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

Method and device for training electrocardiogram ST segment raising recognition model and ST segment raising recognition method and device

A technology of recognition model and training method, applied in the field of data processing, can solve the problems of low recognition accuracy and misrecognition, and achieve the effect of improving the accuracy.

Pending Publication Date: 2022-03-22
NEUSOFT CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the method of identifying ST-segment elevation heart beats in ECG waveform signals has misidentification, resulting in low recognition accuracy

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
  • Method and device for training electrocardiogram ST segment raising recognition model and ST segment raising recognition method and device
  • Method and device for training electrocardiogram ST segment raising recognition model and ST segment raising recognition method and device
  • Method and device for training electrocardiogram ST segment raising recognition model and ST segment raising recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0086] In a possible implementation, the embodiment of the present application provides a specific implementation of determining the key indicators of the training heartbeat waveform signal according to the key sampling points, including:

[0087] A1: Calculate the mean amplitude of each sampling point between the end point of the P wave and the start point of the QRS complex as the baseline amplitude.

[0088] Usually, the abscissa of the sampling point / data point on the ECG waveform signal is time, and the ordinate is voltage. Then calculate the average voltage of each sampling point between the end point of P wave and the start point of QRS complex as the baseline amplitude.

[0089] A2: Calculate the mean value of the amplitude of each sampling point within the third preset length after point J as the ST segment amplitude.

[0090] For example, the third preset length may be 60-80ms.

[0091] A3: Calculate the difference between the amplitude of the T point and the start...

example 1

[0139] Example 1, if the second preset length is less than the length of a complete heartbeat signal, the training heartbeat waveform signal is similar to a complete heartbeat, including a complete heartbeat signal minus a small amount of left and right heartbeat data. At this time, a small amount of heartbeat data not divided into training heartbeat waveform signals in the complete heartbeat will not be input into the subsequent waveform recognition model for recognition. For example, the length of the complete heartbeat signal is 300 sampling points, and the heartbeat waveform signal of the second preset length is 256 sampling points. The 44 sampling points in the complete heartbeat signal that are not divided into training heartbeat waveform signals will not be input into the subsequent waveform recognition model. In this case, the heartbeat in the complete heartbeat waveform signal that is not divided into training heartbeat waveform signals The classification result of th...

example 2

[0140] Example 2, if the second preset length is greater than the length of the complete heartbeat signal, the training heartbeat waveform signal is similar to a complete heartbeat, including a complete heartbeat signal plus a small amount of non-heartbeat data. For example, the length of the complete heartbeat signal is 200 sampling points, and the training heartbeat waveform signal of the second preset length is 256 sampling points. The length of the complete heartbeat signal is less than the second preset length. At this time, 200 sampling points in the complete heartbeat signal plus 56 sampling points of a small amount of non-heartbeat data need to be used as the training heartbeat waveform signal.

[0141] During specific implementation, the embodiment of the present application provides a classification result of whether each sampling point in the first input waveform signal is heartbeat data, and at least one training heartbeat waveform signal of a second preset length i...

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 embodiment of the invention discloses an electrocardiogram ST segment raising recognition model training method and device and an ST segment raising recognition method and device. Obtained training heart beat waveform signals of different lead types are input into a waveform recognition model so as to obtain waveform classification results of all sampling points in the training heart beat waveform signals. And according to the waveform classification result of each sampling point, extracting key sampling points in the training heart beat waveform signal. And determining a key index of the training heart beat waveform signal according to the key sampling point, and obtaining a judgment result of whether the ST segment of the training heart beat waveform signal is raised or not according to the key index and the lead type of the training heart beat waveform signal. And taking the judgment result as a label corresponding to the training heart beat waveform signal, and training a residual network by utilizing the training heart beat waveform and the corresponding label to obtain an electrocardiogram ST segment raising recognition model. In this way, the electrocardiogram ST segment elevation recognition model can recognize whether ST segment elevation exists in heart beat waveform signals of different lead types or not, and the accuracy of ST segment elevation recognition is improved.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a training method for an ECG ST segment elevation recognition model, a ST segment elevation recognition method, device and equipment. Background technique [0002] The ECG waveform signal is generated by monitoring the beating process of the patient's heart to represent the beating condition of the patient's heart. By identifying the waveform of the ECG waveform signal, waveforms in the ECG waveform signal can be obtained, such as P wave, QRS complex, T wave, PR interval, and ST segment. By analyzing different waveforms in the ECG waveform signal, the cardiovascular health of the patient can be known. Among them, ST-segment elevation can usually prompt the doctor that the patient may have heart disease. Therefore, it is very important to identify whether ST-segment elevation beats are included in the ECG waveform signal. [0003] At present, the method for id...

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): G06K9/62G06K9/00G06N3/04G06N3/08A61B5/358A61B5/00
CPCG06N3/04G06N3/08A61B5/358A61B5/7267G06F2218/10G06F18/2414
Inventor 刘志伟倪琳刘禄吴庆贺任善多王海永廖锐任丽孙雪
Owner NEUSOFT CORP
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