ECG data processing methods, devices, computer equipment and storage media

Abstract

This application relates to a method, apparatus, computer device, and storage medium for processing electrocardiogram (ECG) data. The method includes: acquiring a high-frequency QRS envelope curve at rest; determining the number of target leads, the average peak voltage of limb leads, the QRS duration, and the high-frequency morphology index of each lead based on the high-frequency QRS envelope curve; the number of target leads is the number of leads whose corresponding peak count exceeds a first threshold and whose corresponding high-frequency morphology index is greater than or equal to a second threshold; the average peak voltage of limb leads is the average of the peak voltages corresponding to each limb lead; leads include limb leads and chest leads; multiplying the weight determined by the QRS duration by the sum of the scores determined by the high-frequency morphology index of each lead to obtain a heart failure risk assessment score; if the number of target leads exceeds a third threshold, determining the heart failure risk assessment level based on the average peak voltage of limb leads and the heart failure risk assessment score. This method can more accurately assess heart failure risk for physician reference.

Description

Technical Field

[0001] This application relates to the field of electrocardiogram (ECG) data processing technology, and in particular to an ECG data processing method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Cardiovascular diseases are becoming increasingly prevalent among younger people, making risk assessment for cardiovascular diseases (such as heart failure) a crucial issue.

[0003] The existing methods for assessing heart failure risk have limitations in terms of accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide an electrocardiogram data processing method, device, computer equipment, and storage medium that can improve the accuracy of heart failure risk assessment, addressing the aforementioned technical problems.

[0005] An electrocardiogram (ECG) data processing method, the method comprising:

[0006] Obtain the high-frequency QRS envelope curve under resting conditions;

[0007] The number of target leads, the average peak voltage and QRS duration of limb leads, and the high-frequency morphology index corresponding to each lead are determined based on the high-frequency QRS envelope curve. The number of target leads is the number of leads whose corresponding peak count exceeds a first threshold and whose corresponding high-frequency morphology index is greater than or equal to a second threshold. The average peak voltage of limb leads is the average value of the peak voltages corresponding to each limb lead. The leads include limb leads and chest leads.

[0008] The score for each lead is determined based on the high-frequency morphology index, and the weight is determined based on the QRS duration. The sum of the scores for each lead is multiplied by the weight to obtain the heart failure risk assessment score.

[0009] If the number of target leads exceeds the third threshold, the heart failure risk assessment level is determined based on the average peak voltage of the limb leads and the heart failure risk assessment score.

[0010] In one embodiment, the method further includes:

[0011] The number of positive leads is determined based on the high-frequency QRS envelope curve; the number of positive leads is the number of leads whose corresponding high-frequency morphological index is greater than or equal to the second threshold.

[0012] The determination of the heart failure risk assessment level based on the average peak voltage of the limb leads and the heart failure risk assessment score includes:

[0013] The heart failure risk assessment level is determined based on the number of positive leads, the average peak voltage of the limb leads, and the heart failure risk assessment score.

[0014] In one embodiment, determining the heart failure risk assessment level based on the number of positive leads, the average peak voltage of the limb leads, and the heart failure risk assessment score includes:

[0015] The first risk assessment level is determined based on the heart failure risk assessment score.

[0016] The second risk assessment level is determined based on the average peak voltage of the limb leads;

[0017] The third risk assessment level is determined based on the number of positive leads;

[0018] The heart failure risk assessment level is determined based on the first risk assessment level, the second risk assessment level, and the third risk assessment level.

[0019] In one embodiment, determining the average peak voltage of limb leads based on the high-frequency QRS envelope curve includes:

[0020] The peak voltage of each limb lead is determined based on the high-frequency QRS envelope curve.

[0021] The average peak voltage of the limb leads is obtained by averaging the peak voltages of each limb lead.

[0022] In one embodiment, the method further includes:

[0023] Acquire low-frequency electrocardiogram data;

[0024] ST segment characteristics were obtained by analyzing the low-frequency ECG data;

[0025] The determination of the heart failure risk assessment level based on the average peak voltage of the limb leads and the heart failure risk assessment score includes:

[0026] The heart failure risk assessment level is determined based on the average peak voltage of the limb leads, the heart failure risk assessment score, and the ST segment characteristics.

[0027] In one embodiment, determining the number of target leads based on the high-frequency QRS envelope curve includes:

[0028] Based on the high-frequency QRS envelope curve, select leads whose corresponding high-frequency morphological index is greater than or equal to the second threshold.

[0029] The total number of leads in the selected leads whose corresponding peak count exceeds the first threshold is determined as the target number of leads.

[0030] An electrocardiogram (ECG) data processing device, the device comprising:

[0031] The acquisition module is used to acquire the high-frequency QRS envelope curve in the resting state;

[0032] The indicator determination module is used to determine the number of target leads, the average peak voltage and QRS duration of limb leads, and the high-frequency morphology index corresponding to each lead based on the high-frequency QRS envelope curve; the number of target leads is the number of leads whose corresponding peak count exceeds a first threshold and whose corresponding high-frequency morphology index is greater than or equal to a second threshold; the average peak voltage of limb leads is the average value of the peak voltages corresponding to each limb lead; the leads include limb leads and chest leads;

[0033] The indicator determination module is also used to determine the score of the corresponding lead based on the high-frequency morphology index, determine the weight based on the QRS duration, and multiply the sum of the scores of each lead by the weight to obtain the heart failure risk assessment score.

