of TCM.Firstly,we introduce the relevant concepts and research status of TCM knowledge graphs.Secondly,we conduct an in-depth analysis of the challenges and trends faced by key technologies in TCM knowledge graph construction,such as knowledge representation,extraction,fusion,and reasoning,and classifies typical knowledge graphs in various subfields of TCM.Next,we comprehensively outline the current medical applications of TCM knowledge graphs in areas such as information retrieval,diagnosis,question answering,recommendation,and knowledge mining.Finally,the current research status and future directions of TCM knowledge graphs are concluded and discussed.We believe this paper contributes to a deeper understanding of the research dynamics in TCM knowledge graphs and provides essential references for scholars in related fields.展开更多
Objective: To grasp the changing trend of research hotspots of traditional Chinese medicine in the prevention and treatment of COVID-19, and to better play the role of traditional Chinese medicine in the prevention an...Objective: To grasp the changing trend of research hotspots of traditional Chinese medicine in the prevention and treatment of COVID-19, and to better play the role of traditional Chinese medicine in the prevention and treatment of COVID-19 and other diseases. Methods: The research literature from 2020 to 2022 was searched in the CNKI database, and CiteSpace software was used for visual analysis. Results: The papers on the prevention and treatment of COVID-19 by traditional Chinese medicine changed from cases, overviews, reports, and efficacy studies to more in-depth mechanism research, theoretical exploration, and social impact analysis, and finally formed a theory-clinical-society Influence-institutional change and other multi-dimensional achievement systems. Conclusion: Analyzing the changing trends of TCM hotspots in the prevention and treatment of COVID-19 can fully understand the important value of TCM, take the coordination of TCM and Western medicine as an important means to deal with public health security incidents, and promote the exploration of the potential efficacy of TCM, so as to enhance the role of TCM in Applications in social stability, emergency security, clinical practice, etc.展开更多
Objective: To analyze the development of traditional Chinese medicine(TCM) over the past 10 years, focus on the key points of research,and predict the diseases that can be treated and prevented through TCM in the futu...Objective: To analyze the development of traditional Chinese medicine(TCM) over the past 10 years, focus on the key points of research,and predict the diseases that can be treated and prevented through TCM in the future.Methods: A systematic computer-based search was conducted to gather relevant literature on preventive treatment in traditional Chinese medicine from database including China National Knowledge Infrastructure(CNKI), VIP, and WanFang in the past 10 years. Data extraction involved details such as authors, institutions, and keywords. Additionally, searching the Web of Science for literature on preventive treatment in traditional Chinese medicine, which was subsequently downloaded. Data analysis and the creation of knowledge graph were performed using VOSviewer and CiteSpace, respectively.Results: Through the relevant analysis of the literature in the field of preventive treatment of disease, the research hotspots and research status of preventive treatment of disease in recent years are shown, which provides certain reference information for future scientific research in our country.Conclusions: The research conducted provides valuable insights and guidance for future studies in the prevention and treatment of diseases using traditional Chinese medicine methods.展开更多
