Electrocardiogram st analysis method, apparatus, medium, and device

Abstract

The application discloses an electrocardiogram ST analysis method, device, medium and equipment, acquires a monitored electrocardiogram signal, and identifies an R wave peak point in the electrocardiogram signal; the electrocardiogram signal is divided into a plurality of heartbeat segments based on the R wave peak point; the heartbeat segments in each preset time length are aligned and similarity is judged, and a standard heartbeat meeting a condition is selected; an average offset of the standard heartbeat in an ST segment is calculated, and a standard ST value in the preset time length is obtained. The application has the advantages of simple implementation, high algorithm calculation efficiency and stable ST calculation.

Description

Technical Field

[0001] This invention relates to the field of technology, and in particular to a method, apparatus, medium, and device for electrocardiogram ST segment analysis. Background Technology

[0002] An electrocardiogram (ECG) is a method of recording the electrical activity of the heart. The ST segment refers to the period from ventricular systole (QRS complex) to ventricular repolarization (the end of the T wave). Changes in the ST segment provide important information, but the waveform variations in the ST segment are diverse, and current methods for analyzing the ST segment are far less mature than those for analyzing the QRS complex.

[0003] Existing ECG ST segment analysis methods, both domestically and internationally, such as the J+X method and the R+X method, are quite complex and lack both universality and accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide methods, devices, media, and equipment for ECG ST analysis to address the problem that existing methods are difficult to achieve both universality and accuracy.

[0005] An electrocardiogram ST segment analysis method, the method comprising:

[0006] Acquire the monitored electrocardiogram signals;

[0007] Identify the R-wave peak point in the electrocardiogram (ECG) signal, and divide the ECG signal into multiple heartbeat segments based on the R-wave peak point;

[0008] Multiple heartbeat segments within each preset duration are aligned with the R-wave peak point as a reference. The first similarity condition is determined based on the difference in curve length between heartbeat segments, and the second similarity condition is determined based on the difference in cosine similarity between heartbeat segments. Heartbeat segments that simultaneously meet the first and second similarity conditions are taken as standard heartbeats.

[0009] The average offset of all standard heartbeats in the ST segment is calculated, and the standard ST value within a preset time period is calculated based on the average offset.

[0010] In one embodiment, the determination of the first similarity condition based on the curve length difference between heartbeat segments and the determination of the second similarity condition based on the cosine similarity difference between heartbeat segments include:

[0011] Calculate the curve length of each heartbeat segment in the discrete state, and sort all heartbeat segments within a preset time based on the length of the curve to obtain the first sorting result;

[0012] In the first sorting result, all heartbeat segments for which the difference in curve length between every two heartbeat segments is less than a preset length threshold are identified as satisfying the first similarity condition;

[0013] Calculate the cosine similarity between every two heartbeat segments pairwise, sort all heartbeat segments within a preset duration based on the magnitude of the cosine similarity, to obtain a second sorting result;

[0014] In the second sorting result, the top preset number of heartbeat segments with the largest cosine similarity are identified as satisfying the second similarity condition.

[0015] In one embodiment, the calculation formula for calculating the curve length of each heartbeat segment in a discrete state is:

[0016]

[0017] In the above formula, w is the length of the time window; w+1<i<N, N is the total number of sampling points, w≤N; Δy i =y i -y i-1 , Δy i represents the amplitude difference between two adjacent sampling points y i and y i-1 , Δt represents the time difference between two adjacent sampling points y i and y i-1 .

[0018] In one embodiment, the calculation formula for the cosine similarity between two heartbeat segments comprises:

[0019]

[0020] Wherein, X i indicates the amplitude of the i-th sampling point of heartbeat segment X, Y i indicates the amplitude of the i-th sampling point of heartbeat segment Y, and n is the total number of sampling points.

[0021] In one embodiment, said identifying R-wave peak points in said electrocardiogram signal comprises:

[0022] Acquiring a preset reference amplitude, and correcting the reference amplitude according to the baseline of a target QRS complex in the electrocardiogram signal, to obtain a corrected reference amplitude corresponding to the target QRS complex; wherein the electrocardiogram signal comprises a plurality of QRS complexes, and the target QRS complex is any one of the plurality of QRS complexes in the electrocardiogram signal;

[0023] Calculate the difference between the amplitude of each sampling point in the target QRS group and the corresponding corrected reference amplitude to obtain multiple amplitude differences, and take the sampling point corresponding to the maximum value of the multiple amplitude differences as the R-wave peak point of the target QRS group.

[0024] In one embodiment, dividing the electrocardiogram signal into multiple heartbeat segments based on the R-wave peak point includes:

[0025] The time difference between the R-wave peak point of the target QRS group and the R-wave peak point of the adjacent QRS group is taken as the RR interval of the target QRS group; wherein, the adjacent QRS group is the previous QRS group or the next QRS group of the target QRS group.

[0026] The average RR interval of all QRS complexes is used as the baseline heartbeat length. The range extending forward and backward by half of the baseline heartbeat length from the R wave peak point of each QRS complex is used as the heartbeat segment to obtain the multiple heartbeat segments.

[0027] In one embodiment, after dividing the electrocardiogram signal into multiple heartbeat segments based on the R-wave peak point, the method further includes:

[0028] The validity of each heartbeat segment is analyzed based on its rhythm, frequency, and variability, and the heartbeat segments that are deemed invalid by the analysis are deleted.

[0029] An electrocardiogram ST segment analysis device, the device comprising:

[0030] The cardiac segmentation module is used to acquire the monitored electrocardiogram (ECG) signal; and to identify the R-wave peak point in the ECG signal, and to divide the ECG signal into multiple cardiac segments based on the R-wave peak point.

[0031] The standard heartbeat screening module is used to align multiple heartbeat segments within each preset duration based on the R-wave peak point, and to determine the first similarity condition based on the curve length difference between heartbeat segments, and to determine the second similarity condition based on the cosine similarity difference between heartbeat segments, and to select heartbeat segments that meet both the first similarity condition and the second similarity condition as standard heartbeats.

[0032] The ST analysis module is used to calculate the average offset of all standard heartbeats in the ST segment and to calculate the standard ST value within a preset time period based on the average offset.

[0033] A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the above-described electrocardiogram ST analysis method.

[0034] An electrocardiogram (ECG) ST segment analysis device includes a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the ECG ST segment analysis described above.

[0035] This invention provides a method, apparatus, medium, and device for ST segment analysis of electrocardiograms (ECGs), including acquiring ECG signals and segmenting them into heartbeat segments based on the R-wave peak point. Heartbeat segments within each preset duration are aligned, and standard heartbeats are selected based on differences in curve length and cosine similarity. The average offset of all standard heartbeats in the ST segment is calculated to obtain the standard ST value within the preset duration. This invention is characterized by its simplicity, high algorithm efficiency, and stable ST calculation. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] in:

[0038] Figure 1 This is a flowchart illustrating the ST segment analysis method for electrocardiograms.

[0039] Figure 2 A diagram illustrating a single heartbeat segment;

[0040] Figure 3 This is a schematic diagram of the ST segment analysis device for electrocardiogram.

[0041] Figure 4 This is a structural block diagram of an electrocardiogram ST segment analysis device. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0044] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0045] like Figure 1 As shown, Figure 1 This is a flowchart illustrating an ECG ST segment analysis method in one embodiment. The steps provided by the ECG ST segment analysis method in this embodiment include:

[0046] S101, acquire the monitored electrocardiogram signal.

[0047] Among them, the electrocardiogram (ECG) signal is a bioelectrical signal that reflects the electrical activity of the heart. The ECG signal is generally composed of multiple leads, with 12 commonly used leads, divided into four parts: limb leads, precordial leads, enhancement leads, and right precordial leads.

[0048] Digital filtering can be performed on the ECG signal of each lead to remove various noises and interferences. Specifically, a finite impulse response (FIR) filter designed using the window function method can eliminate 50Hz power frequency interference generated by the power grid or other equipment. Next, a median filter is used to eliminate baseline drift interference caused by breathing or changes in body position. Finally, a 30Hz low-pass filter is used to eliminate high-frequency interference caused by muscle contraction or other factors. After these filtering processes, the resulting ECG signal is smoother and clearer, facilitating subsequent analysis and diagnosis.