[0034] The rating determination module is used to determine the heart failure risk assessment level based on the average peak voltage of the limb leads and the heart failure risk assessment score if the number of target leads exceeds a third threshold.

[0035] In one embodiment, the index determination module is further configured to determine the number of positive leads based on the high-frequency QRS envelope curve; the number of positive leads is the number of leads with a corresponding high-frequency morphological index greater than or equal to a second threshold.

[0036] The grade determination module is also used to determine the heart failure risk assessment grade based on the number of positive leads, the average peak voltage of the limb leads, and the heart failure risk assessment score.

[0037] A computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps in various method embodiments.

[0038] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the various method embodiments.

[0039] The aforementioned ECG data processing method, device, computer equipment, and storage medium analyze the high-frequency QRS envelope curve in the resting state to obtain the number of target leads for assessing the possibility of heart failure, the QRS duration and high-frequency morphology index of each lead for determining the heart failure risk assessment score, and the average peak voltage of limb leads for determining the heart failure risk assessment level in conjunction with the heart failure risk assessment score. The heart failure risk assessment score is obtained by multiplying the weight determined by the QRS duration with the sum of the scores determined by the high-frequency morphology index of each lead. This improves the matching degree between the heart failure risk assessment score and the heart failure risk. When the number of target leads exceeds a third threshold, i.e., when the possibility of heart failure is determined, the heart failure risk assessment level is determined based on the heart failure risk assessment score and the average peak voltage of limb leads for physician reference. Therefore, it can more accurately and efficiently assess the heart failure risk for physician reference, enabling physicians to efficiently and accurately identify the patient's cardiac health status in conjunction with clinical symptoms. Attached Figure Description

[0040] Figure 1 This is a flowchart illustrating an electrocardiogram (ECG) data processing method in one embodiment;

[0041] Figure 2 This is a schematic diagram of the high-frequency QRS envelope curve in one embodiment;

[0042] Figure 3 This is a flowchart illustrating the ECG data processing method in another embodiment;

[0043] Figure 4 This is a structural block diagram of an electrocardiogram data processing device in one embodiment;

[0044] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0046] The electrocardiogram (ECG) data processing method provided in this application can be applied to a terminal, a server, or an interactive system including both a terminal and a server, and is implemented through the interaction between the terminal and the server; no specific limitations are made here. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, ECG monitoring devices, and portable wearable devices. The server can be a standalone server or a server cluster consisting of multiple servers.

[0047] In one embodiment, such as Figure 1 As shown, an electrocardiogram (ECG) data processing method is provided. Taking its application to a server as an example, the method specifically includes the following steps:

[0048] S102, Obtain the high-frequency QRS envelope curve under resting state.

[0049] Specifically, ECG data collected during the resting ECG test is obtained as resting ECG data, where the subject is in a resting state during the test. The resting ECG data is processed to obtain the high-frequency QRS envelope curve of the subject in the resting state. In other words, the resting ECG data of each lead is processed separately to obtain the corresponding high-frequency QRS envelope curve.

[0050] In one embodiment, the resting electrocardiogram (ECG) data includes multiple QRS complexes. The QRS complexes in the resting ECG data are sequentially aligned, averaged, and filtered at high frequencies to obtain a high-frequency QRS envelope curve. It is understood that the high-frequency QRS envelope curve corresponds to the high-frequency QRS complex data, and a corresponding high-frequency QRS envelope curve can be formed based on the high-frequency QRS complex data. In one or more embodiments of this application, obtaining the high-frequency QRS envelope curve can be understood as obtaining the high-frequency QRS complex data used to form the high-frequency QRS envelope curve. Specifically, the QRS complexes in the resting ECG data are sequentially aligned, averaged, and filtered at high frequencies to obtain the high-frequency QRS complex data, which is used to form the corresponding high-frequency QRS envelope curve. It is understood that the high-frequency QRS envelope curve can also be obtained by sequentially performing high-frequency filtering, alignment, and averaging on the QRS complexes in the resting ECG data, or by extracting high-frequency ECG data from the resting ECG data and sequentially aligning and averaging the QRS complexes in the high-frequency ECG data to obtain the high-frequency QRS envelope curve; no specific limitation is made here.

[0051] S104. Determine the number of target leads, the average peak voltage and QRS duration of limb leads, and the high-frequency morphology index corresponding to each lead based on the high-frequency QRS envelope curve; the number of target leads is the number of leads whose corresponding peak number exceeds the first threshold and whose corresponding high-frequency morphology index is greater than or equal to the second threshold; the average peak voltage of limb leads is the average value of the peak voltages corresponding to each limb lead; leads include limb leads and chest leads.