Syndrome differentiation is the core diagnosis method of Traditional Chinese Medicine(TCM).We propose a method that simulates syndrome differentiation through deductive reasoning on a knowledge graph to achieve automa...Syndrome differentiation is the core diagnosis method of Traditional Chinese Medicine(TCM).We propose a method that simulates syndrome differentiation through deductive reasoning on a knowledge graph to achieve automated diagnosis in TCM.We analyze the reasoning path patterns from symptom to syndromes on the knowledge graph.There are two kinds of path patterns in the knowledge graph:one-hop and two-hop.The one-hop path pattern maps the symptom to syndromes immediately.The two-hop path pattern maps the symptom to syndromes through the nature of disease,etiology,and pathomechanism to support the diagnostic reasoning.Considering the different support strengths for the knowledge paths in reasoning,we design a dynamic weight mechanism.We utilize Naïve Bayes and TF-IDF to implement the reasoning method and the weighted score calculation.The proposed method reasons the syndrome results by calculating the possibility according to the weighted score of the path in the knowledge graph based on the reasoning path patterns.We evaluate the method with clinical records and clinical practice in hospitals.The preliminary results suggest that the method achieves high performance and can help TCM doctors make better diagnosis decisions in practice.Meanwhile,the method is robust and explainable under the guide of the knowledge graph.It could help TCM physicians,especially primary physicians in rural areas,and provide clinical decision support in clinical practice.展开更多
[Objectives]This study was conducted to explore the application and development trend of Chinese medicinal material cinnamon in the field of traditional Chinese medicine.[Methods]Articles published from 2008 to 2023 w...[Objectives]This study was conducted to explore the application and development trend of Chinese medicinal material cinnamon in the field of traditional Chinese medicine.[Methods]Articles published from 2008 to 2023 were exported using"cinnamon"as the subject word in the Chinese database of CNKI.Knowledge graphs were drawn by CiteSpace software on the number of articles published,the institutions publishing articles,and keyword clustering,and the data were sorted by Excel.Combined with the extracted information,the application of cinnamon in traditional Chinese medicine and integrated traditional Chinese and Western medicine was analyzed,and its development trend was discussed and prospected,providing further reference for researchers.[Results]The number of articles published showed an overall upward trend and maintained a high number of articles.In the analysis of the journals publishing articles,the journal with the largest number of articles was West China Journal of Pharmaceutical Sciences,which had certain representativeness.In the analysis of institutions publishing articles,the institution with the largest number of articles was Beijing University of Chinese Medicine,and most institutions had little cooperation.Four categories was obtained in keyword clustering,respectively,general research,component identification,production process and product development of cinnamon."Glycyrrhizin"was the keyword with the earliest burst time,and the hot words that have received much attention in recent years are"medication law"and"data mining".[Conclusions]The application of cinnamon in the field of traditional Chinese medicine is mainly to treat diseases and as raw materials for traditional Chinese medicine products.The development trend is"quality control"and"product research and development".Further research and development of cinnamon in traditional Chinese medicine need to promote the participation of more institutions to participate,and cooperation and communication between institutions should be strengthened to promote the deep integration of production,research and academia.展开更多
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...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.展开更多
With the widespread use of Internet,the amount of data in the field of traditional Chinese medicine(TCM)is growing exponentially.Consequently,there is much attention on the collection of useful knowledge as well as it...With the widespread use of Internet,the amount of data in the field of traditional Chinese medicine(TCM)is growing exponentially.Consequently,there is much attention on the collection of useful knowledge as well as its effective organization and expression.Knowledge graphs have thus emerged,and knowledge reasoning based on this tool has become one of the hot spots of research.This paper first presents a brief introduction to the development of knowledge graphs and knowledge reasoning,and explores the significance of knowledge reasoning.Secondly,the mainstream knowledge reasoning methods,including knowledge reasoning based on traditional rules,knowledge reasoning based on distributed feature representation,and knowledge reasoning based on neural networks are introduced.Then,using stroke as an example,the knowledge reasoning methods are expounded,the principles and characteristics of commonly used knowledge reasoning methods are summarized,and the research and applications of knowledge reasoning techniques in TCM in recent years are sorted out.Finally,we summarize the problems faced in the development of knowledge reasoning in TCM,and put forward the importance of constructing a knowledge reasoning model suitable for the field of TCM.展开更多
