Coronary microcirculation disorder prediction method, device, system and storage medium

Abstract

Disclosed are a coronary microcirculation disorder prediction method, a processing device, a system and a computer readable storage medium, the method comprising: acquiring exercise electrocardiogram data and resting electrocardiogram data output by at least one electrocardiogram lead respectively, and obtaining first and second high-frequency QRS complex data respectively based on the exercise electrocardiogram data and the resting electrocardiogram data; obtaining first and second lead positive indicators based on the first and second high-frequency QRS complex data; determining whether target first high-frequency QRS complex data exists in the first high-frequency QRS complex data corresponding to the first lead positive indicator indicating positivity, the target first high-frequency QRS complex data not having a first waveform feature indicating coronary artery disease and a second waveform feature indicating myocardial bridge; and if the target first high-frequency QRS complex data exists, determining that there is a possibility of coronary microcirculation disorder. The present scheme can realize non-invasive, rapid and specific identification of coronary microcirculation disorder.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical instruments, in particular to a coronary microcirculation disorder prediction method, processing device, system and computer readable storage medium. BACKGROUND

[0002] At present, there are schemes for evaluating the heart health status based on electrocardiogram (ECG). The Chinese patent application with publication number CN114742114A discloses a high-frequency QRS waveform curve analysis method, which evaluates the degree of myocardial ischemia under coronary stenosis by analyzing the electrocardiogram signal under exercise load, but this method only considers the myocardial ischemia caused by coronary stenosis and cannot more accurately evaluate the heart health status. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a coronary microcirculation disorder prediction method, processing device, system and computer readable storage medium, which can more accurately evaluate the heart health status.

[0004] To achieve the above-mentioned purpose, the first aspect of the present application provides a coronary microcirculation disorder prediction method, comprising:

[0005] Respectively acquiring exercise electrocardiogram data and resting electrocardiogram data output by at least one electrocardiogram lead;

[0006] Obtaining first high-frequency QRS complex data according to the exercise electrocardiogram data, and obtaining second high-frequency QRS complex data according to the resting electrocardiogram data;

[0007] Obtaining a first lead positive index corresponding to each electrocardiogram lead according to the first high-frequency QRS complex data;

[0008] Obtaining a second lead positive index corresponding to each electrocardiogram lead according to the second high-frequency QRS complex data;

[0009] Determining whether there is target first high-frequency QRS complex data in the first high-frequency QRS complex data indicated by the first lead positive index, the target first high-frequency QRS complex data does not have a first waveform feature indicating coronary artery disease and a second waveform feature indicating myocardial bridge;

[0010] In the case where it is determined that there is target first high-frequency QRS complex data, it is determined that there is a possibility of coronary microcirculation disorder.

[0011] In the embodiments of the present application, in the case where it is determined that there is target first high-frequency QRS complex data, it is determined that there is a possibility of coronary microcirculation disorder, comprising:

[0012] Determining a target electrocardiogram lead corresponding to the target first high-frequency QRS complex data;

[0013] determining whether the second lead positive indicator corresponding to the target electrocardiogram lead indicates positivity;

[0014] in a case where the second lead positive indicator corresponding to the target electrocardiogram lead indicates positivity, determining that there is a possibility of coronary microcirculation disorder.

[0015] In the embodiments of the present application, the method for predicting coronary microcirculation disorder further comprises:

[0016] determining a first maximum RMS voltage according to a maximum value of RMS voltage in the first high-frequency QRS complex data corresponding to all electrocardiogram leads, and determining a second maximum voltage according to a maximum value of voltage in the second high-frequency QRS complex data corresponding to all electrocardiogram leads;

[0017] determining the number of electrocardiogram leads corresponding to the second lead positive indicator indicating positivity;

[0018] in a case where the number is less than a preset value, and at least the first maximum RMS voltage is greater than the first voltage threshold, determining that there is no coronary microcirculation disorder.

[0019] In the embodiments of the present application, determining whether the first high-frequency QRS complex data has the first waveform feature comprises:

[0020] obtaining a first point sequence corresponding to the first high-frequency QRS complex data of interest according to the first high-frequency QRS complex data of interest, the first point sequence comprising a plurality of sampling points arranged in time sequence;

[0021] for the first point sequence, in an iteration loop, taking any sampling point in the plurality of sampling points in the first point sequence as a current reference sampling point, and iterating the sampling points within a first preset time interval from the current reference sampling point to determine whether there are a first sampling point and a second sampling point satisfying a preset condition within the first preset time interval, wherein the first sampling point is earlier in time sequence than the second sampling point;

[0022] in a case where it is determined that there are the first sampling point and the second sampling point satisfying the preset condition, determining that the first high-frequency QRS complex data of interest has the first waveform feature indicating coronary artery lesion;

[0023] in a case where it is determined that there are no first sampling point and second sampling point satisfying the preset condition, ending the current iteration loop, and determining other sampling points in the first point sequence except the current reference sampling point as new reference sampling points;

[0024] performing the next iteration loop for the new reference sampling points, repeating the iteration loop until it is determined that there are the first sampling point and the second sampling point satisfying the preset condition, or all the sampling points in the first point sequence that need to be iterated have been iterated.

[0025] In the embodiments of the present application, determining whether the first high-frequency QRS complex data has the first waveform feature further includes:

[0026] In the case that all the sampling points in the first point sequence are traversed and there is no first sampling point and second sampling point satisfying the preset condition, it is determined that the first high-frequency QRS complex data of interest does not have the first waveform feature indicating coronary artery lesion.

[0027] In the embodiments of the present application, the preset condition includes:

[0028] The amplitude drop relative value between the first sampling point and the second sampling point reaches a first preset threshold and the voltage drop degree between the first sampling point and the second sampling point reaches a second preset threshold; or

[0029] The amplitude drop relative value between the first sampling point and the second sampling point reaches the first preset threshold or the voltage drop degree between the first sampling point and the second sampling point reaches the second preset threshold.

[0030] In the embodiments of the present application, determining whether the first high-frequency QRS complex data has the second waveform feature includes:

[0031] Determining candidate first high-frequency QRS complex data from the first high-frequency QRS complex data corresponding to each electrocardiogram lead, the candidate first high-frequency QRS complex data not having the first waveform feature;

[0032] Obtaining a corresponding second point sequence according to the candidate first high-frequency QRS complex data, the second point sequence including a plurality of sampling points arranged in time sequence;

[0033] For the second point sequence corresponding to any candidate first high-frequency QRS complex data, in an iteration loop, any sampling point in the plurality of sampling points in the second point sequence is taken as a current reference sampling point, and the sampling points within a second preset time interval from the current reference sampling point are traversed to determine whether there is a third sampling point and a fourth sampling point satisfying another preset condition within the second preset time interval, wherein the third sampling point is earlier in time sequence than the fourth sampling point;

[0034] In the case that it is determined that there is a third sampling point and a fourth sampling point satisfying another preset condition, it is determined that the any candidate first high-frequency QRS complex data has the second waveform feature;

[0035] In the case that it is determined that there is no third sampling point and fourth sampling point satisfying another preset condition, the current iteration loop ends, and other sampling points in the second point sequence except the current reference sampling point are determined as new reference sampling points;

[0036] The next traversal loop is performed for the new reference sampling point, and the traversal loop is repeated until it is determined that there are third and fourth sampling points that satisfy another preset condition or all sampling points in the second point sequence that need to be traversed have been traversed.

[0037] In the embodiments of the present application, determining whether the first high-frequency QRS complex data has the second waveform feature further includes:

[0038] In the case where no third and fourth sampling points that satisfy another preset condition are found after all sampling points in the second point sequence that need to be traversed have been traversed, it is determined that the corresponding candidate first high-frequency QRS complex data does not have the second waveform feature.

[0039] In the embodiments of the present application, the another preset condition includes:

[0040] The amplitude drop relative value between the third sampling point and the fourth sampling point reaches a third preset threshold, the voltage drop degree between the third sampling point and the fourth sampling point reaches a fourth preset threshold, and the root mean square voltage of each sampling point between the third sampling point and the fourth sampling point shows a continuous downward trend; or

[0041] The amplitude drop relative value between the third sampling point and the fourth sampling point reaches a third preset threshold or the voltage drop degree between the third sampling point and the fourth sampling point reaches a fourth preset threshold, and the root mean square voltage of each sampling point between the third sampling point and the fourth sampling point shows a continuous downward trend.

[0042] In the embodiments of the present application, determining whether the first high-frequency QRS complex data has the second waveform feature includes:

[0043] Determining a candidate first high-frequency QRS complex data from the first high-frequency QRS complex data corresponding to each electrocardiogram lead, the candidate first high-frequency QRS complex data not having the first waveform feature;

[0044] For any candidate first high-frequency QRS complex data, at least one sampling point in the candidate first high-frequency QRS complex data within a preset time period is determined as a reference sampling point, the preset time period being a time period from the moment of the end of the exercise to a moment after the end of the exercise in the load exercise electrocardiogram detection process;

[0045] Determining a sampling point to be traversed according to the determined reference sampling point, wherein the sampling point to be traversed is a sampling point in a preset time interval before the reference sampling point in the candidate first high-frequency QRS complex data, and the preset time interval includes a plurality of continuous subintervals;

[0046] Traversing the sampling points in the plurality of subintervals to determine whether there is a target sampling point that satisfies another preset condition corresponding to each subinterval in each subinterval;

[0047] In a case where there is a target sampling point satisfying the corresponding preset condition in any one of the plurality of subintervals, it is determined that the candidate first high-frequency QRS complex data has the second waveform feature;

[0048] In a case where there is no target sampling point satisfying the corresponding preset condition after all sampling points in the plurality of subintervals are traversed, it is determined that the candidate first high-frequency QRS complex data does not have the second waveform feature.

[0049] The second aspect of the present application provides a processing device, comprising a processor and a memory, the memory storing instructions, and the processor being configured to call and execute the instructions from the memory to implement the coronary microcirculation disorder prediction method described above.

[0050] The third aspect of the present application provides a coronary microcirculation disorder prediction system, comprising:

[0051] An electrocardiosignal collection device comprising at least one electrode forming at least one electrocardiogram lead for collecting electrocardiosignals of a subject; and

[0052] The processing device described above.

[0053] The fourth aspect of the present application provides a machine-readable storage medium, the machine-readable storage medium storing instructions for causing a machine to execute the coronary microcirculation disorder prediction method described above.

[0054] The technical scheme provided by the embodiments of the present application, through the waveform features of the first high-frequency QRS complex data (or the high-frequency QRS time intensity curve / high-frequency QRS waveform curve corresponding to the first high-frequency QRS complex data) obtained from the exercise electrocardiosignal data analysis, the pathological waveform interference of typical coronary artery lesions (such as coronary stenosis or coronary sclerosis) and myocardial bridge is excluded, and the specific myocardial electrical activity change possibly caused by coronary microcirculation disorder is directly focused on, which makes up for the defect of the insufficient sensitivity of the traditional non-invasive method (such as the conventional electrocardiogram) to the coronary microcirculation disorder, avoids the risk and inconvenience of the invasive examination (such as the IMR), and realizes the non-invasive, rapid and specific identification of the coronary microcirculation disorder. Further, on the basis of the foregoing, the positive verification of the lead positive index determined by the second high-frequency QRS complex data in the resting state is superimposed, the double evidence is formed relying on the characteristic indexes of myocardial ischemia and myocardial cell activity decrease in the resting state, and the accuracy and diagnostic reliability of the coronary microcirculation disorder are further improved. In addition, the comprehensive screening logic is formed by combining the quantitative index of the heart-lung function and the degree index of the myocardial ischemia / cell activity, the coronary microcirculation disorder can be accurately excluded non-invasively and rapidly, the misjudgment to the light symptom / non-microcirculation disorder population is effectively reduced, and the overall efficiency of the coronary microcirculation disorder screening is greatly improved.

[0055] Other features and advantages of the present embodiments will be set forth in the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0056] The accompanying drawings are included to provide a further understanding of the present embodiments and are incorporated in and constitute a part of this specification, illustrate embodiments of the present embodiments and together with the description serve to explain the present embodiments. In the drawings:

[0057] Figure 1A An example flowchart of a method for predicting coronary microvascular obstruction according to an embodiment of the present application is schematically shown.

[0058] Figure 1B An example flowchart of a method for predicting coronary microvascular obstruction according to another embodiment of the present application is schematically shown.

[0059] Figure 2A A high frequency QRS waveform curve during exercise is schematically shown, in which a sharp drop waveform occurs after 3 minutes of exercise.

[0060] Figure 2B An example flowchart of a method for determining the likelihood of the presence of a coronary artery lesion according to an embodiment of the present application is schematically shown.

[0061] Figure 3 An example flowchart of a method for determining the likelihood of the presence of a coronary artery lesion according to another embodiment of the present application is schematically shown.

[0062] Figure 4 An example flowchart of a method for determining the likelihood of the presence of a coronary artery lesion according to yet another embodiment of the present application is schematically shown.

[0063] Figure 5 An example flowchart of a method for determining the likelihood of the presence of a myocardial bridge according to an embodiment of the present application is schematically shown.

[0064] Figure 6 An example flowchart of a method for determining the likelihood of the presence of a myocardial bridge according to an embodiment of the present application is schematically shown.

[0065] Figure 7 An example flowchart of a method for determining the likelihood of the presence of a myocardial bridge according to another embodiment of the present application is schematically shown.

[0066] Figure 8 An example flowchart of a method for determining the likelihood of the presence of a myocardial bridge according to yet another embodiment of the present application is schematically shown.

[0067] Figure 9An example flowchart of a method for determining the likelihood of the presence of a myocardial bridge is schematically illustrated according to yet another embodiment of the present application.

[0068] Figure 10 An example flowchart of a method for determining the likelihood of the presence of a myocardial bridge is schematically illustrated according to yet another embodiment of the present application.

[0069] Figure 11 An example block diagram of a coronary microcirculation disorder prediction system is schematically illustrated according to an embodiment of the present application. DETAILED DESCRIPTION

[0070] The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to illustrate and explain the present application, and are not intended to limit the present application.

[0071] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solutions of the present application comply with relevant provisions of laws and regulations. In the embodiments of the present application, some industry existing solutions, such as software, components, models, etc. may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solutions.

[0072] The coronary microcirculation disorder prediction method provided by the embodiments of the present application can be applied to a terminal, a server, or an interactive system including a terminal and a server, and is implemented through the interaction of the terminal and the server, which is not limited here. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, electrocardiogram monitoring devices, and portable wearable devices, and the server can be implemented by an independent server or a server cluster composed of multiple servers.

[0073] The "exercise electrocardio data" or its equivalent terms mentioned in the embodiments of the present application can refer to the electrocardio data collected by the subject during the load exercise electrocardio detection process. The load exercise electrocardio detection is a method of electrocardio detection for collecting the electrocardio data of the subject by increasing the heart load through a certain amount of exercise and analyzing the heart health condition of the subject based on the collected electrocardio data, which is widely used in the detection of heart disease and cardiovascular disease. The exercise electrocardio data can include a plurality of QRS complexes reflecting the changes of left and right ventricular depolarization potential and time, and each QRS complex is a set of Q wave, R wave and S wave in the electrocardiogram. Based on the QRS complex in the exercise electrocardio data, a corresponding high-frequency QRS waveform curve can be analyzed. The high-frequency QRS waveform curve can be a curve obtained by connecting a plurality of sampling points in time sequence. The high-frequency QRS waveform curve, also known as high-frequency QRS time intensity curve, can be used to represent the trend of the root mean square voltage of the high-frequency component of the QRS complex of the subject with respect to time during the entire load exercise electrocardio detection process, that is, to reflect the energy change trend during the entire load exercise electrocardio detection process. The high-frequency QRS waveform curve is presented by a high-frequency QRS waveform graph, in which the horizontal coordinate can be time corresponding to the detection time of the load exercise electrocardio detection process, and the unit can be min (minute), and the vertical coordinate can be root mean square voltage (RMS voltage), which can also be understood as intensity or amplitude, and the unit can be uV (microvolt).