[0052] The number of peaks refers to the total number of peaks on the high-frequency QRS envelope curve. The number of peaks on the high-frequency QRS envelope curve is correlated with the viability of the corresponding myocardial cells in the respective leads. A peak count exceeding a first threshold indicates a decrease in the viability of the corresponding myocardial cells. It is understood that the specific number of peaks on the high-frequency QRS envelope curve can be determined using existing technologies, and no specific limitations are imposed here. The first threshold can be customized according to actual needs, such as 3. The second threshold can be customized according to actual conditions, such as 8%, or dynamically determined based on the age of the test subject. For example, if the test subject is older than 50 years old, the second threshold can be, but is not limited to, 8%; if the test subject is younger than or equal to 50 years old, the second threshold can be, but is not limited to, 15%. The second threshold can also be dynamically determined through statistical analysis of the high-frequency morphological indices of multiple test subjects. For example, the high-frequency morphological indices of each test subject can be sorted from largest to smallest, the average of the top three high-frequency morphological indices can be obtained, and then the average of the high-frequency morphological indices of multiple test subjects can be calculated to obtain the second threshold. It is understood that the method for setting the second threshold is not specifically limited here. QRS duration is the length of the QRS complex from its inception to its termination. Prolonged QRS duration is associated with conduction block. If heart failure is suspected, QRS duration is positively correlated with the overall risk of heart failure; a wider QRS duration indicates a higher overall risk of heart failure, meaning poorer overall cardiac function. The mean peak voltage in limb leads is positively correlated with cardiac systolic function and pumping capacity. Decreased cardiac systolic function and pumping capacity are manifestations of heart failure; a higher mean peak voltage in limb leads indicates stronger cardiac systolic function and pumping capacity, suggesting a lower risk of heart failure. Leads, also known as electrocardiogram leads, include limb leads and chest leads.

[0053] Specifically, by analyzing the high-frequency QRS envelope curves corresponding to each lead, the QRS duration and the high-frequency morphological index corresponding to each lead are obtained. Leads with a peak count exceeding a first threshold and a high-frequency morphological index greater than or equal to a second threshold are selected and counted to obtain the target number of leads. The corresponding peak voltage is determined based on the high-frequency QRS envelope curves of each limb lead, and the average peak voltage of the limb leads is obtained by averaging the peak voltages of each limb lead.

[0054] In one embodiment, the number of peaks and the high-frequency morphology index are determined based on the high-frequency QRS envelope curve of each lead, so as to determine the target number of leads based on the number of peaks and the high-frequency morphology index corresponding to each lead. Alternatively, the high-frequency morphology index is determined based on the high-frequency QRS envelope curve of each lead, leads with a high-frequency morphology index greater than or equal to a second threshold are selected, the number of peaks is determined based on the high-frequency QRS envelope curve of the selected leads, and leads with a number of peaks greater than or equal to a first threshold are further selected and counted to obtain the target number of leads.

[0055] In one embodiment, the high-frequency QRS envelope curve of each lead is analyzed to obtain the total area of ​​each amplitude-decreasing region on the high-frequency QRS envelope curve as the first total area, and the total area below the high-frequency QRS envelope curve as the second total area. The ratio of the first total area to the second total area is used as the high-frequency morphology index of the corresponding lead. Further, if the high-frequency morphology index corresponding to a lead is greater than or equal to a second threshold, indicating a possibility of myocardial ischemia, then the positive indicator of the corresponding lead is determined to be positive; otherwise, the positive indicator of the corresponding lead is determined to be negative. It can be understood that the target number of leads can refer to the number of leads where the number of corresponding peaks exceeds the first threshold and the corresponding positive indicator indicates a positive result.

[0056] In one embodiment, the QRS duration can be determined based on the high-frequency QRS envelope curve of any lead, or the average of the QRS durations corresponding to each lead can be used as the QRS duration for determining the heart failure risk assessment score, or the QRS duration can be determined based on low-frequency ECG data in the resting ECG data, without any limitation.

[0057] S106: Determine the score of the corresponding lead based on the high-frequency morphology index, determine the weight based on the QRS duration, and multiply the sum of the scores of each lead by the weight to obtain the heart failure risk assessment score.

[0058] Specifically, the high-frequency morphological index of each lead is matched with preset index intervals to determine the score for the corresponding lead. The QRS duration is matched with preset time intervals to determine the weight. The scores of all leads are summed, and the product of the sum of the scores and the weight is used as the heart failure risk assessment score. Here, each preset index interval is associated with the score, and each preset time interval is associated with the weight. It can be understood that the heart failure risk assessment score is related to the cardiac function classification; the higher the heart failure risk assessment score, the higher the corresponding cardiac function classification, indicating a greater decline in cardiac function. Heart failure is a manifestation of overall cardiac function decline. Furthermore, the QRS duration is associated with overall cardiac function, and the QRS duration has individual differences. Therefore, by multiplying the weight determined by the QRS duration with the sum of the scores determined by the high-frequency morphological index of each lead, a heart failure risk assessment score with a higher degree of matching to heart failure risk can be obtained.

