TCMSF: A Construction Framework of Traditional Chinese Medicine Syndrome Ancient Book Knowledge Graph

Abstract

Background

Syndrome is a unique and crucial concept in traditional Chinese medicine (TCM). However, much of the syndrome knowledge lacks systematic organization and correlation, and current information technologies are unsuitable for TCM ancient texts.

Objectives

We aimed to develop a knowledge graph that presents this knowledge in a more orderly, structured, and semantically oriented manner, providing a foundation for computer-aided diagnosis and treatment.

Methods

We developed a construction framework of TCM syndrome knowledge from ancient books, using a pretrained model and rules (TCMSF). We conducted fine-tuning training on Enhanced Representation through Knowledge Integration (ERNIE), Bidirectional Encoder Representation from Transformers pretrained language models, and chatGLM3–6b large language models for named entity recognition (NER) tasks. Furthermore, we employed the progressive entity relationship extraction method based on the dual pattern feature combination to extract and standardize entities and relationships between entities in these books.

Results

We selected Yin deficiency syndrome as a case study and constructed a model layer suitable for the expression of knowledge in these books. Compared with multiple NER methods, the combination of ERNIE and Conditional Random Fields performs the best. By utilizing this combination, we completed the entity extraction of Yin deficiency syndrome, achieving an average F1 value of 0.77. The relationship extraction method we proposed reduces the number of incorrectly connected relationships compared with fully connected pattern layers. We successfully constructed a knowledge graph of ancient books on Yin deficiency syndrome, including over 120,000 entities and over 1.18 million relationships.

Conclusion

We developed TCMSF in line with the knowledge characteristics of ancient TCM books and improved the accuracy of knowledge graph construction.

Keywords

TCM - knowledge organization - knowledge graph - ancient book - relationship extraction

• References

• 1 Guo MY, Zhou L, Sun Y. The application of “domain ontology seven step method” in the construction of traditional Chinese medicine syndrome differentiation and reasoning knowledge base world science and technology. Modern Trad Chin Med 2019; 12: 2646-2651
• 2 Zhou H, Peng FL, Wei CF. [Research and practice on the construction of a knowledge graph for diagnosis and differentiation of traditional Chinese medicine]. Journal of Medical Informatics 2020; 12: 41-44
• 3 Zhang MZ, Yang ZG, Liu C, Fang L. Traditional Chinese medicine knowledge service based on semi-supervised BERT-BiLSTM-CRF Model. 2020 International Conference on Service Science (ICSS), Xining, China. 2020: 64-69
• 4 Sun Y, Zhao Z, Wang Z. et al. Leveraging a joint learning model to extract mixture symptom mentions from traditional Chinese medicine clinical notes. BioMed Res Int 2022; 2022: 2146236
• 5 Chen K, Wang W, Cai J. TRBNER: named entity recognition of TCM medical records based on multi-feature fusion. IET Conf Proc 2025; 2024 (21) 174-181
• 6 Jiang M, Sanger T, Liu X. Combining contextualized embeddings and prior knowledge for clinical named entity recognition: evaluation study. JMIR Med Inform 2019; 7 (04) e14850
• 7 Bao ZS, Song BY, Zhang WB. [Named entity recognition in traditional Chinese medicine books combining semi-supervised learning and rule-based approach.]. J Chinese Information Processing 2022; 6: 90-100
• 8 Song Z, Xu W, Liu Z, Chen L, Su H. A BERT-based named entity recognition method of warm disease in traditional Chinese medicine. In: 2023 IEEE 18th Conference on Industrial Electronics and Applications (ICIEA) Ningbo, China: IEEE; 2023: 1226-1231
• 9 Zhang W, Wu Z, Song G, Huo Q, Wang B. [named entity recognition of traditional Chinese medicine classics based on SiKuBERT and multivariate data embedding]. J South China Univ Technol Nat Sci Ed 2024; 52 (06) 128-137
• 10 Tuo MM, Yang WZ. Review of entity relation extraction. J Intell Fuzzy Syst 2023; 44 (05) 7391-7405
• 11 Wang XT, Miao F, Liu HX, Zhang GT, Jin LB. Joint extraction of entities and relations from ancient Chinese medical literature. International Conference on Culture-Oriented Science & Technology (ICCST). 2021: 369-372
• 12 Jiang S, Li Z, Zhao H, Ding W. Entity-relation extraction as full shallow semantic dependency parsing. IEEE/ACM Trans Audio Speech Lang Process 2024; 32: 1088-1099
• 13 Zhang T, Huang Z, Wang Y, Wen C, Peng Y, Ye Y. Information extraction from the text data on Traditional Chinese Medicine: a review on tasks, challenges, and methods from 2010 to 2021. Evid Based Complement Alternat Med 2022; 2022: 1679589
• 14 Liu W, Yin M, Zhang J, Cui L. A joint entity relation extraction model based on relation semantic template automatlyical constructed. Comput Mater Continua 2024; 78 (01) 975-997
• 15 Hu J, Tang B, Lyu N, He Y, Xiong Y. CMBEE: a constraint-based multi-task learning framework for biomedical event extraction. J Biomed Inform 2024; 150: 104599