AI-Assisted TCM Syndrome Differentiation: Key Issues and Technical Challenges

2024, Volume 26, Issue 2

Abstract

Keywords

Figures

References

Related Research

Strategic Study of CAE >> 2024, Volume 26, Issue 2 doi: 10.15302/J-SSCAE-2024.02.010

AI-Assisted TCM Syndrome Differentiation: Key Issues and Technical Challenges

1. School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China;

2. Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province, Jiaxing 314001, Zhejiang, China;

3. Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems, Jiaxing 314001, Zhejiang, China;

4. Guang’anmen Hospital, China Academy of Chinese Medical Sciences, Beijing 100053, China

Funding project：中国工程院咨询项目“面向中医药的人工智能发展战略研究”(2023-HY-10)；浙江省“鲲鹏行动”计划 Received: 2024-02-26 Revised: 2024-03-27 Available online: 2024-04-28

HTML275 PDF 83 Collect 0

Next Previous

Abstract

Traditional Chinese medicine (TCM) syndrome differentiation, as the core of the traditional Chinese medical system, has played an indispensable role in guaranteeing the health of the Chinese nation for thousands of years. Recently, with the collaborative promotion of multiple departments, the TCM technology innovation capability of China has been continuously enhanced. The integration of TCM syndrome differentiation with artificial intelligence AI, big data, and other fields has made new progress. Engineering frontier methods and technologies have provided an effective route for breaking through the theoretical bottlenecks of TCM syndrome differentiation. Against the backdrop of the modernization and intelligent development of TCM diagnosis in the new era, this study summarizes the fundamental theories, basic processes, and key technical links of AI-assisted TCM syndrome differentiation. The key technical links include multimodal data fusion, symptom correlation analysis, syndrome quantification, syndrome reasoning, and large-scale TCM models. It also expounds on the research ideas and development status of each link and summarizes the challenges faced by AI-assisted TCM syndrome differentiation. For instance, publicly available data are insufficient and have a poor quality; syndrome differentiation models are inadequate, have poor universality, and lack interpretability and consistency; and the evaluation of syndrome differentiation model results is limited and lack credibility. Therefore, the following suggestions are proposed for reference: (1) strengthening data integration and quality control; (2) deeply integrating AI with TCM syndrome differentiation to enhance model interpretability; (3) developing large language models for the subdivisions of TCM; (4) strengthening the construction of intelligent TCM talent teams and encouraging cooperation among experts in multiple fields; and (5) improving international standards and regulations to strengthen international cooperation and exchanges. These efforts aim to provide references for the technological exploration and innovation of AI-assisted TCM diagnosis and treatment.

Keywords

traditional Chinese medicine ; TCM diagnosis ; artificial intelligence ; intelligent syndrome differentiation ; intelligent development of TCM

Figures

图1

图2

References

[ 1 ] 中国人民政治协商会议全国委员会‍. 习近平对中医药工作作出重要指示强调传承精华守正创新为建设健康中国贡献力量李克强作出批示 [EB/OL]. (2019-10-20)‍[2023-10-25]. http://www.cppcc.gov.cn/zxww/2019/10/25/ARTI1571984502832414.shtml.
National Committee of the Chinese People´s Political Consultative Conference. Xi Jinping has made important instructions on the work of traditional Chinese medicine, emphasizing the need to inherit the essence, maintain the right path, and innovate, in order to contribute to the building of a Healthy China. Li Keqiang has given instructions in this regard [EB/OL].(2019-10-20)‍[2023-10-25]. http://www.cppcc.gov.cn/zxww/2019/10/25/ARTI1571984502832414.shtml.

[ 2 ] 薛晓娟, 刘彩, 王益民, 等‍. 新时代中医药发展现状与思考 [J]. 中国工程科学, 2023, 25(5): 11‒20.
Xue X J, Liu C, Wang Y M, et al. Status quo and development strategy of traditional Chinese medicine in the new era [J]. Strategic Study of CAE, 2023, 25(5): 11‒20.

[ 3 ] 国务院办公厅. "十四五"中医药发展规划 [EB/OL]. (2022-03-03)[2024-02-03]. https://www.gov.cn/gongbao/content/2022/content_5686029.htm.
General Office of the State Council of the People´s Republic of China. The 14th Five Year Plan for the development of traditional Chinese medicine [EB/OL]. (2022-03-03)[2024-02-03]. https://www.gov.cn/gongbao/content/2022/content_5686029.htm.

