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

Auxiliary diagnosis method and system based on electronic medical record texts

An electronic medical record and auxiliary diagnosis technology, applied in the field of healthcare informatics, can solve the problems of difficult to achieve accuracy, low model accuracy upper limit, etc., and achieve the effect of small difference in data nature, high accuracy upper limit, and low cost.

Pending Publication Date: 2021-03-26
贵州小宝健康科技有限公司 +1
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using these two different types of medical record texts as the text source of the same model, the difference in input data will inevitably lead to a low upper limit of model accuracy, making it difficult to achieve a high enough accuracy rate

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
  • Auxiliary diagnosis method and system based on electronic medical record texts
  • Auxiliary diagnosis method and system based on electronic medical record texts
  • Auxiliary diagnosis method and system based on electronic medical record texts

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] like figure 1 A method for auxiliary diagnosis based on electronic medical record text is shown, using the TextCNN model and the TextRNN model, respectively for the medical record text obtained from a single consultation activity and the medical record text obtained from multiple observations, after preprocessing and generating word vectors Classify diseases.

[0030] When the TextCNN model and the TextRNN model need to be trained, augmentation processing is performed after the word vector is generated from the electronic medical record text.

[0031] A typical process of preprocessing and generating word vectors is as follows:

[0032] 1) Based on the stop word corpus, remove the words that appear frequently in the electronic medical record text but have nothing to do with the content expression;

[0033] 2) Using the Word2Vec model technology, the electronic medical record text vocabulary is mapped to a vector to provide a basic semantic model for subsequent classif...

Embodiment 2

[0038] like figure 2 A system for auxiliary diagnosis based on electronic medical record text is shown, including a preprocessing unit group and a taxonomic unit group;

[0039] The taxon group includes TextCNN model units and TextRNN model units;

[0040] The preprocessing unit group obtains and preprocesses a variety of electronic medical record texts, and sends the processing results of the medical record texts obtained from a single consultation activity to the TextCNN model unit, and sends the medical record texts obtained from multiple observations to the TextRNN model unit .

[0041] The preprocessing unit group includes input unit, corpus preprocessing unit, word vector unit, augmentation processing unit, and output unit;

[0042] Input unit: get the text of the electronic medical record, and mark the type of the text of the electronic medical record;

[0043] Corpus preprocessing unit: based on the stop word corpus, delete content-irrelevant words in the electroni...

Embodiment 3

[0054] Another realization of the integration of the above schemes is to obtain more accurate auxiliary diagnosis conclusions through the analysis of various clinical data generated during the fusion diagnosis process. Specifically, the following three stages are adopted:

[0055] Phase 1: Data Preprocessing

[0056] Step 1: Electronic medical record text data preprocessing

[0057] Based on the stop word corpus, the words that appear frequently in the electronic medical record text but have nothing to do with the content expression are removed;

[0058] Using the Word2Vec model technology, the electronic medical record text vocabulary is mapped to a vector to provide a basic semantic model for subsequent classification tasks;

[0059] Based on the above basic semantic model, apply the Skip-Gram algorithm to generate word vectors;

[0060] Perform data augmentation processing on electronic medical record text data:

[0061] Aiming at the problem that the text data of elect...

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 an auxiliary diagnosis method based on electronic medical record texts, belongs to the field of medical care informatics, and adopts multiple text classification models to perform disease classification on multiple electronic medical record texts respectively. The electronic medical record texts comprise two types, namely a medical record text obtained by single inquiry activity and a medical record text obtained by multiple observations. The invention further provides an auxiliary diagnosis system based on electronic medical record texts. The system comprises a preprocessing unit group and a classification unit group. Through the mode that multiple models correspond to multiple texts, the data property difference of the texts as input data can be considered, so thatthe influence of the data property difference is smaller when the models are used for disease classification, the overall accuracy is higher, the upper limit of the accuracy is higher, and a better diagnosis and classification effect can be obtained more easily at a lower cost.

Description

technical field [0001] The invention relates to a method and system for auxiliary diagnosis based on electronic medical record text, belonging to the field of medical care informatics. Background technique [0002] In the prior art, there is a method for diagnosing patients' conditions based on electronic medical record texts. For example, the Chinese invention patent with the application number CN201910594042.5 discloses a method, system and computer equipment for automatically generating diagnostic results, which can extract useful information from text content. , and build a model for training to generate diagnostic results. The inventors of the present application found that: this kind of indiscriminate treatment of text content will cause the text to be used as the input data of the model, which itself has a large deviation. The medical record texts are short and concise, and they tend to be short sentences compared with ordinary texts. The important information is eve...

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): G16H10/60G16H50/20G06F16/35G06N3/04G06N3/08
CPCG16H10/60G16H50/20G06F16/35G06N3/08G06N3/045
Inventor 李晖张大斌冯刚韦海涛
Owner 贵州小宝健康科技有限公司
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