Myocardial injury risk assessment method and device, computer equipment and storage medium

Abstract

The invention relates to a myocardial injury risk assessment method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring and analyzing a resting electrocardiosignal to obtain a high-frequency QRS envelope curve and a resting low-frequency electrocardiosignal; analyzing the high-frequency QRS envelope curve to obtain a resting high-frequency QRS feature including a resting positive lead number, a resting critical lead number, a first target lead number, a second target lead number, a third target lead number and a high-frequency form index; the first target lead number refers to a lead number of which the wave crest number is greater than or equal to a first number threshold; the second target lead number refers to the lead number with the wave crest number equal to the second number threshold value; the third target lead number refers to the number of leads of which the crest number is equal to a third number threshold; the resting low-frequency electrocardiosignals are analyzed to obtain resting low-frequency characteristics such as old myocardial infarction information; and analyzing the myocardial injury risk assessment feature set comprising the resting high-frequency QRS feature and the resting low-frequency feature to obtain a myocardial injury risk assessment score.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, computer equipment and storage medium for assessing the risk of myocardial injury. Background Art

[0002] Myocardial injury refers to the damage to myocardial cells caused by various reasons, including but not limited to bacterial and viral infections, imbalance of oxygen supply and demand, cardiac causes, systemic diseases, etc. Myocardial injury can have various effects on the body, and severe myocardial injury can also lead to heart failure, cardiogenic shock and other problems. Therefore, timely diagnosis and treatment are needed to improve the state of myocardial injury and avoid serious damage.

[0003] At present, in addition to evaluating myocardial injury based on relevant biomarkers (such as cardiac troponin), myocardial injury is usually evaluated based on changes in low-frequency components such as ST segment elevation and T wave inversion in the electrocardiogram. However, not all myocardial injuries are reflected in the low-frequency components of the electrocardiogram, thus resulting in a problem of low assessment accuracy. Summary of the invention

[0004] Based on this, it is necessary to provide a myocardial injury assessment method, device, computer equipment, storage medium and computer program product that can improve the accuracy of myocardial injury assessment in response to the above technical problems.

[0005] A method for assessing myocardial injury risk, comprising: Acquire resting ECG signals; Analyze the resting ECG signal to obtain a high-frequency QRS envelope curve and a resting low-frequency ECG signal; Performing feature analysis on the high-frequency QRS envelope curve to obtain a resting high-frequency QRS feature; the resting high-frequency QRS feature includes the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads and the high-frequency morphological index of each lead; the first target number of leads refers to the number of leads whose number of peaks is greater than or equal to a first number threshold; the second target number of leads refers to the number of leads whose number of peaks is equal to a second number threshold; the third target number of leads refers to the number of leads whose number of peaks is equal to a third number threshold; Performing feature analysis on the resting low-frequency electrocardiogram signal to obtain a resting low-frequency feature; the resting low-frequency feature includes old myocardial infarction information; The myocardial injury risk assessment feature set is evaluated and analyzed to obtain a myocardial injury risk assessment score; the myocardial injury risk assessment feature set includes the resting high-frequency QRS feature and the resting low-frequency feature.

[0006] In one embodiment, the resting high-frequency QRS feature also includes a fourth target lead number and a fifth target lead number; the fourth target lead number is the number of chest leads for which the lead positive indicator indicates a positive result; the fifth target lead number is the number of limb leads for which the lead positive indicator indicates a positive result.

[0007] In one embodiment, the myocardial injury risk assessment feature set further includes a target myocardial ischemia risk assessment score; the method further includes: Obtaining a historical myocardial ischemia risk assessment score and / or a current myocardial ischemia risk assessment score; the historical myocardial ischemia risk assessment score is obtained by analyzing historical test data within a first time period; the current myocardial ischemia risk assessment score is obtained by analyzing current test data within a second time period; the first time period is earlier than the second time period; A target myocardial ischemia risk assessment score is obtained according to the historical myocardial ischemia risk assessment score and / or the current myocardial ischemia risk assessment score.

[0008] In one embodiment, obtaining a current myocardial ischemia risk assessment score includes: Acquire the exercise electrocardiogram signal collected in the second time period; Analyzing the exercise electrocardiogram signal to obtain a high-frequency QRS envelope curve; Performing feature analysis on the high-frequency QRS waveform curve to obtain a motion high-frequency QRS feature; the motion high-frequency QRS feature includes the number of motion positive leads and the number of motion critical leads; The myocardial ischemia risk assessment feature set is evaluated and analyzed to obtain a current myocardial ischemia risk assessment score; the myocardial ischemia risk assessment feature set includes the motion high-frequency QRS feature.

[0009] In one embodiment, the myocardial ischemia risk assessment feature set further includes a motion low-frequency feature; the step of acquiring the motion low-frequency feature includes: Extracting a motion low-frequency electrocardiogram signal from the motion electrocardiogram signal; The motion low-frequency electrocardiogram signal is subjected to feature analysis to obtain motion low-frequency features; the motion low-frequency features include the degree of ST-T segment change and the duration of ST-T segment change of each lead.

[0010] In one embodiment, the myocardial injury risk assessment feature set also includes user basic information; the method further includes: Obtain user basic information; the user basic information includes at least one of chronic basic disease information, drinking information, and staying up late information.

[0011] In one embodiment, the step of evaluating and analyzing the myocardial injury risk assessment feature set to obtain a myocardial injury risk assessment score includes: Input each feature in the myocardial injury risk assessment feature set into the corresponding feature function to obtain the corresponding myocardial injury risk assessment sub-score, and sum each myocardial injury risk assessment sub-score to obtain the myocardial injury risk assessment score; The pre-configuration steps of the feature function corresponding to each feature in the myocardial injury risk assessment feature set include: Segmenting the value range corresponding to the feature to obtain one or more corresponding value ranges; Determine the characteristic sub-function corresponding to each numerical range according to the correlation between the characteristic and the risk of myocardial injury and the weight of the characteristic; According to each characteristic sub-function corresponding to the characteristic, a corresponding pre-configured characteristic function is obtained.

[0012] A myocardial injury risk assessment device, comprising: An acquisition module, used for acquiring a resting ECG signal; An analysis module, used for analyzing the resting ECG signal to obtain a high-frequency QRS envelope curve and a resting low-frequency ECG signal; The analysis module is further used to perform feature analysis on the high-frequency QRS envelope curve to obtain a resting high-frequency QRS feature; the resting high-frequency QRS feature includes the number of resting positive leads, the number of resting critical leads, the first target number of leads, the second target number of leads, the third target number of leads and the high-frequency morphological index of each lead; the first target number of leads refers to the number of leads whose number of peaks is greater than or equal to a first number threshold; the second target number of leads refers to the number of leads whose number of peaks is equal to a second number threshold; the third target number of leads refers to the number of leads whose number of peaks is equal to a third number threshold; The analysis module is further used to perform feature analysis on the resting low-frequency electrocardiogram signal to obtain resting low-frequency features; the resting low-frequency features include old myocardial infarction information; An evaluation module is used to evaluate and analyze a myocardial injury risk evaluation feature set to obtain a myocardial injury risk evaluation score; the myocardial injury risk evaluation feature set includes the resting high-frequency QRS feature and the resting low-frequency feature.

[0013] In one embodiment, a computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in each method embodiment when executing the computer program.

[0014] In one embodiment, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in each method embodiment are implemented.

[0015] In one embodiment, a computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method described in each method embodiment are implemented.

[0016] The above-mentioned myocardial injury assessment method, device, computer equipment, storage medium and computer program product obtain a high-frequency QRS envelope curve and a resting low-frequency ECG signal by acquiring and analyzing the resting ECG signal, and obtain resting high-frequency QRS features such as the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads and the high-frequency morphology index of each lead based on the high-frequency QRS envelope curve analysis, and obtain resting low-frequency features such as information on old myocardial infarction based on the resting low-frequency ECG signal analysis, so as to comprehensively assess the risk of myocardial injury by combining the resting high-frequency QRS features and the resting low-frequency features, and obtain a myocardial injury risk assessment score with higher accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a process of a method for assessing risk of myocardial injury in one embodiment; Figure 2 A schematic diagram of a process for assessing risk of myocardial injury in another embodiment; Figure 3 is a structural block diagram of a myocardial injury risk assessment device in one embodiment; Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0019] The myocardial injury assessment method provided in 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 between the terminal and the server, which is not specifically limited here. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, electrocardiogram monitoring devices, and portable wearable devices, and the server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0020] In one embodiment, Figure 1 As shown, a myocardial injury assessment method is provided. Taking application to a server as an example, the method includes the following steps: S102, obtaining a resting electrocardiogram signal.