[0074] In an embodiment, the load exercise electrocardio detection process includes a plurality of stages, specifically, can include three stages of resting stage, exercise stage and recovery stage in sequence, and the exercise electrocardio data includes the electrocardio data of each stage. It can be understood that the division of stages is not limited to this, and can be divided according to the actual situation. The pre-exercise in the embodiments of the present application is located in the resting stage, the exercise is located in the exercise stage, and the post-exercise is located in the recovery stage.

[0075] The "resting electrocardio data" or its equivalent terms mentioned in the embodiments of the present application can refer to electrocardio data collected in the resting electrocardio detection process. The subject is in a resting state in the resting electrocardio detection process. The resting electrocardio data can include a plurality of QRS complexes. The QRS complexes in the resting electrocardio data are sequentially aligned, averaged, and high-frequency filtered to obtain high-frequency QRS complex data, or the QRS complexes in the resting electrocardio data are sequentially high-frequency filtered, aligned, and averaged to obtain high-frequency QRS complex data, or high-frequency electrocardio data is extracted from the resting electrocardio data by analysis, and the QRS complexes in the high-frequency electrocardio data are sequentially aligned and averaged to obtain high-frequency QRS complex data, which is not specifically limited here. The high-frequency QRS complex data corresponds to the high-frequency QRS envelope curve, and the corresponding high-frequency QRS envelope curve can be formed based on the high-frequency QRS complex data. As can be seen, the corresponding high-frequency QRS envelope curve can be obtained by data processing of the resting electrocardio data.

[0076] The "routine ECG data" or its equivalent terms mentioned in the embodiments of the present application can refer to ECG data that can be obtained from a routine electrocardiogram (ECG) signal. In the embodiments of the present application, the routine ECG data can be obtained by analyzing and processing the resting electrocardio data, for example, by low-pass filtering the resting electrocardio data to filter out the high-frequency components and retain the low-frequency effective electrocardio components, and the routine ECG data is obtained after the filtering.

[0077] Figure 1A An example flowchart of the coronary microcirculation disorder prediction method according to the embodiments of the present application is schematically shown. Specifically, as shown in Figure 1A The coronary microcirculation disorder prediction method can include the following steps.

[0078] In step S101, exercise electrocardio data and resting electrocardio data output by at least one electrocardiogram lead are respectively acquired.

[0079] Specifically, during the collection of electrocardiogram, at least one electrode patch can be used for signal collection for the subject. For example, taking 10 electrode patches as an example, the electrode patches can be distributed on the chest and limbs of the human body to form 12 electrocardiogram leads (such as V1, V2, V3, V4, V5, V6, I, II, III, aVL, aVF, and aVR), corresponding to the output of 12 groups of electrocardio data. It can be understood that 10 electrode patches are only used as an example and do not specifically limit the number of electrode patches, and more or fewer electrode patches can be used according to actual needs. The electrocardio signal collection of the subject in the process of load exercise can obtain exercise electrocardio data, and the electrocardio signal collection of the subject in the resting state can obtain resting electrocardio data and also routine ECG data.

[0080] In step S102, first high-frequency QRS complex data is obtained according to the exercise electrocardiogram data, and second high-frequency QRS complex data is obtained according to the resting electrocardiogram data.

[0081] Specifically, in the embodiments of the present application, high-frequency QRS complex data can be obtained by analyzing and processing exercise electrocardiogram data, specifically, the high-frequency components of QRS complex in exercise electrocardiogram data can be analyzed to obtain corresponding high-frequency QRS complex data. Specifically, exercise electrocardiogram data includes ECG (electrocardiogram) corresponding to each heartbeat of the subject during the entire load exercise electrocardiogram detection process, and the ECG includes QRS complex. The exercise electrocardiogram data is divided into a plurality of electrocardiogram subsets by a window function according to time sequence and a preset moving step length, each electrocardiogram subset includes ECG corresponding to multiple heartbeats. For each electrocardiogram subset, the ECG or QRS complex corresponding to the multiple heartbeats it includes is sequentially aligned, averaged, and band-pass filtered to obtain a corresponding high-frequency QRS complex (high-frequency band of QRS complex), and the root mean square of the high-frequency QRS complex is obtained to obtain a corresponding root mean square voltage as the root mean square voltage corresponding to the electrocardiogram subset. Thus, a time-intensity data point set arranged in time sequence can be obtained, each data point corresponding to a time and a root mean square voltage (or intensity or amplitude), and the high-frequency QRS complex data can include these data point sets (for ease of distinction, hereinafter referred to as first high-frequency QRS complex data). The corresponding high-frequency QRS time-intensity curve can be obtained based on the time-intensity data point set, in other words, the visualization of the time-intensity data point set is the aforementioned high-frequency QRS time-intensity curve.

[0082] It can be understood that the window length of the window function and the preset moving step length can be customized according to actual needs, for example, the window length is set to 10 seconds, and the preset moving step length is set to 10 seconds or one heartbeat period, which refers to the time interval between adjacent two heartbeats, which is not limited here. According to time sequence refers to the order of the collection time / detection time of the signal advancing in the load exercise electrocardiogram detection process.

[0083] In step S103, a first lead positive indicator corresponding to each electrocardiogram lead is obtained according to the first high-frequency QRS complex data, and a second lead positive indicator corresponding to each electrocardiogram lead is obtained according to the second high-frequency QRS complex data.

[0084] The first high frequency QRS complex data can be used to obtain a lead positive indicator corresponding to each ECG lead (for ease of distinction, hereinafter referred to as a first lead positive indicator). The first lead positive indicator can be obtained using methods disclosed in the prior art. For example, in an example, the amplitude drop relative value and the amplitude absolute value can be calculated from the first high frequency QRS complex data to form the first lead positive indicator. A set function can be used to process the first high frequency QRS complex data to calculate the amplitude drop relative value and the amplitude absolute value between the two reference points with the most rapid drop in RMS voltage in the high frequency QRS waveform before exercise, during exercise, and after exercise. The amplitude absolute value is obtained by subtracting the RMS voltage of the two reference points, and the amplitude drop relative value is calculated as a percentage based on the amplitude absolute value and the RMS voltage value of the reference point with the highest RMS voltage. The amplitude drop relative value and the amplitude absolute value are mainly used to evaluate the blood flow change of the human heart.

[0085] The resting ECG data can be analyzed to obtain high frequency QRS complex data (for ease of distinction, hereinafter referred to as second high frequency QRS complex data). The specific operation of analyzing the resting ECG data to obtain the corresponding high frequency QRS complex data is described above and will not be repeated here. Thus, the wave group time domain envelope line formed when the second high frequency QRS complex data is visualized is the aforementioned high frequency QRS envelope curve. The second high frequency QRS complex data can be used to obtain a lead positive indicator corresponding to each ECG lead (for ease of distinction, hereinafter referred to as a second lead positive indicator). For example, in an example, the second high frequency QRS envelope curve based on the second high frequency QRS complex data corresponding to each ECG lead can be analyzed to obtain a first total area of each amplitude reduction region on the high frequency QRS envelope curve and a second total area below the high frequency QRS envelope curve, and the ratio of the first total area to the second total area is taken as the high frequency morphology index corresponding to the resting lead. The corresponding lead positive indicator is determined according to the age of the subject and the high frequency morphology index corresponding to each resting lead. For example, if the age is ≥ 50 years old, the second lead positive indicator is determined to be positive when the high frequency morphology index is ≥ 8%, and if the age is < 50 years old, the second lead positive indicator is determined to be positive when the high frequency morphology index is ≥ 15%.

[0086] The ST segment of the conventional ECG data can be analyzed to determine the positive indicator of the corresponding ECG lead (for ease of distinction, hereinafter referred to as a third lead positive indicator). For example, if the ST segment horizontal depression or downward slope depression in the conventional ECG data is ≥ 0.1 mV (millivolt) and the duration is > 2 min (minutes), the corresponding third lead positive indicator is determined to be positive.

[0087] In step S104, it is determined whether the target first high-frequency QRS complex data exists in the first high-frequency QRS complex data corresponding to the lead positive indicator indicating positive. The target first high-frequency QRS complex data does not have the first waveform feature indicating coronary artery lesion and the second waveform feature indicating myocardial bridge.

[0088] Specifically, the first high-frequency QRS complex data in which the lead positive indicator indicates positive can be determined from all the first high-frequency QRS complex data. It is determined whether the target first high-frequency QRS complex data exists in the first high-frequency QRS complex data in which the lead positive indicator indicates positive. The target first high-frequency QRS complex data does not have the waveform feature indicating coronary artery lesion (which can be referred to as the first waveform feature here) and / or the waveform feature indicating myocardial bridge (which can be referred to as the second waveform feature here). When analyzing the first high-frequency QRS complex data to determine whether there is a coronary microcirculation disorder, the first high-frequency QRS complex data having the first waveform feature (e.g., a steep drop wave) and / or the second waveform feature (e.g., a slow drop wave) can be excluded first. That is, if the first high-frequency QRS complex data has the first waveform feature and / or the second waveform feature, the first high-frequency QRS complex data is no longer used to determine whether there is a coronary microcirculation disorder. The method for determining whether the first high-frequency QRS complex data has the first waveform feature indicating coronary artery lesion, and the method for determining whether the first high-frequency QRS complex data has the second waveform feature indicating myocardial bridge will be described in detail below.

[0089] In step S105, in the case where it is determined that the target first high-frequency QRS complex data exists, it is determined that there is a possibility of a coronary microcirculation disorder.

[0090] In order to further improve the accuracy of determining the possibility of a coronary microcirculation disorder, it can be further determined whether the lead positive indicator of the target second high-frequency QRS complex data corresponding to the target electrocardiogram lead associated with the target first high-frequency QRS complex data indicates positive.

[0091] Specifically, when a target first high-frequency QRS complex data is determined, the target electrocardiogram lead associated with the target first high-frequency QRS complex data can be determined, i.e., the target first high-frequency QRS complex data is output through the target electrocardiogram lead. The target second high-frequency QRS complex data output through the target electrocardiogram lead can be analyzed to determine whether the lead positive indicator of the target second high-frequency QRS complex data indicates positive.

[0092] In a case where the lead positivity index of the target second high-frequency QRS complex data indicates positive, it is determined that there is a possibility of coronary microcirculation disorder. For example, if the target first high-frequency QRS complex data corresponds to the V1 lead of the electrocardiogram, and the lead positivity index of the second high-frequency QRS complex data corresponding to the V1 lead in the resting state indicates positive, it is determined that there is a possibility of coronary microcirculation disorder.

[0093] In the embodiments of the present application, the method for predicting coronary microcirculation disorder can further include determining that there is no coronary microcirculation disorder. Figure 1B An example flowchart of a method for predicting coronary microcirculation disorder according to another embodiment of the present application is schematically shown. As shown in the figure, specifically, in step S106, a first maximum RMS voltage is determined according to the maximum value of the RMS voltage in the first high-frequency QRS complex data corresponding to all electrocardiogram leads, and a second maximum voltage is determined according to the maximum value of the voltage in the second high-frequency QRS complex data corresponding to all electrocardiogram leads. Figure 1B

[0094] In an example, the first maximum RMS voltage can be the maximum voltage value in the above-mentioned embodiments, and for single exercise load detection, the maximum value of the RMS voltage in the first high-frequency QRS complex data corresponding to all electrocardiogram leads can be rounded up to an even integer to obtain a voltage value as the first maximum RMS voltage. In another example, the maximum value of the RMS voltage in the first high-frequency QRS complex data corresponding to all electrocardiogram leads can also be taken as the first maximum RMS voltage.

[0095] Similarly, the second maximum voltage can take the maximum value of the voltage / amplitude in the second high-frequency QRS complex data (or the second high-frequency QRS envelope curve) corresponding to all electrocardiogram leads and round it up to an even integer to obtain a voltage value as the second maximum voltage. In another example, the maximum value of the voltage in the second high-frequency QRS complex data corresponding to all electrocardiogram leads can also be taken as the second maximum voltage.

[0096] In step S107, the number of positive leads in at least one electrocardiogram lead corresponding to the second QRS complex data indicated by the second lead positivity index is determined according to the second high-frequency QRS complex data;

[0097] In step S108, the number of positive leads is compared with a preset value, the first maximum RMS voltage is compared with a first voltage threshold, and the second maximum voltage is compared with a second voltage threshold;

[0098] ​In step S109, in the case that the number of positive leads is less than the preset value, and at least the first maximum RMS voltage is greater than the first voltage threshold, it is indicated that the heart and lung function of the subject is strong, and it can be determined that there is no coronary microcirculation disorder. Wherein, at least the first maximum RMS voltage greater than the first voltage threshold can include the first maximum RMS voltage greater than the first voltage threshold, and the second maximum voltage greater than the second voltage threshold, or the first maximum RMS voltage greater than the first voltage threshold, but the second maximum voltage less than or equal to the second voltage threshold. In an example, the preset value may, for example, be 3, the first voltage threshold may, for example, be 8 uV, and the second voltage threshold may, for example, be 14 uV. However, those skilled in the art can understand that the predetermined value and the voltage threshold can be set to other values according to actual application.

[0099] Whether the first high-frequency QRS complex data has the first waveform feature can be determined by determining whether there is a possibility of coronary artery lesion.

[0100] The coronary artery lesion may, for example, be a coronary artery large vessel lesion, and specifically can include coronary stenosis and coronary sclerosis. When it is determined according to the exercise electrocardiogram data that there is a possibility of coronary stenosis or coronary sclerosis, it can be considered that there is a possibility of coronary artery lesion.

[0101] Specifically, in an embodiment of the present application, the method disclosed in the Chinese patent application with the publication number CN114742114A previously applied for by the applicant of the present application can be used to determine the possibility of coronary stenosis. The application discloses a high-frequency QRS waveform curve analysis method, which comprises obtaining a high-frequency QRS waveform curve (first high-frequency QRS waveform curve) corresponding to exercise electrocardiogram data; selecting the first high-frequency QRS waveform curve in a first time period as a first reference waveform curve; selecting a point with the minimum root mean square voltage on the first reference waveform curve as a first reference point, and a point with the maximum root mean square voltage earlier in time than the first reference point as a second reference point; determining a first amplitude drop relative value according to the root mean square voltages of the first reference point and the second reference point; if the first amplitude drop relative value is greater than or equal to a first preset threshold, it is determined that the first high-frequency QRS waveform curve satisfies a preset condition, i.e., the high-frequency QRS waveform curve has a waveform feature indicating coronary stenosis, and thus it can be judged or determined that there is a possibility of coronary stenosis.

