JMIR Publications

ABSTRACT

Background:

With the increasing incidences and mortality of digestive system tumor diseases in China, how to use the clinical experience in Chinese Electronic Medical Records (CEMRs) to excavate the potential effective relationships between diagnosis and treatment has become an urgent problem. As an important part of artificial intelligence, knowledge graph is a powerful tool for information processing and knowledge organization, which provides an ideal means to solve this problem.

Objective:

This study aimed to construct a semantic-driven digestive system tumor knowledge graph (DSTKG) to represent the knowledge in CEMRs with fine granularity and semantics.

Methods:

This paper focused on the knowledge graph schema and semantic relationships which were the main problems of constructing Chinese tumor knowledge graph. The DSTKG was developed through a multistep procedure. As an initial step, a complete DSTKG construction framework based on CEMRs was proposed. Then this research built a knowledge graph schema containing seven classes of concepts and sixteen kinds of semantic relationships, and accomplished the DSTKG by knowledge extraction, named entity linking and knowledge graph drawing. Finally, the quality of DSTKG was evaluated from three aspects: data, schema and application layer.

Results:

Experts were agreed that the DSTKG was good on the whole (average score= 4.20). Especially in the aspects of "rationality of schema structure", “scalability” and "readability of results", the DSTKG performed well with scores of 4.72, 4.67 and 4.69 respectively, which were much higher than the average. However, the small amount of data in DSTKG has a bad effect on its score of "practicability". Compared with other Chinese tumor knowledge graphs, DSTKG can represent more fine-grained entities, properties and semantic relationships. In addition, DSTKG was flexible, allowing personalized customization to meet the designer's focus on specific interests in the digestive system tumor.

Conclusions:

We constructed a fine-grained semantic digestive system tumor knowledge graph. It would provide guidance for the construction of tumor knowledge graph and take a preliminary step for the intelligent application of knowledge graph based on CEMRs. This study needs to further increase the data sources and strengthen the research on assertion classification in order to gain insight into the DSTKG’s entire potential.