[0021] The resting ECG signal is the ECG signal collected during the resting ECG test. The user is in a resting state during the resting ECG test.

[0022] In one embodiment, the user's resting ECG signal is collected by an ECG signal collection device during the resting ECG detection process. The ECG signal collection device can be independent of the terminal or server, and transmit data through Bluetooth, network, electrical connection, etc., or it can be built into the terminal or server as a component, so that the server and the terminal can obtain the resting ECG signal from the ECG signal collection device through data interaction / transmission, and the specific method is not specifically limited.

[0023] S104, analyzing the resting ECG signal to obtain a high-frequency QRS envelope curve and a resting low-frequency ECG signal.

[0024] The high-frequency QRS envelope curve reflects the shape of the high-frequency QRS complex (the high-frequency component of the QRS complex) in the resting ECG signal after averaging, and is specifically presented as a single high-frequency QRS complex envelope curve. The high-frequency QRS envelope curve is presented through a high-frequency QRS envelope diagram. In the high-frequency QRS envelope diagram, the horizontal axis is time, corresponding to the duration of the QRS complex, in ms (milliseconds), and the vertical axis is voltage, in uV (microvolts).

[0025] Specifically, the resting ECG signal includes high-frequency components and low-frequency components. The resting low-frequency ECG signal can be obtained by analyzing the low-frequency components in the resting ECG signal. The resting ECG signal includes multiple QRS wave groups that reflect the changes in the left and right ventricular depolarization potentials and time. The high-frequency QRS envelope curve is obtained by analyzing the high-frequency components of the QRS wave group in the resting ECG signal. It can be understood that the high-frequency components of the QRS wave group in the resting ECG signal can be analyzed with reference to the methods disclosed in the prior art to obtain the corresponding high-frequency QRS envelope curve. Similarly, the resting ECG signal can be analyzed in the manner disclosed in the prior art to obtain a resting low-frequency ECG signal. For example, the resting ECG signal can be low-pass filtered to obtain a resting low-frequency ECG signal, which will not be repeated here.

[0026] S106, performing feature analysis on the high-frequency QRS envelope curve to obtain resting high-frequency QRS features; the resting high-frequency QRS features include the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads and the high-frequency morphology index of each lead; the first target number of leads refers to the number of leads whose number of peaks is greater than or equal to a first number threshold; the second target number of leads refers to the number of leads whose number of peaks is equal to a second number threshold; the third target number of leads refers to the number of leads whose number of peaks is equal to a third number threshold.

[0027] The number of resting positive leads refers to the number of leads in which the positive index of the corresponding lead indicates positive, which can be used to characterize the vitality of myocardial cells. The fewer the number of resting positive leads, the stronger the characterization of myocardial cell vitality. The number of resting critical leads refers to the number of leads in which the positive index of the corresponding lead indicates critical, which can be used to assist in the assessment of myocardial cell vitality. The number of peaks refers to the total number of peaks on the high-frequency QRS envelope curve. The number of peaks is related to myocardial cell vitality. The more peaks there are, the less vitality of myocardial cells there is. The first quantity threshold, the second quantity threshold and the third quantity threshold can be flexibly set according to actual needs, such as 4, 3 and 2 respectively.

[0028] Specifically, the high-frequency QRS envelope curve corresponding to each lead is analyzed, and the total area of ​​each amplitude reduction region on the high-frequency QRS envelope curve is obtained as the first total area, and the total area below the high-frequency QRS envelope curve is taken as the second total area, and the ratio of the first total area to the second total area is taken as the high-frequency morphological index corresponding to the lead. According to the high-frequency morphological index of each lead, the positive index of the corresponding lead is determined, and the number of leads indicated as positive by the positive index of the lead is screened and counted to obtain the number of resting positive leads, and the number of leads indicated as critical by the positive index of the lead is screened and counted to obtain the number of resting critical leads. The high-frequency QRS envelope curve of each lead is subjected to characteristic analysis to obtain the corresponding number of peaks, and the number of peaks of each lead is subjected to statistical analysis based on each number threshold to obtain the first target number of leads, the second target number of leads, and the third target number of leads. It can be understood that the number of peaks on each high-frequency QRS envelope curve can be determined in a specific manner disclosed in the prior art, such as determining the number of maximum values ​​on the high-frequency QRS envelope curve as the number of peaks, which is not specifically limited here.

[0029] In one embodiment, if the high-frequency morphology index of the lead is greater than or equal to the first index threshold, the lead positive index corresponding to the lead is identified as positive. If the high-frequency morphology index of the lead is greater than or equal to the second index threshold and less than the first index threshold, the lead positive index corresponding to the lead is identified as critical. The first index threshold and the second index threshold can be flexibly set according to demand, such as 15% and 6% or 8% for the first index threshold. The first index threshold and the second index threshold can also be dynamically adjusted according to the age of the user, without specific limitation.

[0030] In one embodiment, if the user's age is greater than or equal to the preset age, the first index threshold is 8% and the second index threshold is 6%. If the user's age is less than the preset age, the first index threshold is 15% and the second index threshold is 8%. The preset age can be flexibly set, such as 50 years old, and is not specifically limited here.

[0031] S108, performing feature analysis on the resting low-frequency electrocardiogram signal to obtain resting low-frequency features; the resting low-frequency features include information on old myocardial infarction.

[0032] The information of old myocardial infarction is used to characterize whether there is old myocardial infarction. Specifically, referring to the method of evaluating old myocardial infarction based on ECG (electrocardiogram) in the prior art, the characteristic analysis of the resting low-frequency ECG signal is performed to obtain the old myocardial infarction information, which will not be repeated here. For example, analyze whether there is a pathological Q wave in the resting low-frequency ECG signal. If so, it is determined that there is a old myocardial infarction. For another example, analyze whether there is a pathological Q wave in the resting low-frequency ECG signal, and whether the ST segment and T wave are normal. If there is a pathological Q wave, and the ST segment and T wave are normal, it is determined that there is a old myocardial infarction.

[0033] In one embodiment, the resting low-frequency feature also includes myocardial damage information. Myocardial damage information is information obtained based on the evaluation of the resting low-frequency ECG signal to characterize whether myocardial damage exists. Specifically, reference can be made to the method of evaluating myocardial damage based on ECG (electrocardiogram) in the prior art to perform feature analysis on the resting low-frequency ECG signal to obtain myocardial damage information, which will not be repeated here. For example, the ST segment and T wave in the resting low-frequency ECG signal are analyzed. If the ST segment is arched and elevated and accompanied by T wave inversion, it is determined that myocardial damage exists.

[0034] S110, evaluating and analyzing the myocardial injury risk assessment feature set to obtain a myocardial injury risk assessment score; the myocardial injury risk assessment feature set includes a resting high-frequency QRS feature and a resting low-frequency feature.

[0035] The myocardial injury risk assessment score is used to characterize the risk of myocardial injury. The two are positively correlated. The higher the myocardial injury risk assessment score, the greater the risk of myocardial injury. Specifically, the myocardial injury risk assessment feature set is input into a preset myocardial injury risk assessment function or a pre-trained myocardial injury risk assessment model to obtain a corresponding myocardial injury risk assessment score.

[0036] In one embodiment, the expression corresponding to the myocardial injury risk assessment function is dynamically determined based on the myocardial injury risk assessment feature set as the input feature. The myocardial injury risk assessment function includes the feature function corresponding to each feature in the myocardial injury risk assessment feature set. Similarly, the input features of the myocardial injury risk assessment model are dynamically determined based on the myocardial injury risk assessment feature set. The corresponding myocardial injury risk assessment models can be pre-trained for different myocardial injury risk assessment feature sets. The input features during model training are the same as the input features during the assessment application to ensure the accuracy of the assessment.

