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

Electrocardiosignal quality evaluation method

A technology for evaluating the quality of ECG signals, applied in diagnostic recording/measurement, medical science, diagnosis, etc., can solve problems such as error analysis, poor quality ECG records, increase the workload of doctors, etc., and achieve the effect of improving accuracy

Active Publication Date: 2021-07-02
SHANDONG ARTIFICIAL INTELLIGENCE INST +1
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional ECG requires doctors to analyze the characterization information of the patient's ECG signal waveform, but due to the influence of various noises and interferences, a large number of poor-quality ECG records will be generated, which will greatly increase the doctor's workload and even cause errors. Analysis, therefore, requires an automated assessment of the quality of the ECG signal

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
  • Electrocardiosignal quality evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Step b) The central electrical signal E(t) is segmented into equal-length segments of 10s, and the segmented ECG signals are marked as acceptable and unacceptable according to the annotation standards of the 2011 PhysioNet / Computingin Cardiology Challenge.

Embodiment 2

[0039] The feature in the statistical feature matrix StaF in step c) includes:

[0040] c-1) Take the maximum R-peak interval as the quality index 1 of the ECG record.

[0041] c-2) The minimum R-peak interval is used as the quality index 2 of the ECG record.

[0042] c-3) The average R peak interval is used as the quality index 3 of the ECG record.

[0043] c-4) The standard deviation of the R peak interval is used as the quality index 4 of the ECG record.

[0044] c-5) The ratio pNN50 of the difference between adjacent R peaks greater than 50 ms is used as the quality index 5 of the ECG record.

[0045] c-6) The R peak density (that is, the number of R peaks / record length) is used as the quality index 6 of the ECG record.

[0046] c-7) The root mean square RMSSD of the difference between adjacent R peaks is used as the quality index 7 of the ECG record.

[0047] c-8) The RR interval sampling entropy, which measures the confusion of R peak interval changes, will be used a...

Embodiment 3

[0050] The S-transform in step d) is the inheritance and development of the wavelet transform and the short-time Fourier transform, which can not only maintain a high high-frequency time resolution, but also maintain a high low-frequency frequency resolution. The formula for the S-transform is: Through this calculation, the time-spectrum matrix S(τ,f) is obtained, where x(t) is the ECG signal to be analyzed, τ is the time shift factor, p is a rational number, i is an imaginary number unit, t is time, and e is an irrational number , f is the frequency.

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 electrocardiosignal quality evaluation method which comprises the following steps: obtaining depth features from a time-frequency graph obtained through S transformation through an integrated neural network of a depth residual shrinkage network and a convolutional neural network, combining the depth features with extracted statistical features, extracting the depth features by using a proposed double-proportion loss function, and evaluating the quality of the electrocardiosignals in combination with statistical characteristics, so that the problem of relatively poor quality of the electrocardiosignals in actual application is solved, and the accuracy of quality evaluation of the 12-lead electrocardiosignals can be greatly improved. The residual shrinkage network can delete a lot of original information irrelevant to the current task in the data through soft threshold processing to obtain information most relevant to the current task. The convolutional neural network has the advantages of parameter sharing and sparse connection, the depth features extracted by the residual shrinkage network can be further purified and optimized, and the depth features most suitable for the current task are obtained.

Description

technical field [0001] The invention relates to the technical field of electrocardiographic signal processing, in particular to a method for evaluating the quality of electrocardiographic signals. Background technique [0002] Electrocardiogram (ECG) signal is of great significance as a comprehensive reflection of heart activity. The traditional ECG requires doctors to analyze the characterization information of the patient's ECG signal waveform, but due to the influence of various noises and interferences, a large number of poor-quality ECG records will be generated, which will greatly increase the doctor's workload and even cause errors. Analysis, therefore, requires an automated assessment of the quality of the ECG signal. Contents of the invention [0003] In order to overcome the deficiencies of the above technologies, the present invention provides a method that combines a deep residual shrinkage network and a convolutional neural network to greatly improve the accu...

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): A61B5/346A61B5/352
CPCA61B5/7221A61B5/7264A61B5/7267A61B5/7235
Inventor 舒明雷王海生田岚王英龙
Owner SHANDONG ARTIFICIAL INTELLIGENCE INST