EUVIMEDObjevte EUVIMED
Open access

Research on Traditional Chinese Medicine: Domain Knowledge Graph Completion and Quality Evaluation

Chang Liu iD, Zhan Li iD, Jianmin Li iD, Yiqian Qu iD, Ying Chang iD, Qing Han iD, Lingyong Cao iD, Shuyuan Lin iD

JMIR Medical Informatics · 2024-08-02 · 12 · e55090

DOI: 10.2196/55090 ↗

At a glance

Journal article in JMIR Medical Informatics, published online on 2024-08-02. Written by Chang Liu and 7 co-authors. Institution: School of Basic Medical Sciences, Zhejiang Chinese Medical University, Hangzhou, China. Cited 18 times so far (Crossref); 55 references. The full text is freely available in PubMed Central.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Knowledge graphs (KGs) can integrate domain knowledge into a traditional Chinese medicine (TCM) intelligent syndrome differentiation model. However, the quality of current KGs in the TCM domain varies greatly, related to the lack of knowledge graph completion (KGC) and evaluation methods.

Objective

This study aims to investigate KGC and evaluation methods tailored for TCM domain knowledge.

Methods

In the KGC phase, according to the characteristics of TCM domain knowledge, we proposed a 3-step “entity-ontology-path” completion approach. This approach uses path reasoning, ontology rule reasoning, and association rules. In the KGC quality evaluation phase, we proposed a 3-dimensional evaluation framework that encompasses completeness, accuracy, and usability, using quantitative metrics such as complex network analysis, ontology reasoning, and graph representation. Furthermore, we compared the impact of different graph representation models on KG usability.

Results

In the KGC phase, 52, 107, 27, and 479 triples were added by outlier analysis, rule-based reasoning, association rules, and path-based reasoning, respectively. In addition, rule-based reasoning identified 14 contradictory triples. In the KGC quality evaluation phase, in terms of completeness, KG had higher density and lower sparsity after completion, and there were no contradictory rules within the KG. In terms of accuracy, KG after completion was more consistent with prior knowledge. In terms of usability, the mean reciprocal ranking, mean rank, and hit rate of the first N tail entities predicted by the model (Hits@N) of the TransE, RotatE, DistMult, and ComplEx graph representation models all showed improvement after KGC. Among them, the RotatE model achieved the best representation.

Conclusions

The 3-step completion approach can effectively improve the completeness, accuracy, and availability of KGs, and the 3-dimensional evaluation framework can be used for comprehensive KGC evaluation. In the TCM field, the RotatE model performed better at KG representation.

Subjects

Author keywords

graph completiongraph quality evaluationgraph representationknowledge graphtraditional Chinese medicine

Authors and institutions

  • School of Basic Medical Sciences, Zhejiang Chinese Medical University, Hangzhou, China.
  • Breast Disease Specialist Hospital of Guangdong Provincial Hospital of Chinese Medicine, Guangdong Provincial Hospital of Chinese Medicine, Guangzhou, China.
  • Zhejiang Chinese Medical University and Gancao Doctor Chinese Medicine Artificial Intelligence Joint Engineering Center, Zhejiang Chinese Medical University, Hangzhou, China.
  • School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, China.

ORCID profiles: Chang Liu, Zhan Li, Jianmin Li, Yiqian Qu, Ying Chang, Qing Han, Lingyong Cao, Shuyuan Lin

Cite

APA

Liu, C., Li, Z., Li, J., Qu, Y., Chang, Y., Han, Q., Cao, L., & Lin, S. (2024). Research on Traditional Chinese Medicine: Domain Knowledge Graph Completion and Quality Evaluation. JMIR Medical Informatics, 12, e55090. https://doi.org/10.2196/55090

Vancouver

Liu C, Li Z, Li J, Qu Y, Chang Y, Han Q, et al. Research on Traditional Chinese Medicine: Domain Knowledge Graph Completion and Quality Evaluation. JMIR Medical Informatics. 2024;12:e55090. doi:10.2196/55090

BibTeX
@article{Liu2024,
  author = {Liu, Chang and Li, Zhan and Li, Jianmin and Qu, Yiqian and Chang, Ying and Han, Qing and Cao, Lingyong and Lin, Shuyuan},
  title = {Research on Traditional Chinese Medicine: Domain Knowledge Graph Completion and Quality Evaluation},
  journal = {JMIR Medical Informatics},
  year = {2024},
  volume = {12},
  pages = {e55090},
  doi = {10.2196/55090}
}
Start for free →