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

Intelligent analysis method and system of paroxysmal atrial fibrillation based on difference time scatter diagram

An intelligent analysis and scatterplot technology, applied in the field of medical artificial intelligence, can solve the problems of inability to quantify the load of atrial fibrillation, the difficulty of manual analysis and work intensity, and the high rate of misdiagnosis, so as to reduce the economic burden and social burden, and reduce the detection and detection rate. cost, harm reduction effect

Active Publication Date: 2019-11-05
武汉海星通技术股份有限公司
View PDF8 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Long-term continuous ECG detection and analysis requires multi-day and long-term monitoring. Manual analysis is difficult and work-intensive, and the rate of misdiagnosis is also high. At the same time, the burden of atrial fibrillation cannot be quantified

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
  • Intelligent analysis method and system of paroxysmal atrial fibrillation based on difference time scatter diagram
  • Intelligent analysis method and system of paroxysmal atrial fibrillation based on difference time scatter diagram
  • Intelligent analysis method and system of paroxysmal atrial fibrillation based on difference time scatter diagram

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments, but these embodiments should not be construed as limiting the present invention.

[0045] A kind of paroxysmal atrial fibrillation intelligent analysis method based on difference time scatter diagram proposed by the present invention, such as figure 1 with figure 2 As shown, including the training phase and the detection phase;

[0046] The training phase consists of steps:

[0047] A1) Collect several pieces of original training data of long-term ambulatory electrocardiogram, and filter signal segments with too low quality.

[0048] Acquire a large amount of raw data of dynamic electrocardiograms of long-duration paroxysmal atrial fibrillation, and filter out low-quality signal segments. Collect a large number of ambulatory electrocardiogram samples, the sampling frequency is 500Hz, and each sample lasts 24 hours. Based on the shape of the ...

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 intelligent analysis method and system of paroxysmal atrial fibrillation based on a difference time scatter diagram. The method includes a training stage and a detection stage; the training stage includes the steps: A1) collecting original ECG training data; A2) drawing the difference time scatter diagram of the training stage; A3) labeling the difference time scatter diagram with an atrial fibrillation attack label and a non-atrial fibrillation attack label; and A4) training a convolution neural network model. The detection stage includes the steps: B1) collecting original ECG detection data; B2) drawing the difference time scatter diagram of the detection stage; and B3) inputting the difference time scatter diagram of the detection stage to the convolution neural network model and outputting intelligent analysis results of paroxysmal atrial fibrillation. The intelligent diagnosis of paroxysmal atrial fibrillation can be realized and the detection of subclinical atrial fibrillation patients can be realized by using the method for classification by the differential time scatter diagram.

Description

technical field [0001] The invention relates to the technical field of medical artificial intelligence, in particular to an intelligent analysis method and system for paroxysmal atrial fibrillation based on difference time scatter diagrams. Background technique [0002] Atrial fibrillation (abbreviated as atrial fibrillation) is the most common tachyarrhythmia symptom. Epidemiological studies have shown that the prevalence and incidence of clinical atrial fibrillation increased significantly between 1990 and 2010. In 2010, the number of clinical atrial fibrillation worldwide was estimated to be 3350. The number of patients with atrial fibrillation in my country exceeds 10 million, and the statistical data of clinical atrial fibrillation-related mortality has doubled in the past 10 years. Atrial fibrillation can form left atrial thrombus, 90% of the resulting embolism is cerebral artery embolism (ischemic stroke), and 10% is peripheral arterial embolism or mesenteric artery em...

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): A61B5/046A61B5/361
CPCA61B5/7267A61B5/361
Inventor 林凡杨晓云马飞冯晶柯凯
Owner 武汉海星通技术股份有限公司
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