[0059] For example, the preset index intervals include [10%, 19.9%], [20%, 29.9%], [30%, 39.9%], [40%, 49.9%], and [50%, 100%]. The corresponding scores for these five intervals are 1, 2, 3, 4, and 5, respectively. If the high-frequency morphology index is in the range of [10%, 19.9%], the corresponding lead's score is 1, and so on. In this example, if the high-frequency morphology index is less than 10%, the corresponding lead's score is 0. The preset time limit intervals include [0, 119], [120, 149], and greater than or equal to 150, where the unit is milliseconds (ms). The weights for these three preset time limit intervals are 1, 1.25, and 1.5, respectively.

[0060] S108. If the number of target leads exceeds the third threshold, the heart failure risk assessment level is determined based on the average peak voltage of the limb leads and the heart failure risk assessment score.

[0061] The third threshold can be customized based on actual circumstances, such as 3, and is not specifically limited here. Specifically, the number of target leads can be used to assess the likelihood of heart failure. If the number of target leads is greater than or equal to the third threshold, it indicates a likelihood of heart failure in the subject. The heart failure risk assessment level is then determined based on the average peak voltage of the limb leads and the heart failure risk assessment score. The heart failure risk assessment level is positively correlated with the heart failure risk assessment score and negatively correlated with the average peak voltage of the limb leads. A higher heart failure risk assessment score and a lower average peak voltage in the limb leads result in a higher heart failure risk assessment level. The heart failure risk assessment level is used to characterize the magnitude of the risk of heart failure. A higher risk assessment level indicates a greater risk of heart failure, providing doctors with a reference during the diagnostic process. This allows doctors to efficiently and accurately identify the subject's cardiac health status in conjunction with clinical symptoms, thereby providing further diagnostic or testing recommendations. It is understandable that when outputting the heart failure risk assessment level, at least one of the following can also be output: the number of target leads, the average peak voltage of limb leads, the QRS duration, and the high-frequency morphological index of each lead, for doctors' reference, so that doctors can more efficiently and accurately identify the patient's cardiac health status.

[0062] In one embodiment, if the number of target leads is greater than or equal to a third threshold, the heart failure risk assessment score is compared with each preset score interval, and the average peak voltage of the limb leads is matched with each preset voltage interval to determine the corresponding heart failure risk assessment level. The preset score intervals and preset voltage intervals can be customized according to actual circumstances.

[0063] In one embodiment, a first risk assessment level is determined based on the heart failure risk assessment score, a second risk assessment level is determined based on the average peak voltage in limb leads, and the heart failure risk assessment level is determined based on both the first and second risk assessment levels. When determining the heart failure risk assessment level, the heart failure risk assessment score can be used as the primary reference feature, and the average peak voltage in limb leads as a secondary reference feature. Taking an example where both the first and second risk assessment levels include four grades: if both the first and second risk assessment levels are at grade one, then the heart failure risk assessment level is determined to be grade one; if the first risk assessment level is grade one and the second risk assessment level is grade two, then the heart failure risk assessment level is determined to be grade two; if the first risk assessment level is grade two and the second risk assessment level is grade one, then the heart failure risk level is determined to be grade five, and so on.

[0064] The heart failure risk assessment score is positively correlated with the first risk assessment level; the higher the heart failure risk assessment score, the higher the first risk assessment level. The first risk assessment level corresponds to a preset score range. The first risk assessment level is determined by matching the heart failure risk assessment score with each preset score range. For example, suppose the first risk assessment level includes four progressively higher levels: Level 1, Level 2, Level 3, and Level 4. The preset score ranges corresponding to these four levels are [0, 15], [16, 30], [31, 40], and [41, 100], respectively. If the heart failure risk assessment score is in the range [0, 15], then the first risk assessment level is determined to be Level 1, and so on.

[0065] The average peak voltage of limb leads is negatively correlated with the second risk assessment level; the lower the average peak voltage of limb leads, the higher the second risk assessment level. The second risk assessment level corresponds to a preset voltage range. The second risk assessment level is determined by matching the average peak voltage of limb leads with each preset voltage range. For example, suppose the second risk assessment levels include a first level, a second level, a third level, and a fourth level, with preset voltage ranges corresponding to these four levels being greater than or equal to 5.1, [4.1, 5], [3.1, 4], and [0, 3], respectively, in microvolts (µV). If the average peak voltage of limb leads is greater than or equal to 5.1, then the second risk assessment level is determined to be the first level, and so on.

[0066] The aforementioned ECG data processing method analyzes the high-frequency QRS envelope curve at rest to obtain the number of target leads for assessing the possibility of heart failure, the QRS duration and high-frequency morphology index of each lead for determining the heart failure risk assessment score, and the average peak voltage of limb leads for determining the heart failure risk assessment level in conjunction with the heart failure risk assessment score. Based on the weights determined by the QRS duration and the scores determined by the high-frequency morphology index of each lead, the heart failure risk assessment score is obtained. This method improves the matching degree between the heart failure risk assessment score and the heart failure risk. When the number of target leads exceeds a third threshold, i.e., when the possibility of heart failure is determined, the heart failure risk assessment level is determined based on the heart failure risk assessment score and the average peak voltage of limb leads for physician reference. Therefore, it can more accurately and efficiently assess the heart failure risk for physician reference, enabling physicians to efficiently and accurately identify the patient's cardiac health status in conjunction with clinical symptoms.

