Chinese electronic medical record named entity extraction method and system

A technology of named entities and electronic medical records, which is applied in the fields of electronic digital data processing, instruments, calculations, etc., can solve the problems that there is no method and system for optimizing medical named entity recognition and extraction of rare disease electronic medical records, and achieve improved case structure Efficiency, no manual consumption, good recognition effect

Active Publication Date: 2021-07-13
TSINGHUA UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there is no method and system for medical named entity recognition and extraction specially optimized for rare disease electronic medical records

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
  • Chinese electronic medical record named entity extraction method and system
  • Chinese electronic medical record named entity extraction method and system
  • Chinese electronic medical record named entity extraction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention:

[0073] figure 1 Schematically shows the flow of the Chinese electronic medical record named entity extraction method of the present invention, figure 2 Shows the structure of the named entity extraction system in the present invention, the system implements as figure 1 process shown. like figure 2 The shown (Chinese electronic medical records) named entity extraction system includes: an initialization unit 10, an adaptive unit 20, and a decoding unit 30, wherein the adaptive unit 20 includes: an LSTM processing module 21, a grid coding module 22, and a weight analysis module twenty three. In the present invention, each step of the method is implemented by executing a computer program through the processor of the terminal device, that is, the functions of each ...

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 extracting named entities from Chinese electronic medical records. The method includes: mapping each word in the input sentence to a vector through the character embedding layer; using the LSTM model to input the character sequence to obtain the hidden representation vector; taking each word as the last word of the semantic unit ending with the word , perform semantic segmentation to obtain all the grid codes corresponding to the word; linearly combine all the grid codes of each word to obtain the final vector of each character, where the weight in the linear combination is given by the self-attention mechanism output; use the deep residual network as the output decoding layer to decode the named entity chain. The method and system for extracting named entities from Chinese electronic medical records of the present invention can automatically extract various medical named entities from Chinese electronic medical records, improve the extraction efficiency, and avoid manual consumption in the process of structuring medical records.

Description

technical field [0001] The invention belongs to the technical field of medical text data mining, in particular to a method and system for extracting named entities from Chinese electronic medical records, especially for the identification and extraction of medical named entities in Chinese electronic medical records for a rare disease called multiple system atrophy . Background technique [0002] On the one hand, in recent years, hospitals at all levels in my country have gradually adopted electronic medical record management systems to replace traditional handwritten medical records, thus accumulating more and more electronic medical records. In conventional electronic medical records, the main carrier of information is natural language, such as imaging reports, medication records, disease course reports, and case examination reports. It can be said that these natural language texts contain the main clinical information in the process of patient diagnosis and treatment. O...

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): G06F40/295G06F40/30
CPCG06F40/295G06F40/30
Inventor 江瑞黄浩
Owner TSINGHUA 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

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