A method and system for searching similar medical records based on deep learning

A technology of deep learning and medical records, which is applied in the field of search methods and systems for similar medical records based on deep learning, can solve problems affecting retrieval efficiency, difficulty in obtaining medical information from word embedding vectors, incomplete similarity retrieval results, etc., to improve clinical Determine and improve the effectiveness of the formulation process

Active Publication Date: 2021-07-09
SHANDONG UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This is because there are a lot of medical terminology, and it is difficult to learn medical information from ordinary word embedding vectors
This leads to incomplete and inaccurate similarity retrieval results, affecting retrieval efficiency

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and system for searching similar medical records based on deep learning
  • A method and system for searching similar medical records based on deep learning
  • A method and system for searching similar medical records based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Whether it is based on feature engineering or deep learning, prior knowledge is rarely used in existing research work, and prior knowledge is of great help to computers to better understand the semantics of sentences, especially in specific In the medical field, the use of knowledge graphs in professional fields is of great help in calculating the similarity of medical texts.

[0032] Based on this, in one or more implementations, a method for searching similar medical records based on deep learning is disclosed, such as figure 1 shown, including the following steps:

[0033] Step (1): Construct a knowledge graph in the medical field through the knowledge graph construction technology, where the entities in the knowledge graph represent medical concepts, and the edges in the knowledge graph represent the relationship between medical concepts. Store the constructed knowledge graph in Neo4j for later use.

[0034] Specifically, the following processes are included:

[...

Embodiment 2

[0069] In one or more implementations, a similar medical record search system based on deep learning is disclosed, including:

[0070] means for building knowledge graphs capable of representing relationships between medical concepts;

[0071] A device for extracting the subject of the medical record sample information as characteristic information of the medical record after preprocessing the obtained medical record sample information, and storing it in a database;

[0072] A device for extracting medical record feature information from the input electronic medical record information; obtaining a subgraph vector containing medical common sense related to the electronic medical record in the knowledge graph;

[0073] It is used to input the characteristic information of the current medical record, the subgraph vector and the characteristic information of the medical record in the medical record information sample database into the trained neural network model, and calculate th...

Embodiment 3

[0076] In one or more embodiments, a terminal device is disclosed, including a server, the server includes a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor executes the The program realizes the search method for similar medical records based on deep learning in the first embodiment. For the sake of brevity, details are not repeated here.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method and system for searching similar medical records based on deep learning, including: constructing a knowledge map; extracting the subject of medical record sample information as characteristic information of the medical record, and storing it in a database; extracting the characteristics of the medical record from the input electronic medical record information information; obtain the subgraph vector containing medical common sense related to the electronic medical record in the knowledge map; input the characteristic information of the current medical record, the subgraph vector and the characteristic information of the medical record in the medical record information sample database to the trained neural network In the model, calculate the similarity between the current medical record and each medical record in the database; output a set number of similar cases according to the similarity. Beneficial effects of the present invention: use the siamese-transformer deep learning neural network model enhanced by the knowledge map in the medical field to automatically extract the characteristics of the medical records, map the medical records to the same vector space, and use the similarity calculation in this space to calculate the similarity between the two medical records Spend.

Description

technical field [0001] The invention relates to the technical field of searching for similar cases, in particular to a method and system for searching similar medical records based on deep learning. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] More and more researchers are beginning to use technologies in the field of Natural Language Processing (NLP) to solve problems in the medical field. In the field of NLP, text similarity is a relatively basic problem. At present, there are still difficulties in calculating the similarity between texts. Because the similarity between two sentences is measured through the semantic level, and semantics belongs to the cognitive level, which brings great difficulty to the research. Because the current connectionism can only solve semantic representation and cannot learn logical reasoning. Secondly, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G16H50/70G06F16/36G06N3/08
CPCG06N3/08G16H50/70G06F16/367
Inventor 崔立真姜涛鹿旭东郭伟
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products