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

Multi-label stomach disease classification method and device based on medical record text

A disease classification and multi-label technology, applied in neural learning methods, biological neural network models, patient-specific data, etc., can solve problems such as insufficient data sets, and alleviate the problem of insufficient data sets, reduce human factors, and shorten computing. effect of time

Pending Publication Date: 2021-05-14
紫东信息科技(苏州)有限公司
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application provides a multi-label gastric disease classification method and device based on medical record texts, which can alleviate the problem that the medical record text data set is not large enough, and realize automatic multi-label classification of medical record texts with higher performance

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
  • Multi-label stomach disease classification method and device based on medical record text
  • Multi-label stomach disease classification method and device based on medical record text
  • Multi-label stomach disease classification method and device based on medical record text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The specific implementation manners of the present application will be further described in detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0041] First, some terms involved in this application are introduced.

[0042] Bidirectional Encoder Representations from Transformers (Bidirectional Encoder Representations from Transformers, BERT): It is a large-scale unsupervised pre-training language model. As a substitute for Word2vec, it refreshes the accuracy in the field of Natural Language Processing (NLP). One of the most groundbreaking techniques from residual networks in recent years. The essence of BERT is to learn a good feature representation for words by running a self-supervised learning method on the basis of massive corpus, and it provides a transferable model for other tasks. Its advantage is that it integrates the Trans...

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 relates to a multi-label stomach disease classification method and device based on a medical record text, and belongs to the technical field of medical text intelligent processing. The method comprises the steps that multiple sets of training data are acquired, and each set of training data comprises the medical record text and a disease label corresponding to the medical record text; training a preset network structure based on the multiple groups of training data to obtain a disease classification model; using the disease classification model for identifying disease classification in the input medical record text, wherein the network structure is a combination of a pre-training model and a seq2seq model; and converting a multi-label classification problem into a sequence generation problem by utilizing a network of a pre-training model and a self-attention mechanism, so that very good multi-label classification performance is obtained on limited training samples. Besides, manual participation is not needed in the classification process, human factors are reduced, meanwhile, accurate diagnosis reference can be provided for doctors, and the working pressure of medical staff is relieved.

Description

【Technical field】 [0001] The application relates to a multi-label gastric disease classification method and device based on medical record texts, belonging to the technical field of medical text intelligent processing. 【Background technique】 [0002] Stomach disease is an organic or functional disease that occurs in the stomach. The etiology is very complex, including physical and chemical stimulation, infection, toxin, genetics, mental factors, developmental disorders, and surgical effects. Symptoms related to gastric diseases will be recorded in the medical record text, which will be used by medical staff to determine the classification of diseases. [0003] However, manual extraction of diseases in medical record texts will consume the time of medical staff, and the efficiency of gastric disease classification is low. 【Content of invention】 [0004] This application provides a multi-label gastric disease classification method and device based on medical record texts, w...

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): G16H10/60G16H50/20G06N3/08G06N3/04
CPCG16H10/60G16H50/20G06N3/08G06N3/044G06N3/045
Inventor 李寿山陆文捷谭惜姿朱苏阳周国栋
Owner 紫东信息科技(苏州)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