Objective To analyze the intellectual structure,hotspots and trends of traditional Chinese medicine(TCM)in immune regulation research.Methods The data were extracted from the Web of Science Core Collection(WoSCC)and t...Objective To analyze the intellectual structure,hotspots and trends of traditional Chinese medicine(TCM)in immune regulation research.Methods The data were extracted from the Web of Science Core Collection(WoSCC)and the China National Knowledge Infrastructure(CNKI)and verified by two experienced TCM researchers.The time of literature retrieval is up to 2020.CiteSpace 5.7.R1 and Microsoft Excel 2016 were used for the statistical analysis and bibliometric diagrams,including the co-occurrence network of authors,institutions,countries,keywords,references,dual-map overlays of journals and citation bursts,etc.Results A total of 12270 publications related to TCM in immune regulation were included.The annual number of publications has increased in this field.There was close cooperation of countries and institutions,while the distribution of scholars was scattered.China was the core of the cooperation network.The dual-map overlays analysis of journals showed that core and marginal fields had increased.The keywords and references analysis showed that network pharmacology,metabolism and cancer were the most high-frequency keywords with high-intensity bursts.Conclusion TCM in immune regulation has attracted wider attention,with multi-country,multi-field,multi-disciplinary and multi-level research developing toward informatization.Network pharmacology,metabolism and cancer may be the focus of future research in this field.展开更多
针对中医问诊领域数据规模大,以及医生在问诊中主观性强、数据对齐难的问题,提出了一种中医问答领域的大语言模型ChatTCM。利用大语言模型(large language model,LLM)在处理自然语言理解与文本生成方面的强大能力,通过对大语言模型进行...针对中医问诊领域数据规模大,以及医生在问诊中主观性强、数据对齐难的问题,提出了一种中医问答领域的大语言模型ChatTCM。利用大语言模型(large language model,LLM)在处理自然语言理解与文本生成方面的强大能力,通过对大语言模型进行微调,使LLM具有在中医问答领域的专业知识和能力,避免模型在生成时出现幻觉的现象。提取中医书籍中的三元组信息,构建中医知识图谱数据库,实现中医知识的数据对齐与系统化整合,并为大语言模型生成答案提供背景知识;结合思维链(chain-of-thought,COT)与知识图谱数据库的动态交互,生成客观的推理过程,确保诊疗建议具有科学依据;把思维链与知识图谱的推理结果作为新知识进行存储,从而不断扩展本地知识库。与中医领域的HuaTuoGPT模型对比实验表明,ChatTCM模型在MedChatZH数据集上BLEU-4和ROUGE-L的评测指标分别提高了10.6和10.5个百分点,并且在已开源的数据集上准确度达到了70%,比同类型的MedChatZH模型提升了10个百分点。展开更多
Traditional Chinese Medicine(TCM)has a long history and a comprehensive theoreticalsystem.However,its diagnostic process heavily relies on subjective experience,posing chal-lenges to modernization and standardization....Traditional Chinese Medicine(TCM)has a long history and a comprehensive theoreticalsystem.However,its diagnostic process heavily relies on subjective experience,posing chal-lenges to modernization and standardization.This study explores the integration of artifi-cial intelligence(AI)into TCM,aiming to construct an intelligent diagnosis and treatmentplatform.By leveraging AI technologies such as deep learning,natural language processing(NLP),and knowledge graphs,the platform enhances the accuracy of syndrome recogni-tion,intelligent consultation,and personalized treatment recommendations.The researchalso focuses on structuring TCM knowledge,developing AI-based imaging analysis,andoptimizing intelligent text analysis.The results indicate that AI-driven TCM diagnosis canimprove diagnostic accuracy,reduce subjectivity,and facilitate modernization,contribut-ing to smart healthcare development.展开更多
