An electrocardiogram classifying method based on a deep learning algorithm

A technology of deep learning and classification methods, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve problems such as incorrect calculation parameters and misclassification, and achieve the effect of improving data accuracy, accuracy, and accuracy

Active Publication Date: 2016-11-16
杨一平 +1
View PDF8 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the traditional electrocardiogram measurement classification method existing in the prior art. When classifying some waveforms with inconspicuous segmentation points, misclassification often occurs, result

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
  • An electrocardiogram classifying method based on a deep learning algorithm
  • An electrocardiogram classifying method based on a deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The electrocardiogram classification method based on deep learning algorithm, its flow chart is as follows figure 1 As shown, it specifically includes the following steps:

[0033] a. (1) Obtain single-lead ECG waveform data and ECG additional information, and intercept the data with a length of 10 seconds as the original ECG waveform data according to the single-lead ECG waveform data, wherein the single-lead ECG waveform data can be passed through Some databases, such as the ECG waveform database (CSE), or obtained through other means, ECG additional information includes gender, height, bust, weight, fat percentage, race.

[0034] (2) as required, the original electrocardiogram waveform data obtained in step (1) can be denoised, and the denoised process includes the following steps:

[0035] a11. Use a high-pass filter to remove baseline drift noise;

[0036] a12. Confirm whether the noise is too high based on the standard variance and threshold method of the PQ segme...

Embodiment 2

[0053] The electrocardiogram classification method based on deep learning algorithm, its flow chart is as follows figure 1 As shown, it specifically includes the following steps:

[0054] a. (1) Obtain single-lead ECG waveform data and ECG additional information, and intercept the data with a length of 8 seconds as the original ECG waveform data according to the single-lead ECG waveform data, in which the single-lead ECG waveform data and ECG additional information Information can be obtained through physical examination results, existing databases such as the ECG waveform database (CSE), or other means. Additional information on the ECG includes gender, height, bust, weight, fat percentage, and race .

[0055] (2) as required, the original electrocardiogram waveform data obtained in step (1) can be denoised, and the denoised process includes the following steps:

[0056] a11. Use a high-pass filter to remove baseline drift noise;

[0057] a12. Confirm whether the noise is ...

Embodiment 3

[0074] The electrocardiogram classification method based on deep learning algorithm, its flow chart is as follows figure 1 As shown, it specifically includes the following steps:

[0075] a. (1) Obtain single-lead ECG waveform data and ECG additional information, and intercept the data with a length of 16 seconds as the original ECG waveform data according to the single-lead ECG waveform data, in which the single-lead ECG waveform data and ECG additional information Information can be obtained through physical examination results, existing databases such as the ECG waveform database (CSE), or other means. Additional information on the ECG includes gender, height, bust, weight, fat percentage, and race .

[0076] (2) as required, the original electrocardiogram waveform data obtained in step (1) can be denoised, and the denoised process includes the following steps:

[0077] a11. Use a high-pass filter to remove baseline drift noise;

[0078] a12. Confirm whether the noise is...

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 electrocardiogram classifying method based on a deep learning algorithm. The method comprises the steps of acquiring original electrocardiogram waveform data with a measuring time being longer than 8s and electrocardiogram additional information, and acquiring electrocardiogram rhythm information and representative PQRST waveform data according to the original electrocardiogram waveform data; inputting the representative PQRST waveform data from an input end of a trained deep learning algorithm to obtain P-wave type data, QRS-wave type data and T-wave type data, and analyzing the representative PQRST waveform data and calculating representative PQRST waveform characteristic data; inputting the representative PQRST waveform characteristic data, the electrocardiogram additional information, and the electrocardiogram rhythm information into a conventional electrocardiogram computer automatic classifying algorithm to obtain an electrocardiogram classifying result. Based on the characteristics of electrocardiogram classification, the method trains a deep learning method via the above-mentioned steps and performs waveform classification by using the deep learning method, so that the accuracy of electrocardiogram classification results can be greatly increased.

Description

technical field [0001] The invention relates to an electrocardiogram classification method, in particular to an electrocardiogram classification method based on a deep learning algorithm. Background technique [0002] ECG waveform data acquisition and ECG classification results are important auxiliary means and reference information for doctors to diagnose heart disease. Usually, ECG waveform data acquisition and classification are carried out in hospitals or physical examination centers, which have disadvantages such as inconvenient detection and low detection frequency, and cannot It is difficult to effectively prevent and timely treat heart disease if the ECG classification information is provided to doctors for real-time diagnosis. In recent years, with the popularity of the Internet and mobile smart phones, it has become possible to launch portable ECG monitors and family personal ECG monitors. Such monitors currently on the market are based on the traditional measurem...

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): A61B5/0402A61B5/00
CPCA61B5/7203A61B5/7225A61B5/725A61B5/7264A61B5/7271A61B5/316
Inventor 杨一平朱欣
Owner 杨一平
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap