A cardiac state monitoring method based on ECG mapping signal eigenvalue change

Abstract

The application discloses a kind of ECG mapping signal characteristic value change heart state monitoring method, comprising the following steps: step 1, using electrocardiogram signal acquisition instrument obtains the ECG signal to be measured;Step 2, according to the signal to be measured obtained in step 1, establish transpose matrix;Step 3, the similarity of the transpose matrix of the signal to be measured in step 2 and the transpose matrix of reference signal is calculated;Step 4, according to the similarity calculated in step 3, whether the judgment of cardiac state anomaly is carried out.The application has the characteristics such as strong anti-noise interference ability, self-adaptability between different equipment, life state quick perception, can be quickly carried out after obtaining the robust identification of body state ECG signal.

Description

A method for monitoring cardiac status based on changes in ECG mapping signal features Technical Field

[0001] This invention relates to the fields of medical signal processing and vital health status monitoring, and in particular to a method for monitoring cardiac status based on changes in the characteristic values ​​of ECG mapping signals. Background Technology

[0002] According to a report by the World Health Organization (WHO), cardiovascular disease has become a leading cause of death worldwide, attracting widespread attention from researchers. Cardiac arrhythmias are the most common type of cardiovascular disease, including irregular heart rate or rhythm. Electrocardiogram (ECG) signals are easily affected by internal and external noise during acquisition, and the morphological characteristics of ECG signals vary significantly among different patients. Even for the same patient, ECG signals can differ at different times and under different environments. Therefore, accurately predicting changes in ECG mapping signal characteristics remains a challenge for robust monitoring of cardiac status. Thus, finding a method for monitoring cardiac status based on changes in ECG mapping signal characteristics and utilizing it for intelligent diagnosis of vital signs and health status, thereby reducing the misdiagnosis rate of ECG signals, has become an urgent problem to be solved. Summary of the Invention

[0003] The purpose of this invention is to provide a method for monitoring cardiac status based on changes in the feature values ​​of ECG mapping signals. This invention features strong resistance to noise interference, adaptability to different devices, and rapid perception of vital signs, enabling robust identification of bodily status quickly after acquiring ECG signals.

[0004] The technical solution of this invention: A method for monitoring cardiac status based on changes in ECG mapping signal feature values, comprising the following steps:

[0005] Step 1: Use an electrocardiogram (ECG) signal acquisition instrument to acquire the ECG signal to be measured;

[0006] Step 2: Establish the transpose matrix based on the signal to be tested obtained in Step 1;

[0007] Step 3: Calculate the similarity between the transpose matrix of the signal under test and the transpose matrix of the reference signal from Step 2;

[0008] Step 4: Determine whether the heart condition is abnormal based on the similarity calculated in Step 3.

[0009] In the above-mentioned cardiac state monitoring method based on changes in ECG mapping signal eigenvalues, the transpose matrix establishment algorithm in step 2 is as follows:

[0010] X = x × x T -mean(x×x T );

[0011] In the formula, X is the transpose matrix of signal x, T is the transpose sign, and mean(·) is the formula for calculating the average value.

[0012] In the aforementioned cardiac state monitoring method based on ECG mapping signal feature value changes, the similarity evaluation algorithm in step 3 is as follows:

[0013]

[0014] In the formula, S is the similarity of the transpose matrix, and X... x Let X be the transpose of signal x. ref is the transpose matrix of the reference signal.

[0015] In the aforementioned cardiac state monitoring method based on changes in ECG mapping signal feature values, the algorithm for determining whether the cardiac state is abnormal in step 4 is as follows:

[0016]

[0017] In the formula, S is the similarity of the transpose matrix, S th This is the preset similarity threshold for the transpose matrix.

[0018] Compared with existing technologies, this invention is based on ECG signals, which are easy to acquire and thus have the characteristics of rapid perception. At the same time, it obtains the transpose matrix of the signal under test through an algorithm to achieve filtering, thereby improving the resistance to noise interference. Furthermore, it calculates a similarity value with a fixed reference signal transpose matrix and compares it with a fixed similarity threshold. Each reference standard can be adjusted according to different devices to ensure its adaptability across different devices. The quantified similarity value also improves the accuracy of the comparison results, enabling robust identification of body status quickly after acquiring ECG signals. Attached Figure Description

[0019] Figure 1 is a flowchart of the present invention;

[0020] Figure 2 shows the time-domain waveform of the signal under test in Example 1;

[0021] Figure 3 shows the transpose matrix of the signal to be tested in Example 1;

[0022] Figure 4 shows the time-domain waveform of the normal signal in Example 1;

[0023] Figure 5 shows the transpose matrix of the normal signal in Example 1;

[0024] Figure 6 shows the confusion matrix of the judgment results of 600 signals to be tested in Example 2. Detailed Implementation

[0025] The present invention will be further described below with reference to the accompanying drawings and embodiments, but this should not be construed as limiting the present invention.