Traditional Chinese medicine(TCM)is an interesting research topic in China’s thousands of years of history.With the recent advances in artificial intelligence technology,some researchers have started to focus on lear...Traditional Chinese medicine(TCM)is an interesting research topic in China’s thousands of years of history.With the recent advances in artificial intelligence technology,some researchers have started to focus on learning the TCM prescriptions in a data-driven manner.This involves appropriately recommending a set of herbs based on patients’symptoms.Most existing herb recommendation models disregard TCM domain knowledge,for example,the interactions between symptoms and herbs and the TCM-informed observations(i.e.,TCM formulation of prescriptions).In this paper,we propose a knowledge-guided and TCM-informed approach for herb recommendation.The knowledge used includes path interactions and co-occurrence relationships among symptoms and herbs from a knowledge graph generated from TCM literature and prescriptions.The aforementioned knowledge is used to obtain the discriminative feature vectors of symptoms and herbs via a graph attention network.To increase the ability of herb prediction for the given symptoms,we introduce TCM-informed observations in the prediction layer.We apply our proposed model on a TCM prescription dataset,demonstrating significant improvements over state-of-the-art herb recommendation methods.展开更多
目的基于国内外公开发表的中药药物警戒为主题的期刊文献,构建中药药物警戒研究知识图谱,探讨其研究热点及发展方向。方法在中国知网、Web of science数据库检索近10年来国内外以“中药药物警戒”为主题的学术研究机构发表的相关文献,利...目的基于国内外公开发表的中药药物警戒为主题的期刊文献,构建中药药物警戒研究知识图谱,探讨其研究热点及发展方向。方法在中国知网、Web of science数据库检索近10年来国内外以“中药药物警戒”为主题的学术研究机构发表的相关文献,利用CiteSpace软件对其作者分布、关键词共现、关键词聚类、关键词突现等进行知识图谱分析。结果共纳入2785篇中文文献和229篇英文文献,主要突显出3个研究团队与研究机构。研究范畴主要集中于中药不良反应的识别、中药毒性机制的理解、中药风险防范与合理用药转化3个方面,研究内容不断深入、丰富。国内外发文热点各有侧重,对中药注射剂等安全问题关注持久。结合研究现状与未来发展思考,建立中药药物警戒发展与研究思维导图。结论中药药物警戒的建设应在传承中医药传统的同时,创新发挥现代技术优势,示范引领国际植物药药物警戒发展。展开更多
基金supported by the research“Evidence Study Based on Multimodal Knowledge Graph Reasoning of the Idea of Treating Pre-disease in TCM(2023016)”the National Natural Science Foundation of China(No.82374621).
文摘As an advanced data science technology,the knowledge graph systematically integrates and displays the knowledge framework within the field of traditional Chinese medicine(TCM).This not only contributes to a deeper comprehension of traditional Chinese medical theories but also provides robust support for the intelligent decision systems and medical applications of TCM.Against this backdrop,this paper aims to systematically review the current status and development trends of TCM knowledge graphs,offering theoretical and technical foundations to facilitate the inheritance,innovation,and integrated development of TCM.Firstly,we introduce the relevant concepts and research status of TCM knowledge graphs.Secondly,we conduct an in-depth analysis of the challenges and trends faced by key technologies in TCM knowledge graph construction,such as knowledge representation,extraction,fusion,and reasoning,and classifies typical knowledge graphs in various subfields of TCM.Next,we comprehensively outline the current medical applications of TCM knowledge graphs in areas such as information retrieval,diagnosis,question answering,recommendation,and knowledge mining.Finally,the current research status and future directions of TCM knowledge graphs are concluded and discussed.We believe this paper contributes to a deeper understanding of the research dynamics in TCM knowledge graphs and provides essential references for scholars in related fields.
文摘Objective: To grasp the changing trend of research hotspots of traditional Chinese medicine in the prevention and treatment of COVID-19, and to better play the role of traditional Chinese medicine in the prevention and treatment of COVID-19 and other diseases. Methods: The research literature from 2020 to 2022 was searched in the CNKI database, and CiteSpace software was used for visual analysis. Results: The papers on the prevention and treatment of COVID-19 by traditional Chinese medicine changed from cases, overviews, reports, and efficacy studies to more in-depth mechanism research, theoretical exploration, and social impact analysis, and finally formed a theory-clinical-society Influence-institutional change and other multi-dimensional achievement systems. Conclusion: Analyzing the changing trends of TCM hotspots in the prevention and treatment of COVID-19 can fully understand the important value of TCM, take the coordination of TCM and Western medicine as an important means to deal with public health security incidents, and promote the exploration of the potential efficacy of TCM, so as to enhance the role of TCM in Applications in social stability, emergency security, clinical practice, etc.