[0037] In one embodiment, S110 includes: inputting each feature in the myocardial injury risk assessment feature set into the corresponding feature function to obtain the corresponding myocardial injury risk assessment sub-score, and summing up each myocardial injury risk assessment sub-score to obtain the myocardial injury risk assessment score; the preconfiguration step of the feature function corresponding to each feature in the myocardial injury risk assessment feature set includes: segmenting the value range corresponding to the feature to obtain one or more corresponding numerical ranges; determining the feature sub-function corresponding to each corresponding numerical range according to the correlation between the feature and the myocardial injury risk, and the weight of the feature; and obtaining the corresponding preconfigured feature function according to each feature sub-function corresponding to the feature.

[0038] Specifically, a corresponding feature function is pre-configured for each feature in the myocardial injury risk assessment feature set. The correlation between the feature and the risk of myocardial injury includes a positive correlation and / or a negative correlation. According to the correlation between the feature and the risk of myocardial injury, the value range corresponding to the feature is divided into one or more numerical ranges, and the feature sub-function corresponding to each numerical range is determined according to the correlation between the feature and the risk of myocardial injury and the weight of the feature, and the feature sub-functions corresponding to the feature are combined to obtain the corresponding pre-configured feature function. After obtaining the myocardial injury risk assessment sub-score corresponding to each feature, each myocardial injury risk assessment sub-score is summed according to the weight of the corresponding feature to obtain the myocardial injury risk assessment score. If the myocardial injury risk assessment sub-score corresponding to the feature is greater than the weight corresponding to the feature, the myocardial injury risk assessment sub-score is reset to the weight of the corresponding feature to improve the assessment accuracy.

[0039] Taking the number of resting positive leads and the number of resting critical leads as examples, both are positively correlated with the degree of myocardial cell viability deficiency or decline, and thus positively correlated with the risk of myocardial injury. Therefore, the value range of the number of resting positive leads and the number of resting critical leads can be determined as a segmented numerical range, and the value range can also be segmented into multiple numerical ranges according to the correlation between the number of resting positive leads, the number of resting critical leads and the degree of myocardial cell viability deficiency. Taking the total number of leads as 12 as an example, if the number of resting positive leads is [1, 2], [3, 4], [5, 7], [8, 10], [11, 12], the degree of myocardial cell viability deficiency is represented as level one, level two, level three, level four, and level five, respectively. The higher the level, the more serious the degree of myocardial cell viability deficiency.

[0040] In one embodiment, the value range corresponding to the number of resting positive leads and the number of resting critical leads is segmented to obtain a numerical range, and the expression of the characteristic function corresponding to the number of resting positive leads and the number of resting critical leads is as follows:

[0041] in, is the first myocardial injury risk assessment sub-score based on the number of resting positive leads and the number of resting critical leads. , then Reset to , is the maximum value of the first myocardial injury risk assessment sub-score, which is used to characterize the weight of the first myocardial injury risk assessment sub-score in the myocardial injury risk assessment score, that is, it is used to characterize the weight of the number of resting positive leads and the number of resting critical leads in the myocardial injury risk assessment. and are the number of resting positive leads and the number of resting critical leads, and They are all weights and can be flexibly set according to actual needs. Flexible settings, including , such as Take 35 as an example, and They are 3 and 1.5 respectively, with no specific limitation.

[0042] In one embodiment, the value range corresponding to the number of resting positive leads and the number of resting critical leads is segmented to obtain five value ranges, and the expression of the characteristic function corresponding to the number of resting positive leads and the number of resting critical leads is as follows:

[0043] in, is the first myocardial injury risk assessment sub-score based on the number of resting positive leads and the number of resting critical leads. , then Reset to , is the weight corresponding to the number of resting positive leads and the number of resting critical leads, and The scores are based on the number of resting positive leads and the number of resting borderline leads, respectively.

[0044] Based on the number of resting positive leads, the corresponding score is obtained according to the following characteristic function :

[0045] in, is the number of resting positive leads, , , , , are coefficients, which can be determined based on Flexible settings, , such as Take 35 as an example, , , , , They are 0.58, 1.75, 2.92, 4.08 and 5.83 respectively, with no specific limitation.

[0046] Based on the number of resting critical leads, the corresponding score is obtained according to the following characteristic function :

[0047] in, is the number of resting critical leads, , , , , are coefficients, which can be determined based on Flexible settings, , such as Take 35 as an example, , , , , They are 0.29, 0.87, 1.46, 2.04 and 2.92 respectively, with no specific limitation.

[0048] In one embodiment, the preconfigured characteristic functions for the first target number of leads, the second target number of leads, and the third target number of leads are as follows:

[0049] in, is the second myocardial injury risk assessment sub-score obtained based on the first target lead number, the second target lead number and the third target lead number. If , then Reset to , is the maximum value of the second myocardial injury risk assessment sub-score, which is used to characterize the weight of the second myocardial injury risk assessment sub-score in the myocardial injury risk assessment score, that is, it is used to characterize the weights of the first target lead number, the second target lead number, and the third target lead number in the myocardial injury risk assessment. , and They are the first target lead number, the second target lead number and the third target lead number, , and They are all weights and can be flexibly set according to actual needs. Flexible settings, , such as Take 25 as an example, , and They are 2.1, 1 and 0.5 respectively, with no specific limitation.

[0050] In one embodiment, the characteristic function preconfigured for the high-frequency morphology index is as follows:

[0051] in, is the third myocardial injury risk assessment sub-score obtained based on the high-frequency morphology index of each lead. , then Reset to , is the maximum value of the third myocardial injury risk assessment sub-score, which is used to characterize the weight of the third myocardial injury risk assessment sub-score in the myocardial injury risk assessment score, that is, it is used to characterize the weight of the high-frequency morphology index in the myocardial injury risk assessment. is the total number of leads used to collect resting ECG signals during resting ECG detection. Based on The score obtained by the high-frequency morphology index of the leads, It can be obtained by the following expression: or

[0052] in, For the The high-frequency morphology index of the leads, , , , , , and Respectively The score when the high-frequency morphology index of the lead is in the corresponding value range can be flexibly set according to needs, and can also be set according to Flexible settings, ,and , such as Take 25 as an example, , , , , , and They are 2.09, 1.88, 1.46, 1.05, 0.63, 0.31 and 4.18 respectively, and are not specifically limited here.

[0053] In one embodiment, the feature function preconfigured for the resting low-frequency feature is as follows:

[0054] in, is the fourth myocardial injury risk assessment sub-score based on the resting low-frequency characteristics, is the maximum value of the fourth myocardial injury risk assessment sub-score, which is used to characterize the weight of the fourth myocardial injury risk assessment sub-score in the myocardial injury risk assessment score, that is, it is used to characterize the weight of the resting low-frequency feature in the myocardial injury risk assessment. It is the information of old myocardial infarction in the resting low-frequency features, which is used to characterize whether there is old myocardial infarction.

[0055] In one embodiment, the myocardial injury risk assessment score is the sum of the sub-scores corresponding to each feature in the myocardial injury risk assessment feature set. Thus, a myocardial injury risk assessment function used to obtain a corresponding myocardial injury risk assessment score based on the myocardial injury risk assessment feature set is dynamically determined by the features in the myocardial injury risk assessment feature set.

[0056] If the myocardial injury risk assessment feature set includes the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads, the high-frequency morphological index of each lead, and the resting low-frequency feature, the expression of the preconfigured myocardial injury risk assessment function is as follows:

[0057] in, is the myocardial injury risk assessment score obtained based on the myocardial injury risk assessment feature set, is the first myocardial injury risk assessment sub-score, is the second myocardial injury risk assessment sub-score, The third myocardial injury risk assessment sub-score, is the myocardial injury risk assessment sub-score, , , , They are respectively derived based on the expressions in the corresponding embodiments and will not be described in detail here. , , , The corresponding weights can be flexibly set according to actual needs, such as 35, 25, 25 and 15 respectively, and no specific limitation is made here.