[0049] S102 identifies the R-wave peak point in the electrocardiogram (ECG) signal and divides the ECG signal into multiple heartbeat segments based on the R-wave peak point.

[0050] Among them, such as Figure 2 As shown, Figure 2This is a schematic diagram of a single heartbeat segment. The R-wave peak point refers to the time point when the R-wave reaches its maximum amplitude. A heartbeat segment refers to the signal portion of an electrocardiogram (ECG) signal corresponding to a complete process of cardiac contraction and relaxation, reflecting the heart's pulsating cycle and rhythm.

[0051] In one specific implementation, the peak point of the R wave in the electrocardiogram signal is identified through the following steps:

[0052] (1) Obtain the preset reference amplitude and correct the reference amplitude according to the baseline of the target QRS complex in the electrocardiogram signal to obtain the corrected reference amplitude corresponding to the target QRS complex.

[0053] The electrocardiogram (ECG) signal contains multiple QRS complexes, and the target QRS complex is any one of the multiple QRS complexes in the ECG signal. In other words, the same correction operation is performed on all QRS complexes.

[0054] The baseline is a horizontal line in an electrocardiogram (ECG) signal that does not show waveform changes. It represents the heart's potential at rest. The baseline amplitude is the amplitude of the baseline. The baseline may drift differently in different QRS complexes, so it needs to be adaptively corrected according to the baseline.

[0055] Here, a straight line can be drawn between the starting points of the first and second QRS groups, and the slope of this line can be calculated. The drift value of different QRS groups relative to the reference amplitude can then be determined based on the slope. The corresponding drift value is then added to the reference amplitude of each QRS group to obtain the corrected reference amplitude.

[0056] (2) Calculate the difference between the amplitude of each sampling point in the target QRS group and the corresponding corrected reference amplitude to obtain multiple amplitude differences, and take the sampling point corresponding to the maximum value of the multiple amplitude differences as the R-wave peak point of the target QRS group.

[0057] Here, a sampling point refers to the voltage value recorded at regular time intervals in the electrocardiogram (ECG) signal, representing the electrical activity of the heart at a certain moment. The maximum value among multiple amplitude differences represents the highest and sharpest sampling point in the target QRS complex, i.e., the R-wave peak point.

[0058] In one specific implementation, the electrocardiogram signal is divided into multiple heartbeat segments through the following steps:

[0059] (1) The time difference between the R-wave peak point of the target QRS group and the R-wave peak point of the adjacent QRS group is taken as the RR interval of the target QRS group.

[0060] In this context, the adjacent QRS complex is either the preceding or following QRS complex of the target QRS complex; the adjacent QRS complex is adjacent to the target QRS complex but does not overlap. The RR interval represents a complete cardiac beat cycle.

[0061] (2) Take the average of the RR intervals of all QRS complexes as the baseline heartbeat length, and take the R wave peak point of each QRS complex as the center and extend half of the baseline heartbeat length forward and backward as the heartbeat segment to obtain multiple heartbeat segments.

[0062] This step is to divide the ECG signal into several independent and complete segments, each containing an R-wave peak and a certain range of signals before and after it. The baseline beat length refers to the average RR interval of all QRS complexes, representing a typical heartbeat cycle. Extending half the baseline beat length forward and backward from the R-wave peak of each QRS complex as a beat segment ensures that each beat segment contains complete and symmetrical P, Q, S, and T waves.

[0063] In one specific implementation, the following steps are also performed: each heartbeat segment is analyzed for validity based on its rhythm, frequency, and variability, and heartbeat segments that are invalid according to the analysis are deleted.

[0064] For example, by analyzing the rhythm, frequency, and variability of heartbeat segments, if the heartbeat is identified as a premature ventricular contraction, ventricular escape beat, ventricular tachycardia, or other ECG signals that cannot be effectively analyzed by ST segment, the heartbeat segment can be directly declared invalid and deleted, and an alarm can be issued.

[0065] S103, align multiple heartbeat segments within each preset duration with the R-wave peak point as the reference, and determine the first similarity condition based on the curve length difference between heartbeat segments, and determine the second similarity condition based on the cosine similarity difference between heartbeat segments, and take the heartbeat segment that meets both the first and second similarity conditions as the standard heartbeat.

[0066] Optionally, a preset duration of 1 minute is set, and ECG segments that can be effectively calculated within each minute are extracted and aligned with the R wave peak point as a reference. This ensures that all heartbeat segments are on the same baseline, facilitating subsequent similarity judgment.

[0067] According to the ECG theory, the myocardial electrical activity can be regarded as a synthetic electric dipole vector moving in a conductive space. The trajectory of the end point of the electric dipole vector forms a spatial curve, and its projections on each axis form corresponding cardiac electric potential differences. Based on this theory, in this embodiment, the first similarity condition is judged based on the curve length difference between heartbeat segments, and the second similarity condition is judged based on the cosine similarity difference between heartbeat segments, so as to select heartbeat waveforms that have both similar curve lengths and similar cosine similarities from all heartbeat waveforms, and use them as standard heartbeats representing normal heart function and ST segment changes.

[0068] In a specific implementation, the judgment of the first similarity condition and the second similarity condition is performed through the following steps, including:

[0069] (1) Calculate the curve length of each heartbeat segment in a discrete state, and sort all heartbeat segments within a preset duration based on the length of the curve to obtain a first sorting result.

[0070] Specifically, first in a continuous situation, the integral formula for curve length is:

[0071]

[0072] In the above formula, w is the length of the time window, y is the amplitude of the ECG signal, and t is time (unit: ms);

[0073] Since the ECG signal reflects voltage values at different discrete sampling points, the above formula is rewritten to calculate the curve length of each heartbeat segment in the discrete state, and the calculation formula is:

[0074]

[0075] In the above formula, w is the length of the time window; w+1<i<N, N is the total number of sampling points, w<<N; Δy i =y i -y i-1 , Δy i represents the amplitude difference between two adjacent sampling points y i and y i-1 , and Δt represents the time difference between two adjacent sampling points y i and y i-1 .

[0076] On this basis, all heartbeat segments within a preset duration are sorted based on the length of the curve, and the obtained first sorting result can be recorded as [L1,L2,L3……L P , where P is the total number of all calculated heartbeat segments, L1 is the maximum, and L P is the minimum.

[0077] (2) In the first sorting result, all heart beat segments that satisfy the condition that the difference in curve length between any two heart beat segments is less than the preset length threshold are identified as meeting the first similarity condition.

[0078] For example, if the preset length threshold is ΔL, and L1-L3 is less than ΔL, then the heartbeat segments corresponding to L1, L2, and L3 satisfy the first similarity condition; and if L5-L 10 If it is less than ΔL, then from L5 to L 10 The corresponding heartbeat fragments satisfy the first similarity condition.

[0079] (3) Calculate the cosine similarity between two heartbeat segments in pairs, and sort all heartbeat segments within the preset time based on the magnitude of the cosine similarity to obtain the second sorting result.

[0080] The formula for calculating the cosine similarity between two heartbeat segments is as follows:

[0081]

[0082] Among them, X i Indicates the amplitude of the i-th sampling point of the heartbeat segment X, Y i The amplitude of the i-th sampling point of the heartbeat segment Y is indicated, where n is the total number of sampling points.

[0083] Based on this, all heartbeat segments within a preset duration are sorted according to the magnitude of cosine similarity. The resulting second sorting result can be denoted as... cosθ1 is the largest. Minimum.

[0084] (4) In the second sorting results, the first preset number of heartbeat segments with the highest cosine similarity are identified as meeting the second similarity condition.

[0085] For example, if the preset number is set to 10, then the two heartbeat segments corresponding to cosθ1 can be identified as meeting the second similarity condition. Similarly, the two heartbeat segments corresponding to cosθ2 can be identified as meeting the second similarity condition, and so on, until cosθ 10 The two corresponding heartbeat segments were identified as meeting the second similarity criteria.

[0086] For example, if the pairwise differences between heartbeat segments A, B, and C are less than a preset length threshold, then these heartbeat segments are considered to meet the first similarity condition; and if the pairwise cosine similarity between heartbeat segments A, B, and C all belong to the largest preset number, then these heartbeat segments are considered to meet the second similarity condition. Heartbeat segments A, B, and C can be used as standard heartbeats. Of course, the number of standard heartbeats is not limited.

[0087] S104, calculate the average offset of all standard heartbeats in the ST segment, and calculate the standard ST value within a preset time period based on the average offset.

[0088] First, locate the ST segment, such as... Figure 2 As shown, the ST segment is a horizontal line segment from the end of the R peak to the beginning of the T wave. The ST segment can be located above and below the R peak using ECG analysis software or specialized equipment.

[0089] Next, select the calculation time or time window. You can choose a specific time or set a fixed time window to calculate the ST value as needed. For example, the ST value can be calculated within 20 milliseconds after the R peak.

[0090] Next, calculate the average offset of the ST segment. This involves first summing the values ​​of all sampling points on the ST segment and dividing by the number of sampling points to obtain the offset of a segment, and then taking the average of the offsets of all segments to obtain the average offset.

[0091] Finally, calculate the ST value: Within the selected time point or time window, compare the ST segment offset with the baseline. The ST value can be calculated using the following formula: ST = Average ST segment offset - Baseline value.

[0092] Here, the baseline value is typically the amplitude of the R peak. Furthermore, unit conversion can be performed as needed: depending on the actual requirements, the ST value can be converted from its original unit to millivolts (mV) or microvolts (μV).

[0093] The aforementioned ECG ST segment analysis method includes acquiring the ECG signal and segmenting it into heart beat segments based on the R-wave peak point. Heart beat segments within each preset duration are aligned, and standard heart beats are selected based on differences in curve length and cosine similarity. The average offset of all standard heart beats in the ST segment is calculated to obtain the standard ST value within the preset duration. This invention is characterized by its simplicity, high computational efficiency, and stable ST calculation.

[0094] In one embodiment, such as Figure 3 As shown, an electrocardiogram ST segment analysis device is proposed, which includes:

[0095] A heartbeat segment division module 301, configured to acquire a detected electrocardiogram signal; identify R-wave peak points in the electrocardiogram signal, and divide the electrocardiogram signal into a plurality of heartbeat segments based on the R-wave peak points;

[0096] A standard heartbeat screening module 302, configured to align multiple heartbeat segments within each preset duration based on R-wave peak points, perform a first similarity condition judgment based on curve length differences between heartbeat segments, perform a second similarity condition judgment based on cosine similarity differences between heartbeat segments, and take the heartbeat segments that simultaneously satisfy the first similarity condition and the second similarity condition as standard heartbeats;

[0097] An ST analysis module 303, configured to obtain an average offset of all standard heartbeats in the ST segment, and calculate a standard ST value within the preset duration according to the average offset.

[0098] In one embodiment, the performing of a first similarity condition judgment based on curve length differences between heartbeat segments, and performing a second similarity condition judgment based on cosine similarity differences between heartbeat segments comprises: calculating a curve length of each heartbeat segment in a discrete state, sorting all heartbeat segments within the preset duration based on the length of the curve, to obtain a first sorting result; in the first sorting result, all heartbeat segments in which the difference in curve length between every two heartbeat segments is less than a preset length threshold are determined to satisfy the first similarity condition; calculating the cosine similarity between every two heartbeat segments, sorting all heartbeat segments within the preset duration based on the magnitude of the cosine similarity, to obtain a second sorting result; in the second sorting result, the first preset number of heartbeat segments with the largest cosine similarity is determined to satisfy the second similarity condition.

[0099] In one embodiment, the calculation formula for calculating the curve length of each heartbeat segment in the discrete state is:

[0100]

[0101] In the above formula, w is the length of a time window; w+1<i<N, N is the total number of sampling points, w<N; Δy i =y i -y i-1 , Δy i represents the amplitude difference between two adjacent sampling points y i and y i-1 , Δt represents the time difference between two adjacent sampling points y i and y i-1 .

[0102] In one embodiment, the formula for calculating the cosine similarity between two heartbeat segments includes:

[0103]

[0104] Among them, X i Indicates the amplitude of the i-th sampling point of the heartbeat segment X, Y i The amplitude of the i-th sampling point of the heartbeat segment Y is indicated, where n is the total number of sampling points.

[0105] In one embodiment, identifying the R-wave peak point in the electrocardiogram (ECG) signal includes: acquiring a preset reference amplitude, and correcting the reference amplitude according to a baseline of a target QRS complex in the ECG signal to obtain a corrected reference amplitude corresponding to the target QRS complex; wherein the ECG signal contains multiple QRS complexes, and the target QRS complex is any one of the multiple QRS complexes in the ECG signal; calculating the difference between the amplitude of each sampling point in the target QRS complex and the corresponding corrected reference amplitude to obtain multiple amplitude differences, and taking the sampling point corresponding to the maximum value among the multiple amplitude differences as the R-wave peak point of the target QRS complex.

[0106] In one embodiment, dividing the ECG signal into multiple heartbeat segments based on the R-wave peak point includes: using the time difference between the R-wave peak point of the target QRS complex and the R-wave peak point of an adjacent QRS complex as the RR interval of the target QRS complex; wherein the adjacent QRS complex is the previous or next QRS complex of the target QRS complex; using the average value of the RR intervals of all QRS complexes as the reference heartbeat length, and extending half of the reference heartbeat length forward and backward from the R-wave peak point of each QRS complex as a heartbeat segment to obtain the multiple heartbeat segments.

[0107] In one embodiment, after dividing the electrocardiogram signal into multiple heartbeat segments based on the R-wave peak point, the method further includes: performing an effectiveness analysis on each heartbeat segment based on the rhythm, frequency, and variability of each heartbeat segment, and deleting heartbeat segments that are invalid according to the analysis results.

[0108] Figure 4 An internal structural diagram of an ECG ST segment analysis device in one embodiment is shown. Figure 4As shown, the ECG ST segment analysis device includes a processor, a memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement the ECG ST segment analysis method. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to perform the ECG ST segment analysis method. Those skilled in the art will understand that… Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the ECG ST analysis device to which the present application is applied. A specific ECG ST analysis device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0109] A computer-readable storage medium storing a computer program, which, when executed by a processor, performs the following steps: acquiring a monitored electrocardiogram (ECG) signal; identifying the R-wave peak point in the ECG signal and dividing the ECG signal into multiple heartbeat segments based on the R-wave peak point; aligning multiple heartbeat segments within each preset duration based on the R-wave peak point, and determining a first similarity condition based on the curve length difference between heartbeat segments, and a second similarity condition based on the cosine similarity difference between heartbeat segments, and taking heartbeat segments that simultaneously meet the first similarity condition and the second similarity condition as standard heartbeats; calculating the average offset of all standard heartbeats in the ST segment, and calculating the standard ST value within the preset duration based on the average offset.

[0110] An electrocardiogram (ECG) ST segment analysis device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following steps: acquiring a monitored ECG signal; identifying the R-wave peak point in the ECG signal and dividing the ECG signal into multiple heartbeat segments based on the R-wave peak point; aligning multiple heartbeat segments within each preset duration based on the R-wave peak point, and determining a first similarity condition based on the curve length difference between heartbeat segments, and a second similarity condition based on the cosine similarity difference between heartbeat segments; selecting heartbeat segments that simultaneously meet both the first and second similarity conditions as standard heartbeats; calculating the average offset of all standard heartbeats in the ST segment, and calculating the standard ST value within the preset duration based on the average offset.

[0111] It should be noted that the above-mentioned ECG ST analysis method, apparatus, device, and computer-readable storage medium belong to the same general inventive concept, and the contents of the embodiments of the ECG ST analysis method, apparatus, device, and computer-readable storage medium are applicable to each other.

[0112] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0113] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for ST segment analysis in electrocardiogram, characterized in that, The method includes: Acquire the monitored electrocardiogram signals; The R-wave peak point in the electrocardiogram (ECG) signal is identified, and the ECG signal is divided into multiple heartbeat segments based on the R-wave peak point. The validity of each heartbeat segment is analyzed based on the rhythm, frequency, and variability of each heartbeat segment, and the heartbeat segments that are invalid according to the analysis result are deleted. Multiple heartbeat segments within each preset duration are aligned with the R-wave peak point as a reference. The first similarity condition is determined based on the difference in curve length between heartbeat segments, and the second similarity condition is determined based on the difference in cosine similarity between heartbeat segments. Heartbeat segments that simultaneously meet the first and second similarity conditions are taken as standard heartbeats. Obtain the average offset of all standard heartbeats in the ST segment, and calculate the standard ST value within a preset time period based on the average offset; The identification of the R-wave peak point in the electrocardiogram signal includes: A preset reference amplitude is obtained, and the reference amplitude is corrected according to the baseline of the target QRS complex in the ECG signal to obtain the corrected reference amplitude corresponding to the target QRS complex; wherein, the ECG signal contains multiple QRS complexes, and the target QRS complex is any one of the multiple QRS complexes in the ECG signal; the difference between the amplitude of each sampling point in the target QRS complex and the corresponding corrected reference amplitude is calculated to obtain multiple amplitude differences, and the sampling point corresponding to the maximum value among the multiple amplitude differences is taken as the R-wave peak point of the target QRS complex.

2. The method according to claim 1, characterized in that, The determination of the first similarity condition based on the curve length difference between heartbeat segments and the determination of the second similarity condition based on the cosine similarity difference between heartbeat segments include: Calculate the curve length of each heartbeat segment in the discrete state, and sort all heartbeat segments within a preset time based on the length of the curve to obtain the first sorting result; In the first sorting result, all heartbeat segments that satisfy the condition that the difference in curve length between any two heartbeat segments is less than a preset length threshold are identified as meeting the first similarity condition. Calculate the cosine similarity between two heartbeat segments pairwise, and sort all heartbeat segments within a preset time period based on the magnitude of the cosine similarity to obtain a second sorting result; In the second sorting result, the first preset number of heartbeat segments with the highest cosine similarity are identified as meeting the second similarity condition.

3. The method according to claim 2, characterized in that, The formula for calculating the curve length of each heartbeat segment in a discrete state is as follows: In the above formula, The time window length; w+1 N is the total number of sampling points. ; , Indicates two adjacent sampling points and The difference in amplitude between them Indicates two adjacent sampling points and The time difference between them.

4. The method according to claim 2, characterized in that, The formula for calculating the cosine similarity between two heartbeat segments is as follows: in, Indicates the amplitude of the i-th sampling point of the heartbeat segment X. The amplitude of the i-th sampling point of the heartbeat segment Y is indicated, where n is the total number of sampling points.

5. The method according to claim 1, characterized in that, The process of dividing the electrocardiogram signal into multiple heartbeat segments based on the R-wave peak point includes: The time difference between the R-wave peak point of the target QRS group and the R-wave peak point of the adjacent QRS group is taken as the RR interval of the target QRS group; wherein, the adjacent QRS group is the previous QRS group or the next QRS group of the target QRS group. The average RR interval of all QRS complexes is used as the baseline heartbeat length. The range extending forward and backward by half of the baseline heartbeat length from the R wave peak point of each QRS complex is used as the heartbeat segment to obtain the multiple heartbeat segments.

6. An electrocardiogram ST segment analysis device, characterized in that, The apparatus for performing the method as described in any one of claims 1-5, the apparatus comprising: The cardiac segmentation module is used to acquire the monitored electrocardiogram (ECG) signal; and to identify the R-wave peak point in the ECG signal, and to divide the ECG signal into multiple cardiac segments based on the R-wave peak point. The standard heartbeat screening module is used to align multiple heartbeat segments within each preset duration based on the R-wave peak point, and to determine the first similarity condition based on the curve length difference between heartbeat segments, and to determine the second similarity condition based on the cosine similarity difference between heartbeat segments, and to select heartbeat segments that meet both the first similarity condition and the second similarity condition as standard heartbeats. The ST analysis module is used to obtain the average offset of all standard heartbeats in the ST segment, and to calculate the standard ST value within a preset time period based on the average offset.

7. A computer-readable storage medium, characterized in that, The device stores a computer program that, when executed by a processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 5.

8. An electrocardiogram ST segment analysis device, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 5.

Images