[0026] Example 1: A method for monitoring cardiac status based on changes in ECG mapping signal feature values, as shown in Figure 1, includes the following steps:

[0027] Step 1: Use an electrocardiogram (ECG) signal acquisition instrument to acquire the ECG signal to be measured, as shown in Figure 2;

[0028] Step 2: Establish the transpose matrix based on the signal to be tested obtained in Step 1, as shown in Figure 3; the algorithm for establishing the transpose matrix is ​​as follows:

[0029] X = x × x T -mean(x×x T );

[0030] In the formula, X is the transpose matrix of signal x, T is the transpose sign, and mean(·) is the formula for calculating the average value;

[0031] Step 3: Calculate the similarity between the transpose matrix of the signal to be tested from Step 2 and the transpose matrix of the reference signal; the similarity evaluation algorithm is as follows:

[0032]

[0033] In the formula, S is the similarity of the transpose matrix, and X... x Let X be the transpose of signal x. ref The transpose matrix of the reference signal is given. The waveform and transpose matrix of the normal signal are shown in Figures 4 and 5. The matrix similarity in this embodiment is calculated to be 0.864.

[0034] Step 4: Determine whether the heart condition is abnormal based on the similarity calculated in Step 3; the algorithm for determining whether the heart condition is abnormal is as follows:

[0035]

[0036] In the formula, S is the similarity of the transpose matrix, S th The preset similarity threshold for the transpose matrix is ​​0.6 in this embodiment. The previously obtained matrix similarity is greater than this value, therefore the sample in this embodiment is arrhythmic.

[0037] Example 2: A method for monitoring cardiac status based on changes in ECG mapping signal feature values, comprising the following steps:

[0038] Step 1: Obtain the ECG signals of 600 samples from the MIT-BIH public dataset;

[0039] Step 2: Establish the transpose matrix based on the signal to be tested obtained in Step 1; the algorithm for establishing the transpose matrix is ​​as follows:

[0040] X = x × x T -mean(x×x T );

[0041] In the formula, X is the transpose matrix of signal x, T is the transpose sign, and mean(·) is the formula for calculating the average value;

[0042] Step 3: Calculate the similarity between the transpose matrix of the signal to be tested from Step 2 and the transpose matrix of the reference signal; the similarity evaluation algorithm is as follows:

[0043]

[0044] In the formula, S is the similarity of the transpose matrix, and X... x Let X be the transpose of signal x. ref This is the transpose matrix of the reference signal;

[0045] Step 4: Determine whether the heart condition is abnormal based on the similarity calculated in Step 3; the algorithm for determining whether the heart condition is abnormal is as follows:

[0046]

[0047] In the formula, S is the similarity of the transpose matrix, S th The preset similarity threshold for the transpose matrix;

[0048] The confusion matrix of the results is shown in Figure 6. Only 65 out of 600 samples were incorrectly judged, and the success rate of the proposed method was 89.17%.

Claims

1. A method for monitoring cardiac status based on changes in ECG mapping signal feature values, characterized in that: The process includes the following steps: Step 1, acquiring the ECG signal to be tested using an ECG signal acquisition instrument; Step 2, establishing a transpose matrix based on the signal obtained in Step 1; Step 3, calculating the similarity between the transpose matrix of the signal to be tested obtained in Step 2 and the transpose matrix of the reference signal; Step 4, determining whether the heart condition is abnormal based on the similarity calculated in Step 3; The algorithm for establishing the transpose matrix in Step 2 is as follows: In the formula, For signal The transpose of the matrix, It is the transpose symbol. This is the formula for calculating the average value.

2. The cardiac state monitoring method based on ECG mapping signal feature value changes according to claim 1, characterized in that: The similarity evaluation algorithm in step 3 is as follows: In the formula, For the similarity of transpose matrices, For signal The transpose of the matrix, is the transpose matrix of the reference signal.

3. The cardiac state monitoring method based on ECG mapping signal feature value changes according to claim 1, characterized in that: The algorithm for determining whether the heart condition is abnormal in step 4 is as follows: In the formula, For the similarity of transpose matrices, This is the preset similarity threshold for the transpose matrix.

Images