[0102] The high-frequency QRS waveform curve analysis method disclosed in the above embodiments mainly focuses on whether the first amplitude drop relative value is greater than or equal to the first preset threshold in the QRS waveform curve segment corresponding to the first 3 minutes in the motion in the high-frequency QRS waveform curve, that is, mainly determines whether there is a steep drop waveform in the high-frequency QRS waveform curve in the first 3 minutes in the motion, and if there is, it is determined that there is coronary stenosis. However, the actual situation may be that the position (time point) where the first amplitude drop relative value greater than or equal to the first preset threshold appears in the high-frequency QRS waveform curve is located after 3 minutes, that is, the high-frequency QRS waveform curve appears a steep drop waveform after 3 minutes in the motion (as shown in Figure 2A The method of the above embodiments may ignore this situation and fail to determine the existence of coronary stenosis. In addition, this method also ignores the identification of the possibility of coronary arteriosclerosis.

[0103] In view of this, the inventors of the present application have further studied and proposed an innovative method for determining the possibility of coronary artery disease, which can improve the accuracy of determining the possibility of coronary stenosis and also determine the possibility of coronary arteriosclerosis compared with the method provided in the above embodiments disclosed before.

[0104] In the preferred embodiments of the present application, the overall inventive concept of determining whether there is a coronary artery disease can include obtaining first high-frequency QRS wave group data from exercise electrocardiogram data. The first high-frequency QRS wave group data can include a set of data points arranged in time sequence (i.e., chronological order), where each data point corresponds to a time point (time stamp) and an amplitude value (or intensity value), which can be, for example, an RMS voltage value. The first high-frequency QRS waveform curve can be essentially a curve obtained by connecting these data points in time sequence, or a curve obtained by removing minor fluctuations through curve smoothing processing.

[0105] A point sequence for each electrocardiogram lead can be obtained from the first high-frequency QRS wave group data, which can include a plurality of data points sampled or selected from a plurality of data point sets of the first high-frequency QRS wave group data at a set sampling period (sampling interval) or sampling frequency. Each sampling point in the point sequence is traversed to determine whether the first high-frequency QRS wave group data has a waveform feature indicative of a coronary artery disease, such as a steep drop wave, and if so, it can be determined that there is a possibility of a coronary artery disease.

[0106] Figure 2B An example flowchart of a method for determining the possibility of a coronary artery disease according to an embodiment of the present application is schematically shown. As shown in Figure 2B The method can include the following steps in this embodiment.

[0107] In step S1031, a point sequence (which can be referred to as a first high-frequency QRS time-intensity point sequence) corresponding to each electrocardiogram lead is obtained according to the first high-frequency QRS wave group data corresponding to each electrocardiogram lead. The point sequence can include a plurality of sampling points arranged in time sequence.

[0108] In step S1032, for the point sequence corresponding to any electrocardiogram lead, any sampling point in the plurality of sampling points in the point sequence is taken as a reference sampling point, and the sampling points in a preset time interval from the reference sampling point are traversed to determine whether there are a first sampling point and a second sampling point that meet a preset condition in the preset time interval. The sampling points in the preset time interval include the reference sampling point. In an example, the preset condition can be that the amplitude drop relative value between the first sampling point and the second sampling point reaches a first preset threshold and the voltage drop degree between the first sampling point and the second sampling point reaches a second preset threshold (which can be referred to as a first preset condition below). In another example, the preset condition can be that the amplitude drop relative value between the first sampling point and the second sampling point reaches the first preset threshold or the voltage drop degree between the first sampling point and the second sampling point reaches the second preset threshold (which can be referred to as a second preset condition below).

[0109] The amplitude drop relative value may, for example, be: (RMS voltage of the first sampling point - RMS voltage of the second sampling point) / RMS voltage of the first sampling point. In an example, the voltage drop degree can be a voltage drop absolute value, which can be the RMS voltage of the first sampling point minus (-) the RMS voltage of the second sampling point. In an alternative example, the voltage drop degree can be a ratio of the voltage drop absolute value to a maximum voltage value, i.e. (RMS voltage of the first sampling point - RMS voltage of the second sampling point) / maximum voltage value, which can be understood as a maximum power, which can be used to reflect the maximum heart pumping function of the subject, i.e. the peak value of the first high-frequency QRS wave group data (or the first high-frequency QRS waveform curve) will not exceed the maximum voltage value. The maximum voltage value can be determined according to the maximum value of the RMS voltages in the high-frequency QRS wave group data corresponding to all electrocardiogram leads (for example, the maximum RMS voltage is taken as an even integer). In this example, the second preset threshold can be in the form of a percentage as the first preset threshold.

[0110] In step S1033, in the case where the preset condition is met, it is determined that there is a possibility of coronary artery lesion. If the first sampling point and the second sampling point that meet the preset condition appear during the traversal, it indicates that the first high-frequency QRS wave group data has a waveform feature indicating coronary artery lesion, such as a steep drop wave, in which case it can be determined that there is a possibility of coronary artery lesion.

[0111] In step S1034, if the preset condition is not met, the step S1032 is repeated after replacing the reference sampling point. In this step, if all the sampling points in the preset time interval are traversed and no first sampling point and second sampling point meeting the preset condition are found, the current traversal loop ends, and the reference sampling point can be replaced, and the next traversal loop is entered. For example, the adjacent sampling point of the current reference sampling point is taken as the replaced (new) reference sampling point, and the sampling points in the preset time interval from the replaced reference sampling point are traversed based on the replaced reference sampling point to determine whether there are first sampling point and second sampling point meeting the preset condition. If there are first sampling point and second sampling point meeting the preset condition, it indicates that the first high-frequency QRS complex data has the waveform feature indicating the coronary artery lesion, and the traversal ends. If the current traversal loop ends and no first sampling point and second sampling point meeting the preset condition are found, the next traversal loop is entered, and the traversal loop is repeated until the first sampling point and second sampling point meeting the preset condition are found, or all the sampling points in the point sequence to be traversed are traversed. If all the sampling points to be traversed are traversed and the preset condition is still not met, it is determined that there is no waveform feature indicating the coronary artery lesion.

[0112] The traversal manner or rule of the sampling points can be various. Figure 3 An example flowchart of a method for determining the presence of a coronary artery lesion according to an embodiment of the present application is schematically shown. As shown in FIG. 6, the method comprises the following steps. Figure 3As shown, in this embodiment, for the first high-frequency QRS complex data corresponding to each electrocardiogram lead, the first sampling point in the point sequence in time sequence can be taken as a reference sampling point (which can be referred to as an initial reference point), the next sampling point of the initial reference point in time sequence is taken as a traversal starting point to perform traversal in time sequence, and the amplitude drop relative value and the voltage drop degree between the initial reference point (the first sampling point in this embodiment) and the current traversal sampling point (the second sampling point in this embodiment) are calculated. It is judged whether the initial reference point and the current traversal sampling point satisfy a preset condition. If the two sampling points satisfy the preset condition, it can be determined that the first high-frequency QRS complex data corresponding to the lead exists a waveform feature indicating coronary artery lesion, for example, a steep drop wave, so that it can be determined that there is a possibility of coronary artery lesion, and the traversal is stopped. If the preset condition is not satisfied, it is judged whether the time interval between the current traversal sampling point and the initial reference point exceeds a preset time length, and whether the current traversal sampling point is the last sampling point in the point sequence. If the time interval between the current traversal sampling point and the initial reference point does not exceed the preset time length and the current traversal sampling point is not the last sampling point, the next sampling point of the current traversal sampling point is switched to, the next sampling point is taken as a new current traversal sampling point, and the same operation is performed on the new current traversal sampling point. Specifically, the amplitude drop relative value and the voltage drop degree between the initial reference point and the new current traversal sampling point are calculated. It is judged whether the initial reference point and the new current traversal sampling point satisfy the preset condition. If the preset condition is satisfied, it can be determined that the first high-frequency QRS complex data corresponding to the lead exists a steep drop wave, that is, it can be determined that there is a possibility of coronary artery lesion, and the traversal is stopped. If the preset condition is not satisfied, the above operation can be repeated to traverse the subsequent sampling points, and if the preset condition is still not satisfied, the traversal can be continued until the time interval between the current traversal sampling point and the initial reference point reaches the preset time length (the preset time interval in this embodiment) or the current traversal sampling point is the last sampling point in the point sequence. If the time interval between the current traversal sampling point and the initial reference point reaches the preset time length or the current traversal sampling point is the last sampling point in the point sequence, the next sampling point of the initial reference point is switched to, the next sampling point is taken as a reference sampling point, and the next traversal loop is performed in the same manner as the above traversal operation. If the preset condition is still not satisfied, the traversal loop can be continuously performed until the preset condition is satisfied or until all the sampling points except the last sampling point in the point sequence are taken as reference sampling points to complete the traversal. That is, when the previous sampling point of the last sampling point is taken as a reference sampling point to complete the traversal, and the preset condition is still not satisfied, it is indicated that there is no waveform feature indicating coronary artery lesion, for example, a steep drop wave, for the first high-frequency QRS complex data corresponding to the electrocardiogram lead.

[0113] In this embodiment, the preset time length can be, for example, 1 minute to 3 minutes. If the preset condition is that the amplitude drop relative value between the first sampling point and the second sampling point reaches a first preset threshold value and the voltage drop degree between the first sampling point and the second sampling point reaches a second preset threshold value (the first preset condition), the value range of the first preset threshold value can be 30% to 40%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the second preset threshold value can be 1 uV to 2 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value can be 10% to 20%.

[0114] If the preset condition is that the amplitude drop relative value between the first sampling point and the second sampling point reaches a first preset threshold value, or, the voltage drop degree between the first sampling point and the second sampling point reaches a second preset threshold value (the first preset condition), the value range of the first preset threshold value can be 50% to 60%. In this case, the value of the second preset threshold value is associated with the preset time length. In general, the value of the second preset threshold value is positively correlated with the preset time length, that is, the greater the preset time length, the greater the second preset threshold value. For example, taking the value range of the preset time length as 1 minute to 3 minutes, if the preset time length is 1 minute, in the case where the voltage drop degree is the voltage drop absolute value, the value range of the second preset threshold value is 1 uV to 2 uV, and in the case where the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value is 10% to 20%. If the preset time length is 2 minutes, in the case where the voltage drop degree is the voltage drop absolute value, the value range of the second preset threshold value is 2 uV to 3 uV, and in the case where the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value is 20% to 30%. If the preset time length is 3 minutes, in the case where the voltage drop degree is the voltage drop absolute value, the value range of the second preset threshold value is 3 uV to 4 uV, and in the case where the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value is 30% to 40%. Those skilled in the art can understand that the specific values of the above preset threshold values are exemplary, and are intended to illustrate that the second preset threshold value is associated with the preset time length. For a smaller preset time length, if a larger second preset threshold value is used, the steep drop wave will be misjudged as a non-steep drop wave. For a larger preset time length, if a smaller second preset threshold value is used, the non-steep drop wave will be misjudged as a steep drop wave, thereby reducing the recognition accuracy. The specific values can be adjusted according to actual applications.

[0115] The first high-frequency QRS complex data corresponding to all electrocardiogram leads can be processed as above. If the first high-frequency QRS complex data corresponding to at least one electrocardiogram lead has waveform characteristics indicative of coronary artery lesion, such as a steep drop wave, it can be determined that there is a possibility of coronary artery lesion. Conversely, if the first high-frequency QRS complex data corresponding to all electrocardiogram leads does not have waveform characteristics indicative of coronary artery lesion, it can be determined that there is no coronary artery lesion.

[0116] Although the above embodiment processes the multiple sampling points in the point sequence in the time sequence from early to late, those skilled in the art can understand that the above method is also applicable to the multiple sampling points in the time sequence from late to early, in which case, the amplitude drop relative value and the voltage drop degree between the current traversal sampling point and the reference sampling point are calculated (in this case, the current traversal sampling point is earlier in time than the reference sampling point).

[0117] Figure 4 An example flowchart of a method for determining the possibility of coronary artery lesion according to another embodiment of the present application is schematically shown. As shown in FIG. 6, the method comprises the following steps. Figure 4As shown, in this embodiment, a window function can be preset, and the window of the window function includes a start point and an end point, and the distance between the start point and the end point is a window length (in this embodiment, the window length is the preset time interval described above). The window length can be, for example, 1 minute to 3 minutes. For the first high-frequency QRS complex data corresponding to each electrocardiogram lead, the point sequence of the first high-frequency QRS complex data is traversed using the window function. Specifically, the earliest first sampling point in the point sequence in time sequence can be taken as the start point of the window, and the sampling point with the maximum RMS voltage among the multiple sampling points in the point sequence included in the window (the first sampling point in this embodiment) and the sampling point with the minimum RMS voltage among the sampling points after the first sampling point in time sequence (the second sampling point in this embodiment) can be determined. The amplitude drop relative value between the first sampling point and the second sampling point and the voltage drop degree are calculated. It is determined whether the first sampling point and the second sampling point satisfy a preset condition. If the two sampling points satisfy the preset condition, it can be determined that the first high-frequency QRS complex data corresponding to the lead exists a sharp drop wave, that is, it can be determined that there is a possibility of coronary artery lesion, and the traversal is stopped. If the preset condition is not satisfied, the window of the window function is slid backward by a preset step, and the above operation is repeatedly performed. If there is still no situation satisfying the preset condition, the window is slid backward by the preset step again until the preset condition is satisfied or until the end point of the window reaches or exceeds the last sampling point in the point sequence. That is, when the end point of the window reaches or exceeds the last sampling point after the window is slid by the preset step, and there is still no situation satisfying the preset condition, it means that there is no waveform feature indicating coronary artery lesion, such as a sharp drop wave, for the first high-frequency QRS complex data of the electrocardiogram lead. In this embodiment, the preset step can be, for example, an integer multiple of the time interval (for example, a sampling period) between adjacent two sampling points, and is preferably the time interval between adjacent two sampling points, for example, 10 seconds. Of course, those skilled in the art can understand that it is also feasible to set the preset step to other values.

[0118] In this embodiment, if the preset condition is that the amplitude drop relative value between the first sampling point and the second sampling point reaches a first preset threshold and the voltage drop degree between the first sampling point and the second sampling point reaches a second preset threshold (the first preset condition), the value range of the first preset threshold can be 30% to 40%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the second preset threshold can be 1 uV to 2 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold can be 10% to 20%.

[0119] If the preset condition is that the amplitude drop relative value between the first sampling point and the second sampling point reaches a first preset threshold value, or the voltage drop degree between the first sampling point and the second sampling point reaches a second preset threshold value (the first preset condition), the value range of the first preset threshold value can be 50% to 60%. In this case, the value of the second preset threshold value is associated with the window length. In general, the value of the second preset threshold value is positively correlated with the window length, that is, the longer the window length, the larger the second preset threshold value. For example, taking the value range of the window length as 1 minute to 3 minutes as an example, if the window length is 1 minute, the value range of the second preset threshold value is 1 uV to 2 uV when the voltage drop degree is the voltage drop absolute value, and the value range of the second preset threshold value is 10% to 20% when the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value. If the window length is 2 minutes, the value range of the second preset threshold value is 2 uV to 3 uV when the voltage drop degree is the voltage drop absolute value, and the value range of the second preset threshold value is 20% to 30% when the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value. If the window length is 3 minutes, the value range of the second preset threshold value is 3 uV to 4 uV when the voltage drop degree is the voltage drop absolute value, and the value range of the second preset threshold value is 30% to 40% when the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value. Those skilled in the art can understand that the specific values of the above preset threshold values are exemplary, and the purpose is to explain that the second preset threshold value is associated with the window length. For a shorter window length, if a larger second preset threshold value is used, the steep drop wave will be misjudged as a non-steep drop wave. For a longer window length, if a smaller second preset threshold value is used, the non-steep drop wave will be misjudged as a steep drop wave, thereby reducing the recognition accuracy. The specific value can be adjusted according to actual application.

