Myocardial ischemia identification method and system based on three-dimensional dynamic parameters of magnetic heart space and time

Abstract

The present invention belongs to the technical field of magnetocardiographic data processing, and provides a method and system for identifying myocardial ischemia based on magnetocardiographic spatiotemporal three-dimensional dynamic parameters. The method and system analyze and process a magnetocardiogram and generate six block data sets by segmentation. The spatial and temporal characteristics of the six block data sets are processed and analyzed to effectively explore the distribution law of characteristic parameters, and the characteristic parameters are fully utilized to screen sensitive characteristic parameters of myocardial ischemia. At the same time, a model for identifying myocardial ischemia can be constructed, and the spatial indicators and temporal characteristics of each dimension of the magnetocardiogram are fully combined and utilized, thereby avoiding a complex source reconstruction process, fully reflecting the rich information that the magnetocardiogram can reflect, and the physical meaning of the indicators is intuitive and clear.

Description

Technical Field

[0001] The present invention belongs to the technical field of magnetocardiographic data processing, and in particular relates to a method and system for identifying myocardial ischemia based on magnetocardiographic spatiotemporal three-dimensional dynamic parameters. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Magnetocardiography (MCG) is a technology that detects changes in the human heart's magnetic signals. The magnetocardiograph based on spin-exchange relaxation-free (SERF) has high sensitivity and can clearly display the heart's magnetic signals and their changing patterns. It has the advantages of non-cold operation, miniaturization, non-invasiveness, no radiation, and non-contact, providing more accurate auxiliary detection for heart diseases such as myocardial ischemia.

[0004] The magnetocardiography equipment includes array-type SERF sensors with 32 channels, 36 channels, 64 channels and other specifications. The sensor probes form a plane, and each probe position can detect the corresponding magnetocardiogram. The one-dimensional butterfly diagram is a simple superposition of the magnetocardiogram line diagrams of all channels, while the two-dimensional isomagnetic diagram is a plane diagram drawn according to the magnetic field strength of each probe by intercepting the one-dimensional butterfly diagram at a certain moment.

[0005] The effectiveness of magnetocardiography in diagnosing cardiovascular diseases depends on the effective use of data, so magnetocardiography data processing technology is very important. At present, the data for magnetocardiography uses characteristic parameters extracted from traditional one-dimensional and two-dimensional magnetocardiography. These traditional magnetocardiography parameters are relatively simple in identifying diseases and have limited effectiveness. Myocardial ischemia affects the dynamic process of depolarization and repolarization of a certain part of the myocardium. The electromagnetic activity of ischemic myocardium is not stable, and there are often dynamic and irregular spatiotemporal changes in magnetocardiography signals, which will be reflected in the irregularity of the spatial distribution of magnetocardiography signals and the signal fluctuations in time dynamics.

[0006] In summary, the current processing and understanding of the dynamic changes of key cardiac magnetic parameters in time and space are very lacking, and the important signals of myocardial ischemia are often hidden in the differences in these dynamic changes, and new data processing methods are urgently needed. Summary of the invention

[0007] In order to solve the above technical problems, the present invention proposes a myocardial ischemia identification method and system based on magnetocardiogram three-dimensional dynamic parameters in space-time. The method analyzes and processes the magnetocardiogram and generates six block data sets by segmentation. The spatial and temporal characteristics of the six block data sets are processed and analyzed to effectively explore the distribution law of characteristic parameters, and the characteristic parameters are fully utilized to screen sensitive characteristic parameters of myocardial ischemia. At the same time, a model for myocardial ischemia identification can be constructed, and the spatial indicators and temporal characteristics of each dimension of the magnetocardiogram are fully combined and utilized, thereby avoiding a complex source reconstruction process, fully reflecting the rich information that the magnetocardiogram can reflect, and the physical meaning of the indicators is intuitive and clear.

[0008] The technical solution of the present invention is:

[0009] The present invention proposes a method for identifying myocardial ischemia based on three-dimensional magnetic-temporal-spatial dynamic parameters, comprising the following steps:

[0010] S1, obtain the initial dataset of magnetocardiogram containing multiple channels;

[0011] S2, processing multiple channels in the initial data set, collecting and extracting characteristic parameters in each channel, and constructing a sample data set containing the characteristic parameters;

[0012] S3, segmenting the sample data set to generate six block data sets;

[0013] S4, generating corresponding spatial distribution difference maps and time dynamic fluctuation maps according to the block data sets;

[0014] S5, extracting a first mean value index, a divergence index, and a smoothness index from the spatial distribution difference map, and extracting a range index, a second mean value index, a frequency index, and a fluctuation index from the time dynamic fluctuation map;

[0015] S6, identifying a myocardial ischemic state according to the first mean value index, the dispersion index, the smoothness index, the range index, the second mean value index, the frequency index, and the fluctuation index, or

[0016] The first mean index, the dispersion index, the smoothness index, the range index, the second mean index, the frequency index, and the fluctuation index are used to identify the construction and training of a myocardial ischemia model.

[0017] Furthermore, the step also includes: inputting the parameters to be identified into the myocardial ischemia model, and if they exceed the threshold of the myocardial ischemia model or the parameter comparison is abnormal, it is judged as a high risk of myocardial ischemia, otherwise it is a low risk of myocardial ischemia. The parameters to be identified include but are not limited to the first mean value index, divergence index, and smoothness index extracted from the spatial distribution difference map of a single individual, and the range index, second mean value index, frequency index, and fluctuation index extracted from the time dynamic fluctuation map.

[0018] Preferably, the spatial coordinate system of the spatial distribution difference map is a coordinate system composed of the probe arrays of multiple channels as the X-axis and the Y-axis, and the characteristic parameter as the Z-axis.

[0019] Preferably, the calculation formula of the smoothness index is as follows:

[0020] ,

[0021] ,in:

[0022] T is the total number of probes in the block data set;

[0023] j, is the probe located at position j in the block data set;

[0024] m, is the probe at position m that is adjacent to and closest to the probe at position j in the block data set;

[0025] n is the number of probes in the block data set that are adjacent to and closest to the probe at position j;

[0026] , is the magnetic cardiotonic parameter value measured by the probe at position j;

[0027] , is the magnetic heart parameter value detected at position m.

[0028] Preferably, the two-dimensional coordinate system of the time dynamic fluctuation diagram is a coordinate system consisting of the dynamic time axis as the horizontal axis and the characteristic parameter as the vertical axis.

[0029] Preferably, the calculation formula of the volatility index is as follows:

[0030] ,in:

[0031] , is the ordinate value of the first peak in the time dynamic fluctuation diagram;

[0032] , is the ordinate value of the last peak in the time dynamic fluctuation diagram;

[0033] , is the difference in ordinate between adjacent peaks and troughs in the time dynamic fluctuation diagram;

[0034] M is the number of troughs and peaks in the time dynamic fluctuation diagram.

[0035] Preferably, the characteristic parameters include R wave apex amplitude, T wave apex amplitude, ST segment integral, R wave integral, and T wave integral.

[0036] Preferably, the model for identifying myocardial ischemia includes any one or more of a machine learning model, a big data model, and a feature selection algorithm.

[0037] The present invention also provides a myocardial ischemia identification system based on magnetocardiographic three-dimensional dynamic parameters in space-time, which specifically includes: a data acquisition module, used to acquire an initial magnetocardiogram data set containing multiple channels; a feature extraction module, used to extract feature parameters from the initial data set to generate a sample data set; a block segmentation module, used to segment the sample data set to generate six block data sets; an image drawing module, used to generate corresponding spatial distribution difference maps and time dynamic fluctuation maps according to the block data sets; and an identification analysis module, used to generate identification information of myocardial ischemia according to the spatial distribution difference map and the time dynamic fluctuation map.

[0038] Compared with the prior art, the present invention has the following advantages and effects:

[0039] (1) The present invention generates spatial distribution difference maps and time dynamic fluctuation maps based on the existing one-dimensional magnetocardiogram. It is significantly different from the traditional two-dimensional isomagnetic map. Starting from the pathological and physiological mechanism of magnetocardiogram changes in myocardial ischemia, the signal extraction dimension is expanded and displayed through three-dimensional perspectives of different spatial and temporal dynamics, which fully reflects the information contained in the magnetocardiogram, and the physical meaning of the indicators is intuitive and clear;

[0040] (2) The present invention adopts the mean index, divergence index, smoothness index, range index, second mean index, frequency index, and fluctuation index in space and time respectively, so that the characterization index has strong anti-interference ability, calculates the magnetic cardioversion difference from multiple levels, and can better reflect the real information contained in the magnetic cardioversion data. By deeply calculating the dynamic changes of the differences in magnetic cardioversion parameters in time and space, the changes in these differences reflect more myocardial ischemia information, thereby improving the ability of magnetic cardioversion images to identify myocardial ischemia, which has an important contribution to the use of magnetic cardioversion equipment to assist in the identification of myocardial ischemia. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Schematic diagram of the process of the myocardial ischemia identification method based on the three-dimensional dynamic parameters of magnetic heart space-time in an embodiment of the present invention;

[0042] Figure 2 Schematic diagram of the principle of the myocardial ischemia identification method based on the three-dimensional dynamic parameters of magnetic heart space and time in an embodiment of the present invention;

[0043] Figure 3 Schematic diagram of the effect of the myocardial ischemia identification method based on the three-dimensional dynamic parameters of magnetic heart space-time in an embodiment of the present invention;

[0044] Figure 4 Schematic diagram of the structure of a myocardial ischemia identification system based on magnetocardiographic spatiotemporal three-dimensional dynamic parameters in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the present invention, the present invention is further described in conjunction with specific implementation methods.

[0046] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0047] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0048] Terminology explanation:

[0049] Magnetocardiography: Magnetocardiography is a non-invasive, radiation-free, non-contact functional diagnostic technology that uses the human body's "magnetic transparency" to clearly display the heart's magnetic signals and their changing patterns. It has certain advantages over similar tests such as coronary artery stenosis detection.

[0050] Specifically, this embodiment specifically uses an optically pumped magnetometer (OPM) magnetocardiograph for testing and explanation, which is a new weak magnetic sensing technology developed based on the spin-exchange relaxation-free (SERF) theory, and has the advantages of high sensitivity, no need for refrigeration, stable signal, and no need for a special magnetic shielding room, etc., and is superior to the SQUID magnetometer used in the past.

[0051] like Figure 1~Figure 3As shown, the present invention provides a method for identifying myocardial ischemia based on three-dimensional magnetic-temporal-spatial dynamic parameters, which specifically includes the following steps:

[0052] S1, using a multi-channel (taking 64 channels as an example) optically pumped magnetometer magnetocardiograph based on the SERF effect to obtain an initial magnetocardiogram data set containing multiple channels; by using ultra-high sensitivity and extremely weak magnetic detection technology based on the SERF effect, given its advantages of small size, light weight, high sensitivity, no need for refrigeration, and wearability, the inspection process can be completed in a short time, non-invasively, noise-free, and without patient contact, which helps to fill the blank areas of heart disease diagnosis.

[0053] S2, processing multiple channels in the initial data set, collecting and extracting characteristic parameters in each channel, and constructing a sample data set containing characteristic parameters; wherein the characteristic parameters include R wave apex amplitude, T wave apex amplitude, ST segment integral, R wave integral, and T wave integral.

[0054] Specifically, based on the initial dataset of magnetocardiography, a one-dimensional butterfly diagram is constructed in combination with the magnetic field strength and channel position obtained from each channel. According to the one-dimensional butterfly diagram, five types of characteristic parameters, including R wave apex amplitude, T wave apex amplitude, ST segment integral, R wave integral, and T wave integral, are extracted for each channel respectively, and a sample dataset containing the above five types of characteristic parameters is constructed.

[0055] Furthermore, the sample data set is specifically a magnetocardiogram data set containing the above five types of characteristic parameters collected at multiple time points (determined by the number of heartbeats) within a specified time interval (such as 3 minutes) for each channel of the multiple channels.

[0056] It should be noted that the R wave apex amplitude is the strength of the cardiac magnetic field at the apex of the R wave, the T wave apex amplitude is the strength of the cardiac magnetic field at the apex of the T wave, the ST segment integral is based on the small fluctuations in magnetic field intensity in the ST segment, and the area under the curve of each fluctuation wave is added to obtain the ST segment integral, the R wave integral is the area under the curve of the R wave magnetic field intensity, and the T wave integral is the area under the curve of the T wave magnetic field intensity.

[0057] S3, segmenting the sample data set to generate six block data sets; it should be noted that in the process of segmenting the sample data set to generate six block data sets, the magnetocardiogram is divided into six blocks according to the similarity of the magnetocardiogram waveforms of each channel and combined with the anatomical regions of the heart, and the corresponding six block data sets are generated. Subsequently, based on the multi-channel array, the spatial distribution difference map and the time dynamic fluctuation map of the six blocks are drawn and generated respectively.

[0058] S4, generating the spatial distribution difference maps of the corresponding six blocks and the time dynamic fluctuation maps of the six blocks respectively according to the block data set.

[0059] Specific, combined Figure 2 and Figure 3 As shown, the spatial coordinate system of the spatial distribution difference map is a coordinate system composed of a probe array of multiple channels as the X-axis and Y-axis, and a characteristic parameter as the Z-axis; that is, the six block data sets formed by segmentation are arranged with the array of multi-channel probes as the X-axis and Y-axis, and the values ​​of each characteristic parameter of R wave apex amplitude, T wave apex amplitude, ST segment integral, R wave integral, and T wave integral as the Z-axis, and isoline maps of the spatial information distribution differences of the five types of characteristic parameters are drawn.

[0060] The two-dimensional coordinate system of the time dynamic fluctuation diagram is a coordinate system composed of the dynamic time axis as the horizontal axis and the characteristic parameters as the vertical axis; that is, the six block data sets formed by segmentation are based on multiple heartbeat time points within 3 minutes of collection, with the dynamic time axis as the horizontal axis and the values ​​of each characteristic parameter of R wave apex amplitude, T wave apex amplitude, ST segment integral, R wave integral, and T wave integral as the vertical axis to draw the time dynamic fluctuation diagram of five types of characteristic parameters.

[0061] S5. Extract and obtain the first mean value index, divergence index, and smoothness index from the drawn spatial distribution difference map. That is, in the drawn spatial distribution difference map of the six major blocks, respectively calculate the first mean value index, divergence index, and smoothness index of the R-wave apex amplitude, T-wave apex amplitude, ST-segment fluctuation integral, T-wave integral, and R-wave integral.

[0062] Among them, the first mean value index is used to evaluate the average level of the characteristic parameter, the divergence index is used to evaluate the spatial variation of the characteristic parameter by calculating the difference between the maximum value and the minimum value of the characteristic parameter, and the smoothness index is used to evaluate the spatial smoothness index of the characteristic parameter in the partition.

[0063] Furthermore, the calculation formula of the smoothness index is as follows:

[0064] ,

[0065] ,in:

[0066] T, is the total number of probes in the block dataset;

[0067] j, is the probe at position j in the block dataset;

[0068] m, is the probe at position m that is adjacent to and closest to the probe at position j in the block data set;

[0069] n, is the number of probes in the block data set that are adjacent to and closest to the probe at position j;

[0070] , is the magnetic cardiotonic parameter value measured by the probe at position j;

[0071] , is the magnetic heart parameter value detected at position m.

[0072] Combined with the calculation formula of the above smoothness index, the average value of the difference between the magnetic heart parameter value at each position (probe position) in each block data set and its adjacent position is obtained, and the average value of the difference between all probe positions in the space within the partition is taken to obtain the spatial smoothness index of the characteristic parameter in the partition.

[0073] Furthermore, the range index, second mean value index, frequency index, and fluctuation index are extracted from the time dynamic fluctuation diagram; that is, in the time dynamic fluctuation diagram of the six major blocks drawn, the range index, second mean value index, frequency index, and fluctuation index of the R wave apex amplitude, T wave apex amplitude, ST segment fluctuation integral, T wave integral, and R wave integral are calculated respectively.

[0074] Among them, based on the time dynamic fluctuation diagram of the six major blocks drawn based on the above-mentioned R wave apex amplitude, T wave apex amplitude, ST segment fluctuation integral, T wave integral, and R wave integral, the maximum and minimum values ​​of the characteristic parameters are obtained respectively, and the range index is obtained by calculating the difference between the two, which is used to evaluate the fluctuation of the characteristic parameter over time; the second mean value index is used to evaluate the average level of the characteristic parameter; the frequency index is calculated by obtaining the number of fluctuations within the set time period.

[0075] Furthermore, the calculation formula of the volatility index is as follows:

[0076] ,in:

[0077] , is the ordinate value of the first peak in the time dynamic fluctuation diagram;

[0078] , is the ordinate value of the last peak in the time dynamic fluctuation diagram;

[0079] , is the difference in ordinate between adjacent peaks and troughs in the time dynamic fluctuation diagram;

[0080] M is the number of troughs and peaks in the time dynamic fluctuation diagram.

[0081] S6, according to the first mean value index, the divergence index, the smoothness index, the range index, the second mean value index, the frequency index, and the fluctuation index, the above-mentioned related indexes are processed and analyzed, and the processing and analysis results are used to identify the myocardial ischemia state.

[0082] Specifically, the first mean index, divergence index, and smoothness index of each characteristic parameter of the spatial distribution difference map of the above six blocks, and the range index, second mean index, frequency index, and fluctuation index of each characteristic parameter of the time dynamic fluctuation map of the six blocks are included in the training set.

[0083] First, perform feature selection. Use a feature selection algorithm (such as the chi-square test) to sort the feature data of the training set according to the class separability standard and select the first N1 features (N1 is selected as the number of observations in the training set).

[0084] Secondly, the linear cross-correlation of the selected N1 features is judged, and the features with a cross-correlation coefficient less than 0.5 are retained, of which N2 features are retained;

[0085] Furthermore, the number of features is selected. The training set data is used to plot the changes in the misclassification rate and the number of features of the 10-fold cross-validation. The point where the misclassification rate no longer decreases significantly with the increase in the number of features is selected as the optimal point. The number of features corresponding to this point is the number of features finally selected.

[0086] Finally, the mean ± standard deviation of each characteristic parameter in the normal and patient populations is calculated, and a judgment threshold (an integer value between 1 and N2) is set. If the number of abnormal values ​​in the N2 characteristic values ​​of a subject exceeds the judgment threshold, it is considered to be in a state of myocardial ischemia, and if it is less than the threshold, it is in a normal state.

[0087] It should be noted that the present invention analyzes the time and space characteristics of each characteristic parameter of the magnetocardiogram in six partitions, explores the distribution law of the characteristic parameters, makes full use of the characteristic parameters to screen the sensitive characteristic parameters of myocardial ischemia, and further innovatively constructs a recognition model for myocardial ischemia, so that the model sensitivity reaches 90%, thereby improving the accuracy of myocardial ischemia recognition.

[0088] It not only fully combines the spatial and temporal characteristics of various dimensional indicators of the magnetocardiogram, but also avoids the complicated source reconstruction process, is non-invasive and harmless to the human body, and has strong clinical feasibility. It is easy to operate, greatly saves manpower and time costs, effectively overcomes the various shortcomings of the existing technology, and has high industrial utilization value.

[0089] Optionally, in some embodiments, the first mean index, divergence index, smoothness index, range index, second mean index, frequency index, and fluctuation index are used for training to identify myocardial ischemia models, wherein the methods used to identify myocardial ischemia models include any one or more of machine learning models, big data models, and feature selection algorithms.

[0090] Optionally, in some embodiments, the present invention also provides a myocardial ischemia identification system based on magnetocardiographic three-dimensional spatiotemporal dynamic parameters, which specifically includes: a data acquisition module, used to acquire an initial magnetocardiogram data set containing multiple channels, such as using a magnetocardiogram initial data set containing multiple channels using a multi-channel (taking 64 channels as an example) optically pumped magnetometer magnetocardiograph based on the SERF effect.

[0091] The feature extraction module is used to extract feature parameters from the initial data set and generate a sample data set. Based on the initial data set of the magnetocardiogram, it combines the magnetic field strength and channel position obtained by each channel to construct a one-dimensional butterfly diagram, and extracts five types of feature parameters, namely, the R wave apex amplitude, the T wave apex amplitude, the ST segment integral, the R wave integral, and the T wave integral, from each channel according to the one-dimensional butterfly diagram, and constructs a sample data set containing the above five types of feature parameters. Furthermore, the sample data set is specifically a magnetocardiogram data set containing the above five types of feature parameters collected at multiple time points (determined by the number of heartbeats) within a specified time interval (such as 3 minutes) for each channel of the multiple channels.

[0092] The block segmentation module is used to segment the sample data set to generate six block data sets; according to the similarity of the magnetocardiogram waveforms of each channel and in combination with the cardiac anatomical region, the magnetocardiogram image is divided into six blocks and the corresponding six block data sets are generated.

[0093] The image drawing module is used to generate corresponding spatial distribution difference maps and time dynamic fluctuation maps according to the block data set. The specific description of the spatial distribution difference map and the time dynamic fluctuation map is detailed in the above related content and will not be repeated here.

[0094] The identification and analysis module is used to generate identification information of myocardial ischemia based on the spatial distribution difference map and the time dynamic fluctuation map, such as determining whether the subject is in a state of myocardial ischemia.

[0095] In summary, the method and system for identifying myocardial ischemia based on magnetocardiographic spatiotemporal three-dimensional dynamic parameters provided by the present invention analyze and process the magnetocardiogram and generate six block data sets by segmentation. By processing and analyzing the spatial and temporal characteristics of the six block data sets, the distribution law of the characteristic parameters is effectively discovered, and the characteristic parameters are fully utilized to screen the sensitive characteristic parameters of myocardial ischemia. At the same time, a model for identifying myocardial ischemia can be constructed, and the spatial indicators and temporal characteristics of each dimension of the magnetocardiogram are fully combined and utilized, thereby avoiding a complex source reconstruction process, fully reflecting the rich information that the magnetocardiogram can reflect, and the physical meaning of the indicators is intuitive and clear.

[0096] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent changes and modifications made within the scope of the present invention should still fall within the scope of the present invention.

Claims

1. A method for identifying myocardial ischemia based on three-dimensional dynamic parameters of magnetic heart space-time, characterized in that: The following steps are involved: S1, obtain the initial dataset of magnetocardiogram containing multiple channels; S2, processing multiple channels in the initial data set, collecting and extracting characteristic parameters in each channel, and constructing a sample data set containing the characteristic parameters, wherein the characteristic parameters include R wave apex amplitude, T wave apex amplitude, ST segment integral, R wave integral, and T wave integral; S3, segmenting the sample data set, dividing the magnetocardiogram into six blocks according to the similarity of the magnetocardiogram waveforms of each channel and in combination with the cardiac anatomical regions, and generating corresponding six block data sets; S4, generating corresponding spatial distribution difference maps and time dynamic fluctuation maps according to the block data sets; S5, extracting a first mean value index, a divergence index, and a smoothness index from the spatial distribution difference map, and extracting a range index, a second mean value index, a frequency index, and a fluctuation index from the time dynamic fluctuation map; S6, identifying a myocardial ischemia state according to the first mean value index, the divergence index, the smoothness index, the range index, the second mean value index, the frequency index, and the fluctuation index, or using the first mean value index, the divergence index, the smoothness index, the range index, the second mean value index, the frequency index, and the fluctuation index to identify the construction and training of a myocardial ischemia model; The spatial coordinate system of the spatial distribution difference map is a coordinate system composed of the probe arrays of multiple channels as the X-axis and the Y-axis, and the characteristic parameter as the Z-axis; The two-dimensional coordinate system of the time dynamic fluctuation diagram is a coordinate system consisting of the dynamic time axis as the horizontal axis and the characteristic parameter as the vertical axis; The calculation formula of the smoothness index is as follows: ， ,in: T is the total number of probes in the block data set; j, is the probe located at position j in the block data set; m, is the probe at position m that is adjacent to and closest to the probe at position j in the block data set; n is the number of probes in the block data set that are adjacent to and closest to the probe at position j; , is the magnetic cardiotonic parameter value measured by the probe at position j; , is the magnetic heart parameter value detected at position m; The divergence index is calculated as the difference between the maximum value and the minimum value of the characteristic parameter.

2. The method for identifying myocardial ischemia based on three-dimensional magnetic-temporal-spatial dynamic parameters according to claim 1, characterized in that: The calculation formula of the volatility index is as follows: ,in: , is the ordinate value of the first peak in the time dynamic fluctuation diagram; , is the ordinate value of the last peak in the time dynamic fluctuation diagram; , is the difference in ordinate between adjacent peaks and troughs in the time dynamic fluctuation diagram; M is the number of troughs and peaks in the time dynamic fluctuation diagram.

3. The method for identifying myocardial ischemia based on three-dimensional magnetic-temporal-spatial dynamic parameters according to claim 1, characterized in that: The model for identifying myocardial ischemia includes any one or more of a machine learning model, a big data model, and a feature selection algorithm.

Images