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

Method and device of recognizing ventricular tachycardia heart rhythm based on transfer learning

A technology of ventricular tachycardia and transfer learning, which is applied in medical science, sensors, diagnostic recording/measurement, etc., can solve the problems of insufficient recognition accuracy of ventricular tachycardia heart rhythm, and achieve high accuracy and recognition accuracy high effect

Inactive Publication Date: 2020-03-24
SHANGHAI SID MEDICAL CO LTD
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: in order to solve the problem of insufficient recognition accuracy of ventricular tachycardia due to lack of data in the prior art, thereby providing a transfer learning-based ventricular tachycardia with high recognition accuracy. tachycardia 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
  • Method and device of recognizing ventricular tachycardia heart rhythm based on transfer learning
  • Method and device of recognizing ventricular tachycardia heart rhythm based on transfer learning
  • Method and device of recognizing ventricular tachycardia heart rhythm based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0106] This embodiment provides a ventricular tachycardia rhythm recognition method based on transfer learning, comprising the following steps:

[0107] S1: Obtain multi-lead ECG signals, such as 12-lead signals;

[0108] S2: Input the multi-lead ECG signal into the SCNN neural network with several convolutional layers, several pooling layers and several fully connected layers whose output value is [X, Y] trained based on transfer learning, the simplest Processing can directly set X to 0 and Y to 1;

[0109] S3: If the output result of the SCNN neural network is greater than or equal to (X+Y) / 2, X is set to 0 and Y is set to 1 and greater than or equal to 0.5, then the type of the multi-lead ECG signal is considered to be ventricular Otherwise, it is considered that the type of the multi-lead ECG signal is non-ventricular tachycardia.

[0110] In the S2 step, the following steps are included when the SCNN neural network is trained:

[0111]S21: Collect enough (not less than...

Embodiment approach

[0116] As a specific implementation, the SCNN neural network includes fifteen convolutional layers, fifteen pooling layers, and two fully connected layers;

[0117] Among them, the first layer is a convolutional layer, which contains 12 filters, the convolution kernel size is (121,12), the step size is 1, and the activation function is leakyReLU;

[0118] The second layer is the pooling layer, the pooling window size is 2, and the pooling method is used to maximize the pooling;

[0119] The third layer is the convolution layer, which contains 10 filters, the convolution kernel size is (91,12), the step size is 1, and the activation function is leakyReLU;

[0120] The fourth layer is the pooling layer, the pooling window size is 2, and the maximum pooling method is used for pooling;

[0121] The fifth layer is the convolution layer, which contains 8 filters, the convolution kernel size is (71,10), the step size is 1, and the activation function is leakyReLU;

[0122] The sixt...

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 method and a device of recognizing ventricular tachycardia heart rhythm based on transfer learning. The method includes the following steps: imputing a multi-lead electrocardiogram signal into a trained SCNN neural network; and judging the type of the multi-lead electrocardiogram signal according to the output result of the SCNN neural network. During the training of theSCNN neural network, firstly plenty of non-ventricular tachycardia electrocardiogram signals of known types and collected and copied ventricular tachycardia electrocardiogram signals are adopted to train the SCNN neural network to confirm the parameters of convolutional layers and pooling layers; and then the SCNN neural network is trained by the collected ventricular tachycardia electrocardiogram signals to confirm the parameters of fully connected layers. Through training twice, the parameters of the convolutional layers and the pooling layers are confirmed by the first training and the parameters of the fully connected layers are confirmed by the second training. Therefore, the invention provides the method of recognizing the ventricular tachycardia heart rhythm based on the transfer learning with high recognition accuracy without collecting too many ventricular tachycardia electrocardiogram signals.

Description

technical field [0001] The present application belongs to the technical field of electrocardiographic type identification, and in particular relates to a method and device for identifying ventricular tachycardia based on transfer learning. Background technique [0002] Ventricular tachycardia (VT) refers to the rapid arrhythmia that occurs in the bundle branches, myocardial conduction fibers, and ventricular myocardium below the His bundle bifurcation. Ventricular tachycardia can originate from the left ventricle and right ventricle. The frequency of attacks often exceeds 100 times / min, and the hemodynamic state may deteriorate, which may degenerate into ventricular flutter and ventricular fibrillation, leading to sudden cardiac death, which requires active treatment. [0003] The signal of ventricular tachycardia is difficult to obtain clinically, and the amount of data is small. Therefore, when using a data-driven method for automatic diagnosis of ventricular tachycardia, ...

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): A61B5/0402A61B5/00
CPCA61B5/7203A61B5/7235A61B5/7267A61B5/316A61B5/318
Inventor 朱俊江璞玉汪朝阳
Owner SHANGHAI SID MEDICAL CO LTD
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