Combining the External Medical Knowledge Graph Embedding to Improve the Performance of Syndrome Differentiation Model

Abstract

The electronic medical records (EMRs) of traditional Chinese medicine (TCM) include a wealth of TCM knowledge and syndrome diagnosis information, which is crucial for improving the quality of TCM auxiliary decision-making. In practical diagnosis, one disease corresponds to one syndrome, posing considerable hurdles for the informatization of TCM. The purpose of this work was to create an end-to-end TCM diagnostic model, and the knowledge graph (KG) created in this article is used to improve the model’s information and realize auxiliary decision-making for TCM disorders. We approached auxiliary decision-making for syndrome differentiation in this article as a multilabel classification task and presented a knowledge-based decision support model for syndrome differentiation (KDSD). Specifically, we created a KG based on TCM features (TCMKG), supplementing the textual representation of medical data with embedded information. Finally, we proposed fusing medical text with KG entity representation (F-MT-KER) to get prediction results using a linear output layer. After obtaining the vector representation of the medical record text using the BERT model, the vector representation of various KG embedded models can provide additional hidden information to a certain extent. Experimental results show that our method improves by 1% (P@1) on the syndrome differentiation auxiliary decision task compared to the baseline model BERT. The usage of EMRs can aid TCM development more efficiently. With the help of entity level representation, character level representation, and model fusion, the multilabel classification method based on the pretraining model and KG can better simulate the TCM syndrome differentiation of the complex cases.