[0120] The first high-frequency QRS complex data corresponding to all electrocardiogram leads can be processed as above. If the first high-frequency QRS complex data corresponding to at least one electrocardiogram lead has a waveform feature indicating coronary artery lesion, such as a steep drop wave, it can be determined that there is a possibility of coronary artery lesion. Conversely, if the first high-frequency QRS complex data corresponding to all electrocardiogram leads does not have a waveform feature indicating coronary artery lesion, it can be determined that there is no coronary artery lesion.

[0121] Although the window function used in the above embodiment starts from the earliest sampling point in the point sequence, those skilled in the art can understand that it can also start from the latest sampling point in the point sequence.

[0122] Figure 5An example flowchart illustrating a method for determining the likelihood of coronary artery disease according to another embodiment of this application is shown. Figure 5 As shown, in this embodiment, a window function can be preset. The window of this window function includes a start point and an end point, and the distance between the start point and the end point is the window length (in this embodiment, the window length is the preset time interval mentioned above). The window length can range from, for example, 1 minute to 3 minutes. For the first high-frequency QRS complex data corresponding to each ECG lead, the start point of the window can be aligned with the earliest sampling point in the time sequence (i.e., these two points coincide in time). Using this first sampling point as a reference point, each sampling point within the window is traversed sequentially. Specifically, the relative value of amplitude decrease and the degree of voltage decrease between the reference point and the currently traversed sampling point within the window can be calculated. It is determined whether the reference point and the currently traversed sampling point meet preset conditions. If these two sampling points meet the preset conditions, it can be determined that the first high-frequency QRS complex data corresponding to the lead has waveform characteristics indicating coronary artery disease, such as a steep drop wave, and the possibility of coronary artery disease can be determined, and the traversal stops. If the preset conditions are not met, the next sampling point within the window is traversed. If the reference point and the currently traversed sampling point meet the preset conditions, the traversal stops; otherwise, it continues until the last sampling point within the traversal window. If the preset conditions are still not met after all sampling points within the window have been traversed, the traversal loop ends, and the window of the window function can be slid backward (time-wise backward) by a preset step size, and the above operation is repeated (the next traversal loop). If the preset conditions are still not met after the traversal loop ends, the window can be slid backward by the preset step size again until the preset conditions are met, or until the end of the window reaches or exceeds the last sampling point in the point sequence. That is, if the preset conditions are still not met after the window has slid by the preset step size and its end reaches or exceeds the last sampling point, it indicates that there are no waveform characteristics indicating coronary artery lesions, such as steep descent waves, for the first high-frequency QRS complex data of that ECG lead. In this embodiment, the preset step size can be, for example, an integer multiple of the time interval (e.g., sampling period) between two adjacent sampling points, preferably, the time interval between two adjacent sampling points, such as 10 seconds. Of course, those skilled in the field can understand that setting the preset step size to other values ​​is also feasible.

[0123] In this embodiment, if the preset condition is that the amplitude drop relative value between the first sampling point and the second sampling point reaches a first preset threshold value and the voltage drop degree between the first sampling point and the second sampling point reaches a second preset threshold value (the first preset condition), the value range of the first preset threshold value can be 30% to 40%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the second preset threshold value can be 1 uV to 2 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value can be 10% to 20%.

[0124] If the preset condition is that the amplitude drop relative value between the first sampling point and the second sampling point reaches a first preset threshold value, or, the voltage drop degree between the first sampling point and the second sampling point reaches a second preset threshold value (the first preset condition), the value range of the first preset threshold value can be 50% to 60%. In this case, the value of the second preset threshold value is associated with the window length. In general, the value of the second preset threshold value is positively correlated with the window length, that is, the longer the window length, the larger the second preset threshold value. For example, taking the value range of the window length as 1 minute to 3 minutes as an example, if the window length is 1 minute, in the case of the voltage drop degree being the voltage drop absolute value, the value range of the second preset threshold value is 1 uV to 2 uV, and in the case of the voltage drop degree being the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value is 10% to 20%. If the window length is 2 minutes, in the case of the voltage drop degree being the voltage drop absolute value, the value range of the second preset threshold value is 2 uV to 3 uV, and in the case of the voltage drop degree being the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value is 20% to 30%. If the window length is 3 minutes, in the case of the voltage drop degree being the voltage drop absolute value, the value range of the second preset threshold value is 3 uV to 4 uV, and in the case of the voltage drop degree being the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value is 30% to 40%. Those skilled in the art can understand that the specific values of the above preset threshold values are exemplary, and the purpose is to explain that the second preset threshold value is associated with the window length. For a shorter window length, if a larger second preset threshold value is used, the steep drop wave will be misjudged as a non-steep drop wave. For a longer window length, if a smaller second preset threshold value is used, the non-steep drop wave will be misjudged as a steep drop wave, thereby reducing the recognition accuracy. The specific values can be adjusted according to actual application.

[0125] The first high-frequency QRS complex data corresponding to all electrocardiogram leads can be processed as above. If the first high-frequency QRS complex data corresponding to at least one electrocardiogram lead has a waveform feature indicative of coronary artery lesion, such as a steep drop wave, it can be determined that there is a possibility of coronary artery lesion. Conversely, if the first high-frequency QRS complex data corresponding to all electrocardiogram leads does not have a waveform feature indicative of coronary artery lesion, it can be determined that there is no coronary artery lesion.

[0126] Although the window function adopted in the above embodiment starts from the earliest sampling point in time sequence in the point sequence, it can be understood by those skilled in the art that it can also start from the latest sampling point in time sequence in the point sequence.

[0127] In the above embodiment, if it is determined in the traversal process that there are two sampling points that satisfy the preset condition, but the first high-frequency QRS complex data (or the first high-frequency QRS waveform curve) can have a significant fluctuation amplitude between the two sampling points, the cause of this situation can be coronary spasm or other factors such as microcirculation disorder. In order to exclude this interference factor, in the preferred embodiment of the present application, after the first sampling point and the second sampling point that satisfy the preset condition are determined, the first-order difference of the RMS voltage / amplitude / value / intensity of the sampling points between the first sampling point and the second sampling point is calculated to determine a third sampling point corresponding to a minimum value (minimum point) and at least one fourth sampling point corresponding to a maximum value (maximum point). Here, the minimum point refers to a point where the first-order difference result changes from negative to positive, and the maximum point refers to a point where the first-order difference result changes from positive to negative. For any one of the at least one fourth sampling point, the absolute value of the RMS voltage difference between the fourth sampling point and the third sampling point (referred to as the first RMS voltage difference) is calculated, and the RMS voltage difference between the first sampling point and the second sampling point (referred to as the second RMS voltage difference) is calculated. If the ratio of the first RMS voltage difference to the second RMS voltage difference is greater than or equal to a third preset threshold, it is determined that there is a significant fluctuation amplitude, it is determined that the two sampling points (the first sampling point and the second sampling point) of the first high-frequency QRS complex data do not have a waveform feature indicative of coronary artery lesion (it is considered that the first sampling point and the second sampling point do not satisfy the preset condition), and the traversal continues according to the case where the preset condition is not satisfied in the above embodiment. If the ratio is less than the third preset threshold, the influence of the significant fluctuation amplitude can be excluded, and the first sampling point and the second sampling point satisfy the preset condition, and it can be determined that there is a steep drop wave. In the case where the number of fourth sampling points is multiple, it is preferred that the ratio obtained for each fourth sampling point is less than the third preset threshold, and the influence of the significant fluctuation amplitude can be excluded. In an example, the third preset threshold can be, for example, 40%, 50%, etc. Excluding the interference of the significant fluctuation amplitude on the determination of whether there is a steep drop wave in this way can further improve the evaluation specificity.

[0128] Compared with the scheme for judging whether there is coronary stenosis disclosed in the prior patent application, the coronary artery lesion judgment method provided in the above embodiments can significantly improve the sensitivity while ensuring that the specificity does not decrease significantly or even does not decrease.

[0129] In further embodiments of the present application, the type of coronary artery lesion, i.e., coronary stenosis or coronary sclerosis, can be further determined. In this embodiment, the method for determining the presence of coronary artery lesion possibility can further include the following steps.

[0130] In step S1035, a first lead positive indicator corresponding to the first high-frequency QRS complex data indicating the waveform feature of the coronary artery lesion is determined. The determination method of the first lead positive indicator is as described above, which will not be repeated here.

[0131] In step S1035, in the case where the first lead positive indicator indicates positive, the type of coronary artery lesion is determined to be coronary stenosis. Wherein, if considering the critical case (i.e., the state between positive and negative), the case where the first lead positive indicator indicates positive includes the case where the first lead positive indicator indicates positive or critical.

[0132] In step S1036, in the case where the first lead positive indicator indicates negative, the type of coronary artery lesion is determined to be coronary sclerosis.

[0133] In step S104, the possibility of the presence of myocardial bridge is determined according to the exercise electrocardiogram data.

[0134] Whether the first high-frequency QRS complex data has the second waveform feature can be determined by the following method, i.e., determining whether there is a possibility of myocardial bridge. Figure 6 An example flowchart of a method for determining the possibility of the presence of myocardial bridge according to an embodiment of the present application is schematically shown. As shown, specifically, in this embodiment, the method can include the following steps. Figure 6

[0135] ​In step S1041, candidate first high-frequency QRS complex data without waveform features indicative of coronary artery lesions, such as a steep drop wave, are determined from the first high-frequency QRS complex data corresponding to each electrocardiogram lead. When analyzing the first high-frequency QRS complex data to determine whether a myocardial bridge exists, first high-frequency QRS complex data with waveform features indicative of coronary artery lesions can be excluded first. That is, if the first high-frequency QRS complex data has waveform features indicative of coronary artery lesions, such as a steep drop wave, the first high-frequency QRS complex data is no longer used to determine whether a myocardial bridge exists. The method for determining whether the first high-frequency QRS complex data has waveform features indicative of coronary artery lesions is as described in the embodiments regarding the method for determining the likelihood of the existence of coronary artery lesions, which will not be described here again.

[0136] In step S1042, a point sequence (which can be referred to as a first high-frequency QRS time-intensity point sequence) of each candidate first high-frequency QRS complex data is obtained, which can include a plurality of sampling points arranged in time sequence. The plurality of sampling points can be a plurality of data points sampled or selected from a plurality of data point sets of the candidate first high-frequency QRS complex data at a set sampling period (sampling interval) or sampling frequency.

[0137] In step S1043, for the point sequence of any candidate first high-frequency QRS complex data, any sampling point in the plurality of sampling points of the point sequence is taken as a reference sampling point, and the sampling points within a preset time interval from the reference sampling point are traversed to determine whether there are an earlier first sampling point and a later second sampling point within the preset time interval that satisfy a preset condition.

[0138] In an example scenario, the preset condition can be that the amplitude drop relative value between the first sampling point and the second sampling point reaches a fourth preset threshold value, and the voltage drop degree between the first sampling point and the second sampling point reaches a fifth preset threshold value, and the root mean square voltage of each sampling point between the first sampling point and the second sampling point shows a continuous downward trend (which can be referred to as a third preset condition hereinafter). In another example scenario, the preset condition can be that the amplitude drop relative value between the first sampling point and the second sampling point reaches a fourth preset threshold value or the voltage drop degree between the first sampling point and the second sampling point reaches a fifth preset threshold value, and the root mean square voltage of each sampling point between the first sampling point and the second sampling point shows a continuous downward trend (which can be referred to as a fourth preset condition hereinafter).

[0139] The amplitude reduction relative value may be, for example, (first sampling point root mean square voltage (RMS voltage) - second sampling point RMS voltage) / first sampling point RMS voltage. In an example, the voltage reduction degree can be a voltage reduction absolute value, which can be the first sampling point root mean square voltage (RMS voltage) minus ( - ) the second sampling point RMS voltage. In an alternative example, the voltage reduction degree can be a ratio of the voltage reduction absolute value to a maximum voltage value, i.e. (first sampling point root mean square voltage (RMS voltage) - second sampling point RMS voltage) / maximum voltage value, which can be understood as a maximum power that can be used to reflect the maximum cardiac pumping function of the subject, i.e. the peak value of the candidate first high-frequency QRS complex data does not exceed the maximum voltage value, and the maximum voltage value is determined according to the maximum value of the root mean square voltage in the high-frequency QRS complex data of all electrocardiogram leads. In this example, the fifth preset threshold value can be in the form of a percentage as the fourth preset threshold value.

[0140] In step S1044, it is determined that there is a possibility of myocardial bridge when the preset condition is met. During the traversal, if the first sampling point and the second sampling point that meet the preset condition appear, it indicates that the candidate first high-frequency QRS complex data has a waveform feature indicating a myocardial bridge, such as a slow descent wave, in which case it can be determined that there is a possibility of myocardial bridge. Here, the slow descent wave has a more gentle waveform downward trend than the steep descent wave.

[0141] In step S1045, the reference sampling point is replaced and step S1043 is repeated when the preset condition is not met. In this step, if all the sampling points in the preset time interval are traversed and no first sampling point and second sampling point that meet the preset condition appear, the current traversal loop ends, and the reference sampling point is replaced at this time. Enter the next traversal loop, for example, the adjacent sampling point of the current reference sampling point is taken as the replaced (new) reference sampling point, and the replaced reference sampling point is taken as the reference to traverse the sampling points in the preset time interval from the reference sampling point to determine whether there are first sampling points and second sampling points that meet the preset condition. If there are first sampling points and second sampling points that meet the preset condition, it indicates that the candidate first high-frequency QRS complex data line has a waveform feature indicating a myocardial bridge, and the traversal ends. If the current traversal loop ends and no first sampling point and second sampling point that meet the preset condition appear, enter the next traversal loop and repeat the traversal loop until a first sampling point and a second sampling point that meet the preset condition appear, or all the sampling points in the point sequence that need to be traversed are traversed. If all the sampling points that need to be traversed are traversed and still do not meet the preset condition, it is determined that there is no waveform feature indicating a myocardial bridge.

[0142] There can be various ways or rules for traversing the sampling points. Figure 7An example flowchart illustrating a method for determining the likelihood of the presence of myocardial bridging according to an embodiment of this application is shown. Figure 7As shown, in this embodiment, for each candidate first high-frequency QRS complex data (i.e., the complex data does not have waveform features indicative of coronary artery lesions), the first sampling point in time sequence in its point sequence can be taken as a reference sampling point (which can be referred to as an initial reference point), the next sampling point in time sequence of the initial reference point can be taken as a traversal starting point to perform traversal in time sequence, and the amplitude drop relative value and voltage drop degree between the initial reference point (the first sampling point in this embodiment) and the current traversal sampling point (the second sampling point in this embodiment) can be calculated. It is determined whether the initial reference point and the current traversal sampling point satisfy a preset condition. If the two sampling points satisfy the preset condition, it can be determined that the candidate first high-frequency QRS complex data has waveform features indicative of myocardial bridge, such as a slow descent wave, thereby determining the possibility of myocardial bridge, and stopping traversal. If the preset condition is not satisfied, it is determined whether the time interval between the current traversal sampling point and the initial reference point exceeds a preset time length, and whether the current traversal sampling point is the last sampling point in the point sequence. If the time interval between the current traversal sampling point and the initial reference point does not exceed the preset time length and the current traversal sampling point is not the last sampling point, the next sampling point of the current traversal sampling point is switched to, the next sampling point is taken as a new current traversal sampling point, and the same operation is performed on the new current traversal sampling point. Specifically, the amplitude drop relative value and voltage drop degree between the initial reference point and the new current traversal sampling point are calculated. It is determined whether the initial reference point and the new current traversal sampling point satisfy the preset condition. If the preset condition is satisfied, it can be determined that the candidate first high-frequency QRS complex data has a slow descent wave, i.e., the possibility of myocardial bridge is determined, and the traversal is stopped. If the preset condition is not satisfied, the above operation can be repeated to traverse the subsequent sampling points, and if the preset condition is still not satisfied, the traversal can be continued until the time interval between the current traversal sampling point and the initial reference point reaches the preset time length (the preset time interval in this embodiment) or the current traversal sampling point is the last sampling point in the point sequence. If the time interval between the current traversal sampling point and the initial reference point reaches the preset time length or the current traversal sampling point is the last sampling point in the point sequence, the next sampling point of the initial reference point is switched to, the next sampling point is taken as a reference sampling point, and the next traversal cycle is performed in the same manner as the above traversal operation. If the preset condition is still not satisfied, the traversal cycle can be continuously performed until the preset condition is satisfied or until all sampling points except the last sampling point in the point sequence are taken as reference sampling points to complete traversal. That is, when the previous sampling point of the last sampling point is taken as a reference sampling point to complete traversal, and the preset condition is still not satisfied, it is indicated that the candidate first high-frequency QRS complex data does not have waveform features indicative of myocardial bridge, such as a slow descent wave.

[0143] In this embodiment, the preset time length can be, for example, 4 to 6 minutes. If the preset condition includes that the amplitude drop relative value between the first sampling point and the second sampling point reaches the fourth preset threshold value and the voltage drop degree between the first sampling point and the second sampling point reaches the fifth preset threshold value (the third preset condition), the value range of the fourth preset threshold value can be 30% to 40%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the fifth preset threshold value can be 1 uV to 2 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the fifth preset threshold value can be 10% to 20%.

[0144] If the preset condition includes that the amplitude drop relative value between the first sampling point and the second sampling point reaches the fourth preset threshold value, or, the voltage drop degree between the first sampling point and the second sampling point reaches the fifth preset threshold value (the fourth preset condition), the value range of the fourth preset threshold value can be 50% to 60%. In this case, the value of the fifth preset threshold value is associated with the preset time length. In general, the value of the fifth preset threshold value is positively correlated with the preset time length, that is, the greater the preset time length, the greater the fifth preset threshold value. For example, taking the value range of the preset time length as 4 to 6 minutes, if the preset time length is 4 minutes, the value range of the fifth preset threshold value is 1 uV to 2 uV when the voltage drop degree is the voltage drop absolute value, and the value range of the fifth preset threshold value is 10% to 20% when the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value. If the preset time length is 5 minutes, the value range of the fifth preset threshold value is 2 uV to 3 uV when the voltage drop degree is the voltage drop absolute value, and the value range of the second preset threshold value is 20% to 30% when the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value. If the preset time length is 6 minutes, the value range of the fifth preset threshold value is 3 uV to 4 uV when the voltage drop degree is the voltage drop absolute value, and the value range of the second preset threshold value is 30% to 40% when the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value. Those skilled in the art can understand that the specific values of the above preset threshold values are exemplary, and are used to illustrate that the fifth preset threshold value is associated with the preset time length. For a smaller preset time length, if a larger fifth preset threshold value is used, the slow decline wave will be misjudged as a non-slow decline wave. For a larger preset time length, if a smaller fifth preset threshold value is used, the non-slow decline wave (such as a flat wave) will be misjudged as a slow decline wave, thereby reducing the recognition accuracy. Similarly, the preset time length is positively correlated with the fourth preset threshold value, so as to further improve the recognition accuracy. The specific values can be adjusted according to actual applications.

[0145] All candidate first high frequency QRS complex data can be processed as above, if at least one candidate first high frequency QRS complex data has waveform characteristics indicative of myocardial bridge, for example, a slow descent wave, it can be determined that there is a possibility of myocardial bridge. Conversely, if all candidate first high frequency QRS complex data do not have waveform characteristics indicative of myocardial bridge, it can be determined that there is no myocardial bridge.

[0146] Although the above embodiment is to process multiple sampling points in the point sequence in the time sequence from early to late, those skilled in the art can understand that the above method is also applicable to multiple sampling points in the time sequence from late to early, and in this case, the amplitude drop relative value and the voltage drop degree between the current traversal sampling point and the reference sampling point are calculated (in this case, the current traversal sampling point is earlier in time than the reference sampling point).

[0147] Figure 8 An example flow chart of a method for determining the possibility of myocardial bridge according to another embodiment of the present application is schematically shown. As shown in the figure, the method comprises the following steps: Figure 8As shown, in this embodiment, a window function can be preset, the window of the window function including a start point and an end point, the distance between the start point and the end point being a window length (in this embodiment, the window length is the preset time interval described above). The window length can be, for example, 4 minutes to 6 minutes. For each candidate first high-frequency QRS complex data, the point sequence of the candidate first high-frequency QRS complex data is traversed using the window function. Specifically, the earliest first sampling point in the point sequence in time sequence can be taken as the start point of the window, and the sampling point with the maximum RMS voltage among the multiple sampling points in the point sequence included in the window (the first sampling point in this embodiment) and the sampling point with the minimum RMS voltage among the sampling points after the first sampling point in time sequence (the second sampling point in this embodiment) can be determined. The amplitude drop relative value between the first sampling point and the second sampling point and the voltage drop degree are calculated. It is determined whether the first sampling point and the second sampling point satisfy a preset condition. If the two sampling points satisfy the preset condition, it can be determined that the candidate first high-frequency QRS complex data has a slow descent wave, i.e., it can be determined that there is a possibility of myocardial bridge, and the traversal is stopped. If the preset condition is not satisfied, the window of the window function is slid backward by a preset step, and the above operation is repeatedly performed. If the situation where the preset condition is still not satisfied still does not appear, the window is slid backward by the preset step again until the preset condition is satisfied, or until the end point of the window reaches or exceeds the last sampling point in the point sequence. That is, when the end point of the window reaches or exceeds the last sampling point after the window is slid by the preset step, and the situation where the preset condition is satisfied still does not appear, it means that there is no wave form feature indicating myocardial bridge, such as a slow descent wave, for the candidate first high-frequency QRS complex data. In this embodiment, the preset step can be, for example, an integer multiple of the time interval (e.g., a sampling period) between adjacent two sampling points, and is preferably the time interval between adjacent two sampling points, e.g., 10 seconds. Of course, those skilled in the art can understand that it is also feasible to set the preset step to other values.

[0148] In this embodiment, if the preset condition includes that the amplitude drop relative value between the first sampling point and the second sampling point reaches a fourth preset threshold and the voltage drop degree between the first sampling point and the second sampling point reaches a fifth preset threshold (a third preset condition), the value range of the fourth preset threshold can be 30% to 40%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the fifth preset threshold can be 1 uV to 2 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the fifth preset threshold can be 10% to 20%.

[0149] If the preset condition includes that the amplitude drop relative value between the first sampling point and the second sampling point reaches a fourth preset threshold value, or, the voltage drop degree between the first sampling point and the second sampling point reaches a fifth preset threshold value (the fourth preset condition), the value range of the fourth preset threshold value can be 50% to 60%. In this case, the value of the fifth preset threshold value is associated with the window length. In general, the value of the fifth preset threshold value is positively correlated with the window length, that is, the larger the window length, the larger the fifth preset threshold value. For example, taking the value range of the window length as 4 minutes to 6 minutes as an example, if the window length is 4 minutes, the value range of the fifth preset threshold value is 1 uV to 2 uV in the case of the voltage drop degree being the voltage drop absolute value, and the value range of the fifth preset threshold value is 10% to 20% in the case of the voltage drop degree being the ratio of the voltage drop absolute value to the maximum voltage value. If the window length is 5 minutes, the value range of the fifth preset threshold value is 2 uV to 3 uV in the case of the voltage drop degree being the voltage drop absolute value, and the value range of the second preset threshold value is 20% to 30% in the case of the voltage drop degree being the ratio of the voltage drop absolute value to the maximum voltage value. If the window length is 6 minutes, the value range of the fifth preset threshold value is 3 uV to 4 uV in the case of the voltage drop degree being the voltage drop absolute value, and the value range of the second preset threshold value is 30% to 40% in the case of the voltage drop degree being the ratio of the voltage drop absolute value to the maximum voltage value. Those skilled in the art can understand that the specific values of the above preset threshold values are exemplary, and are used to explain that the fifth preset threshold value is associated with the window length. For a smaller window length, if a larger fifth preset threshold value is used, the slow drop wave will be misjudged as a non-slow drop wave. For a larger window length, if a smaller fifth preset threshold value is used, the non-slow drop wave (such as a flat wave) will be misjudged as a slow drop wave, thereby reducing the recognition accuracy. Similarly, the window length is positively correlated with the fourth preset threshold value, so as to further improve the recognition accuracy. The specific values can be adjusted according to actual application.

[0150] The above processing can be performed on all candidate first high-frequency QRS complex data. If at least one candidate first high-frequency QRS complex data has a waveform feature indicating a myocardial bridge, such as a slow drop wave, it can be determined that there is a possibility of a myocardial bridge. Conversely, if all candidate first high-frequency QRS complex data do not have a waveform feature indicating a myocardial bridge, it can be determined that there is no myocardial bridge.

[0151] Although the window function used in the above embodiments starts from the earliest sampling point in the point sequence, those skilled in the art can understand that it can also start from the latest sampling point in the point sequence.

[0152] Figure 9An example flowchart illustrating a method for determining the likelihood of the presence of myocardial bridging according to another embodiment of this application is shown. Figure 9 As shown, in this embodiment, a window function can be preset. The window of this window function includes a start point and an end point, and the distance between the start point and the end point is the window length (in this embodiment, the window length is the preset time interval mentioned above). The value range of the window length can be, for example, 4 minutes to 6 minutes. For each candidate first high-frequency QRS complex data, the start point of the window can be aligned with the earliest sampling point in the point sequence in terms of time (i.e., these two points coincide in time). Using this first sampling point as a reference point, each sampling point within the window is traversed sequentially. Specifically, the relative value of amplitude decrease and the degree of voltage decrease between the reference point and the currently traversed sampling point within the window can be calculated. It is determined whether the reference point and the currently traversed sampling point meet preset conditions. If these two sampling points meet the preset conditions, it can be determined that the candidate first high-frequency QRS complex data has waveform characteristics indicating myocardial bridging, such as a slow-falling wave, and the possibility of myocardial bridging can be determined, and the traversal stops. If the preset conditions are not met, the next sampling point within the window is traversed. If the reference point and the currently traversed sampling point meet the preset conditions, the traversal stops; otherwise, it continues until the last sampling point within the traversal window. If the preset conditions are still not met after all sampling points within the window have been traversed, the traversal loop ends, and the window of the window function can be slid backward (time-wise backward) by a preset step size, and the above operation (the next traversal loop) is repeated. If no situation meets the preset conditions after the traversal loop ends, the window can be slid backward by the preset step size again until the preset conditions are met, or until the end of the window reaches or exceeds the last sampling point in the point sequence. That is, if no situation meets the preset conditions after the window has slid by a preset step size and its end reaches or exceeds the last sampling point, it indicates that there are no waveform features indicative of myocardial bridging, such as a slow-falling wave, for the candidate first high-frequency QRS complex data. In this embodiment, the preset step size can be, for example, an integer multiple of the time interval (e.g., sampling period) between two adjacent sampling points, preferably, the time interval between two adjacent sampling points, such as 10 seconds. Of course, those skilled in the art will understand that setting the preset step size to other values ​​is also feasible.

[0153] In this embodiment, if the preset condition includes that the amplitude drop relative value between the first sampling point and the second sampling point reaches the fourth preset threshold value and the voltage drop degree between the first sampling point and the second sampling point reaches the fifth preset threshold value (the third preset condition), the value range of the fourth preset threshold value can be 30% to 40%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the fifth preset threshold value can be 1 uV to 2 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the fifth preset threshold value can be 10% to 20%.

[0154] If the preset condition includes that the amplitude drop relative value between the first sampling point and the second sampling point reaches the fourth preset threshold value or the voltage drop degree between the first sampling point and the second sampling point reaches the fifth preset threshold value (the fourth preset condition), the value range of the fourth preset threshold value can be 50% to 60%. In this case, the value of the fifth preset threshold value is associated with the window length. In general, the value of the fifth preset threshold value is positively correlated with the window length, that is, the larger the window length, the larger the fifth preset threshold value. For example, taking the value range of the window length as 4 minutes to 6 minutes, if the window length is 4 minutes, in the case of the voltage drop degree being the voltage drop absolute value, the value range of the fifth preset threshold value is 1 uV to 2 uV, and in the case of the voltage drop degree being the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value is 10% to 20%. If the window length is 5 minutes, in the case of the voltage drop degree being the voltage drop absolute value, the value range of the fifth preset threshold value is 2 uV to 3 uV, and in the case of the voltage drop degree being the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value is 20% to 30%. If the window length is 6 minutes, in the case of the voltage drop degree being the voltage drop absolute value, the value range of the fifth preset threshold value is 3 uV to 4 uV, and in the case of the voltage drop degree being the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the second preset threshold value is 30% to 40%. Those skilled in the art can understand that the specific values of the above preset threshold values are exemplary, and are used to illustrate that the fifth preset threshold value is associated with the window length. For a smaller window length, if a larger fifth preset threshold value is used, the slow decline wave will be misjudged as a non-slow decline wave. For a larger window length, if a smaller fifth preset threshold value is used, the non-slow decline wave (such as a flat wave) will be misjudged as a slow decline wave, thereby reducing the recognition accuracy. Similarly, the window length is positively correlated with the fourth preset threshold value, so as to further improve the recognition accuracy. The specific values can be adjusted according to actual application.

[0155] The above processing can be performed on all candidate first high-frequency QRS complex data. If at least one candidate first high-frequency QRS complex data has a waveform feature indicative of a myocardial bridge, such as a slow descent wave, it can be determined that there is a possibility of a myocardial bridge. Conversely, if all candidate first high-frequency QRS complex data do not have a waveform feature indicative of a myocardial bridge, it can be determined that there is no myocardial bridge.

[0156] Although the window function used in the above embodiment starts from the earliest sampling point in time sequence in the point sequence, it can be understood by those skilled in the art that it can also start from the latest sampling point in time sequence in the point sequence.

[0157] In the above embodiment, the value of the preset time interval (e.g., preset time length, window length) for myocardial bridge determination is larger than the value of the preset time interval (e.g., preset time length, window length) for coronary artery lesion determination, the fourth preset threshold is greater than or equal to the first preset threshold, and the fifth preset threshold is greater than or equal to the second preset threshold. In addition, the time interval between two adjacent sampling points in the plurality of sampling points for myocardial bridge determination can be larger than the time interval between two adjacent sampling points in the plurality of sampling points for coronary artery lesion determination. For example, the time interval between two adjacent sampling points in the plurality of sampling points for myocardial bridge determination can be, for example, 12 seconds, and the time interval between two adjacent sampling points in the plurality of sampling points for coronary artery lesion determination can be, for example, 10 seconds.

[0158] In the preferred embodiment of the present application, in order to improve the accuracy of myocardial bridge determination, after obtaining the candidate first high-frequency QRS complex data, the candidate first high-frequency QRS complex data can be smoothed to smooth out the points with slight fluctuations. For example, the root mean square voltage / intensity / amplitude corresponding to a plurality of data points can be curve-smoothed in time sequence to obtain the candidate first high-frequency QRS complex data after smoothing.

[0159] In the preferred embodiment of the present application, the root mean square voltage of each sampling point between the first sampling point and the second sampling point in the first preset condition can be determined in the following manner. Increasing the determination of this condition can further improve the accuracy of myocardial bridge determination or recognition.

[0160] Specifically, if it is determined that the candidate first high-frequency QRS complex data has a first sampling point and a second sampling point that satisfy the following conditions, i.e.,

[0161] the amplitude drop relative value between the first sampling point and the second sampling point reaches the fourth preset threshold and the voltage drop degree between the first sampling point and the second sampling point reaches the fifth preset threshold (the case of the third preset condition); or

[0162] The amplitude drop between the first sampling point and the second sampling point reaches a fourth preset threshold, or the voltage drop between the first sampling point and the second sampling point reaches a fifth preset threshold (the fourth preset condition). The first difference of the RMS voltage / amplitude / intensity of the sampling points in the candidate first high-frequency QRS complex data located in the current preset time interval (for example, a preset time length, a window length) can be calculated to obtain a difference sequence, and the number of continuous values greater than or equal to zero in the difference sequence is determined. If the number is less than or equal to a number threshold, for example, 2 (that is, the flat wave or rising wave can be excluded), it can be determined that the RMS voltage of each sampling point between the first sampling point and the second sampling point shows a continuous downward trend. At this time, it can be determined that the candidate first high-frequency QRS complex data has a waveform feature indicating a myocardial bridge, for example, a slow drop wave, and it can be determined that there is a possibility of a myocardial bridge.

[0163] In the preferred embodiment of the present application, in order to further improve the accuracy of myocardial bridge judgment or identification, for example, to further exclude the possibility of a steep drop wave in the candidate first high-frequency QRS complex data, after obtaining the difference sequence, all difference sequence groups are determined, each difference sequence group includes a number of continuous difference values, and the sum of the number of difference values in each sequence group is calculated. For example, assuming that the difference sequence includes N difference values, the number of continuous difference values is n, N and n are natural numbers, and n < N. The first sequence group can include the first difference value to the n-th difference value, the second sequence group can include the second difference value to the n+1-th difference value, and so on. If the number of continuous values greater than or equal to zero in the difference sequence is less than or equal to 2, and the sum of the difference values of each difference sequence group is greater than or equal to a predetermined value, it can be determined that the candidate first high-frequency QRS complex data has a waveform feature indicating a myocardial bridge, for example, a slow drop wave, and it can be determined that there is a possibility of a myocardial bridge. The sum of the continuous difference values can further exclude the steep drop, that is, exclude the case that the candidate first high-frequency QRS complex data has a steep drop wave. In an example, the number of continuous difference values in each sequence group can be, for example, 5, and the predetermined value can be, for example, -15. Of course, those skilled in the art can understand that as long as the purpose of excluding the steep drop wave is achieved, other numerical values can be set according to actual application.

[0164] In theory, the RMS voltage drop of the first high-frequency QRS complex data caused by the myocardial bridge will continue until the exercise ends or even a period of time (for example, 20 seconds) after the exercise ends, and the duration is at least 3 minutes, and is a continuous slow drop. In alternative or additional embodiments of the present application, a technical solution can be designed according to this phenomenon to determine whether there is a possibility of a myocardial bridge.

[0165] Figure 10An example flowchart of a method for judging the possibility of existence of myocardial bridge according to another embodiment of the present application is schematically shown. As shown in the figure, in this embodiment, candidate first high-frequency QRS complex data can be determined from the first high-frequency QRS complex data corresponding to each electrocardiogram lead, which does not have waveform features indicative of coronary artery lesions, such as a sharp drop wave. Figure 10

[0166] For any candidate first high-frequency QRS complex data, at least one sampling point in the candidate first high-frequency QRS complex data within a preset time period is determined as a reference sampling point. In an example, the preset time period can be a time period from the time when the exercise ends in the exercise electrocardiogram detection process to a time after the exercise ends, for example, from the time when the exercise ends to 20-30 seconds after the exercise ends. In this embodiment, the reference sampling point in step S1043 is determined from the sampling points within a period of time after the exercise ends.

[0167] According to the determined reference sampling point, the sampling points to be traversed are determined, wherein the sampling points to be traversed are the sampling points within a preset time interval before the reference sampling point in the candidate first high-frequency QRS complex data. In an example, the preset time interval is within the exercise phase of the load exercise electrocardiogram detection process. The preset time interval can include a plurality of continuous sub-intervals (i.e., adjacent to each other but not overlapping). For example, taking the reference sampling point as the exercise end point and the time point of the exercise end point as 9 minutes (counted from the start of the load exercise electrocardiogram detection process), the preset time interval can be 3-6 minutes before the reference sampling point, and the preset time interval can include a first sub-interval, a second sub-interval, and a third sub-interval. The first sub-interval can be 3-4 minutes before the reference sampling point (not including 3 minutes but including 4 minutes), and taking the start of the load exercise electrocardiogram detection process as the zero point, the first sub-interval can be represented as: [5 minutes, 6 minutes); the second sub-interval can be 4-5 minutes before the reference sampling point, which can also be represented as: [4 minutes, 5 minutes); and the third sub-interval can be 5-6 minutes before the reference sampling point, which can also be represented as: [3 minutes, 4 minutes). In the embodiments of the present application, if the number of at least one reference sampling point includes multiple, each reference sampling point can have a corresponding preset time interval. That is, the time position (timestamp) of the reference sampling point can be different, and the (time) position of the corresponding preset time interval can also be different, and the (time) position of each sub-interval of the corresponding preset time interval can also be different.

[0168] The sampling points in the plurality of sub-intervals can be traversed to determine whether there is a target sampling point in each sub-interval that satisfies the preset condition corresponding to the sub-interval. In the embodiments of the present application, the preset conditions corresponding to different sub-intervals can be different.​

[0169] In an example case, the preset condition can be that the root mean square voltage of each sampling point between the target sampling point and the reference sampling point is in a continuous decreasing trend, and the amplitude drop relative value between the target sampling point and the reference sampling point reaches a fourth preset threshold and the voltage drop degree between the target sampling point and the reference sampling point reaches a fifth preset threshold (a third preset condition). In another example case, the preset condition can be that the root mean square voltage of each sampling point between the target sampling point and the reference sampling point is in a continuous decreasing trend, and the amplitude drop relative value between the target sampling point and the reference sampling point reaches the fourth preset threshold or the voltage drop degree between the target sampling point and the reference sampling point reaches the fifth preset threshold (a fourth preset condition).

[0170] In the embodiments of the present application, the preset conditions corresponding to different sub-intervals can be different. Specifically, the fourth preset threshold and the fifth preset threshold corresponding to different sub-intervals can be different. The farther the sub-interval is from the reference sampling point in time, the greater the fourth preset threshold and the fifth preset threshold are.

[0171] For example, if the preset condition includes that the amplitude drop relative value between the target sampling point and the reference sampling point reaches the fourth preset threshold and the voltage drop degree between the target sampling point and the reference sampling point reaches the fifth preset threshold (the third preset condition), the value range of the fourth preset threshold can be 30% to 40% for the first sub-interval. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the fifth preset threshold can be 2 uV to 3 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the fifth preset threshold can be 30% to 40%. For the second sub-interval, the value range of the fourth preset threshold can be 40% to 50%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the fifth preset threshold can be 3 uV to 4 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the fifth preset threshold can be 40% to 50%. For the third sub-interval, the value range of the fourth preset threshold can be 50% to 60%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the fifth preset threshold can be 4 uV to 5 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the fifth preset threshold can be 50% to 60%.

[0172] If the preset condition includes that the amplitude drop relative value between the target sampling point and the reference sampling point reaches a fourth preset threshold value and the voltage drop degree between the target sampling point and the reference sampling point reaches a fifth preset threshold value (the third preset condition), for the first sub-interval, the value range of the fourth preset threshold value can be 40% to 50%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the fifth preset threshold value can be 3 uV to 4 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the fifth preset threshold value can be 40% to 50%. For the second sub-interval, the value range of the fourth preset threshold value can be 50% to 60%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the fifth preset threshold value can be 4 uV to 5 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the fifth preset threshold value can be 50% to 60%. For the third sub-interval, the value range of the fourth preset threshold value can be 60% to 70%. In this case, if the voltage drop degree is the voltage drop absolute value, the value range of the fifth preset threshold value can be 5 uV to 6 uV. If the voltage drop degree is the ratio of the voltage drop absolute value to the maximum voltage value, the value range of the fifth preset threshold value can be 60% to 70%.

[0173] During the traversal, if there is a target sampling point satisfying the corresponding preset condition in any one of the plurality of sub-intervals, it can be determined that there is a possibility of myocardial bridge. The traversal manner can include sequentially traversing the to-be-traversed sampling points in the reverse order of time sequence, or performing parallel traversal for the plurality of sub-intervals. For the case where the at least one reference sampling point includes a plurality of reference sampling points, if no target reference point satisfying the preset condition is found after completing the traversal for a certain reference sampling point, the traversal operation is switched to the next reference sampling point to be re-performed. If no target reference point satisfying the preset condition is found after the traversal is performed for all the reference sampling points, it can be determined that the candidate first high-frequency QRS complex data does not have the waveform feature indicating myocardial bridge.

[0174] All candidate first high-frequency QRS complex data can be processed as above, and if at least one candidate first high-frequency QRS complex data has a waveform feature indicating myocardial bridge, such as a slow descent wave, it can be determined that there is a possibility of myocardial bridge. Conversely, if all candidate first high-frequency QRS complex data do not have the waveform feature indicating myocardial bridge, it can be determined that there is no myocardial bridge.

[0175] The determination method of the root mean square voltage of each sampling point between the target sampling point and the reference sampling point in the preset condition in this embodiment can be the same as that in the previous embodiments, which will not be described here.

[0176] In embodiments of the present application, a processor is configured to perform the method described in the above embodiments.

[0177] In embodiments of the present application, a machine readable storage medium is provided, and the machine readable storage medium has stored instructions for causing a machine to perform the method described in the above embodiments.

[0178] In embodiments of the present application, a processing device is provided, and the processing device includes a processor and a memory, and the memory has stored instructions, and the processor is configured to call and execute the instructions from the memory to implement the method described in the above embodiments.

[0179] Examples of the processor can include, but are not limited to, a single-chip microcomputer, a microprocessor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc.

[0180] The memory can include a non-persistent memory in a computer readable medium, a random access memory (RAM) and / or a non-volatile memory such as a read-only memory (ROM) or a flash memory, and the memory includes at least one memory chip.

[0181] Figure 11 An example block diagram of a coronary microcirculation disorder prediction system according to embodiments of the present application is schematically shown. As shown, in embodiments of the present application, a coronary microcirculation disorder prediction system can include: Figure 11

[0182] An electrocardiosignal acquisition device 100 including at least one electrode forming at least one electrocardiogram lead for acquiring electrocardiosignals of a subject; and

[0183] The processing device 200 described above.

[0184] The electrocardiosignal acquisition device 100 can further include a display configured to display various data and information including, but not limited to, for example, subject information such as age, height, weight, etc., and electrocardiosignal / QRS complex data / QRS waveform curve, etc. acquired through the electrocardiogram lead.

[0185] The processing device 200 can be configured to perform the various methods described in the above embodiments.

[0186] Specifically, in an embodiment, a method performed by a computer for assessing a heart health status of a subject can include:

[0187] ​acquire an exercise electrocardiogram signal of a subject collected through at least one electrocardiogram lead during a load exercise electrocardiogram detection process, and a resting electrocardiogram signal of the subject collected through at least one electrocardiogram lead during a resting electrocardiogram detection process;

[0188] analyze the exercise electrocardiogram signal to obtain exercise electrocardiogram data, and analyze the resting electrocardiogram signal to obtain resting electrocardiogram data and conventional electrocardiogram data;

[0189] obtain first high-frequency QRS complex data according to the exercise electrocardiogram data, and obtain second high-frequency QRS complex data according to the resting electrocardiogram data.

[0190] In an embodiment, a first lead positive indicator corresponding to each electrocardiogram lead is obtained according to the first high-frequency QRS complex data obtained from the exercise electrocardiogram data;

[0191] In an embodiment, a second lead positive indicator corresponding to each electrocardiogram lead is obtained according to the second high-frequency QRS complex data obtained from the resting electrocardiogram data;

[0192] In an embodiment, a third lead positive indicator corresponding to each electrocardiogram lead is obtained according to the conventional electrocardiogram data;

[0193] In an embodiment, the coronary microcirculation disorder prediction method comprises:

[0194] determine whether there is target first high-frequency QRS complex data in the first high-frequency QRS complex data indicated by the first lead positive indicator as positive, the target first high-frequency QRS complex data being free of the first waveform feature and the second waveform feature;

[0195] In a case where it is determined that there is target first high-frequency QRS complex data, determine the possibility of existence of coronary microcirculation disorder.

[0196] In an embodiment, in a case where it is determined that there is target first high-frequency QRS complex data, the possibility of existence of coronary microcirculation disorder is determined, comprising:

[0197] determine a target electrocardiogram lead corresponding to the target first high-frequency QRS complex data;

[0198] determine whether the second lead positive indicator corresponding to the target electrocardiogram lead indicates positive;

[0199] In a case where the second lead positive indicator corresponding to the target electrocardiogram lead indicates positive, determine the possibility of existence of coronary microcirculation disorder.

[0200] In an embodiment, the coronary microcirculation disorder prediction method further comprises:

[0201] determining a first maximum root mean square voltage in first high frequency QRS complex data corresponding to any electrocardiogram lead and a second maximum voltage in second high frequency QRS complex data corresponding to the electrocardiogram lead;

[0202] determining a number of electrocardiogram leads corresponding to which the second lead positive indicator indicates positive;

[0203] in a case where the number is less than a preset value and at least the first maximum root mean square voltage is greater than a first voltage threshold, determining that there is no coronary microcirculation disorder.

[0204] In an embodiment, determining the possibility of existence of coronary artery lesion according to the exercise electrocardiogram data comprises:

[0205] obtaining a first point sequence corresponding to each electrocardiogram lead from first high frequency QRS complex data corresponding to each electrocardiogram lead obtained from the exercise electrocardiogram data, the first point sequence comprising a plurality of sampling points arranged in time sequence;

[0206] for the first point sequence corresponding to any electrocardiogram lead, in a traversal loop, taking any sampling point in the plurality of sampling points in the first point sequence as a current reference sampling point, traversing sampling points in a first preset time interval from the current reference sampling point to determine whether there are first and second sampling points satisfying a preset condition in the first preset time interval, wherein the first sampling point is earlier than the second sampling point in time sequence, and the sampling points in the first preset time interval include the current reference sampling point;

[0207] in a case where it is determined that there are first and second sampling points satisfying the preset condition, determining that the first high frequency QRS complex data corresponding to the any electrocardiogram lead has a first waveform feature indicating coronary artery lesion, thereby determining the possibility of existence of coronary artery lesion;

[0208] in a case where it is determined that there are no first and second sampling points satisfying the preset condition, ending the current traversal loop, and determining other sampling points in the first point sequence except the current reference sampling point as new reference sampling points;

[0209] performing the next traversal loop for the new reference sampling points, repeating the traversal loop until it is determined that there are first and second sampling points satisfying the preset condition, or all sampling points in the first point sequence that need to be traversed have been traversed.

[0210] In an embodiment, determining the possibility of existence of coronary artery lesion according to the exercise electrocardiogram data further comprises:

[0211] In a case where no first sampling point and second sampling point satisfying the preset condition are found after all sampling points in the first point sequence are traversed, it is determined that the first high-frequency QRS complex data corresponding to the first point sequence does not have the first waveform feature indicative of the coronary artery lesion.

[0212] In a case where no first high-frequency QRS complex data corresponding to any electrocardiogram lead has the first waveform feature indicative of the coronary artery lesion, it is determined that there is no possibility of the coronary artery lesion.

[0213] In an embodiment, the preset condition includes:

[0214] a relative amplitude drop value between the first sampling point and the second sampling point reaches a first preset threshold value and a voltage drop degree between the first sampling point and the second sampling point reaches a second preset threshold value; or

[0215] a relative amplitude drop value between the first sampling point and the second sampling point reaches the first preset threshold value or a voltage drop degree between the first sampling point and the second sampling point reaches the second preset threshold value.

[0216] In an embodiment, the first preset time interval includes a preset time length. For the first point sequence corresponding to any electrocardiogram lead, in a traversal loop, any sampling point in the first point sequence is taken as a current reference sampling point, and sampling points in the first preset time interval from the current reference sampling point are traversed to determine whether there is a first sampling point and a second sampling point satisfying the preset condition in the first preset time interval, including:

[0217] the first sampling point in the first point sequence is taken as the current reference sampling point, and a sampling point next to the current reference sampling point in time sequence is traversed to determine whether the current traversal sampling point and the current reference sampling point satisfy the preset condition;

[0218] In a case where the current traversal sampling point and the current reference sampling point do not satisfy the preset condition, it is determined whether a time interval between the current traversal sampling point and the current reference sampling point exceeds the preset time length;

[0219] In a case where it is determined that the time interval between the current traversal sampling point and the current reference sampling point exceeds the preset time length, it is determined that the traversal loop ends.

[0220] In an embodiment, in a case where it is determined that there is a first sampling point and a second sampling point satisfying the preset condition, it is determined that the first high-frequency QRS complex data corresponding to the arbitrary electrocardiogram lead has the first waveform feature indicative of the coronary artery lesion, thereby determining that there is a possibility of the coronary artery lesion, including:

[0221] In a case where it is determined that the current traversing sampling point and the current reference sampling point satisfying the preset condition exist during the traversing loop, it is determined that the first high-frequency QRS complex data corresponding to the arbitrary electrocardiogram lead has the first waveform feature indicating the coronary artery lesion, so that it is determined that the coronary artery lesion possibility exists.

[0222] In an embodiment, after the current traversing loop ends, other sampling points in the first point sequence except the current reference sampling point are determined as new reference sampling points, including:

[0223] The next sampling point of the current reference sampling point in time sequence is determined as the new reference sampling point.

[0224] In an embodiment, the next traversing loop is performed for the new reference sampling point, and the traversing loop is repeated until it is determined that the first sampling point and the second sampling point satisfying the preset condition exist, or all the sampling points to be traversed in the first point sequence are traversed, including:

[0225] The next traversing loop is started from the next sampling point of the new reference sampling point in time sequence, and the traversing loop is repeated until it is determined that the current traversing sampling point and the current reference sampling point satisfying the preset condition exist, or the current traversing sampling point is the last sampling point in the first point sequence.

[0226] In an embodiment, the first preset time interval includes a window length of a window function. For the first point sequence corresponding to the arbitrary electrocardiogram lead, in a traversing loop, any sampling point of the plurality of sampling points in the first point sequence is taken as a current reference sampling point, and the sampling points in the first preset time interval from the current reference sampling point are traversed to determine whether the first sampling point and the second sampling point satisfying the preset condition exist in the first preset time interval, including:

[0227] The first sampling point with the maximum root mean square (RMS) voltage and the second sampling point with the minimum RMS voltage located after the first sampling point in time sequence in the current window are determined by taking the first sampling point in the first point sequence in time sequence as a starting point of the window and traversing the sampling points in the first point sequence contained in the window.

[0228] It is determined whether the first sampling point and the second sampling point satisfy the preset condition.

[0229] In an embodiment, in a case where it is determined that the first sampling point and the second sampling point satisfying the preset condition exist, it is determined that the first high-frequency QRS complex data corresponding to the arbitrary electrocardiogram lead has the first waveform feature indicating the coronary artery lesion, so that it is determined that the coronary artery lesion possibility exists, including:

[0230] In a case where it is determined that the first sampling point and the second sampling point in the current window satisfy the preset condition, it is determined that the first high-frequency QRS complex data corresponding to the arbitrary electrocardiogram lead has a first waveform feature indicating the coronary artery lesion, so that it is determined that there is a possibility of the coronary artery lesion.

[0231] In an embodiment, in a case where it is determined that there is no first sampling point and second sampling point satisfying the preset condition, the current traversal loop ends, and other sampling points in the first point sequence except the current reference sampling point are determined as new reference sampling points, including:

[0232] In a case where it is determined that there is no first sampling point and second sampling point satisfying the preset condition in the current window, the current traversal loop ends, and the window is moved backward by a preset step in time sequence.

[0233] In an embodiment, a next traversal loop is performed for the new reference sampling point, and the traversal loop is repeated until it is determined that there is a first sampling point and a second sampling point satisfying the preset condition, or all sampling points to be traversed in the first point sequence are traversed, including:

[0234] A next traversal loop is performed on the sampling points in the window moved by the preset step, and the traversal loop is repeated until it is determined that there is a first sampling point and a second sampling point satisfying the preset condition, or the end point of the current window reaches at least the last sampling point in the first point sequence.

[0235] In an embodiment, the first preset time interval includes a window length of a window function. For the first point sequence corresponding to the arbitrary electrocardiogram lead, in a traversal loop, any sampling point in the plurality of sampling points in the first point sequence is taken as a current reference sampling point, and the sampling points in the first preset time interval from the current reference sampling point are traversed to determine whether there is a first sampling point and a second sampling point satisfying the preset condition in the first preset time interval, including:

[0236] The first sampling point in the first point sequence that is earliest in time sequence is taken as a starting point of the window, and the sampling points in the first point sequence included in the window are traversed to determine whether there is a first sampling point and a second sampling point satisfying the preset condition in the current window;

[0237] In an embodiment, in a case where it is determined that there is a first sampling point and a second sampling point satisfying the preset condition, it is determined that the first high-frequency QRS complex data corresponding to the arbitrary electrocardiogram lead has a first waveform feature indicating the coronary artery lesion, so that it is determined that there is a possibility of the coronary artery lesion, including:

[0238] In a case where it is determined that the first sampling point and the second sampling point in the current window satisfy the preset condition, it is determined that the first high-frequency QRS complex data corresponding to the arbitrary electrocardiogram lead has a first waveform feature indicating the coronary artery lesion, so that it is determined that there is a possibility of the coronary artery lesion.

[0239] In an embodiment, in a case where it is determined that there is no first sampling point and second sampling point satisfying the preset condition, the current traversal loop ends, and other sampling points in the first point sequence except the current reference sampling point are determined as new reference sampling points, including:

[0240] In a case where it is determined that there is no first sampling point and second sampling point satisfying the preset condition in the current window, the current traversal loop ends, and the window is moved backward by a preset step in time sequence.

[0241] In an embodiment, a next traversal loop is performed for the new reference sampling point, and the traversal loop is repeated until it is determined that there is a first sampling point and a second sampling point satisfying the preset condition, or all sampling points to be traversed in the first point sequence are traversed, including:

[0242] A next traversal loop is performed on the sampling points in the window moved by the preset step, and the traversal loop is repeated until it is determined that there is a first sampling point and a second sampling point satisfying the preset condition, or the end point of the current window reaches at least the last sampling point in the first point sequence.

[0243] In an embodiment, determining the possibility of the coronary artery lesion according to the motion electrocardiogram data further includes:

[0244] In a case where it is determined that the first sampling point and the second sampling point satisfy the preset condition, a first-order difference of mean square error voltages of the sampling points between the first sampling point and the second sampling point in the first point sequence is determined to determine a minimum value sampling point corresponding to a minimum value and at least one maximum value sampling point corresponding to a maximum value;

[0245] A first root mean square voltage difference value between the maximum value sampling point and the minimum value sampling point is calculated;

[0246] A second root mean square voltage difference value between the first sampling point and the second sampling point is calculated;

[0247] In a case where a ratio of the first root mean square voltage difference value to the second root mean square voltage difference value is greater than or equal to a third threshold value, the first sampling point and the second sampling point are re-determined as not satisfying the preset condition.

[0248] In an embodiment, determining the possibility of the coronary artery lesion according to the motion electrocardiogram data further includes:

[0249] a first lead positive indicator corresponding to the first high-frequency QRS complex data of the first waveform feature indicating existence of a coronary artery lesion;

[0250] in a case where the first lead positive indicator indicates positive or critical, determining that the type of the coronary artery lesion is coronary stenosis;

[0251] in a case where the first lead positive indicator indicates negative, determining that the type of the coronary artery lesion is coronary sclerosis.

[0252] In an embodiment, determining the possibility of existence of the myocardial bridge according to the exercise electrocardiogram data comprises:

[0253] determining candidate first high-frequency QRS complex data from the first high-frequency QRS complex data corresponding to each electrocardiogram lead, the candidate first high-frequency QRS complex data being free of the first waveform feature indicating existence of a coronary artery lesion;

[0254] obtaining a second point sequence corresponding to the candidate first high-frequency QRS complex data, the second point sequence comprising a plurality of sampling points arranged in time sequence;

[0255] for the second point sequence corresponding to any candidate first high-frequency QRS complex data, in an iteration loop, taking any sampling point in the plurality of sampling points in the second point sequence as a current reference sampling point, and traversing sampling points within a second preset time interval from the current reference sampling point to determine whether there are third and fourth sampling points satisfying another preset condition within the second preset time interval, wherein the third sampling point is earlier in time sequence than the fourth sampling point;

[0256] in a case where it is determined that there are third and fourth sampling points satisfying another preset condition, determining that the any candidate first high-frequency QRS complex data has a second waveform feature indicating existence of a myocardial bridge, thereby determining the possibility of existence of the myocardial bridge;

[0257] in a case where it is determined that there are no third and fourth sampling points satisfying another preset condition, ending the current iteration loop, and determining other sampling points in the second point sequence except the current reference sampling point as new reference sampling points;

[0258] performing the next iteration loop for the new reference sampling points, repeating the iteration loop until it is determined that there are third and fourth sampling points satisfying another preset condition, or all sampling points in the second point sequence that need to be traversed have been traversed.

[0259] In an embodiment, the second preset time interval includes a preset time length. For the second point sequence corresponding to any candidate first high-frequency QRS complex data, in an iteration loop, any sampling point in the second point sequence is taken as a current reference sampling point, and sampling points within the second preset time interval from the current reference sampling point are iterated to determine whether there are third and fourth sampling points satisfying another preset condition within the second preset time interval, including:

[0260] The first sampling point in the second point sequence in time sequence is taken as the current reference sampling point, and the next sampling point in time sequence from the current reference sampling point is iterated to determine whether the current iteration sampling point and the current reference sampling point satisfy another preset condition.

[0261] In the case where the current iteration sampling point and the current reference sampling point do not satisfy another preset condition, it is determined whether the time interval between the current iteration sampling point and the current reference sampling point exceeds a preset time length.

[0262] In the case where it is determined that the time interval between the current iteration sampling point and the current reference sampling point exceeds the preset time length, it is determined that the iteration loop ends.

[0263] In an embodiment, in the case where it is determined that there are third and fourth sampling points satisfying another preset condition, it is determined that the arbitrary candidate first high-frequency QRS complex data has a second waveform feature indicating a myocardial bridge, thereby determining the possibility of a myocardial bridge, including:

[0264] In the case where it is determined during the iteration loop that there are current iteration sampling points and current reference sampling points satisfying a preset condition, it is determined that the arbitrary candidate first high-frequency QRS complex data has a second waveform feature indicating a myocardial bridge, thereby determining the possibility of a myocardial bridge.

[0265] In an embodiment, after the current iteration loop ends, other sampling points in the second point sequence except the current reference sampling point are determined as new reference sampling points, including:

[0266] The next sampling point in time sequence from the current reference sampling point is determined as the new reference sampling point.

[0267] In an embodiment, the next iteration loop is performed for the new reference sampling point, and the iteration loop is repeated until it is determined that there are third and fourth sampling points satisfying another preset condition, or all sampling points in the second point sequence that need to be iterated are iterated, including:

[0268] The next traversal loop is repeated from a next sampling point in time sequence of the new reference sampling point until it is determined that there exist the current traversal sampling point and the current reference sampling point satisfying the preset condition, or the current traversal sampling point is the last sampling point in the second point sequence.

[0269] In an embodiment, the second preset time interval includes a window length of a window function. For the second point sequence corresponding to any candidate first high-frequency QRS complex data, in a traversal loop, any sampling point in the second point sequence is taken as a current reference sampling point, and sampling points within the second preset time interval from the current reference sampling point are traversed to determine whether there exist a third sampling point and a fourth sampling point satisfying another preset condition within the second preset time interval, wherein the third sampling point is earlier in time sequence than the fourth sampling point, including:

[0270] The first sampling point in time sequence in the second point sequence is taken as a starting point of a window, and sampling points in the second point sequence contained in the window are traversed to determine a third sampling point with maximum root mean square (RMS) voltage and a fourth sampling point with minimum RMS voltage after the third sampling point in time sequence in the current window;

[0271] It is determined whether the third sampling point and the fourth sampling point satisfy another preset condition.

[0272] In an embodiment, in a case where it is determined that there exist the third sampling point and the fourth sampling point satisfying another preset condition, it is determined that the second waveform feature indicating the myocardial bridge exists in the arbitrary candidate first high-frequency QRS complex data, and thus it is determined that the myocardial bridge possibility exists, including:

[0273] In a case where it is determined that the third sampling point and the fourth sampling point in the current window satisfy another preset condition, it is determined that the second waveform feature indicating the myocardial bridge exists in the arbitrary candidate first high-frequency QRS complex data, and thus it is determined that the myocardial bridge possibility exists.

[0274] In an embodiment, in a case where it is determined that there do not exist the third sampling point and the fourth sampling point satisfying another preset condition, the current traversal loop ends, and other sampling points except the current reference sampling point in the second point sequence are determined as new reference sampling points, including:

[0275] In a case where it is determined that there do not exist the third sampling point and the fourth sampling point satisfying another preset condition in the current window, the current traversal loop ends, and the window is moved backward by a preset step in time sequence.

[0276] In an embodiment, the new reference sampling point performs a next traversal loop, and the traversal loop is repeated until it is determined that there exist the third sampling point and the fourth sampling point satisfying another preset condition, or all sampling points to be traversed in the second point sequence are traversed, including:

[0277] The next iteration cycle is performed on the sampling points in the window after the preset step size is moved, and the iteration cycle is repeated until it is determined that there are third sampling points and fourth sampling points that meet another preset condition, or the end point of the current window reaches at least the last sampling point in the second point sequence.

[0278] In an embodiment, the second preset time interval includes a window length of a window function. For a second point sequence corresponding to any candidate first high-frequency QRS complex data, in an iteration cycle, any sampling point in the plurality of sampling points in the second point sequence is taken as a current reference sampling point, and the sampling points in the second preset time interval from the current reference sampling point are iterated to determine whether there are third sampling points and fourth sampling points that meet another preset condition in the second preset time interval, including:

[0279] The first sampling point in the second point sequence that is the earliest in time sequence is taken as the start point of the window, and the sampling points in the second point sequence contained in the window are iterated to determine whether there are third sampling points and fourth sampling points that meet another preset condition in the current window.

[0280] In an embodiment, in a case where it is determined that there are third sampling points and fourth sampling points that meet another preset condition, it is determined that the second waveform feature indicating a myocardial bridge exists in the arbitrary candidate first high-frequency QRS complex data, thereby determining the possibility of the myocardial bridge, including:

[0281] In a case where it is determined that the third sampling points and the fourth sampling points in the current window meet another preset condition, it is determined that the second waveform feature indicating a myocardial bridge exists in the arbitrary candidate first high-frequency QRS complex data, thereby determining the possibility of the myocardial bridge.

[0282] In an embodiment, in a case where it is determined that there are no third sampling points and fourth sampling points that meet another preset condition, the current iteration cycle ends, and other sampling points in the second point sequence except the current reference sampling point are determined as new reference sampling points, including:

[0283] In a case where it is determined that there are no third sampling points and fourth sampling points that meet another preset condition in the current window, the current iteration cycle ends, and the window is moved backward by a preset step size in time sequence.

[0284] In an embodiment, the next iteration cycle is performed for the new reference sampling point, and the iteration cycle is repeated until it is determined that there are third sampling points and fourth sampling points that meet another preset condition, or all the sampling points that need to be iterated in the second point sequence are iterated, including:

[0285] The next traversal loop is performed on the sampling points in the window after the preset step size is moved, and the traversal loop is repeated until it is determined that there are third sampling points and fourth sampling points that satisfy another preset condition, or the end point of the current window reaches at least the last sampling point in the second point sequence.

[0286] In an embodiment, determining the possibility of the myocardial bridge according to the motion electrocardiogram data further comprises:

[0287] In a case where no third sampling point and fourth sampling point that satisfy another preset condition are found after all the sampling points in the second point sequence are traversed, it is determined that the corresponding candidate first high-frequency QRS complex data does not have the second waveform feature indicating the myocardial bridge.

[0288] In a case where all the candidate first high-frequency QRS complex data do not have the second waveform feature indicating the myocardial bridge, it is determined that there is no myocardial bridge.

[0289] In the embodiments of the present application, the another preset condition comprises:

[0290] The amplitude drop relative value between the third sampling point and the fourth sampling point reaches a fourth preset threshold, and the voltage drop degree between the third sampling point and the fourth sampling point reaches a fifth preset threshold, and the root mean square voltage of each sampling point between the third sampling point and the fourth sampling point shows a continuous downward trend; or

[0291] The amplitude drop relative value between the third sampling point and the fourth sampling point reaches a fourth preset threshold, or the voltage drop degree between the third sampling point and the fourth sampling point reaches a fifth preset threshold, and the root mean square voltage of each sampling point between the third sampling point and the fourth sampling point shows a continuous downward trend.

[0292] In an embodiment, the length of the second preset time interval is greater than the length of the first preset time interval.

[0293] In an embodiment, the fourth preset threshold is greater than the first preset threshold, and the fifth preset threshold is greater than the second preset threshold.

[0294] In an embodiment, in a case where it is determined that the amplitude drop relative value between the third sampling point and the fourth sampling point reaches the fourth preset threshold and / or the voltage drop degree between the third sampling point and the fourth sampling point reaches the fifth preset threshold, a first-order difference of the root mean square voltage of the sampling points in the second point sequence corresponding to the candidate first high-frequency QRS complex data in the current second preset time interval is calculated to obtain a difference sequence.

[0295] The number of consecutive values greater than or equal to zero in the difference sequence is determined.

[0296] If the number is less than or equal to a first number threshold, it is determined that the root mean square voltage of each sampling point between the third sampling point and the fourth sampling point is in a sustained downward trend.

[0297] In an embodiment, all difference sequence groups are determined according to the difference sequence, each difference sequence group including a number of consecutive difference values;

[0298] The sum of the difference values of each difference sequence group is calculated.

[0299] If the number of consecutive values greater than or equal to zero in the difference sequence is less than or equal to a second number threshold, and the sum of the difference values of each difference sequence group is greater than or equal to a predetermined value, it is determined that the candidate first high-frequency QRS complex data has a waveform feature indicative of a myocardial bridge.

[0300] In an embodiment, determining the likelihood of the presence of a myocardial bridge according to the exercise electrocardiogram data includes:

[0301] Determining candidate first high-frequency QRS complex data from the corresponding first high-frequency QRS complex data of each electrocardiogram lead, the candidate first high-frequency QRS complex data not having a first waveform feature indicative of a coronary artery lesion;

[0302] Obtaining a corresponding second point sequence from the candidate first high-frequency QRS complex data, the second point sequence including a plurality of sampling points arranged in time sequence;

[0303] Determining, from the second point sequence corresponding to any candidate first high-frequency QRS complex data, at least one sampling point within a preset time period in the second point sequence as a reference sampling point;

[0304] Determining, according to the determined reference sampling point, a to-be-traversed sampling point in the second point sequence, wherein the to-be-traversed sampling point is a sampling point within a third preset time interval before the reference sampling point;

[0305] Traversing the to-be-traversed sampling point to determine whether a target sampling point exists, wherein the target sampling point and the reference sampling point satisfy another preset condition;

[0306] In a case where it is determined that the target sampling point exists, it is determined that the candidate first high-frequency QRS complex data has a second waveform feature indicative of a myocardial bridge, thereby determining the likelihood of the presence of a myocardial bridge.

[0307] In an embodiment, the preset time period is a time period from the time when the exercise ends to a time after the exercise ends.

[0308] In an embodiment, the third preset time interval is within the exercise phase of the load exercise electrocardiogram detection process.

[0309] In an embodiment, the third preset time interval includes a plurality of continuous sub-intervals, and different sub-intervals correspond to different preset conditions.

[0310] The technical scheme provided by the embodiments of the present application, through the waveform characteristics of the first high-frequency QRS complex data (or the high-frequency QRS time intensity curve / high-frequency QRS waveform curve corresponding to the first high-frequency QRS complex data) obtained from the motion electrocardiogram data, excludes the pathological waveform interference of typical coronary artery lesions (such as coronary stenosis or coronary sclerosis) and myocardial bridge, and directly focuses on the specific myocardial electrical activity change that may be caused by coronary microcirculation disorder, which makes up for the defect of the insufficient sensitivity of the traditional non-invasive method (such as the conventional electrocardiogram) to the coronary microcirculation disorder, avoids the risk and inconvenience of the invasive examination (such as the IMR), and realizes the non-invasive, rapid and specific identification of the coronary microcirculation disorder. Further, on the basis of the foregoing, the positive verification of the lead positive index determined by the second high-frequency QRS complex data in the resting state is superimposed, and the double evidence is formed relying on the characteristic indexes of myocardial ischemia and myocardial cell activity in the resting state, so as to further improve the accuracy and diagnostic reliability of the coronary microcirculation disorder. In addition, the comprehensive screening logic is formed by combining the quantitative index of the heart-lung function and the degree index of myocardial ischemia / cell activity, so as to accurately exclude the coronary microcirculation disorder non-invasively and rapidly, effectively reduce the misjudgment of the light symptom / non-microcirculation disorder population, and greatly improve the overall efficiency of the coronary microcirculation disorder screening.

[0311] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0312] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0313] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart or flowsheets and / or block or blocks of the block diagrams.

[0314] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheets and / or block or blocks of the block diagrams.

[0315] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0316] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), flash memory, or other memory technologies, about which the processor can execute instructions. The memory is an example of computer readable media.

[0317] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to computing devices. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0318] It should also be noted that the terms "comprising", "comprises" or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0319] The above embodiments are only used to illustrate the present application, but not to limit it. Instead of the above, various modifications and changes can be made to the application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall fall into the scope of the claims of the application.

Claims

1. A device for predicting coronary microcirculation disorders, characterized in that, Configured to implement a method for predicting coronary microcirculation obstruction, the method comprising: Acquire both exercise ECG data and resting ECG data output from at least one ECG lead; The first high-frequency QRS complex data is obtained from the exercise ECG data, and the second high-frequency QRS complex data is obtained from the resting ECG data. The positive index of the first lead corresponding to each electrocardiogram lead is obtained based on the first high-frequency QRS complex data, and the positive index of the second lead corresponding to each electrocardiogram lead is obtained based on the second high-frequency QRS complex data. Determine whether there is a target first high-frequency QRS complex data in the first high-frequency QRS complex data corresponding to the positive indicator in the first lead, and whether the target first high-frequency QRS complex data does not have the first waveform characteristics indicating coronary artery lesions and the second waveform characteristics indicating myocardial bridging; Given the existence of the target first high-frequency QRS complex data, the possibility of coronary microcirculatory disturbance is determined. Determining whether the first high-frequency QRS group data contains a second waveform feature includes: Candidate first high-frequency QRS complex data are determined from the first high-frequency QRS complex data corresponding to each electrocardiogram lead. The candidate first high-frequency QRS complex data does not have the first waveform feature. The corresponding second point sequence is obtained based on the candidate first high-frequency QRS group data. The second point sequence includes multiple sampling points arranged in time sequence. For any candidate first high-frequency QRS group data corresponding to the second point sequence, in one traversal loop, any one of the multiple sampling points in the second point sequence is taken as the current reference sampling point, and the sampling points in the second preset time interval starting from the current reference sampling point are traversed to determine whether there are a third sampling point and a fourth sampling point that satisfy another preset condition in the second preset time interval, wherein the third sampling point is earlier than the fourth sampling point in time. If it is determined that there are third and fourth sampling points that satisfy another preset condition, it is determined that the arbitrary candidate first high-frequency QRS group data has a second waveform feature; If it is determined that there are no third or fourth sampling points that satisfy another preset condition, the current traversal loop ends, and other sampling points in the second point sequence other than the current reference sampling point are determined as new reference sampling points; For the new reference sampling point, perform the next traversal loop, repeat the traversal loop until it is determined that there are a third sampling point and a fourth sampling point that satisfy another preset condition, or all the sampling points that need to be traversed in the second point sequence have been traversed. If, after all the sampling points that need to be traversed in the second point sequence have been traversed, there are no third and fourth sampling points that meet another preset condition, it is determined that the corresponding candidate first high-frequency QRS group data does not have the second waveform feature.

2. The coronary microcirculation disorder prediction device according to claim 1, characterized in that, Given the existence of target first high-frequency QRS complex data, the possibility of coronary microcirculatory disturbance is determined, including: Determine the target electrocardiogram lead corresponding to the first high-frequency QRS complex data of the target; Determine whether the positive indicator in the second lead corresponding to the target electrocardiogram lead indicates a positive result; If the second lead corresponding to the target electrocardiogram lead shows a positive indicator, it confirms the possibility of coronary microcirculation disorder.

3. The coronary microcirculation disorder prediction device according to claim 1, characterized in that, The method for predicting coronary microcirculation disorders also includes: The first maximum root mean square voltage is determined based on the maximum value of the root mean square voltage in the first high-frequency QRS complex data corresponding to all ECG leads, and the second maximum voltage is determined based on the maximum value of the voltage in the second high-frequency QRS complex data corresponding to all ECG leads. Determine the number of ECG leads corresponding to a positive result indicated by the positive index in the second lead; If the quantity is less than a preset value and at least the first maximum root mean square voltage is greater than the first voltage threshold, it is determined that there is no coronary microcirculation disorder.

4. The coronary microcirculation disorder prediction device according to claim 1, characterized in that, Determining whether the first high-frequency QRS group data contains the first waveform feature includes: The first point sequence is obtained from any first high-frequency QRS group data of interest, and the first point sequence includes multiple sampling points arranged in time sequence; For the first point sequence, in one iteration, any one of the multiple sampling points in the first point sequence is taken as the current reference sampling point, and the sampling points within the first preset time interval starting from the current reference sampling point are traversed to determine whether there is a first sampling point and a second sampling point that meet the preset conditions within the first preset time interval, wherein the first sampling point is earlier than the second sampling point in time. If a first sampling point and a second sampling point that meet the preset conditions are determined, the first waveform feature of the first high-frequency QRS complex data of interest that indicates coronary artery lesions is determined. If it is determined that there is no first sampling point or second sampling point that meets the preset conditions, the current traversal loop ends, and other sampling points in the first point sequence other than the current reference sampling point are determined as new reference sampling points; For the new reference sampling point, perform the next traversal loop, repeat the traversal loop until it is determined that there is a first sampling point and a second sampling point that meet the preset conditions, or all the sampling points that need to be traversed in the first point sequence have been traversed.

5. The coronary microcirculation disorder prediction device according to claim 4, characterized in that, Determining whether the first high-frequency QRS group data contains the first waveform feature also includes: If, after all the sampling points that need to be traversed in the first point sequence have been traversed, there are no first sampling points or second sampling points that meet the preset conditions, it is determined that the first waveform feature of the first high-frequency QRS complex data of interest does not indicate coronary artery lesions.

6. The coronary microcirculation disorder prediction device according to claim 4, characterized in that, The preset conditions include: The relative decrease in amplitude between the first sampling point and the second sampling point reaches a first preset threshold, and the degree of voltage decrease between the first sampling point and the second sampling point reaches a second preset threshold; or The relative value of the amplitude decrease between the first sampling point and the second sampling point reaches the first preset threshold, or the degree of voltage decrease between the first sampling point and the second sampling point reaches the second preset threshold.

7. The coronary microcirculation disorder prediction device according to claim 1, characterized in that, The other preset condition includes: The relative decrease in amplitude between the third and fourth sampling points reaches the third preset threshold, and the degree of voltage decrease between the third and fourth sampling points reaches the fourth preset threshold, and the root mean square voltage of each sampling point between the third and fourth sampling points shows a continuous decreasing trend; or The relative value of the amplitude decrease between the third and fourth sampling points reaches the third preset threshold or the degree of voltage decrease between the third and fourth sampling points reaches the fourth preset threshold, and the root mean square voltage of each sampling point between the third and fourth sampling points shows a continuous downward trend.

8. A coronary microcirculation disorder prediction system, characterized in that, include: An electrocardiogram (ECG) signal acquisition device includes at least one electrode forming at least one ECG lead for acquiring the ECG signal of a subject. as well as The coronary microcirculation disorder prediction device according to any one of claims 1 to 7.

9. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the coronary microcirculation disorder prediction method according to any one of claims 1 to 7.

Images