Digestive endoscopy report structuralization method and system based on deep learning

A technology of digestive endoscopy and deep learning, applied in neural learning methods, medical reports, informatics, etc., can solve problems such as difficult structured methods, large gaps, and difficult applications

Pending Publication Date: 2020-09-01
SHANDONG UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, although they are both medical texts, different medical texts focus on different content, and the information that needs to be extracted and structured in the text is also quite different. It is difficult to have a universal structuring method
As a comprehensive report, the d...

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
  • Digestive endoscopy report structuralization method and system based on deep learning
  • Digestive endoscopy report structuralization method and system based on deep learning
  • Digestive endoscopy report structuralization method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] A method for structuring digestive endoscopy reports based on deep learning, comprising the following steps:

[0048] (1) Build a structured template for digestive endoscopy reports;

[0049] (2) Retrieve the existing unstructured endoscopy report data from the hospital digestive endoscopy database, and mark the endoscopy report data according to the template content;

[0050] (3) Carry out word vector and document matrix representation to the obtained endoscopic report data;

[0051] (4) For the endoscopic report text word representation vector and document representation matrix obtained in step (3), the context is modeled using a bidirectional long-short-term memory network model.

[0052](5) For the context vector representation of each word obtained in step (4), use conditional random fields to identify and label structured word information.

[0053] (6) Match the marked result with the structured template, extract the marked result as structured value information...

Embodiment 2

[0100] A structuring system for digestive endoscopy reports based on deep learning, including:

[0101] Used to build a structured template module for digestive endoscopy reports;

[0102] Used to call and label digestive endoscopy report data module;

[0103] A word vector and document matrix representation module for the called report document;

[0104] A module for modeling word contexts from matrix representations of documents;

[0105] A module for identifying and marking structured words based on the word vector representation of the word context;

[0106] A module for constructing a structured report of digestive endoscopy according to the annotation of structured words and a structured template.

Embodiment 3

[0108] A computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are suitable for being loaded and executed by a processor of a terminal device to execute the method for structuring digestive endoscopy reports based on deep learning.

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 provides a gastroendoscope report structuring method and system based on deep learning, and the method comprises the steps: obtaining gastroendoscope report data, and marking the data; performing word vector and document matrix representation on the acquired digestive endoscopy report information; modeling the constructed word representation vector and the constructed document representation matrix by using a bidirectional long-short-term memory model in combination with a document context; using a conditional random field to identify and label report information needing to be structured for the word vector based on context coding; and matching the identification and extraction results with a pre-constructed structured template, constructing a key value pair relationship by the structured template based on different disease information and lesion part information in the historical data, and obtaining a final structured result according to the matched template. According to the invention, the structuralization of the digestive endoscopy report can be realized.

Description

technical field [0001] The disclosure belongs to the field of natural language processing, and relates to a method and system for structuring digestive endoscopy reports based on deep learning. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] At present, the informatization of hospitals is in full swing and in the process of flourishing. It not only changes the traditional management mode of many hospitals, but also is the inevitable trend of the development of modern hospitals. Therefore, how to effectively utilize the electronic medical information stored in the hospital information system has become a hot issue that researchers are concerned about, and many systems and methods for medical information structuring such as electronic medical records have been proposed and used. [0004] However, although they are both medical texts, diffe...

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): G06F40/169G06F40/151G16H15/00G06N3/04G06N3/08
CPCG06F40/169G06F40/151G16H15/00G06N3/049G06N3/08G06N3/045
Inventor 崔立真柏欣雨鹿旭东郭伟
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