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

A training framework for multi-group electrocardiography (mg-ecg) analysis

A technology of electrocardiogram and data group, applied in the direction of neural architecture, medical image, instrument, etc., can solve the problem of not being able to provide comprehensive information of heartbeat

Pending Publication Date: 2021-12-03
TENCENT AMERICA LLC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the existing works are only valid for single-lead ECG data, which cannot provide comprehensive information of the heartbeat

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
  • A training framework for multi-group electrocardiography (mg-ecg) analysis
  • A training framework for multi-group electrocardiography (mg-ecg) analysis
  • A training framework for multi-group electrocardiography (mg-ecg) analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] Some embodiments of the present disclosure are designed to accomplish multiple data analysis tasks with single-lead and multi-lead ECG data. In one embodiment, a multigroup electrocardiogram (MG-ECG) analysis framework uses a grouping module that groups data streams from multiple ECG leads into groups based on different criteria. Two criteria could be, for example, (1) to have all leads form a single group; (2) to have each lead form a specific group. In one embodiment, the multi-axis feature extraction module employs multiple models for each predefined group from the grouping module, and the data features from the multiple models are collected for the final analysis module. Therefore, the MG-ECG analysis framework of the embodiments can be widely applied to various types of analysis tasks. When analyzing, the MG-ECG analysis framework can also take into account background knowledge, such as geometric properties, ontology.

[0014] figure 1 is a diagram of an environ...

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

A method of performing electrocardiography (ECG) analysis by at least one processor, the method including receiving ECG data that is from multiple leads; grouping the ECG data into groups of data; generating, from each group of the groups of data, a feature vector using a respective machine learning model; and performing ECG analysis using the feature vectors generated from each of the groups of data.

Description

[0001] Cross References to Related Applications [0002] This application claims priority to U.S. Patent Application Serial No. 16 / 556,491 filed in the United States Patent and Trademark Office on August 30, 2019, the disclosure of which is incorporated herein by reference in its entirety. Background technique [0003] An electrocardiogram (ECG) is one of the most common medical procedures that helps doctors diagnose many heart conditions, including atrial fibrillation, myocardial infarction, and acute coronary syndrome (ACS). Approximately 300 million ECGs are recorded annually. Traditional methods for ECG analysis tend to use digital signal processing algorithms, such as wavelet transform, to compute features from the ECG signal. However, such methods are not comprehensive, so using such methods alone may not be sufficient to distinguish between multiple types of arrhythmias. Recent methods employ deep neural networks such as convolutional neural networks (CNN) and recurre...

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): A61B5/00
CPCG16H50/20G06N20/00G06N3/044G06N3/045G16H30/20
Inventor 王堃杨陶涂旻李亚亮谭辉范伟
Owner TENCENT AMERICA LLC