Figure 1 - available via license: Creative Commons Attribution-NonCommercial 4.0 International
Content may be subject to copyright.
Context in source publication
Context 1
... this paper, a process for text information normalization of EMR of TCM is constructed, as shown in Figure 1. The whole process is divided into the following four stages: (1) data acquisition: obtaining data from the EMR of TCM, then determining the entity types to be recognized, constructing the corresponding entity corpus, and finally selecting the recognition model for the entity extraction stage; (2) event extraction: extracting the treatment events from the medical history text according to the trigger words; (3) entity extraction: add the constructed corpus of entities such as symptoms, diseases, institutions, departments, time, drug treatment, non-drug treatment, surgery names, and tests, etc., and use the selected entity recognition model to recognize and extract the entities from various texts of EMR of TCM; (4) data storage: store the extracted entities in the database. ...