[0058] The above-mentioned myocardial injury assessment method obtains and analyzes the resting ECG signal to obtain the high-frequency QRS envelope curve and the resting low-frequency ECG signal, and obtains the resting high-frequency QRS characteristics such as the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads and the high-frequency morphology index of each lead based on the high-frequency QRS envelope curve analysis, and obtains the resting low-frequency characteristics such as old myocardial infarction information based on the resting low-frequency ECG signal analysis, so as to comprehensively assess the risk of myocardial injury by combining the resting high-frequency QRS characteristics and the resting low-frequency characteristics, and obtain a myocardial injury risk assessment score with higher accuracy.

[0059] In one embodiment, the resting high-frequency QRS feature also includes a fourth target lead number and a fifth target lead number; the fourth target lead number is the number of chest leads for which the lead positive indicator indicates a positive result; the fifth target lead number is the number of limb leads for which the lead positive indicator indicates a positive result.

[0060] Specifically, the leads include chest leads and limb leads. After obtaining the corresponding lead positive index based on the high-frequency QRS envelope curve analysis of each lead, the number of leads indicated as positive by the chest lead positive index is screened and counted to obtain the fourth target lead number, and the number of leads indicated as positive by the limb lead positive index is screened and counted to obtain the fifth target lead number, so as to assess the risk of myocardial injury in combination with the fourth target lead number and the fifth target lead number.

[0061] In one embodiment, the characteristic functions preconfigured for the fourth target number of leads and the fifth target number of leads are as follows:

[0062] in, is the fifth myocardial injury risk assessment sub-score obtained based on the fourth target lead number and the fifth target lead number. If , then Reset to , is the maximum value of the fifth myocardial injury risk assessment sub-score, which is used to characterize the weight of the fifth myocardial injury risk assessment sub-score in the myocardial injury risk assessment score, that is, it is used to characterize the weight of the fourth target lead number and the fifth target lead number in the myocardial injury risk assessment. and are the fourth target lead number and the fifth target lead number, and They are all weights and can be flexibly set according to actual needs. Flexible settings, , such as Take 10 as an example, and They are 1 and 0.7 respectively, with no specific limitation.

[0063] In one embodiment, if the myocardial injury risk assessment feature set includes the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads, the high-frequency morphological index and the resting low-frequency characteristics of each lead, and the number of fourth target leads and the number of fifth target leads, the expression of the preconfigured myocardial injury risk assessment function is as follows:

[0064] in, is the myocardial injury risk assessment score obtained based on the myocardial injury risk assessment feature set, , , , and The meanings and expressions of refer to the corresponding embodiments and will not be repeated here. , , , and The corresponding weights can be flexibly set according to actual needs, such as 32, 22, 22, 14 and 10 respectively, and no specific limitation is made here.

[0065] In the above embodiment, the risk of myocardial injury is assessed by combining the number of chest leads indicated as positive by the lead positive index and the number of limb leads indicated as positive by the lead positive index, which can further improve the accuracy of the assessment.

[0066] In one embodiment, the myocardial injury risk assessment feature set also includes a target myocardial ischemia risk assessment score; the above-mentioned myocardial injury risk assessment method also includes: obtaining a historical myocardial ischemia risk assessment score and / or a current myocardial ischemia risk assessment score; the historical myocardial ischemia risk assessment score is obtained by analyzing historical detection data within a first time period; the current myocardial ischemia risk assessment score is obtained by analyzing current detection data within a second time period; the first time period is earlier than the second time period; and the target myocardial ischemia risk assessment score is obtained based on the historical myocardial ischemia risk assessment score and / or the current myocardial ischemia risk assessment score.

[0067] The myocardial ischemia risk assessment score is used to characterize the size of the risk of myocardial ischemia, and the two are positively correlated. The higher the myocardial ischemia risk assessment score, the greater the risk of myocardial ischemia. The first time period and the second time period can be flexibly set according to actual needs. For example, the first time period is the day before the execution of the myocardial injury risk assessment method in this application as the end time, and the duration is a preset time period. The second time period is the day when the myocardial injury risk assessment method in this application is executed. For example, the first time period is the three days before the execution of the myocardial injury risk assessment method in this application as the end time, and the duration is a preset time period. The second time period is the two days before the execution of the myocardial injury risk assessment method in this application as the start time, and the day when the myocardial injury risk assessment method in this application is executed as the end time. The preset duration is such as 1 month, 2 months or 3 months, which is not specifically limited here. The historical detection data includes at least one of the exercise ECG signal, resting ECG signal, exercise myocardial injury risk detection data, exercise treadmill detection data, ECG (electrocardiogram), clinical symptoms, etc. collected in the first time period. The current detection data includes at least one of the currently collected exercise ECG signal, resting ECG signal, exercise myocardial injury risk detection data, exercise treadmill detection data, ECG (electrocardiogram), clinical symptoms, etc.

[0068] Specifically, query and obtain the historical myocardial ischemia risk assessment score obtained by pre-evaluation, or query and obtain the historical test data collected in the first time period, and perform myocardial ischemia risk assessment based on the historical test data to obtain the historical myocardial ischemia risk assessment score. And / or, obtain the current test data collected in the second time period, and perform myocardial ischemia risk assessment based on the current test data to obtain the current myocardial ischemia risk assessment score. If only the historical myocardial ischemia risk assessment score is obtained, the historical myocardial ischemia risk assessment score is determined as the target myocardial ischemia risk assessment score for assessing the risk of myocardial injury. If only the current myocardial ischemia risk assessment score is obtained, the current myocardial ischemia risk assessment score is determined as the target myocardial ischemia risk assessment score. If the historical myocardial ischemia risk assessment score and the current myocardial ischemia risk assessment score are obtained at the same time, the target myocardial ischemia risk assessment score is obtained by weighted summing according to the corresponding weights. Among them, the weights corresponding to the historical myocardial ischemia risk assessment score and the current myocardial ischemia risk assessment score can be flexibly set according to actual needs, such as 40% and 60%, or 30% and 70%, respectively, and are not specifically limited here.

[0069] In one embodiment, the historical myocardial ischemia risk assessment score can be a risk assessment score obtained by automatic analysis based on historical test data, or it can be a risk assessment score obtained by evaluation or correction by a doctor based on historical test data and user basic information. Thus, the historical myocardial ischemia risk assessment score obtained by pre-evaluation can be obtained from a local or other computer device, or the historical test data can be obtained and analyzed to obtain the historical myocardial ischemia risk assessment score. Other computer devices include but are not limited to terminals and servers. It can be understood that the historical myocardial ischemia risk assessment score can be predicted based on the historical test data through a preset myocardial ischemia risk assessment function or a pre-trained myocardial ischemia risk assessment model, and the historical myocardial ischemia risk assessment score can also be evaluated by other methods disclosed in the prior art, without specific limitation. If the historical test data includes an exercise ECG signal collected in the first time period, the method of evaluating the current myocardial ischemia risk assessment score based on the exercise ECG signal in the second time period in this application can be referred to to evaluate the corresponding historical myocardial ischemia risk assessment score.

[0070] In one embodiment, if the current detection data includes an exercise ECG signal collected within the second time period, the exercise ECG signal is acquired and analyzed to obtain a current myocardial ischemia risk assessment score.

[0071] In the above embodiment, myocardial injury is associated with myocardial ischemia, and the risk of myocardial injury is assessed in combination with the myocardial ischemia risk assessment score, which can further improve the accuracy of myocardial injury risk assessment.

[0072] In one embodiment, obtaining the current myocardial ischemia risk assessment score includes: obtaining an exercise ECG signal collected within a second time period; analyzing the exercise ECG signal to obtain a high-frequency QRS envelope curve; performing feature analysis on the high-frequency QRS waveform curve to obtain an exercise high-frequency QRS feature; the exercise high-frequency QRS feature includes the number of exercise-positive leads and the number of exercise-critical leads; evaluating and analyzing a myocardial ischemia risk assessment feature set to obtain the current myocardial ischemia risk assessment score; the myocardial ischemia risk assessment feature set includes an exercise high-frequency QRS feature.

