A J-wave identification and extraction method, device and medium

Abstract

The invention discloses a method, device and medium for identifying and extracting J waves. The steps of the method include: acquiring an electrocardiographic signal, and extracting a QRS complex wave from the electrocardiographic signal; selecting a reference point of the QRS complex wave, and intercepting the reference point The complex wave segment under the preset interval after the complex wave segment; the Legendre transform is performed on the complex wave segment to obtain the coefficient vector, and the coefficient vector is constructed as a decision function through the secondary discriminant analysis algorithm; The target complex wave segment of the wave; convert the target complex wave segment into a delay covariance matrix, diagonalize the delay covariance matrix and obtain a cost function with the minimum degree of diagonalization; the cost function is adjusted by the preset regularization Constraints are made to generate a mixing matrix, and the mixing matrix is ​​passed to extract the J-wave. This method can identify and extract J waves relatively accurately. In addition, the present invention also provides a device for identifying and extracting J waves and a medium, and the beneficial effects are as described above.

Description

technical field [0001] The invention relates to the field of medical analysis, in particular to a method, device and medium for identifying and extracting J waves. Background technique [0002] The J point is the connection point between the end of the QRS complex and the beginning of the ST segment in the ECG. If the J point is elevated and its waveform is hump-shaped or dome-shaped, this special waveform is called a J wave. [0003] Electrophysiologists who study the mechanism of early sudden death of acute myocardial ischemia collectively refer to syndromes with J-wave ECG characteristics, including Bmgada syndrome, characteristic ventricular fibrillation, hyperacute phase of acute coronary syndrome, and early negative pole syndrome. "J wave syndrome", J wave can be used as an indicator for doctors to diagnose ventricular tachycardia, ventricular fibrillation, malignant arrhythmia and other ECG pathological features. In actual use, the amplitude of the J wave is often sm...

AI Technical Summary

Problems solved by technology

[0004] At present, the identification method of J wave is mainly the hidden Markov method. When identifying the J wave through the hidden Markov method, it mainly obtains the ECG signal characteristics in the past time series through the corresponding classifier, but the characteristics must be satisfied. There is strict mutual independence between them, otherwise it will affect the accuracy of recognition

In addition, the current extraction method for J wave is mainly the sparse component analysis through K-means clustering algorithm, but since the ECG signal often does not satisfy the sparsity, it cannot guarantee that the J wave can be accurately extracted

Images