Electronic medical record retrieval method and device based on graph neural network

Abstract

The invention discloses an electronic medical record retrieval method based on a graph neural network, and the method comprises the steps: obtaining a co-occurrence matrix of medical entities in an electronic medical record, adding the co-occurrence information of the medical entities and ancestor medical entities into the medical entity co-occurrence matrix, and obtaining an enhanced medical entity co-occurrence matrix, extracting each medical entity vector representation and patient vector representation by adopting a GloVe model, wherein the electronic medical record heterogeneous graph comprises medical entity nodes, patient nodes, a real link relationship between medical entities and a real link relationship between patients and medical entities; inputting the electronic medical record heterogeneous graph into a graph neural network to respectively obtain a patient node output vector representation, a medical entity node output vector representation and a patient and medical entity link relation probability; the probability of the link relation between the medical entities; training the graph neural network by using the total loss function, and updating parameters to obtain a final graph neural network; the method can prepare to predict a probability of association of a patient with a medical entity.

Description

technical field [0001] The invention relates to the technical field of medical information data processing, in particular to a method and device for retrieving electronic medical records based on a graph neural network. Background technique [0002] Medical practice is a data-driven activity that requires constant access to patient information for analysis and decision-making. As one of the main information sources at present, electronic medical records contain rich information. It is of great significance to use this information to support medical activities such as clinical decision support, clinical research and clinical trials. Data is efficiently queried. In the query tasks carried out by personnel in the medical field, the lack of support from information technicians makes them only rely on their own knowledge to complete the query expression, which makes the process of query tasks full of challenges, and requires a lot of browsing and exploration to find the target i...

AI Technical Summary

Problems solved by technology

However, this kind of method relies too much on the general medical knowledge ontology, and it is easy to ignore the associated information in the electronic medical record; in addition, the entities in the electronic medical record that do not appear in the medical knowledge ontology cannot be expanded, which limits the scope of use of this kind of method

Images