[ 4 ] 国家中医药管理局‍. "十四五"中医药信息化发展规划 [EB/OL].(2022-11-25)[2023-11-25]. https://www.gov.cn/zhengce/zhengceku/202212/06/content_5730292.htm.
State Administration of Traditional Chinese Medicine. The 14th Five Year Plan for the development of traditional Chinese medicine informatization [EB/OL]. (2022-11-25)[2023-11-25]. https://www.gov.cn/zhengce/zhengceku/202212/06/content_5730292.htm.

[ 5 ] 黄明, 杨丰文, 刘耀远, 等. 张伯礼院士谈"中医药发展这十年" [J]. 天津中医药大学学报, 2022, 41(4): 409‒412.
Huang M, Yang F W, Liu Y Y, et al. Academician Zhang Boli talked about "´ten year´ development of traditional Chinese medicine" [J]. Journal of Tianjin University of Traditional Chinese Medicine, 2022, 41(4): 409‒412.

[ 6 ] 董广通, 高琳‍. 论人工智能技术下名老中医诊疗经验传承发展 [J]. 中华中医药杂志, 2023, 38(9): 4026‒4029.
Dong G T, Gao L. Discussion on the inheritance and development of the diagnosis and treatment experience of famous traditional Chinese medicine experts under the artificial intelligence technology [J]. China Journal of Traditional Chinese Medicine and Pharmacy, 2023, 38(9): 4026‒4029.

[ 7 ] Wang Y L, Shi X M, Li L, et al. The impact of artificial intelligence on traditional Chinese medicine [J]. The American Journal of Chinese Medicine, 2021, 49(6): 1297‒1314.

[ 8 ] Zhang H, Ni W D, Li J, et al. Artificial intelligence-based traditional Chinese medicine assistive diagnostic system: Validation study [J]. JMIR Medical Informatics, 2020, 8(6): e17608.

[ 9 ] 李如辉, 王静波, 张卓文, 等‍. 论中医学、中医文化与中国传统文化的关系 [J]. 中华中医药杂志, 2015, 30(6): 1931‒1933.
Li R H, Wang J B, Zhang Z W, et al. Relationship between TCM, TCM culture and traditional Chinese culture [J]. China Journal of Traditional Chinese Medicine and Pharmacy, 2015, 30(6): 1931‒1933.

[10] 孙广仁‍. 中医基础理论 [M]. 北京: 中国中医药出版社, 2002.
Sun G R. Basic theory of traditional Chinese medicine [M]. Beijing: China Traditional Chinese Medicine Press, 2002.

[11] 张华, 刘保延, 田从豁, 等‍. "人机结合、以人为主" 的名老中医经验整理研究方法 [J]. 中医研究, 2007, 20(2): 4‒7.
Zhang H, Liu B Y, Tian C H, et al. The arrangement methods of experience of famous and older TCM physicians [J]. Traditional Chinese Medicinal Research, 2007, 20(2): 4‒7.

[12] 郭振球‍. 中医辨证学研究的前景 [J]. 大自然探索, 1985 (3): 85‒89.
Guo Z Q. The prospects of study on Zheng (syndromes) differentiation science of traditional Chinese medicine [J]. Discovery of Nature, 1985 (3): 85‒89.

[13] 郭振球‍. 论中医诊断学的发展 [J]. 安徽中医学院学报, 1988, 7(3): 2‒5.
Guo Z Q. On the development of TCM diagnostics [J]. Journal of Anhui Traditional Chinese Medical College, 1988, 7(3): 2‒5.

[14] 王忆勤‍. 中医诊断学 [M]. 北京: 中国中医药出版社, 2004.
Wang Y Q. Diagnosis of traditional Chinese medicine [M]. Beijing: China Traditional Chinese Medicine Press, 2004.

[15] 文志华, 肖莉, 刘青萍, 等‍. 中医症状规范化、标准化研究进程及问题探讨 [J]. 湖南中医药大学学报, 2023, 9(12): 2294‒2299.
Wen Z H, Xiao L, Liu Q P, et al. Research progress and discussion of the TCM symptoms normalization and standardization [J]. Journal of Hunan University of Chinese Medicine, 2023, 9(12): 2294‒2299.