[0067] In one embodiment, the above-mentioned ECG data processing method further includes: determining the number of positive leads based on the high-frequency QRS envelope curve; the number of positive leads is the number of leads with a corresponding high-frequency morphological index greater than or equal to a second threshold; determining the heart failure risk assessment level based on the average peak voltage of limb leads and the heart failure risk assessment score, including: determining the heart failure risk assessment level based on the number of positive leads, the average peak voltage of limb leads, and the heart failure risk assessment score.

[0068] The number of positive leads refers to the number of leads with a corresponding high-frequency morphological index greater than or equal to the second threshold; that is, the number of leads whose positive indicators are positive. The number of positive leads is related to cardiomyocyte viability and myocardial ischemia. A higher number of positive leads indicates a greater degree of myocardial ischemia, and a higher number of positive leads indicates a greater degree of decreased cardiomyocyte viability.

[0069] Specifically, the corresponding high-frequency morphological index is determined based on the high-frequency QRS envelope curve of each lead, and the number of positive leads is obtained by screening and counting leads whose corresponding high-frequency morphological index is greater than or equal to the second threshold. Further, the heart failure risk assessment level is determined based on the heart failure risk assessment score and the average peak voltage of the limb leads, combined with the number of positive leads.

[0070] In the above embodiments, myocardial ischemia, myocardial cell viability, cardiac contractile function, and pumping capacity are associated with heart failure. For example, myocardial ischemia and / or decreased myocardial cell viability can cause heart failure, while decreased cardiac contractile function and pumping capacity are manifestations of heart failure. Therefore, by combining the heart failure risk assessment score and the average peak voltage of limb leads with the number of positive leads, a more accurate heart failure risk assessment level can be obtained for doctors' reference, so that doctors can more accurately identify the heart health status of the test subject.

[0071] In one embodiment, determining the heart failure risk assessment level based on the number of positive leads, the average peak voltage of limb leads, and the heart failure risk assessment score includes: determining a first risk assessment level based on the heart failure risk assessment score; determining a second risk assessment level based on the average peak voltage of limb leads; determining a third risk assessment level based on the number of positive leads; and determining the heart failure risk assessment level based on the first, second, and third risk assessment levels.

[0072] Specifically, the heart failure risk assessment level is positively correlated with the heart failure risk assessment score, negatively correlated with the average peak voltage in limb leads, and positively correlated with the number of positive leads. For example, the higher the heart failure risk assessment score, the lower the average peak voltage in limb leads, and the greater the number of positive leads, the higher the heart failure risk assessment level. The heart failure risk assessment score is matched with preset score intervals to determine the first risk assessment level; the average peak voltage in limb leads is matched with preset voltage intervals to determine the second risk assessment level; and the number of positive leads is matched with preset number intervals to determine the third risk assessment level. The final heart failure risk assessment level is determined based on the first, second, and third risk assessment levels.

[0073] In one embodiment, the heart failure risk assessment score is used as the primary reference feature, and the average peak voltage of limb leads and the number of positive leads are used as secondary reference features. For example, if the first, second, and third risk assessment levels are all all level one, then the heart failure risk assessment level is determined to be level one. If the first, second, and third risk assessment levels are all level one, or if the second and third risk assessment levels are all level two, then the heart failure risk assessment level is determined to be level two. If the first, second, and third risk assessment levels are all level two, then the heart failure risk level is determined to be level three, and so on.

[0074] In one embodiment, when determining the heart failure risk assessment level, the reference priority of the average peak voltage in limb leads is higher than the reference priority of the number of positive leads. Taking a first risk assessment level, a second risk assessment level, and a third risk assessment level each comprising four levels as an example, if the first, second, and third risk assessment levels are all level one, then the heart failure risk assessment level is determined to be level one; if the first, second, and third risk assessment levels are level one, then the heart failure risk level is determined to be level two; if the first, second, and third risk assessment levels are all level one, then the heart failure risk level is determined to be level five, and so on.

[0075] The number of positive leads is positively correlated with the third risk assessment level; the more positive leads, the higher the third risk assessment level. The third risk assessment level corresponds to a preset number range. The third risk assessment level is determined by matching the number of positive leads with each preset number range. For example, suppose the third risk assessment levels include progressively higher levels: Level 1, Level 2, Level 3, and Level 4. The preset number ranges corresponding to these four levels are [1, 2], [3, 4], [5, 6], and [7, total number of leads], respectively. The total number of leads refers to the total number of leads used to collect ECG data during resting ECG testing, which can be dynamically determined according to actual needs. If the number of positive leads is in the range [1, 2], then the third risk assessment level is determined to be Level 1, and so on.