[0073] Exercise ECG signal refers to the ECG signal collected during the load exercise ECG detection process. The user is in a state of exercise during the load exercise ECG detection process to increase the user's heart load through exercise. The exercise ECG signal includes multiple QRS wave groups that reflect the changes in the left and right ventricular depolarization potentials and time. Based on the QRS wave groups in the exercise ECG signal, the corresponding high-frequency QRS waveform curve can be analyzed. The high-frequency QRS waveform curve can also be understood as a high-frequency QRS time-intensity curve, which is used to characterize the root mean square voltage (i.e., intensity) of the high-frequency component of the user's QRS wave group over time during the entire load exercise ECG detection process, that is, it is used to reflect the energy change trend during the entire load exercise ECG detection process. The high-frequency QRS waveform curve is presented through a high-frequency QRS waveform graph. In the high-frequency QRS waveform graph, the horizontal axis is time, corresponding to the detection time of the load exercise ECG detection process, and the unit is min (minutes), and the vertical axis is the root mean square voltage (RMS voltage), which can also be understood as intensity or amplitude, and the unit is uV (microvolt). The exercise ECG signal includes the ECG signal corresponding to each lead, and the high-frequency QRS waveform curve corresponding to each lead can be obtained based on the exercise ECG signal. The number of exercise-positive leads refers to the number of leads for which the corresponding lead positive index indicates positive, which can be used to assess the risk of myocardial ischemia under load exercise, and the two are positively correlated. The number of exercise-critical leads refers to the number of leads for which the corresponding lead positive index indicates critical, which can be used to assess the critical risk of myocardial ischemia under load exercise, and the combination of this reference feature can more accurately assess the myocardial ischemia under load exercise.

[0074] Specifically, similar to the resting ECG signal, the motion ECG signal can be obtained from the ECG signal acquisition device through data interaction / transmission, and the specific method is not specifically limited. The motion ECG signal includes high-frequency components and low-frequency components. After the motion ECG signal is obtained, the corresponding high-frequency QRS waveform curve is obtained by analyzing the high-frequency components of the QRS wave group in the motion ECG signal. It can be understood that the method disclosed in the prior art can be used to obtain a high-frequency QRS waveform curve based on the motion ECG signal. For example, the effective QRS wave group in the motion ECG signal is collected, aligned and averaged, and then the ECG signal in the frequency band of 150Hz to 250Hz is filtered by a bandpass digital filter, and then the HFQRS wave group is subjected to root mean square processing, and the voltage intensity change trend is calculated to obtain a high-frequency QRS waveform curve, which will not be repeated here.

[0075] For each lead, a point with the largest root mean square voltage is selected from the high-frequency QRS waveform curve in the first time period as the first reference point, and a point with a time later than the first reference point and the smallest root mean square voltage is selected from the high-frequency QRS waveform curve in the first time period as the second reference point, and the root mean square voltage of the first reference point is subtracted from the root mean square voltage of the second reference point to obtain the absolute value of amplitude drop, and the ratio of the absolute value of amplitude drop to the root mean square voltage of the first reference point is determined as the relative value of amplitude drop, and the lead positive index corresponding to the lead is determined according to the relative value of amplitude drop and the absolute value of amplitude drop. Further, the number of leads indicated as positive by the lead positive index is screened and counted to obtain the number of motion positive leads, and the number of leads indicated as critical by the lead positive index is screened and counted to obtain the number of motion critical leads. After acquiring and analyzing the motion electrocardiogram signal to obtain the motion high-frequency QRS feature, a myocardial ischemia risk assessment feature set is obtained based on the motion high-frequency QRS feature, and a myocardial ischemia risk assessment score is obtained according to the myocardial ischemia risk assessment feature set, so as to also assess the risk of myocardial injury in combination with the myocardial ischemia risk assessment score.

[0076] The first time period includes a period before exercise, during exercise, and after exercise. The period before exercise is in the resting stage, during exercise includes the entire exercise stage, and after exercise is in the recovery stage. The period before exercise, during exercise, and after exercise are continuous time periods. The period before exercise and the period after exercise can be customized according to actual needs, for example, 100 seconds before exercise and 20 seconds after exercise, respectively, without specific limitation.

[0077] In one embodiment, if the absolute value of the amplitude drop is greater than the first absolute value threshold, and the relative value of the amplitude drop is greater than the first relative value threshold, the lead positive indicator is determined to be positive. If the absolute value of the amplitude drop is greater than the first absolute value threshold, the relative value of the amplitude drop is less than or equal to the first relative value threshold and greater than the second relative value threshold, the lead positive indicator is determined to be critical. The first absolute value threshold, the first relative value threshold and the second relative value threshold can be customized according to the actual detection situation, for example, 1uV (microvolt), 50% and 45% respectively, and can also be dynamically adjusted according to the user's age and maximum heart rate, which is not specifically limited here. The second relative value threshold can also be flexibly set according to the first relative value threshold, such as the second relative value threshold is the product of the first relative value threshold and the preset percentage, and the preset percentage can be flexibly set according to needs, such as 90%, which is not specifically limited here.

[0078] In one embodiment, taking the second relative value threshold as the product of the first relative value threshold and the preset percentage as an example, if the user's age is less than the preset age and the maximum heart rate is greater than the target heart rate, the first relative value threshold is 60%; if the user's age is less than the preset age and the maximum heart rate is less than or equal to the target heart rate, the first relative value threshold is 50%; if the user's age is greater than or equal to the preset age and the maximum heart rate is greater than the target heart rate, the first relative value threshold is 50%; if the user's age is greater than or equal to the preset age and the maximum heart rate is less than or equal to the target heart rate, the first relative value threshold is 40%. The preset age can be customized, such as 50 years old. The target heart rate is determined based on the user's age and the third relative value threshold, such as target heart rate = (220-age) * third relative value threshold, "*" means multiplication, and the third relative value threshold is 80% or 85%. The maximum heart rate refers to the maximum value of the user's heart rate during the entire load exercise electrocardiogram detection process. The above is only a specific example, which can be flexibly applied according to user needs in actual applications and is not limited here.

[0079] In one embodiment, the preconfigured characteristic function for the number of motion-positive leads and the number of motion-critical leads is as follows:

[0080] in, is the first myocardial ischemia risk assessment sub-score based on the number of motion-positive leads and the number of motion-critical leads. , then Reset to , is the maximum value of the first myocardial ischemia risk assessment sub-score, which is used to characterize the weight of the first myocardial ischemia risk assessment sub-score in the myocardial ischemia risk assessment score, that is, it is used to characterize the weight of the number of motion-positive leads and the number of motion-critical leads in the myocardial ischemia risk assessment. and are the number of motor-positive leads and the number of motor-critical leads, and They are all weights and can be flexibly set according to actual needs. Flexible settings, , such as Taking 100 as an example, and They are 8.34 and 4.17 respectively, with no specific limitation.

[0081] In one embodiment, if the myocardial ischemia risk assessment feature set includes the number of motion-positive leads and the number of motion-critical leads, the first myocardial ischemia risk assessment sub-score is used as the current myocardial ischemia risk assessment score.

[0082] In one embodiment, if the current detection data in the second time period also includes other data besides the exercise ECG signal, a current myocardial ischemia risk assessment score can be obtained by making a prediction based on the current detection data using a preset evaluation function or a pre-trained evaluation model.

[0083] In the above embodiment, the motion high-frequency QRS feature is obtained by acquiring and analyzing the motion ECG signal, so that the risk of myocardial injury can be assessed in combination with the motion high-frequency QRS feature to improve the accuracy of the assessment.

[0084] In one embodiment, the myocardial ischemia risk assessment feature set also includes motion low-frequency features; the steps for obtaining the motion low-frequency features include: extracting motion low-frequency ECG signals from motion ECG signals; performing feature analysis on the motion low-frequency ECG signals to obtain motion low-frequency features; the motion low-frequency features include the degree of ST-T segment change and the duration of ST-T segment change in each lead.

[0085] ST segment changes include ST segment elevation and ST segment depression. The degree of ST segment change refers to the value of the ST segment change, that is, the value of ST segment elevation or depression, which is used to characterize the degree of ST segment elevation or depression. The duration of ST segment change refers to the duration of ST segment elevation or depression. The ST segment corresponding to each heartbeat within this duration is in an elevated or depressed state.