基金supported by the National Natural Science Foundation of China Youth program (No.81904324)。
文摘Objective: To analyze the development of traditional Chinese medicine(TCM) over the past 10 years, focus on the key points of research,and predict the diseases that can be treated and prevented through TCM in the future.Methods: A systematic computer-based search was conducted to gather relevant literature on preventive treatment in traditional Chinese medicine from database including China National Knowledge Infrastructure(CNKI), VIP, and WanFang in the past 10 years. Data extraction involved details such as authors, institutions, and keywords. Additionally, searching the Web of Science for literature on preventive treatment in traditional Chinese medicine, which was subsequently downloaded. Data analysis and the creation of knowledge graph were performed using VOSviewer and CiteSpace, respectively.Results: Through the relevant analysis of the literature in the field of preventive treatment of disease, the research hotspots and research status of preventive treatment of disease in recent years are shown, which provides certain reference information for future scientific research in our country.Conclusions: The research conducted provides valuable insights and guidance for future studies in the prevention and treatment of diseases using traditional Chinese medicine methods.
基金This work is supported by the National Key Research and Development Program of China under Grant 2017YFB1002304the China Scholarship Council under Grant 201906465021.
文摘Syndrome differentiation is the core diagnosis method of Traditional Chinese Medicine(TCM).We propose a method that simulates syndrome differentiation through deductive reasoning on a knowledge graph to achieve automated diagnosis in TCM.We analyze the reasoning path patterns from symptom to syndromes on the knowledge graph.There are two kinds of path patterns in the knowledge graph:one-hop and two-hop.The one-hop path pattern maps the symptom to syndromes immediately.The two-hop path pattern maps the symptom to syndromes through the nature of disease,etiology,and pathomechanism to support the diagnostic reasoning.Considering the different support strengths for the knowledge paths in reasoning,we design a dynamic weight mechanism.We utilize Naïve Bayes and TF-IDF to implement the reasoning method and the weighted score calculation.The proposed method reasons the syndrome results by calculating the possibility according to the weighted score of the path in the knowledge graph based on the reasoning path patterns.We evaluate the method with clinical records and clinical practice in hospitals.The preliminary results suggest that the method achieves high performance and can help TCM doctors make better diagnosis decisions in practice.Meanwhile,the method is robust and explainable under the guide of the knowledge graph.It could help TCM physicians,especially primary physicians in rural areas,and provide clinical decision support in clinical practice.
基金Supported by Undergraduate Innovation and Entrepreneurship Training Program of Guangxi University of Chinese Medicine[S202310600049,S202310600135]Research Training Projects at Guangxi University of Chinese Medicine in 2022[2022DXS18,2022DXS19].
文摘[Objectives]This study was conducted to explore the application and development trend of Chinese medicinal material cinnamon in the field of traditional Chinese medicine.[Methods]Articles published from 2008 to 2023 were exported using"cinnamon"as the subject word in the Chinese database of CNKI.Knowledge graphs were drawn by CiteSpace software on the number of articles published,the institutions publishing articles,and keyword clustering,and the data were sorted by Excel.Combined with the extracted information,the application of cinnamon in traditional Chinese medicine and integrated traditional Chinese and Western medicine was analyzed,and its development trend was discussed and prospected,providing further reference for researchers.[Results]The number of articles published showed an overall upward trend and maintained a high number of articles.In the analysis of the journals publishing articles,the journal with the largest number of articles was West China Journal of Pharmaceutical Sciences,which had certain representativeness.In the analysis of institutions publishing articles,the institution with the largest number of articles was Beijing University of Chinese Medicine,and most institutions had little cooperation.Four categories was obtained in keyword clustering,respectively,general research,component identification,production process and product development of cinnamon."Glycyrrhizin"was the keyword with the earliest burst time,and the hot words that have received much attention in recent years are"medication law"and"data mining".[Conclusions]The application of cinnamon in the field of traditional Chinese medicine is mainly to treat diseases and as raw materials for traditional Chinese medicine products.The development trend is"quality control"and"product research and development".Further research and development of cinnamon in traditional Chinese medicine need to promote the participation of more institutions to participate,and cooperation and communication between institutions should be strengthened to promote the deep integration of production,research and academia.