[0076] It is understandable that the process of determining the first risk assessment level based on the heart failure risk assessment score and the second risk assessment level based on the average peak voltage of the limb leads can be referred to the corresponding process in each embodiment, and will not be repeated here.

[0077] In the above embodiments, the heart failure risk assessment score, the average peak voltage of limb leads and the number of positive leads are comprehensively considered to assess the heart failure risk, which can provide doctors with a more accurate heart failure risk assessment level for reference, so that doctors can more accurately identify the heart health status of the test subject in combination with clinical symptoms.

[0078] In one embodiment, determining the average peak voltage of limb leads based on the high-frequency QRS envelope curve includes: determining the peak voltage of each limb lead based on the high-frequency QRS envelope curve; and averaging the peak voltages of each limb lead to obtain the average peak voltage of the limb leads.

[0079] Specifically, the peak voltages of each limb lead are obtained by traversing the high-frequency QRS envelope curves of each limb lead. The peak voltage on each high-frequency QRS envelope curve is determined as the peak voltage of the corresponding limb lead, and the average value of the peak voltages of each limb lead is taken as the average peak voltage of the limb lead.

[0080] like Figure 2 As shown, in one embodiment, a schematic diagram of a high-frequency QRS envelope curve is provided. Figure 2 The example shows the high-frequency QRS envelope curve corresponding to limb lead III. The horizontal axis represents time (t) in milliseconds (ms), and the vertical axis represents voltage (U) in microvolts (µV). The high-frequency QRS envelope curve has 2 peaks. Figure 2 The symbol 'a' corresponds to the peak point in the high-frequency QRS envelope curve. The voltage corresponding to this peak point is the peak voltage of lead III for that limb, and the high-frequency morphological index for lead III of that limb is 20.2%. This is understandable. Figure 2 This is for illustrative purposes only and is not intended to limit specific information.

[0081] In the above embodiments, the average peak voltage of limb leads, determined based on the peak voltage of each limb lead, can be used to assess cardiac systolic function and pumping capacity associated with heart failure, so that a more accurate heart failure risk assessment level can be obtained by combining the average peak voltage of limb leads.

[0082] In one embodiment, the above-mentioned electrocardiogram data processing method further includes: acquiring low-frequency electrocardiogram data; analyzing the low-frequency electrocardiogram data to obtain ST segment characteristics; and determining the heart failure risk assessment level based on the average peak voltage of limb leads and the heart failure risk assessment score, including: determining the heart failure risk assessment level based on the average peak voltage of limb leads, the heart failure risk assessment score, and the ST segment characteristics.

[0083] The ST segment characteristics include the ST segment type. The ST segment refers to the segment in low-frequency ECG data from the end of the QRS complex to the beginning of the T wave. The ST segment types include positive, suspected positive, and negative. Specifically, low-frequency ECG data is acquired, the ST segment is extracted from the low-frequency ECG data, the extracted ST segment is analyzed to obtain the corresponding ST segment characteristics, and the heart failure risk assessment level is determined by combining the heart failure risk assessment score and the average peak voltage of the limb leads.

[0084] It is understandable that the specific ST segment characteristics can be obtained by referring to existing technologies for ST segment analysis, which will not be elaborated here. For example, if any of the following three conditions are present, the ST segment characteristics will be determined as a suspected positive result. The following three conditions include: ST segment horizontal or downsloping depression greater than or equal to 0.1mV and lasting less than 2 minutes; ST segment horizontal or downsloping depression greater than or equal to 0.05 to 0.1mV; and ST segment pseudo-horizontal depression of 0.10-0.20mV.

[0085] In one embodiment, in various embodiments where the heart failure risk assessment level is determined based on the number of positive leads, the average peak voltage in limb leads, and the heart failure risk assessment score, the ST segment characteristics are further incorporated into the determination of the heart failure risk assessment level. It is understood that for the same reference characteristics (heart failure risk assessment score, average peak voltage in limb leads, and / or, number of positive leads), the heart failure risk assessment level corresponding to a positive ST segment characteristic is higher than the heart failure risk assessment level corresponding to a suspected positive ST segment characteristic, and the heart failure risk assessment level corresponding to a suspected positive ST segment characteristic is higher than the heart failure risk assessment level corresponding to a negative ST segment characteristic. Specific examples of combining reference characteristics and ST segment characteristics to determine the heart failure risk assessment level are not listed here.

[0086] In one embodiment, low-frequency ECG data can be collected during resting ECG monitoring. The resting ECG data collected during resting ECG monitoring includes both high-frequency and low-frequency ECG data, which can be extracted by analyzing the resting ECG data.

[0087] In the above embodiments, combining ST segment characteristics obtained from low-frequency electrocardiogram data analysis to determine the heart failure risk assessment level can improve the accuracy of heart failure risk assessment.

[0088] In one embodiment, determining the target number of leads based on the high-frequency QRS envelope curve includes: screening leads whose corresponding high-frequency morphology index is greater than or equal to a second threshold based on the high-frequency QRS envelope curve; and determining the total number of leads whose corresponding peak count exceeds a first threshold as the target number of leads.

