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

Electrocardiogram multi-disease analysis method based on deep neural network

A deep neural network and electrocardiographic signal technology, which is applied in the field of electrocardiographic signal multi-disorder analysis based on deep neural network, can solve the problems of poor scalability, unstable analysis effect, and consume a lot of work energy, and achieve strong anti-interference ability. Effect

Active Publication Date: 2019-03-01
安徽心之声医疗科技有限公司
View PDF8 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing ECG signal analysis technology has the following disadvantages: some methods need to rely on a large amount of expert knowledge in the medical field, consume a lot of human resources, have natural bottlenecks in the analysis effect, and some methods require a large number of features first. Engineering, this step requires a lot of work energy, the analysis effect is unstable, it is directly based on the original data, it is easily affected by interference signals, the robustness of the analysis technology is insufficient, the scalability is poor, and the difference under different analysis tasks is not considered commonality

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
  • Electrocardiogram multi-disease analysis method based on deep neural network
  • Electrocardiogram multi-disease analysis method based on deep neural network
  • Electrocardiogram multi-disease analysis method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] refer to figure 1 , a kind of electrocardiographic signal multi-symptom analysis method based on deep neural network that the present invention proposes, comprises:

[0031] Step S1, collecting 12-lead ECG signal data.

[0032] In the specific scheme, the standard ECG signal data is collected, including 12 leads (Leads) including I, II, III, V1, V2, V3, V4, V5, V6, avR, avL, and avF, and the sampling rate is fHz. Each piece of data can be of any length. For any original ECG signal, denoted as X 0 ∈R W×12 Where n is the data length of the signal, n=f×t, and t is the time length of the signal acquisition.

[0033] Step S2, intercepting the 12-lead electrocardiographic signal data into equal-length target electrocardiographic signal data.

[0034] Step S2 specifically includes: using a sliding window to intercept the 12-lead ECG signal data into equal-length target ECG signal data, wherein the width of the sliding window is the length of the target ECG signal data.

...

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 discloses an electrocardiogram multi-disease analysis method based on the deep neural network. The method comprises the following steps that 12-lead electrocardiogram data is collected;the 12-lead electrocardiogram data is cut into target electrocardiogram data with the equal length; the target electrocardiogram data is substituted into a target deep neural network model, and the probability of N tasks predicated by the target deep neural network model is output; and according to the probability of the N tasks and the probability threshold value preset corresponding to the N tasks, the prediction result for the N tasks is obtained.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence data analysis, in particular to a deep neural network-based method for analyzing multiple symptoms of electrocardiographic signals. Background technique [0002] Electrocardiogram (ECG), also known as electrocardiogram. The existing ECG signal analysis techniques are mainly divided into two categories. The first category is the statistical analysis method of ECG signal measurement value based on expert knowledge. This method needs to first identify each heartbeat (Beat) in an ECG signal, and then identify each characteristic wave band (such as P wave, QRS wave group, ST segment, T wave, etc.) in each heartbeat, and finally , according to the measurement values ​​of each characteristic band, judge the possible problems of the heartbeat. [0003] The existing ECG signal analysis technology has the following disadvantages: some methods need to rely on a large amount of expert knowl...

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
CPCA61B5/7264A61B5/316A61B5/318
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