Disease prediction method and related equipment based on dynamic graph and medical knowledge graph

Abstract

The embodiment of the present invention relates to the field of medical technology, and discloses a disease prediction method and related equipment based on dynamic graphs and medical knowledge graphs. The method includes: obtaining a graph structure corresponding to the medical knowledge graph of historical diagnosis and treatment data in sample medical data, And determine the initial knowledge representation vector and initial state representation vector of each node in the graph structure; update the knowledge representation vector and state representation vector of each node according to the historical diagnosis and treatment data; input the knowledge representation vector and state representation vector of each node The multi-layer perceptron model is used to obtain the outcome data of each user, and the multi-layer perceptron model is trained according to the outcome data to obtain a disease prediction model; the target medical data of the user to be tested is input into the disease prediction model, and the next visit of the user to be tested is obtained. For predicting outcome data, dynamic graph technology is used to improve the accuracy of disease prediction results. The present invention relates to block chain technology, and the above-mentioned predicted outcome data can be stored in the block chain.

Description

technical field [0001] The invention relates to the field of medical technology, in particular to a disease prediction method and related equipment based on dynamic graphs and medical knowledge graphs. Background technique [0002] Disease prediction is to infer the risk of future diseases or clinical events based on the user's historical information. In order to solve the problem that data-driven disease prediction methods are easily affected by limited data volume and large data deviation, many works try to integrate medical knowledge maps into the disease prediction process. , to improve prediction accuracy and consistency with existing medical knowledge. [0003] At present, some methods try to introduce knowledge graphs into deep learning models to deal with the impact of insufficient medical data and data deviation. Since the knowledge graph is a static graph, and the user's historical information is dynamically updated, it is often difficult for existing knowledge gr...

AI Technical Summary

Problems solved by technology

Since the knowledge graph is a static graph, and the user's historical information is dynamically updated, it is often difficult for existing disease prediction methods based on knowledge graphs to consider the timing of historical information, thereby affecting prediction performance.

Images