[0089] Specifically, the high-frequency morphology index of the corresponding lead is determined based on the high-frequency QRS envelope curve, the lead positive index of the corresponding lead is determined based on the high-frequency morphology index, the leads indicating positive results are screened from each lead, the high-frequency QRS envelope curve of each screened lead is analyzed to obtain the corresponding number of peaks, the screened leads are further screened to obtain leads with a number of peaks greater than or equal to a first threshold, and the total number of further screened leads is determined as the target number of leads.

[0090] like Figure 3 As shown, in one embodiment, an electrocardiogram (ECG) data processing method is provided, specifically including the following steps:

[0091] S302, acquire the high-frequency QRS envelope curve in the resting state.

[0092] S304 determines the QRS duration, peak voltage of each limb lead, and high-frequency morphological index of each lead based on the high-frequency QRS envelope curve; leads include limb leads and chest leads.

[0093] S306, filter leads whose corresponding high-frequency morphological index is greater than or equal to the second threshold.

[0094] S308, the total number of leads in the selected leads whose corresponding peak count exceeds the first threshold is determined as the target number of leads.

[0095] S310, the total number of selected leads is determined as the number of positive leads.

[0096] S312 calculates the average peak voltage of each limb lead by averaging the peak voltages of all limb leads.

[0097] S314. Determine the score of the corresponding lead based on the high-frequency morphology index, determine the weight based on the QRS duration, and multiply the sum of the scores of each lead by the weight to obtain the heart failure risk assessment score.

[0098] S316. If the number of target leads exceeds the third threshold, the first risk assessment level is determined based on the heart failure risk assessment score.

[0099] S318, the second risk assessment level is determined based on the average peak voltage of the limb leads.

[0100] S320, the third risk assessment level is determined based on the number of positive leads.

[0101] S322, determine the heart failure risk assessment level based on the first risk assessment level, the second risk assessment level, and the third risk assessment level.

[0102] In the above embodiments, the possibility of heart failure is assessed based on the number of target leads. If the possibility of heart failure is determined, the heart failure risk is assessed based on the number of positive leads associated with myocardial ischemia and myocardial cell viability, the average peak voltage of limb leads associated with cardiac contractile function and pumping ability, and the heart failure risk assessment score associated with the degree of heart failure / cardiac function classification. This allows for a rapid and accurate heart failure risk assessment level for doctors to refer to, so that doctors can accurately identify the patient's cardiac health status in combination with clinical symptoms.

[0103] In one embodiment, the numerical ranges involved in one or more embodiments of this application are merely examples and are not intended to limit the scope of the application.

[0104] It should be understood that, although Figure 1 and Figure 3 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 and Figure 3 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0105] In one embodiment, such as Figure 4 As shown, an electrocardiogram (ECG) data processing device 400 is provided, including: an acquisition module 401, an index determination module 402, and a level determination module 403, wherein:

[0106] Acquisition module 401 is used to acquire the high-frequency QRS envelope curve in the resting state;

[0107] The indicator determination module 402 is used to determine the target number of limb leads with average peak voltage and QRS duration based on the high-frequency QRS envelope curve, as well as the high-frequency morphology index corresponding to each lead; the target number of leads is the number of leads whose corresponding peak number exceeds the first threshold and whose corresponding high-frequency morphology index is greater than or equal to the second threshold; the average peak voltage of limb leads is the average value of the peak voltages corresponding to each limb lead; leads include limb leads and chest leads;

[0108] The indicator determination module 402 is also used to determine the score of the corresponding lead based on the high-frequency morphology index, determine the weight based on the QRS duration, and multiply the sum of the scores of each lead by the weight to obtain the heart failure risk assessment score.

[0109] The rating determination module 403 is used to determine the heart failure risk assessment level based on the average peak voltage of the limb leads and the heart failure risk assessment score if the number of target leads exceeds the third threshold.

[0110] In one embodiment, the index determination module 402 is further configured to determine the number of positive leads based on the high-frequency QRS envelope curve; the number of positive leads is the number of leads with a corresponding high-frequency morphological index greater than or equal to a second threshold; the grade determination module 403 is further configured to determine the heart failure risk assessment grade based on the number of positive leads, the average peak voltage of limb leads, and the heart failure risk assessment score.

[0111] In one embodiment, the rating determination module 403 is further configured to determine a first risk assessment rating based on a heart failure risk assessment score; determine a second risk assessment rating based on the average peak voltage of limb leads; determine a third risk assessment rating based on the number of positive leads; and determine a heart failure risk assessment rating based on the first risk assessment rating, the second risk assessment rating, and the third risk assessment rating.

[0112] In one embodiment, the index determination module 402 is further configured to determine the peak voltage of each limb lead based on the high-frequency QRS envelope curve; and to obtain the average peak voltage of the limb leads by averaging the peak voltages of each limb lead.