基金Supported by the National Natural Science Foundation of China(No.82174276 and 82074580)the Key Research and Development Program of Jiangsu Province(No.BE2022712)+2 种基金China Postdoctoral Foundation(No.2021M701674)Postdoctoral Research Program of Jiangsu Province(No.2021K457C)Qinglan Project of Jiangsu Universities 2021。
文摘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.
基金The National Key R&D Program of China(2018AAA0102100)Hunan Provincial Department of Education Outstanding Youth Project(22B0385)+2 种基金Open Fund of the Domestic First-class Discipline Construction Project of Chinese Medicine of Hunan University of Chinese Medicine(2018ZYX17)Electronic Science and Technology Discipline Open Fund Project of School of Information Science and Engineering,Hunan University of Chinese Medicine(2018-2)Hunan University of Chinese Medicine Graduate Innovation Project(2022CX122)。
文摘With the widespread use of Internet,the amount of data in the field of traditional Chinese medicine(TCM)is growing exponentially.Consequently,there is much attention on the collection of useful knowledge as well as its effective organization and expression.Knowledge graphs have thus emerged,and knowledge reasoning based on this tool has become one of the hot spots of research.This paper first presents a brief introduction to the development of knowledge graphs and knowledge reasoning,and explores the significance of knowledge reasoning.Secondly,the mainstream knowledge reasoning methods,including knowledge reasoning based on traditional rules,knowledge reasoning based on distributed feature representation,and knowledge reasoning based on neural networks are introduced.Then,using stroke as an example,the knowledge reasoning methods are expounded,the principles and characteristics of commonly used knowledge reasoning methods are summarized,and the research and applications of knowledge reasoning techniques in TCM in recent years are sorted out.Finally,we summarize the problems faced in the development of knowledge reasoning in TCM,and put forward the importance of constructing a knowledge reasoning model suitable for the field of TCM.
基金We thank for the funding support from the National Natural Science Foundation of China(No.81874492)Key Scientific Research Projects of Hunan Provincial Department of Education(No.18A219)the Domestic First-Class Discipline Construction Project of Chinese Medicine of Hunan University of Chinese Medicine.
文摘Objective To analyze the intellectual structure,hotspots and trends of traditional Chinese medicine(TCM)in immune regulation research.Methods The data were extracted from the Web of Science Core Collection(WoSCC)and the China National Knowledge Infrastructure(CNKI)and verified by two experienced TCM researchers.The time of literature retrieval is up to 2020.CiteSpace 5.7.R1 and Microsoft Excel 2016 were used for the statistical analysis and bibliometric diagrams,including the co-occurrence network of authors,institutions,countries,keywords,references,dual-map overlays of journals and citation bursts,etc.Results A total of 12270 publications related to TCM in immune regulation were included.The annual number of publications has increased in this field.There was close cooperation of countries and institutions,while the distribution of scholars was scattered.China was the core of the cooperation network.The dual-map overlays analysis of journals showed that core and marginal fields had increased.The keywords and references analysis showed that network pharmacology,metabolism and cancer were the most high-frequency keywords with high-intensity bursts.Conclusion TCM in immune regulation has attracted wider attention,with multi-country,multi-field,multi-disciplinary and multi-level research developing toward informatization.Network pharmacology,metabolism and cancer may be the focus of future research in this field.
