Unlock instant, AI-driven research and patent intelligence for your innovation.

Atrial Fibrillation Artificial Intelligence Identification Method and Device Including Ectopic Heartbeat Judgment

A technology of artificial intelligence and recognition method, applied in the field of biomedical signal processing, can solve problems such as sinus rhythm electrocardiogram misdiagnosis, RR interval numerical interference, etc.

Active Publication Date: 2020-07-07
SHANGHAI SID MEDICAL CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide an artificial intelligence identification method and device for atrial fibrillation including ectopic heartbeat judgment, aiming at solving the problem that the RR interval value may be affected when the electrocardiogram includes ectopic heartbeat in the prior art. Interference, a problem that leads to misdiagnosed sinus rhythm ECG

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
  • Atrial Fibrillation Artificial Intelligence Identification Method and Device Including Ectopic Heartbeat Judgment
  • Atrial Fibrillation Artificial Intelligence Identification Method and Device Including Ectopic Heartbeat Judgment
  • Atrial Fibrillation Artificial Intelligence Identification Method and Device Including Ectopic Heartbeat Judgment

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0068] The following predetermined parameters in the embodiments of the present invention are all obtained by the inventor through a large number of experiments or by virtue of his own experience. The embodiments of the present invention do not limit the specific values ​​of these parameters. Preferably, they can be as follows: The first predetermined time is 10 seconds; the predetermined value is 0.5; the second predetermined time is 0.06 seconds; the predetermined ratio is 25%; the third predetermined time is 0.12 seconds; the predetermined multiple is 0.2 times; the first predetermined number is 4066, and the second predetermined number is 4066.

[0069] Select 8132 pieces of single-lead ECG data provided by a hospital as the ECG signals to be processed, such as figure 1 As shown, the embodiment of the present invention provides an artificial intelligence identification method for atrial fibrillation including ectopic heartbeat judgment, which includes the following steps. ...

specific Embodiment 2

[0099] Such as Image 6 As shown, the embodiment of the present invention provides an artificial intelligence identification device for atrial fibrillation including ectopic heartbeat judgment, including:

[0100] The first module is used to: extract a part of the first predetermined time from a certain electrocardiographic signal; use the R wave extraction algorithm to determine the position of each R wave peak in the intercepted electrocardiographic signal in the electrocardiographic signal sequence position r i ;

[0101]The second module is used to: differentiate the position sequence of the R wave crest obtained by the first module, and calculate several RR intervals rr i ;

[0102] The third module is used for: extracting the R wave peak position r obtained according to the first module i , using a method based on mean filtering and wavelet decomposition to determine the suspected P wave peak position p that appeared before the R wave i and the suspected T wave peak...

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 atrial fibrillation artificial intelligence identification method and device including ectopic heartbeat judgment, and provides an atrial fibrillation automatic identification method including ectopic heartbeat correction for a single-lead electrocardiogram with a length greater than 10s, thereby reducing the rate of misdiagnosis. The method firstly extracts the RR interval of the ECG signal, then judges whether there is an ectopic heartbeat and corrects it, then makes statistics on the RR interval, and finally uses the neural network to classify. The method of the invention is simple, the amount of calculation is small, and it is easy to implement on hardware; compared with the traditional atrial fibrillation identification method based on the RR interval, the ectopic heartbeat identification of the present invention has a high accuracy rate and can effectively reduce atrial premature beats, ventricular The misdiagnosis rate of ECG signals such as premature beats and other heartbeats improves the recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of biomedical signal processing, in particular to an artificial intelligence identification method and device for atrial fibrillation including ectopic heartbeat determination. Background technique [0002] Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, affecting approximately 33.5 million people worldwide. Although atrial fibrillation is not fatal, it may lead to the formation of blood clots and increase the risk of stroke. Clinically, the twelve-lead ECG monitoring instrument is generally used for monitoring: first, the ECG signals (Electrocardiogram, ECG) of multiple leads are collected, and then the doctor judges whether the ECG signal represents atrial fibrillation ECG according to the characteristics of the ECG signal. signal to judge. However, relying on manual judgment is time-consuming and labor-intensive, and is also subject to the level of doctors. Therefore, about 30%...

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 Patents(China)
IPC IPC(8): A61B5/0402A61B5/0468A61B5/364
CPCA61B5/7225A61B5/7267A61B5/318A61B5/364
Inventor 朱俊江张德涛伍尚实杨潞潞陈广怡
Owner SHANGHAI SID MEDICAL CO LTD