[16] 杨小丽, 龚致平, 浦科学, 等‍.人工智能赋能中医临床诊疗的现状、问题和对策 [J]. 重庆医学, 2024, 53(4): 613‒616.
Yang X L, Gong Z P, Pu K X, et al. The current situation, problems, and strategies of empowering traditional Chinese medicine clinical diagnosis and treatment with artificial intelligent [J]. Chongqing Medicine Journal, 2024, 53(4): 613‒616.

[17] 张世祺, 孙宇衡, 咸楠星, 等‍. 中医四诊客观化与智能化研究进展 [J]. 中医药导报, 2023, 29(6): 170‒174.
Zhang S Q, Sun Y H, Xian N X, et al. Research progress on objectification and intellectualization of four diagnostic methods in traditional Chinese medicine [J]. Guiding Journal of Traditional Chinese Medicine and Pharmacy, 2023, 29(6): 170‒174.

[18] Guo Y, Ren X, Chen Y X, et al. Artificial intelligence meets Chinese medicine [J]. Chinese Journal of Integrative Medicine, 2019, 25(9): 648‒653.

[19] 温浩, 吕茂斌, 张伟, 等‍. 基于多模态数据融合的2型糖尿病阴虚证智能诊断方法 [J]. 中华中医药杂志, 2023, 38(11): 5436‒5440.
Wen H, Lyu M B, Zhang W, et al. Intelligent diagnosis method of yin deficiency syndrome of type 2 diabetes mellitus based on multimodal data fusion [J]. China Journal of Traditional Chinese Medicine and Pharmacy, 2023, 38(11): 5436‒5440.

[20] 蔡宇锋‍. 基于深度学习的皮肤癌辅助诊断系统设计与实现 [D]. 北京: 北京邮电大学(硕士学位论文), 2023.
Cai Y F. Design and implementation of skin cancer auxiliary diagnosis system based on deep learning [D]. Beijing : Beijing University of Posts and Telecommunications (Master´s thesis), 2023.

[21] 魏仕青‍. 基于脑电与眼动数据融合的轻度抑郁识别应用研究 [D]. 兰州: 兰州大学(硕士学位论文), 2023.
Wei S Q. Application study of mild depression recognition based on EEG and eye movement data fusion [D]. Lanzhou: Lanzhou University (Master´s thesis), 2023.

[22] 张荣春‍. 多囊卵巢综合征基本证型症状关系分析及关联证候量表构建基础研究 [D]. 济南: 山东中医药大学(硕士学位论文), 2023.
Zhang R C. Analysis of the symptoms relationship of PCOS basic syndrome types and basic study on the construction of associated syndrome scale [D]. Jinan: Shandong University of Traditional Chinese Medicine (Master´s thesis), 2023.

[23] 周惠敏. 基于症状关联规律挖掘的2型糖尿病中医辅助智能问诊模型研究 [D]. 福州: 福建中医药大学(硕士学位论文), 2024.
Zhou H M. Research on TCM auxiliary intelligent inquiry model for T2DM based on symptom association law mining [D]. Fuzhou: Fujian University of Traditional Chinese Medicine (Master´s thesis), 2024.

[24] 李颖, 王月, 郝建军, 等‍. 基于互信息的中医症状推荐系统 [J]. 自动化与信息工程, 2023, 44(5): 52‒57.
Li Y, Wang Y, Hao J J, et al. Chinese medicine symptoms recommendation system based on mutual information [J]. Automation & Information Engineering, 2023, 44(5): 52‒57.

[25] 曹静‍. 基于复杂网络的推荐算法在中医辅助问诊中的应用研究 [D]. 镇江: 江苏大学(硕士学位论文), 2018.
Cao J. Application research on recommendation algorithm based on complex network for traditional Chinese medicine assisted inquiry [D]. Zhenjiang: Jiangsu University (Master´s thesis), 2018.

[26] 朱文锋‍. 证素辨证学 [M]. 北京: 人民卫生出版社, 2008: 89.
Zhu W F. Study of TCM syndrome differentiation [M]. Beijing: People´s Health Publishing House, 2008: 89.

[27] 余江维, 余泉, 张太珍, 等‍. 基于TF-IDF相对熵的中医证候量化研究 [J]. 世界科学技术 ‒ 中医药现代化, 2015, 1(10): 1986‒1991.
Yu J W, Yu Q, Zhang T Z, et al. Quantitative research on traditional Chinese medicine syndrome based on TF-IDF relative entropy [J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2015, 1(10): 1986‒1991.

