Abnormal Potential Extraction in QRS Complex Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for extracting abnormal potentials in the QRS complex from ECG signals are inadequate due to the embedded and weak nature of these signals, leading to low extraction accuracy and reliability, which is critical for early warning of sudden cardiac death.
Innovation Solution
A method combining nonlinear transform prediction and spline interpolation to estimate an ideal ECG signal, eliminating interference and accurately extracting abnormal potentials by preprocessing the signal, detecting feature points, and using spline weights for credibility evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If linear models or linear transformation techniques are used to extract AIQPs, then the extraction process is simple, but the extraction accuracy is insufficient because the QRS complex is a nonlinear signal
Solution Approach 1:
The patent transforms the QRS signal from time domain to frequency domain using wavelet transform, changing the representation parameters to expose hidden AIQPs that are not visible in the time domain. This parameter transformation enables accurate extraction of nonlinear characteristics while maintaining computational feasibility.
Solution Approach 2:
The patent replaces traditional linear transformation techniques with wavelet transform-based nonlinear analysis methods. This substitution allows the system to capture the nonlinear dynamics of the QRS complex and accurately extract embedded AIQPs that linear methods cannot detect.
2Measurement precision
If RBF neural network with many parameters is used to approximate QRS waves, then the approximation accuracy improves, but the device complexity and parameter adjustment burden increase significantly
Solution Approach 1:
The patent segments the QRS complex analysis into distinct frequency bands using wavelet transform. By decomposing the signal into different frequency components, the method identifies AIQPs in specific frequency ranges without requiring complex global modeling, thus reducing parameter adjustment complexity while maintaining accuracy.
Solution Approach 2:
Instead of adjusting numerous RBF neural network parameters, the patent changes the analysis approach by using wavelet transform coefficients as features. This parameter transformation eliminates the need for complex neural network training and parameter tuning while achieving comparable or superior approximation accuracy.
3Ease of operation
If only high frequency low amplitude fragmentation potential at QRS terminal is detected, then the detection method is simple, but the positive predictive value is low because AIQPs may be hidden within the QRS complex
Solution Approach 1:
The patent moves the detection from the time domain to the frequency domain using wavelet transform. This dimensional change allows detection of AIQPs that are embedded within the QRS complex in the time domain but become distinguishable in the frequency domain, significantly improving positive predictive value while maintaining operational simplicity.
Solution Approach 2:
The patent introduces wavelet transform as an intermediary that bridges the time domain ECG signal and the frequency domain representation. This intermediary transformation reveals hidden AIQPs without requiring complex direct time-domain analysis, improving detection reliability while keeping the method straightforward.
Data Source
AI summary
A method for accurately extracting an abnormal potential within a QRS, comprising: in an ideal electrocardiographic signal pre-estimation stage, pre-estimating an ideal electrocardiographic signal using a non-linear transformation technology; according to the pre-estimated ideal electrocardiographic signal, further estimating the ideal electrocardiographic signal by using a spline method, so as to accurately estimate the ideal electrocardiographic signal; and according to the accurately estimated ideal electrocardiographic signal, accurately extracting an abnormal potential within the QRS by means of a mobile standard deviation analysis technology. The method can be used not only on an average electrocardiographic signal after multiple superimposition, but also on a single beat electrocardiographic signal.