Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Electronic medical record named entity recognition system and method

A technology of named entity recognition and electronic medical records, applied in neural learning methods, electrical digital data processing, instruments, etc., can solve problems such as excessive dependence on frameworks, failure to recognize nested named entities, high cost of labeling data, etc., and achieve the goal of reducing coupling Effect

Pending Publication Date: 2021-05-14
成都延华西部健康医疗信息产业研究院有限公司
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to provide a named entity recognition system and method for electronic medical records, which is used to solve the problems in the above-mentioned scenarios, such as: starting from the industrial application scenario, the cost of labeling data is too high, the framework is overly dependent, and the model input data Insufficient information mining, unable to identify nested named entities and other issues

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
  • Electronic medical record named entity recognition system and method
  • Electronic medical record named entity recognition system and method
  • Electronic medical record named entity recognition system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Such as Figure 4 As shown, a named entity recognition system for electronic medical records is proposed, including:

[0055] The data cleaning unit performs data cleaning on the original data of the electronic medical records to obtain standardized original data;

[0056] The rule pre-labeling unit performs rule pre-labeling on the standard original data through the labeling rules to obtain the rule pre-labeling data;

[0057] The algorithm pre-labeling unit performs algorithmic pre-labeling on the rule pre-labeled data through the labeling algorithm to obtain the pre-labeled data set;

[0058] Manual inspection and labeling unit, where labelers correct and label pre-labeled datasets to generate standard datasets;

[0059] Construct the input data unit, classify and construct the input for the standard data set, and obtain the input data;

[0060] The model construction unit builds the named entity recognition model of electronic medical records, that is, the first ...

Embodiment 2

[0074] A method for named entity recognition for electronic medical records, comprising the following steps:

[0075] 1. Data cleaning

[0076] Data cleaning of the original data is mainly to standardize and unify punctuation marks and English.

[0077] 2. Rule pre-marking

[0078] For the description of the time point and time period in the electronic medical record, the regularization is extracted, the regularization library is written, and the time expressions of different laws are classified, and the extracted entities are pre-labeled.

[0079] 3. Algorithm pre-labeling

[0080] 4. Construct corresponding entity dictionaries using standardized drug databases, disease databases, surgery databases, symptom databases, and other standardized names. This part of the dictionary is used as a proprietary entity name that needs to be updated iteratively. The names in the dictionary need to exclude characters with a length of less than 2. word. Use the word segmentation package ...

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 an electronic medical record named entity recognition system and method. The method comprises the following steps: performing data cleaning, performing rule-based pre-annotation on cleaned data, returning a result to an annotation algorithm for secondary annotation and generating a pre-annotation data set, and returning the result to annotation personnel for correction and annotation so as to generate a standard data set; correcting the rule and the algorithm by comparing and analyzing the difference between the pre-annotated data set and the standard data set; and acquiring online prediction data, supplementing the online prediction data into a standard data set through manual checking and verification, sending original data into a pre-labeling system to supplement a pre-labeling data set, and retraining a model iteration model after accumulating to a certain scale. According to the method, the whole industrial application process of named entity recognition is integrated and transformed, and a named entity recognition framework suitable for an industrial scene is constructed.

Description

technical field [0001] The invention belongs to the field of new generation information technology, and in particular relates to a system and method for named entity recognition of electronic medical records. Background technique [0002] Named entity recognition of electronic medical records is a basic research on the structure of electronic medical records. Accurate identification of named entities in electronic medical records can provide strong support for subsequent analysis of electronic medical records. Electronic medical records are a semi-structured data structure, in which there are highly readable structured data and free text that is difficult to parse. However, there is a large amount of diagnosis and treatment-related information in free text, which has important applications such as diagnosis and treatment data tracking, medical statistical analysis, and regional epidemic prevention. Named entity recognition is to extract entities from free text in electronic...

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): G16H10/60G16H50/70G06F40/295G06F40/242G06N3/08
CPCG16H10/60G16H50/70G06F40/295G06F40/242G06N3/08
Inventor 杜斌朱智源
Owner 成都延华西部健康医疗信息产业研究院有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com