[28] 章新友, 徐华康, 周小玲, 等‍‍. 改进深度极限学习机在肺癌中医证型分类中的应用研究 [J]. 世界科学技术 ‒ 中医药现代化, 2023, 25(6): 2132‒2139.
Zhang X Y, Xu H K, Zhou X L, et al. Application of improved deep extreme learning machine in the classification of traditional Chinese medicine syndromes of lung cancer [J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2023, 25(6): 2132‒2139.

[29] 熊江辉, 梁峰吉, 常素华‍. 基于DNA甲基化的中医概念与证候量化方法及其在抑郁症和癌症筛查中的应用 [J]. 中国药理学与毒理学杂志, 2023, 9(S1): 37‒38.
Xiong J H, Liang F J, Chang S H. The concept and syndrome quantification method of traditional Chinese medicine based on DNA methylation and its application in depression and cancer screening [J]. Chinese Journal of Pharmacology and Toxicology, 2023, 9(S1): 37‒38.

[30] 陈南杰‍. 基于机器学习的冠心病痰瘀互结证诊断模型构建及其舌象客观量化指标研究 [D]. 北京: 中国中医科学院(硕士学位论文), 2023.
Chen N J. Construction of a Aiagnosis model of coronary heart disease with phlegm and blood stasis syndrome based on machine learning and study on objective quantitative indicators of tongue image [D]. Beijing: China Academy of Chinese Medical Sciences (Master´s thesis), 2023.

[31] 卢恩仕, 韩明光, 刘峰, 等‍. 基于贝叶斯网络分析重症肺炎中医证候规律 [J]. 中医学报, 2022, 37(1): 173‒179.
Lu E S, Han M G, Liu F, et al. Analysis of Chinese medicine syndrome rules of severe pneumonia based on Bayesian network [J]. Acta Chinese Medicine, 2022, 37(1): 173‒179.

[32] 贺鹏飞, 刘聪, 李红典, 等. 运用机器学习构建慢性肾炎中医辨证智能模型及内部验证 [J/OL].辽宁中医药大学学报: 1‒11[2024-03-29]. http://kns.cnki.net/kcms/detail/21.1543.R.20240124.1503.010.html.
He P F, Liu C, Li H D, et al. Construction and internal validation of an intelligent model for the identification of Chinese medicine in chronic glomerulonephritis using machine Learning [J/OL]. Journal of Liaoning University of Traditional Chinese Medicine: 1‒11[2024-03-29]. http://kns.cnki.net/kcms/detail/21.1543.R.20240124.1503.010.html.

[33] 宫文浩, 兰天莹, 杨燕, 等‍. 基于随机森林和偏相关分析的小儿肺炎痰热闭肺证中医证候诊断模型研究 [J]. 中华中医药杂志, 2023, 38(9): 4497‒4501.
Gong W H, Lan T Y, Yang Y, et al. Research on traditional Chinese medicine syndrome diagnosis model of pediatric pneumonia with accumulation of phlegm-heat syndrome based on random forest and partial correlation analysis [J]. China Journal of Traditional Chinese Medicine and Pharmacy, 2023, 38(9): 4497‒4501.

[34] 王麒达‍. 基于多任务网络的中医望诊心脑血管疾病智能化方法研究 [D]. 太原: 太原理工大学(硕士学位论文), 2022.
Wang Q D. Research on intelligent method of TCM diagnosis of cardiovascular and cerebrovascular diseases based on multi-task network [D]. Taiyuan: Taiyuan University of Technology (Master´s thesis), 2022.

[35] 李洪峥, 王阶, 郭雨晨, 等‍. 基于改良Transformer算法的冠心病证候要素诊断处方模型分析 [J]. 中国实验方剂学杂志, 2023, 9(1): 148‒154.
Li H Z, Wang J, Guo Y C, et al. Research on diagnosis and prescription system of coronary heart disease with syndrome elements based on improved transformer algorithm [J]. Chinese Journal of Experimental Traditional Medical Formulae, 2023, 9(1): 148‒154.

[36] 刘勇‍. 基于深度学习的多标签分类在中医哮喘辅助诊断的应用研究 [D]. 南昌: 江西中医药大学(硕士学位论文), 2023.
Liu Y. Research on the application of multi-label classification based on deep learning in the auxiliary diagnosis of asthma in TCM [D]. Nanchang: Jiangxi University of Traditional Chinese Medicine (Master´s thesis), 2023.