文摘针对中医问诊领域数据规模大,以及医生在问诊中主观性强、数据对齐难的问题,提出了一种中医问答领域的大语言模型ChatTCM。利用大语言模型(large language model,LLM)在处理自然语言理解与文本生成方面的强大能力,通过对大语言模型进行微调,使LLM具有在中医问答领域的专业知识和能力,避免模型在生成时出现幻觉的现象。提取中医书籍中的三元组信息,构建中医知识图谱数据库,实现中医知识的数据对齐与系统化整合,并为大语言模型生成答案提供背景知识;结合思维链(chain-of-thought,COT)与知识图谱数据库的动态交互,生成客观的推理过程,确保诊疗建议具有科学依据;把思维链与知识图谱的推理结果作为新知识进行存储,从而不断扩展本地知识库。与中医领域的HuaTuoGPT模型对比实验表明,ChatTCM模型在MedChatZH数据集上BLEU-4和ROUGE-L的评测指标分别提高了10.6和10.5个百分点,并且在已开源的数据集上准确度达到了70%,比同类型的MedChatZH模型提升了10个百分点。
基金2024 Ministry of Education Industry-University Cooperative Education Program:Smart Diagnosis Platform for Traditional Chinese Medicine Based on Artificial Intelligence and Big Data Technologies,a collaboration between Shandong Foreign Affairs Vocational Universityand Kaiyuan Education Technology(Shenzhen)Co.,Ltd,Third Prize Winner in the 2024 TCMIID®Competition on the Preservation and Innovative Development of Traditional Chi-nese Medicine.Article History。
文摘Traditional Chinese Medicine(TCM)has a long history and a comprehensive theoreticalsystem.However,its diagnostic process heavily relies on subjective experience,posing chal-lenges to modernization and standardization.This study explores the integration of artifi-cial intelligence(AI)into TCM,aiming to construct an intelligent diagnosis and treatmentplatform.By leveraging AI technologies such as deep learning,natural language processing(NLP),and knowledge graphs,the platform enhances the accuracy of syndrome recogni-tion,intelligent consultation,and personalized treatment recommendations.The researchalso focuses on structuring TCM knowledge,developing AI-based imaging analysis,andoptimizing intelligent text analysis.The results indicate that AI-driven TCM diagnosis canimprove diagnostic accuracy,reduce subjectivity,and facilitate modernization,contribut-ing to smart healthcare development.
基金supported by the China Knowledge Centre for Engi-neering Sciences and Technology(CKCEST)and the National Natural Science Foundation of China(No.62037001)。
文摘Traditional Chinese medicine(TCM)is an interesting research topic in China’s thousands of years of history.With the recent advances in artificial intelligence technology,some researchers have started to focus on learning the TCM prescriptions in a data-driven manner.This involves appropriately recommending a set of herbs based on patients’symptoms.Most existing herb recommendation models disregard TCM domain knowledge,for example,the interactions between symptoms and herbs and the TCM-informed observations(i.e.,TCM formulation of prescriptions).In this paper,we propose a knowledge-guided and TCM-informed approach for herb recommendation.The knowledge used includes path interactions and co-occurrence relationships among symptoms and herbs from a knowledge graph generated from TCM literature and prescriptions.The aforementioned knowledge is used to obtain the discriminative feature vectors of symptoms and herbs via a graph attention network.To increase the ability of herb prediction for the given symptoms,we introduce TCM-informed observations in the prediction layer.We apply our proposed model on a TCM prescription dataset,demonstrating significant improvements over state-of-the-art herb recommendation methods.
文摘目的基于国内外公开发表的中药药物警戒为主题的期刊文献,构建中药药物警戒研究知识图谱,探讨其研究热点及发展方向。方法在中国知网、Web of science数据库检索近10年来国内外以“中药药物警戒”为主题的学术研究机构发表的相关文献,利用CiteSpace软件对其作者分布、关键词共现、关键词聚类、关键词突现等进行知识图谱分析。结果共纳入2785篇中文文献和229篇英文文献,主要突显出3个研究团队与研究机构。研究范畴主要集中于中药不良反应的识别、中药毒性机制的理解、中药风险防范与合理用药转化3个方面,研究内容不断深入、丰富。国内外发文热点各有侧重,对中药注射剂等安全问题关注持久。结合研究现状与未来发展思考,建立中药药物警戒发展与研究思维导图。结论中药药物警戒的建设应在传承中医药传统的同时,创新发挥现代技术优势,示范引领国际植物药药物警戒发展。