[0113] In one embodiment, the acquisition module 401 is further configured to acquire low-frequency electrocardiogram data; the index determination module 402 is further configured to analyze the low-frequency electrocardiogram data to obtain ST segment characteristics; and the grade determination module 403 is further configured to determine the heart failure risk assessment grade based on the average peak voltage of limb leads, the heart failure risk assessment score, and the ST segment characteristics.

[0114] In one embodiment, the index determination module 402 is further configured to screen leads with a corresponding high-frequency morphological index greater than or equal to a second threshold based on the high-frequency QRS envelope curve; and to determine the total number of leads with a corresponding peak number exceeding a first threshold as the target number of leads.

[0115] Specific limitations regarding the ECG data processing device can be found in the limitations of the ECG data processing method described above, and will not be repeated here. Each module in the aforementioned ECG data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0116] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The database stores high-frequency QRS envelope curves in the resting state. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements an electrocardiogram (ECG) data processing method.

[0117] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0118] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0119] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0120] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, 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), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0121] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0122] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method of processing electrocardiographic data, characterized by, The method comprises: obtaining a high-frequency QRS envelope curve in a resting state; determining a target lead number, an average peak voltage of limb leads and a QRS time limit, and a high-frequency morphology index corresponding to each lead according to the high-frequency QRS envelope curve; the target lead number is the number of leads whose corresponding wave peak number exceeds a first threshold value and whose corresponding high-frequency morphology index is greater than or equal to a second threshold value; the average peak voltage of the limb leads is the average of the peak voltages corresponding to each limb lead; the leads include the limb leads and chest leads; determining a score of a corresponding lead according to the high-frequency morphology index, determining a weight according to the QRS time limit, multiplying the sum of the scores of each lead by the weight to obtain a heart failure risk assessment score; if the target lead number exceeds a third threshold value, determining a heart failure risk assessment level according to the average peak voltage of the limb leads and the heart failure risk assessment score.

2. The method of claim 1, wherein, The method further comprises: determining a positive lead number according to the high-frequency QRS envelope curve; the positive lead number is the number of leads whose corresponding high-frequency morphology index is greater than or equal to a second threshold value; determining a heart failure risk assessment level according to the average peak voltage of the limb leads and the heart failure risk assessment score comprises: determining a heart failure risk assessment level according to the positive lead number, the average peak voltage of the limb leads and the heart failure risk assessment score.

3. The method of claim 2, wherein, determining a heart failure risk assessment level according to the positive lead number, the average peak voltage of the limb leads and the heart failure risk assessment score comprises: determining a first risk assessment level according to the heart failure risk assessment score; determining a second risk assessment level according to the average peak voltage of the limb leads; determining a third risk assessment level according to the positive lead number; determining a heart failure risk assessment level according to the first risk assessment level, the second risk assessment level and the third risk assessment level.

4. The method of claim 1, wherein, determining an average peak voltage of limb leads according to the high-frequency QRS envelope curve comprises: determining a peak voltage of each limb lead according to the high-frequency QRS envelope curve; averaging the peak voltages of each limb lead to obtain the average peak voltage of the limb leads.

5. The method of claim 1, wherein, The method further comprises: obtaining low-frequency electrocardio data; analyzing the low-frequency electrocardio data to obtain an ST segment feature; determining a heart failure risk assessment level according to the average peak voltage of the limb leads and the heart failure risk assessment score comprises: determining a heart failure risk assessment level according to the average peak voltage of the limb leads, the heart failure risk assessment score and the ST segment feature.

6. The method according to any one of claims 1 to 5, characterized in that, determining a target lead number according to the high-frequency QRS envelope curve comprises: screening leads whose corresponding high-frequency morphology index is greater than or equal to a second threshold value according to the high-frequency QRS envelope curve; determining the total number of leads whose corresponding wave peak number exceeds a first threshold value in the screened leads as the target lead number.

7. An electrocardiographic data processing apparatus characterized by comprising: The device comprises: an acquisition module configured to acquire a high-frequency QRS envelope curve in a resting state; The index determination module is configured to determine a target lead number, an average peak voltage of limb leads, a QRS time limit, and a high-frequency morphology index corresponding to each lead according to the high-frequency QRS envelope curve; the target lead number is a number of leads with a corresponding wave peak number exceeding a first threshold value and a corresponding high-frequency morphology index greater than or equal to a second threshold value; the average peak voltage of the limb leads is an average of peak voltages corresponding to each limb lead; and the leads include the limb leads and chest leads; The index determination module is further configured to determine a score of a corresponding lead according to the high-frequency morphology index, determine a weight according to the QRS time limit, multiply a sum of the scores of the leads by the weight to obtain a heart failure risk assessment score, and determine a heart failure risk assessment level according to the average peak voltage of the limb leads and the heart failure risk assessment score. The index determination module is further configured to determine a positive lead number according to the high-frequency QRS envelope curve; the positive lead number is a number of leads with a corresponding high-frequency morphology index greater than or equal to a second threshold value.

8. The apparatus of claim 7, wherein, The index determination module is further configured to determine a heart failure risk assessment level according to the positive lead number, the average peak voltage of the limb leads, and the heart failure risk assessment score. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, ​

Images