[37] Yuan H Y, Yu S. Efficient symptom inquiring and diagnosis via adaptive alignment of reinforcement learning and classification [J]. Artificial Intelligence in Medicine, 2024, 148: 102748.

[38] 陈诗琪‍. 基于多标签学习的中医辨证分析研究 [D]. 南京: 南京邮电大学(硕士学位论文), 2023.
Chen S Q. Study on TCM syndrome differentiation based on multi-label learning [D]. Nanjing: Nanjing University of Posts and Telecommunications (Master´s thesis), 2023.

[39] 刘茂‍. 基于知识图谱的中医问诊系统 [D]. 重庆: 西南大学(硕士学位论文), 2023.
Liu M. Traditional Chinese medicine consultation system based on knowledge graph [D]. Chongqing: Southwest University (Master´s thesis), 2023.

[40] 张鹤译, 王鑫, 韩立帆, 等‍. 大语言模型融合知识图谱的问答系统研究 [J]. 计算机科学与探索, 2023, 17(10): 2377‒2388.
Zhang H Y, Wang X, Han L F, et al. Research on question answering system on joint of knowledge graph and large language models [J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(10): 2377‒2388.

[41] Xu T Y, Guo C, Du L X, et al. A method for traditional Chinese medicine knowledge graph dynamic construction [R]. Qingdao: The 5th International Conference on Big Data Technologies, 2022.

[42] Ye Q, Yang R, Cheng C L, et al. Combining the external medical knowledge graph embedding to improve the performance of syndrome differentiation model [J]. Evidence-Based Complementary and Alternative Medicine: ECAM, 2023, 2023: 2088698.

[43] Zhang Q C, Bai C C, Chen Z K, et al. Deep learning models for diagnosing spleen and stomach diseases in smart Chinese medicine with cloud computing [J]. Concurrency and Computation: Practice and Experience, 2021, 33(7): 1.

[44] Zhang Y J, Bai R J, Han J, et al. Research on TCM diabetes assisted diagnosis and treatment plan integrating association mining and quantitative calculation [J]. Procedia Computer Science, 2021, 188: 52‒60.

[45] 王瑞, 潘志强, 陈杰, 等‍. 面向智能诊断探讨中医证素知识框架体系的构建 [J]. 中医杂志, 2024, 65(4): 341‒346.
Wang R, Pan Z Q, Chen J, et al. Establishment of TCM syndrome elements knowledge framework system for intelligent diagnosis [J]. Journal of Traditional Chinese Medicine, 2024, 65(4): 341‒346.

[46] 张婷婷, 王亚强, 蒋艺宁, 等‍. 构建中医辨证解释体系的挑战与思路 [J]. 中医杂志, 2024, 65(5): 445‒448, 454.
Zhang T T, Wang Y Q, Jiang Y N, et al. Challenges and ideas in constructing an interpretative system for syndrome differentiation in traditional Chinese medicine [J]. Journal of Traditional Chinese Medicine, 2024, 65(5): 445‒448, 454.

[47] 文志华, 夏帅帅, 刘东波, 等‍. 中医智能辨证诊断技术的演进与问题探讨 [J]. 世界科学技术 ‒ 中医药现代化, 2021, 23(11): 4298‒4304.
Wen Z H, Xia S S, Liu D B, et al. Discussion on the evolution and problems of intelligent syndrome differentiation diagnosis technology in traditional Chinese medicine [J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2021, 23(11): 4298‒4304.

[48] 朱文锋‍. 制定全病域中医辨证量表的设计思路 [J]. 辽宁中医杂志, 2005, 32(6): 521‒522.
Zhu W F. Design idea of making TCM syndrome differentiation scale for the whole disease area [J]. Liaoning Journal of Traditional Chinese Medicine, 2005, 32(6): 521‒522.

[49] 孙肇阳, 吕桂娇, 郭义, 等‍. 中医诊疗复杂巨系统的人工神经网络建模原理 [J]. 中华中医药杂志, 2022, 37(10): 5841‒5844.
Sun Z Y, Lyu G J, Guo Y, et al. Modeling principle of artificial neural network for complex giant system of traditional Chinese medicine diagnosis and treatment [J]. China Journal of Traditional Chinese Medicine and Pharmacy, 2022, 37(10): 5841‒5844.

Related Research