[0086] Specifically, the motion ECG signal includes high-frequency components and low-frequency components, and the motion low-frequency ECG signal is extracted from the motion ECG signal by analyzing the motion ECG signal. It can be understood that the method disclosed in the prior art can be used to obtain the motion low-frequency ECG signal based on the motion ECG signal. For example, the motion ECG signal is low-pass filtered to obtain the motion low-frequency ECG signal, which will not be repeated here. Further, the motion low-frequency ECG signal is analyzed to locate and extract the motion low-frequency features such as the degree of ST-T segment change and the duration of ST-T segment change from the motion low-frequency ECG signal of each lead. It can be understood that the method disclosed in the prior art can be used to obtain the corresponding degree of ST segment change and duration of ST segment change based on the analysis of the low-frequency ECG signal of each lead.

[0087] In one embodiment, for each lead of the low-frequency electrocardiogram signal of motion, the low-frequency electrocardiogram signal of motion is divided into multiple signal subsets according to the time sequence and the preset step size by a window function, each signal subset includes an ECG (electrocardiogram) corresponding to at least one heartbeat, and the ECG corresponding to each heartbeat in each signal subset is aligned and averaged in turn to obtain the ECG corresponding to the signal subset (single ECG / electrocardiogram). The ECG corresponding to each signal subset is subjected to ST segment elevation or depression analysis to obtain the ST segment change degree corresponding to the signal subset (ST segment elevation degree or ST segment depression degree), and the maximum value is selected from the ST segment change degree corresponding to each signal subset as the ST segment change degree corresponding to the corresponding lead. If the ST segment elevation degree is represented by a positive number and the ST segment depression degree is represented by a negative number, the ST segment change degree with the largest absolute value is selected from the ST segment change degree corresponding to each signal subset as the ST segment change degree of the corresponding lead.

[0088] According to the time series statistics, the number of signal subsets in which the ST segment in the corresponding ECG is elevated and continuous is obtained to obtain the number of first subsets, and according to the time series statistics, the number of signal subsets in which the ST segment in the corresponding ECG is depressed and continuous is obtained to obtain the number of second subsets. The maximum value is selected from the first subset number and the second subset number as the target subset number, and the duration of ST segment change is determined according to the duration corresponding to the window function, the duration corresponding to the target subset number and the preset step length. Specifically, the duration of ST segment change = the duration corresponding to the window function + the duration corresponding to the preset step length * (target subset number - 1). It can be understood that the duration corresponding to the window function and the preset step length can be flexibly set according to actual needs. The duration of the window function is greater than or equal to the duration of the preset step length, such as 1 minute, and no specific limitation is made here.

[0089] In one embodiment, the feature function preconfigured for the motion low-frequency feature is as follows:

[0090] in, is the second myocardial ischemia risk assessment sub-score based on the low-frequency characteristics of exercise. , then Reset to , is the maximum value of the second myocardial ischemia risk assessment sub-score, which is used to characterize the weight of the second myocardial ischemia risk assessment sub-score in the myocardial ischemia risk assessment score, that is, it is used to characterize the weight of the low-frequency characteristics of movement in the myocardial ischemia risk assessment. It is the total number of leads used to collect exercise ECG signals during the stress exercise ECG detection process. Based on The score is obtained by the degree of ST segment change in the leads. Based on The score is obtained by the duration of ST segment change in the lead. and The specific expressions can be obtained as follows:

[0091] in, For the The degree of ST segment change in leads, The unit of its corresponding value range is mV (millivolt). , and Respectively The score when the ST segment change degree of each lead is within the corresponding numerical range can be flexibly set according to needs, and can also be set according to Flexible settings, , such as Take 10 as an example, , and They are 0.42, 0.25 and 0.11 respectively, and are not specifically limited here.

[0092]

[0093] in, For the The duration of ST segment changes in leads, The corresponding value range is min (minutes), and Respectively The score when the duration of ST segment change of each lead is within the corresponding value range can be flexibly set according to needs, and can also be set according to Flexible settings, , such as Take 10 as an example, and They are 0.42 and 0.21 respectively, and are not specifically limited here.

[0094] In one embodiment, if the myocardial ischemia risk assessment feature set includes the number of motion-positive leads, the number of motion-critical leads, and the motion low-frequency feature, the current myocardial ischemia risk assessment score is obtained based on the following expression:

[0095] in, is the current myocardial ischemia risk assessment score obtained based on the myocardial ischemia risk assessment feature set, and The meaning and expression of refer to the corresponding embodiments and will not be repeated here. and The corresponding weights can be flexibly set according to actual needs, such as 90 and 10 respectively, and no specific limitation is made here.

[0096] In the above embodiment, the high-frequency QRS characteristics and the low-frequency characteristics of movement are combined to assess the risk of myocardial ischemia, which can improve the accuracy of the myocardial ischemia risk assessment score.

[0097] In one embodiment, if the target myocardial ischemia risk assessment score is obtained by weighted summing the historical myocardial ischemia risk assessment score and the current myocardial ischemia risk assessment score according to corresponding weights, the target myocardial ischemia risk assessment score is obtained based on the following expression:

[0098] in, The target myocardial ischemia risk assessment score is and They are respectively a current myocardial ischemia risk assessment score and a historical myocardial ischemia risk assessment score. The respective expressions refer to the corresponding embodiments and are not described in detail here. and The weights of the historical myocardial ischemia risk assessment score and the current myocardial ischemia risk assessment score can be flexibly set according to actual needs, such as 40% and 60% respectively, which are not specifically limited here. and The sum of is 1. It can be understood that if only the historical myocardial ischemia risk assessment score is obtained, the weight of the current myocardial ischemia risk assessment score is set to 0. Similarly, if only the current myocardial ischemia risk assessment score is obtained, the weight of the historical myocardial ischemia risk assessment score is set to 0.

[0099] In one embodiment, if the myocardial injury risk assessment feature set includes the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads, the high-frequency morphological index of each lead, the resting low-frequency feature, the number of fourth target leads, the number of fifth target leads and the myocardial ischemia risk assessment score, the expression of the preconfigured myocardial injury risk assessment function is as follows:

[0100] in, is the myocardial injury risk assessment score obtained based on the myocardial injury risk assessment feature set, , , and The meanings and expressions of refer to the corresponding embodiments and will not be repeated here. The target myocardial ischemia risk assessment score is As the sixth myocardial injury risk assessment sub-score, The specific expressions of can refer to the corresponding embodiments. is the weight of the target myocardial ischemia risk assessment score in the myocardial injury risk assessment score. , , and The corresponding weights, and Both can be flexibly set according to actual needs. For example, the upper limit value (i.e., full score) of the myocardial injury risk assessment score and the target myocardial ischemia risk assessment score are both 100. , , and The corresponding weights, and They are 24, 16, 16, 11, 8 and 25% respectively, that is .

[0101] In one embodiment, the myocardial injury risk assessment feature set also includes user basic information; the above-mentioned myocardial injury risk assessment method also includes: obtaining user basic information; the user basic information includes at least one of chronic basic disease information, drinking information, and staying up late information.

[0102] User basic information includes but is not limited to at least one of chronic underlying disease information, drinking information, staying up late information and vascular plaque information. Chronic underlying disease information is used to indicate whether there is a chronic underlying disease. Chronic underlying diseases include but are not limited to hypertension, hyperlipidemia and diabetes. Drinking information is used to indicate whether there is a drinking habit. Staying up late information is used to indicate whether there is a habit of staying up late.

[0103] In one embodiment, the feature functions preconfigured for the user basic information are as follows:

[0104] in, is the seventh myocardial injury risk assessment sub-score obtained based on the user's basic information, is the maximum value of the seventh myocardial injury risk assessment sub-score, which is used to represent the weight of the seventh myocardial injury risk assessment sub-score in the myocardial injury risk assessment score, that is, it is used to represent the weight of the user's basic information in the myocardial injury risk assessment. It is the user's basic information, used to characterize whether there are chronic underlying diseases, drinking habits, staying up late habits, etc.

[0105] In one embodiment, if the myocardial injury risk assessment feature set includes the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads, the high-frequency morphological index of each lead, the resting low-frequency feature, the number of fourth target leads, the number of fifth target leads and the myocardial ischemia risk assessment score, as well as user basic information, the expression of the preconfigured myocardial injury risk assessment function is as follows:

[0106] in, is the myocardial injury risk assessment score obtained based on the myocardial injury risk assessment feature set, , , , , , and The meanings and expressions of refer to the corresponding embodiments and will not be repeated here. , , , , , and The corresponding weights, and Both can be flexibly set according to actual needs. For example, the upper limit values ​​(i.e., full marks) of the myocardial injury risk assessment score and the myocardial ischemia risk assessment score are both 100. , , , , , and The corresponding weights, and They are 22, 14, 14, 10, 7, 23% and 10 respectively, that is, .

[0107] In the above embodiment, the risk of myocardial injury is also assessed in combination with basic information of the user, which can improve the accuracy of the assessment of the risk of myocardial injury.

[0108] In one or more embodiments of the present application, the coefficient or score of the corresponding feature in each feature function when it is in each numerical range, and the weight of each feature in the risk assessment of myocardial injury, can be determined by the terminal and / or server based on the labeled sample set through automatic learning, or can be manually set or modified in the function pre-configuration stage, or can be determined by a combination of automatic learning and manual setting or modification. In one embodiment, the highest sub-score obtained based on the feature function corresponding to the feature is greater than or equal to the weight corresponding to the feature, and less than or equal to the product of the weight corresponding to the feature and the weight coefficient. The weight coefficient can be flexibly set according to actual needs, such as 10%, which is not specifically limited here.

[0109] In one embodiment, when evaluating the risk of myocardial injury with reference to the myocardial injury risk assessment score, the corresponding reference standard (such as score threshold, score interval, etc.) needs to be dynamically adjusted according to the characteristic function corresponding to each feature.

[0110] In one embodiment, in one or more embodiments of the present application, the sum of the weights corresponding to the features in the myocardial injury risk assessment feature set is 100 as an example, that is, the upper limit value (full score) of the myocardial injury risk assessment score is 100 as an example. It can be understood that the sum of the weights corresponding to the features in the myocardial injury risk assessment feature set may not be limited to 100, that is, the upper limit value (full score) of the myocardial injury risk assessment score may not be limited to 100. If the upper limit value (full score) of the myocardial injury risk assessment score is not limited to 100, when assessing the risk of myocardial injury risk with reference to the myocardial injury risk assessment score, the corresponding reference standard (such as score threshold, score interval, etc.) needs to be dynamically adjusted according to the upper limit value. Similarly, the sum of the weights corresponding to the features in the myocardial ischemia risk assessment feature set may not be limited to 100, that is, the upper limit value (full score) of the myocardial ischemia risk assessment score may not be limited to 100.

[0111] In one embodiment, if the myocardial injury risk assessment feature set is used as an input feature to a pre-trained myocardial injury risk assessment model for prediction to obtain a myocardial injury risk assessment result, the features in the myocardial injury risk assessment feature set used as input features during prediction are the same as the features in the myocardial injury risk assessment feature set used as input features during model training. Thus, corresponding myocardial injury risk assessment models can be trained for one or more combinations of features in the myocardial injury risk assessment feature set, so that the corresponding myocardial injury risk assessment model can be selected according to the actual situation during prediction to perform myocardial injury risk assessment.

[0112] It is worth noting that the meanings, values, value ranges, etc. of the expressions and their parameters in one or more embodiments of the present application are only examples and are not intended to be specific limitations. They can be flexibly set according to actual needs.

[0113] In one embodiment, Figure 2 As shown, a method for assessing the risk of myocardial injury is provided, and the method specifically comprises the following steps: S202, obtaining a resting electrocardiogram signal.

[0114] S204, analyzing the resting ECG signal to obtain a high-frequency QRS envelope curve and a resting low-frequency ECG signal.

[0115] S206, perform feature analysis on the high-frequency QRS envelope curve to obtain resting high-frequency QRS features; the resting high-frequency QRS features include the number of resting positive leads, the number of resting critical leads, the first target number of leads, the second target number of leads, the third target number of leads, the high-frequency morphology index of each lead, the fourth target number of leads and the fifth target number of leads; the first target number of leads refers to the number of leads whose number of peaks is greater than or equal to the first number threshold; the second target number of leads refers to the number of leads whose number of peaks is equal to the second number threshold; the third target number of leads refers to the number of leads whose number of peaks is equal to the third number threshold; the fourth target number of leads is the number of chest leads whose lead positive indicators indicate positive; the fifth target number of leads is the number of limb leads whose lead positive indicators indicate positive.

[0116] S208, performing feature analysis on the resting low-frequency electrocardiogram signal to obtain resting low-frequency features; the resting low-frequency features include information on old myocardial infarction.

[0117] S210, acquiring the exercise electrocardiogram signal collected in the second time period.

[0118] S212, analyzing the motion ECG signal to obtain a high-frequency QRS envelope curve.

[0119] S214, performing feature analysis on the high-frequency QRS waveform curve to obtain a motion high-frequency QRS feature; the motion high-frequency QRS feature includes the number of motion-positive leads and the number of motion-critical leads.

[0120] S216, extracting a motion low-frequency ECG signal from the motion ECG signal.

[0121] S218, performing feature analysis on the motion low-frequency ECG signal to obtain motion low-frequency features; the motion low-frequency features include the degree of ST-T segment change and the duration of ST-T segment change of each lead.

[0122] S220, evaluating and analyzing the myocardial ischemia risk assessment feature set to obtain a current myocardial ischemia risk assessment score; the myocardial ischemia risk assessment feature set includes a high-frequency QRS feature and a low-frequency feature.

[0123] S222, obtaining a historical myocardial ischemia risk assessment score; the historical myocardial ischemia risk assessment score is obtained by analyzing historical detection data within the first time period.

[0124] S224, obtaining a target myocardial ischemia risk assessment score according to the historical myocardial ischemia risk assessment score and the current myocardial ischemia risk assessment score.

[0125] S226, obtaining basic information of the user; the basic information of the user includes at least one of chronic basic disease information, drinking information, and staying up late information.

[0126] S228, evaluating and analyzing the myocardial injury risk assessment feature set to obtain a myocardial injury risk assessment score; the myocardial injury risk assessment feature set includes resting high-frequency QRS features, resting low-frequency features, current myocardial ischemia risk assessment score and user basic information.

[0127] In the above embodiment, the resting ECG signal is acquired and analyzed to obtain the resting high-frequency QRS characteristics and the resting low-frequency characteristics, the exercise ECG signal is acquired and analyzed to obtain the myocardial ischemia risk assessment score, and the user basic information associated with myocardial damage is acquired. The resting high-frequency QRS characteristics and the resting low-frequency characteristics in the resting state are comprehensively considered to obtain the myocardial ischemia risk assessment score that characterizes the size of the myocardial ischemia risk, and the user basic information is used to assess the myocardial damage risk, which can improve the myocardial damage risk assessment score.

[0128] It should be understood that although Figure 1 and Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 and Figure 2 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0129] In one embodiment, Figure 3 As shown, a myocardial injury risk assessment device 300 is provided, comprising: an acquisition module 301, an analysis module 302, and an assessment module 303, wherein: An acquisition module 301 is used to acquire a resting ECG signal; An analysis module 302 is used to analyze the resting ECG signal to obtain a high-frequency QRS envelope curve and a resting low-frequency ECG signal; The analysis module 302 is further used to perform feature analysis on the high-frequency QRS envelope curve to obtain a resting high-frequency QRS feature; the resting high-frequency QRS feature includes the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads and the high-frequency morphological index of each lead; the first target number of leads refers to the number of leads whose number of peaks is greater than or equal to the first number threshold; the second target number of leads refers to the number of leads whose number of peaks is equal to the second number threshold; the third target number of leads refers to the number of leads whose number of peaks is equal to the third number threshold; The analysis module 302 is further used to perform feature analysis on the resting low-frequency ECG signal to obtain resting low-frequency features; the resting low-frequency features include old myocardial infarction information; The evaluation module 303 is used to evaluate and analyze the myocardial injury risk evaluation feature set to obtain a myocardial injury risk evaluation score; the myocardial injury risk evaluation feature set includes a resting high-frequency QRS feature and a resting low-frequency feature.

[0130] In one embodiment, the resting high-frequency QRS feature also includes a fourth target lead number and a fifth target lead number; the fourth target lead number is the number of chest leads for which the lead positive indicator indicates a positive result; the fifth target lead number is the number of limb leads for which the lead positive indicator indicates a positive result.

