EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Ziling Zeng, Lin Tong, Bing Li, Wenjing Zong, Qikai Niu, Sihong Liu, Lei Zhang, Jialun Wang, Siqi Zhang, Siwei Tian, Jing'ai Wang, Wei Zhang und 1 weitere

Methods of Information in Medicine · 01.12.2024 · 63 (05/06) · 183-194

DOI: 10.1055/a-2590-6348 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Methods of Information in Medicine, erschienen am 01.12.2024. Verfasst von Ziling Zeng und 12 weiteren Autor:innen. Beteiligte Einrichtung: Materia Medica Research Center, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing, People's Republic of China. Hauptthemen laut MEDLINE: Medicine, Chinese Traditional, Books. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Medicine, Chinese TraditionalBooksHumansYin DeficiencySyndrome

Autor:innen und Institutionen

  • Materia Medica Research Center, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing, People's Republic of China.
  • The Ancient Book Resources Research Office, Institute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing, People's Republic of China.
  • Materia Medica Digital Intelligence Center, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing, People&s Republic of China.
  • Integrated Research Center for Chinese Materia Medica, Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing, People's Republic of China.
  • Department of Special Collections Research and Development, Institute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing, People's Republic of China.
  • Institute of Basic Theory for Chinese Medicine, China Academy of Chinese Medicine Science, Beijing, People's Republic of China.

Förderung

  • National Key R&D Program of China

Zitieren

APA

Zeng, Z., Tong, L., Li, B., Zong, W., Niu, Q., Liu, S., Zhang, L., Wang, J., Zhang, S., Tian, S., Wang, J., Zhang, W., & Zhang, H. (2024). TCMSF: A Construction Framework of Traditional Chinese Medicine Syndrome Ancient Book Knowledge Graph. Methods of Information in Medicine, 63(05/06), 183-194. https://doi.org/10.1055/a-2590-6348

Vancouver

Zeng Z, Tong L, Li B, Zong W, Niu Q, Liu S, et al. TCMSF: A Construction Framework of Traditional Chinese Medicine Syndrome Ancient Book Knowledge Graph. Methods of Information in Medicine. 2024;63(05/06):183-194. doi:10.1055/a-2590-6348

BibTeX
@article{Zeng2024,
  author = {Zeng, Ziling and Tong, Lin and Li, Bing and Zong, Wenjing and Niu, Qikai and Liu, Sihong and Zhang, Lei and Wang, Jialun and Zhang, Siqi and Tian, Siwei and Wang, Jing'ai and Zhang, Wei and Zhang, Huamin},
  title = {TCMSF: A Construction Framework of Traditional Chinese Medicine Syndrome Ancient Book Knowledge Graph},
  journal = {Methods of Information in Medicine},
  year = {2024},
  volume = {63},
  number = {05/06},
  pages = {183--194},
  doi = {10.1055/a-2590-6348}
}
Kostenlos starten →