AUTHOR=Zhao Xiaoliang , Wang Yifei , Li Penghui , Xu Julia , Sun Yao , Qiu Moyan , Pang Guoming , Wen Tiancai 

TITLE=The construction of a TCM knowledge graph and application of potential knowledge discovery in diabetic kidney disease by integrating diagnosis and treatment guidelines and real-world clinical data

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2023.1147677

DOI=10.3389/fphar.2023.1147677

ISSN=1663-9812

ABSTRACT=Background: The complexity of diabetic kidney disease and the rapid progression of lesions bring significant challenges to clinical diagnosis and treatment. The advantages of Traditional Chinese Medicine (TCM) diagnosis and treatment have gradually become obvious. However, due to the complexity of the disease and the individualized diagnosis and treatment methods of TCM, TCM guidelines are limited in guiding diabetic kidney disease treatment. Most of the existing medical knowledge is stored in the process of recording medical records, which limits the understanding of diseases and the acquisition of diagnosis and treatment knowledge by young doctors. Therefore, there is a lack of sufficient clinical knowledge to support the diagnosis and treatment of diabetic kidney disease in TCM. Objective. To construct a knowledge graph of TCM diagnosis and treatment for diabetic kidney disease based on clinical guidelines, consensus, and real-world clinical data. On this basis, the knowledge of TCM diagnosis and treatment of diabetic kidney disease was systematically combed and mined. Methods. Normative guideline data and actual medical records were used to construct a knowledge graph of TCM diagnosis and treatment for diabetic kidney disease. And the results obtained by data mining techniques enrich the relational attributes. Neo4j graph database was used for knowledge storage, visual knowledge display, and semantic query. The multi-dimensional relations with hierarchical weights are used as the center to carry out reverse retrieval verification on the critical problems of diagnosis and treatment put forward by experts. Results. 903 nodes and 1670 relationships were constructed under nine concepts and 20 relationships. Preliminarily a knowledge graph for TCM diagnosis and treatment of diabetic kidney disease was constructed. Based on multi-dimensional relationships, the diagnosis and treatment questions proposed by experts were reversely verified through multi-hop queries of the graphs. Confirmed by experts with good results. Conclusion. This study systematically combed the TCM diagnosis and treatment knowledge of diabetic kidney disease by constructing the knowledge graph, and in addition, solved the problem of "knowledge island". Through visual display and semantic retrieval, the discovery and sharing of diagnosis and treatment knowledge of diabetic kidney disease were realized.