[0131] In one embodiment, the myocardial injury risk assessment feature set also includes a target myocardial ischemia risk assessment score; the acquisition module 301 is also used to obtain a historical myocardial ischemia risk assessment score and / or a current myocardial ischemia risk assessment score; the historical myocardial ischemia risk assessment score is obtained by analyzing historical detection data within a first time period; the current myocardial ischemia risk assessment score is obtained by analyzing current detection data within a second time period; the first time period is earlier than the second time period; the target myocardial ischemia risk assessment score is obtained based on the historical myocardial ischemia risk assessment score and / or the current myocardial ischemia risk assessment score.

[0132] In one embodiment, the acquisition module 301 is also used to acquire the motion ECG signal collected in the second time period; the analysis module 302 is also used to analyze the motion ECG signal to obtain a high-frequency QRS envelope curve; perform feature analysis on the high-frequency QRS waveform curve to obtain a motion high-frequency QRS feature; the motion high-frequency QRS feature includes the number of motion positive leads and the number of motion critical leads; the evaluation module 303 is also used to evaluate and analyze the myocardial ischemia risk assessment feature set to obtain a current myocardial ischemia risk assessment score; the myocardial ischemia risk assessment feature set includes the motion high-frequency QRS feature.

[0133] In one embodiment, the myocardial ischemia risk assessment feature set also includes motion low-frequency features; the analysis module 302 is also used to extract motion low-frequency ECG signals from motion ECG signals; feature analysis is performed on the motion low-frequency ECG signals to obtain motion low-frequency features; the motion low-frequency features include the degree of ST-T segment change and the duration of ST-T segment change in each lead.

[0134] In one embodiment, the myocardial injury risk assessment feature set also includes user basic information; the acquisition module 301 is also used to obtain user basic information; the user basic information includes at least one of chronic basic disease information, drinking information, and staying up late information.

[0135] In one embodiment, the evaluation module 303 is also used to input each feature in the myocardial injury risk assessment feature set into a corresponding feature function to obtain a corresponding myocardial injury risk assessment sub-score, and sum up each myocardial injury risk assessment sub-score to obtain a myocardial injury risk assessment score; segment the value range corresponding to the feature to obtain one or more corresponding numerical ranges; determine the feature sub-function corresponding to each corresponding numerical range according to the correlation between the feature and the myocardial injury risk, and the weight of the feature; and obtain the corresponding preconfigured feature function according to each feature sub-function corresponding to the feature.

[0136] For the specific definition of the myocardial injury risk assessment device, please refer to the definition of the myocardial injury risk assessment method above, which will not be repeated here. Each module in the above-mentioned myocardial injury risk assessment device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0137] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store resting electrocardiogram signals. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for assessing the risk of myocardial injury is implemented.

[0138] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0139] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0141] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0142] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0143] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for assessing myocardial injury risk, characterized in that: The method comprises: Acquire resting ECG signals; Analyze the resting ECG signal to obtain a high-frequency QRS envelope curve and a resting low-frequency ECG signal; Performing feature analysis on the high-frequency QRS envelope curve to obtain a resting high-frequency QRS feature; the resting high-frequency QRS feature includes the number of resting positive leads, the number of resting critical leads, the number of first target leads, the number of second target leads, the number of third target leads and the high-frequency morphological index of each lead; the first target number of leads refers to the number of leads whose number of peaks is greater than or equal to a first number threshold; the second target number of leads refers to the number of leads whose number of peaks is equal to a second number threshold; the third target number of leads refers to the number of leads whose number of peaks is equal to a third number threshold; Performing feature analysis on the resting low-frequency electrocardiogram signal to obtain a resting low-frequency feature; the resting low-frequency feature includes old myocardial infarction information; The myocardial injury risk assessment feature set is evaluated and analyzed to obtain a myocardial injury risk assessment score; the myocardial injury risk assessment feature set includes the resting high-frequency QRS feature and the resting low-frequency feature.

2. The method according to claim 1, characterized in that The resting high-frequency QRS feature also includes a fourth target lead number and a fifth target lead number; the fourth target lead number is the number of chest leads indicated as positive by the lead positive indicator; the fifth target lead number is the number of limb leads indicated as positive by the lead positive indicator.

3. The method according to claim 1, characterized in that The myocardial injury risk assessment feature set also includes a target myocardial ischemia risk assessment score; the method further includes: Obtaining a historical myocardial ischemia risk assessment score and / or a current myocardial ischemia risk assessment score; the historical myocardial ischemia risk assessment score is obtained by analyzing historical test data within a first time period; the current myocardial ischemia risk assessment score is obtained by analyzing current test data within a second time period; the first time period is earlier than the second time period; A target myocardial ischemia risk assessment score is obtained according to the historical myocardial ischemia risk assessment score and / or the current myocardial ischemia risk assessment score.

4. The method according to claim 3, characterized in that Obtain the current myocardial ischemia risk assessment score, including: Acquire the exercise electrocardiogram signal collected in the second time period; Analyzing the exercise electrocardiogram signal to obtain a high-frequency QRS envelope curve; Performing feature analysis on the high-frequency QRS waveform curve to obtain a motion high-frequency QRS feature; the motion high-frequency QRS feature includes the number of motion positive leads and the number of motion critical leads; The myocardial ischemia risk assessment feature set is evaluated and analyzed to obtain a current myocardial ischemia risk assessment score; the myocardial ischemia risk assessment feature set includes the motion high-frequency QRS feature.

5. The method according to claim 4, characterized in that The myocardial ischemia risk assessment feature set also includes motion low-frequency features; The step of acquiring the low-frequency characteristics of the movement includes: Extracting a motion low-frequency electrocardiogram signal from the motion electrocardiogram signal; The motion low-frequency electrocardiogram signal is subjected to feature analysis to obtain motion low-frequency features; the motion low-frequency features include the degree of ST-T segment change and the duration of ST-T segment change of each lead.

6. The method according to claim 1, characterized in that The myocardial injury risk assessment feature set also includes basic user information; the method also includes: Obtain user basic information; the user basic information includes at least one of chronic basic disease information, drinking information, and staying up late information.

7. The method according to any one of claims 1 to 6, characterized in that: The step of evaluating and analyzing the myocardial injury risk assessment feature set to obtain a myocardial injury risk assessment score includes: Input each feature in the myocardial injury risk assessment feature set into the corresponding feature function to obtain the corresponding myocardial injury risk assessment sub-score, and sum each myocardial injury risk assessment sub-score to obtain the myocardial injury risk assessment score; The pre-configuration steps of the feature function corresponding to each feature in the myocardial injury risk assessment feature set include: Segmenting the value range corresponding to the feature to obtain one or more corresponding value ranges; Determine the characteristic sub-function corresponding to each numerical range according to the correlation between the characteristic and the risk of myocardial injury and the weight of the characteristic; According to each characteristic sub-function corresponding to the characteristic, a corresponding pre-configured characteristic function is obtained.

8. A myocardial injury risk assessment device, characterized in that: The device comprises: An acquisition module, used for acquiring a resting ECG signal; An analysis module, used for analyzing the resting ECG signal to obtain a high-frequency QRS envelope curve and a resting low-frequency ECG signal; The analysis module is further used to perform feature analysis on the high-frequency QRS envelope curve to obtain a resting high-frequency QRS feature; the resting high-frequency QRS feature includes the number of resting positive leads, the number of resting critical leads, the first target number of leads, the second target number of leads, the third target number of leads and the high-frequency morphological index of each lead; the first target number of leads refers to the number of leads whose wave peaks are greater than or equal to a first number threshold; the second target number of leads refers to the number of leads whose wave peaks are equal to a second number threshold; the third target number of leads refers to the number of leads whose wave peaks are equal to a third number threshold; The analysis module is further used to perform feature analysis on the resting low-frequency electrocardiogram signal to obtain resting low-frequency features; the resting low-frequency features include old myocardial infarction information; An evaluation module is used to evaluate and analyze a myocardial injury risk evaluation feature set to obtain a myocardial injury risk evaluation score; the myocardial injury risk evaluation feature set includes the resting high-frequency QRS feature and the resting low-frequency feature.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images