Method, model and system for constructing nephropathy specialized medical knowledge graph

A technology of medical knowledge and nephropathy, applied in the field of knowledge display, can solve the problems of no specialized medical knowledge map of nephropathy, long treatment cycle, long course of disease, etc.

Inactive Publication Date: 2020-08-14
SHENTAIWANG HEALTHCARE TECH NANJING CO LTD
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Although there are many studies on the structure of medical knowledge, there is still no complete medical knowledge map of nephrology. Due to the long course of disease, poor prognosis and long treatment cycle of most kidney diseases, a complete medical knowledge map of nephrology is urgently needed to show nephropathy. Big data facilitates medical diagnosis

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
  • Method, model and system for constructing nephropathy specialized medical knowledge graph
  • Method, model and system for constructing nephropathy specialized medical knowledge graph
  • Method, model and system for constructing nephropathy specialized medical knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] Embodiment 1: as figure 1 As shown, a method for constructing a nephrology specialist medical knowledge graph includes the following steps:

[0070] S1, collecting electronic medical record corpus;

[0071] Export the electronic medical records of the hospital's nephrology department, and the electronic medical records are in the form of TXT text. Manually export the electronic medical records of the nephrology department of the hospital, select the TXT text format, export the electronic medical records of each patient, and obtain many electronic medical records in the TXT text format. At present, each hospital has a hospital electronic medical record system, which belongs to the prior art, and the electronic medical record data involved in the present invention comes from cooperative hospitals.

[0072] Further, the electronic medical records cover dozens of patients with chronic kidney diseases, such as primary glomerular disease, metabolic disease-related kidney da...

Embodiment 2

[0124] The present invention also proposes a model for automatically identifying named entities, entity relationships, and locations of nephropathy, and selects BiLSTM long-term short-term memory neural network and CRF conditional random field as the BIO labeling model; BiLSTM long-term short-term memory neural network includes data input terminal B1 and result The output terminal B2, the CRF conditional random field includes the data input terminal C1 and the result output terminal C2, and the result output terminal B2 of the BiLSTM long-term short-term memory neural network is used as the data input terminal C1 of the CRF conditional random field, thereby establishing a BIO labeling model.

Embodiment 3

[0126] The present invention also proposes a nephrology medical knowledge map generation tool, which uses the method of the present invention to construct a nephrology specialist medical knowledge map to name entities, entity relationships, and entity location information, standardize entities, and generate knowledge maps.

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 BIO annotation model trained by the method can automatically extract entities and relationships in the nephropathy specialized electronic medical record in batches, and can automatically identifymedical named entities such as nephropathy, symptoms, examination and medical treatment in case data in batches. Kidney disease medical big data information is displayed in a kidney disease specialized medical knowledge graph mode, support can be provided for kidney disease specialized clinical intelligent support, evidence-based medical research, disease monitoring and the like, and then the medical service quality is improved.

Description

technical field [0001] The present invention relates to the field of knowledge display, in particular to a method, model and system for constructing a nephrology specialist medical knowledge map. Background technique [0002] Chinese medical text named entity recognition research methods can be roughly divided into rule-based and dictionary-based methods, and machine learning-based methods. The method based on rules and dictionaries is the earliest method used in named entity recognition. Most of these methods use linguistic experts to manually construct rule templates, and match patterns and strings as the main means. Most of these systems rely on knowledge bases and dictionaries. Establish. [0003] The research method of named entity recognition in Chinese medical text involves two important tasks: named entity recognition and named entity relationship extraction. Considering the named entity recognition task as a classification problem of entity boundaries and entity t...

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
IPC IPC(8): G06F16/36G06F40/295G06N3/04G16H50/70G16H10/60
CPCG06F16/367G06F40/295G16H50/70G16H10/60G06N3/044G06N3/045
Inventor 黎海源
Owner SHENTAIWANG HEALTHCARE TECH NANJING CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap