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

Electrocardiosignal QRS wave group identification method based on deep learning

A technology of QRS complexes and ECG signals, applied in the medical field, can solve problems such as noise interference, misunderstanding, and reduce the accuracy of pattern recognition methods, so as to improve accuracy and low noise, improve training accuracy, and maximize application potential and the effect of value

Inactive Publication Date: 2019-11-05
安徽心之声医疗科技有限公司
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the above cases, it is easy to mistake P waves or T waves for QRS complexes using pattern recognition methods
[0008] susceptible to noise
During the acquisition process, different types of noise such as limb movement, electrical interference from nearby equipment, and muscle electrical interference will be encountered. These noises superimposed on the QRS wave group will change the shape and reduce the accuracy of the pattern recognition method.

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
  • Electrocardiosignal QRS wave group identification method based on deep learning
  • Electrocardiosignal QRS wave group identification method based on deep learning
  • Electrocardiosignal QRS wave group identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] refer to figure 1 , a deep learning-based electrocardiographic signal QRS complex recognition method proposed by the present invention, comprising:

[0038] S1. First, set the data preprocessing model: normalize the data sampling rate to a preset frequency threshold, and perform equal-length segmentation on the normalized data to obtain data segments with a length of d. Specifically, in this embodiment, for data whose sampling rate is not equal to the frequency threshold, the sampling rate may be converted to the frequency threshold through existing down-sampling or up-sampling.

[0039] S2. Preprocessing the marked sample data by using the data preprocessing model, and training according to the preprocessed sample data to obtain a prediction model whose output is the probability y that the data segment contains the QRS complex.

[0040] Specifically, in this embodiment, the model training is performed on the data segments by segmenting the data into equal lengths, whi...

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 brings forward an electrocardiosignal QRS wave group identification method based on deep learning, comprising the following steps: firstly setting a data preprocessing model; normalizingdata sampling rate to a preset frequency threshold, carrying out equal-length splitting on the normalized data to obtain data segments with length d; preprocessing the tagged sample data through thedata preprocessing model, and training according to the preprocessed sample data to obtain a prediction model that outputs probability y containing a QRS wave group in the data segments; preprocessingthe electrocardiosignal data according to the data preprocessing model, and inputting the data segments obtained by preprocessing into the prediction model to obtain probability corresponding to eachdata segment; then selecting data segments corresponding to probability which is greater than the preset frequency threshold to form a QRS wave group. The method is dependent on data and has greaterpotential and value for use in today's rapid development of medical informatization and accumulation of large amounts of data.

Description

technical field [0001] The present invention relates to the field of medical technology, in particular to a method for identifying QRS complexes of electrocardiographic signals based on deep learning. Background technique [0002] Electrocardiogram (ECG) records the electrophysiological signals of heart beating. Each beat can be divided into P wave, QRS complex (QRS-complex), T wave, etc., which correspond to atrial depolarization activity and ventricular depolarization respectively. Atrial repolarization activity, ventricular repolarization activity. Among them, the QRS wave group is the most obvious characteristic band of the electrophysiological signal of heart beating, which reflects the myocardial activity when the ventricle contracts and ejects blood. [0003] The identification of the QRS complex is the first step in ECG Interpretation. Only by correctly identifying the position of the QRS complex can we: (1) calculate the duration of each heart activity, and then ca...

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 Applications(China)
IPC IPC(8): A61B5/0472A61B5/00A61B5/366
CPCA61B5/7267A61B5/7203A61B5/366
Inventor 洪申达傅兆吉周荣博俞杰
Owner 安徽心之声医疗科技有限公司
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