Electrocardiogram signal processing method, device and related equipment

Abstract

The present application relates to a method, apparatus, and related devices for processing electrocardiographic signals, the method including the steps of: acquiring electrocardiographic signals in a resting state from a first preset number of leads, the leads including a second preset number of limb leads, the second preset number being smaller than the first preset number; performing data processing on each of the electrocardiographic signals in a resting state to acquire a static high-frequency QRS waveform feature set, the static high-frequency QRS waveform feature set including a QRS time limit, a first number of positive indicators, a first number of target leads, and a number of target limb leads; and evaluating and analyzing a risk assessment feature set to obtain a heart failure risk assessment score, the heart failure risk assessment score being used to determine the degree of risk of developing heart failure, the risk assessment feature set including the static high-frequency QRS waveform feature set.

Description

[Technical Field]

[0001] The present application relates to the technical field of electrocardiogram signal processing, and in particular to a method, apparatus, computer device and storage medium for processing electrocardiogram signals.

[0002] (CROSS-REFERENCE TO RELATED APPLICATIONS)

[0003] This application claims priority to a Chinese patent application filed with the China Patent Office on November 21, 2022, bearing application number 2022114516528 and entitled "Method, device and related equipment for processing electrocardiographic signals," the entire contents of which are incorporated herein by reference. [Background technology]

[0004] As socio-economic development improves, people's living standards are rising year by year, and more people are shifting from physical labor to mental labor. As a result, the average time people spend exercising is decreasing year by year, and diseases that were once common among the elderly, such as myocardial infarction and heart failure, are becoming more common among young people.

[0005] Traditional methods generally use blood tests to assess heart failure risk, such as N-terminal pro-B-type natriuretic peptide (NT-proBNP), plasma homocysteine, left ventricular ejection fraction (LVEF), left ventricular end-systolic diameter (LVESD) measured by echocardiography, and the results of a 6-minute walk test. However, these traditional methods for assessing heart failure risk are time-consuming and often result in inaccurate results. Summary of the Invention [Problem to be solved by the invention]

[0006] According to various embodiments disclosed herein, methods, apparatus and related devices for processing electrocardiographic signals are provided. [Means for solving the problem]

[0007] According to a first aspect, there is provided a method for processing electrocardiographic signals, comprising: acquiring resting electrocardiogram signals for a first preset number of leads, the leads including a second preset number of limb leads, the second preset number being less than the first preset number; performing data processing on each resting-state electrocardiogram signal to obtain a static high-frequency QRS waveform feature set, the static high-frequency QRS waveform feature set including a QRS time limit, a first number of positive indicators, a first number of target leads, and a number of target limb leads, the first positive indicator representing that the high-frequency morphology index of the corresponding lead is greater than a first threshold, the high-frequency morphology index is a ratio of a first total area to a second total area of ​​the corresponding lead, the first total area being a total area of ​​each amplitude reduction region of the corresponding resting-state electrocardiogram signal, the second total area being a total area under the envelope of the corresponding resting-state electrocardiogram signal, the first target lead being a lead whose total number of downward trends of the corresponding resting-state electrocardiogram signal exceeds the second threshold, and the target limb lead being a limb lead whose QRS complex voltage of the corresponding resting-state electrocardiogram signal is less than a third threshold; and a step of evaluating and analyzing the risk assessment feature set to obtain a heart failure risk assessment score, the heart failure risk assessment score being used to determine the degree of risk of developing heart failure, the risk assessment feature set including a static high frequency QRS waveform feature set.

[0008] In one embodiment, the risk assessment feature set further includes a dynamic high-frequency QRS waveform feature set, and the method further includes: acquiring an electrocardiogram signal at a stress state of each lead; performing data processing on the electrocardiogram signal at each stress state to obtain a corresponding high-frequency waveform curve; and performing feature analysis on each high-frequency waveform curve to obtain a dynamic high-frequency QRS waveform feature set, wherein the dynamic high-frequency QRS waveform feature set includes at least two of the number of second positive indicators, an initial average voltage value, a maximum output power, and the number of second target leads, and the second positive indicator indicates that the amplitude decrease relative value of the corresponding lead is greater than a fourth threshold; the amplitude drop relative value is the ratio of the amplitude absolute value to the maximum RMS voltage value, which is the difference between the maximum RMS voltage value and the target RMS voltage value, the maximum RMS voltage value being the maximum RMS voltage value of the corresponding high-frequency waveform curve, the target RMS voltage value being the minimum RMS voltage value after the time point corresponding to the maximum RMS voltage value of the corresponding high-frequency waveform curve, the initial average voltage value being the average value of the initial voltage values ​​of each high-frequency waveform curve, the maximum output power being determined based on the maximum root-mean-square voltage values ​​of each high-frequency waveform curve, and the second target lead being the lead at which the corresponding high-frequency waveform curve exhibits the target waveform, which includes a U wave, an L wave, and a small V wave.

[0009] In one embodiment, the step of performing data processing on the electrocardiogram signal in each resting state to obtain a static high-frequency QRS waveform feature set includes the steps of: performing data extraction on the electrocardiogram signal in each resting state to obtain high-frequency components of the static QRS waveform corresponding to each lead; determining each amplitude reduction region corresponding to each lead based on the high-frequency components of the static QRS waveform of each lead to calculate a first total area and a corresponding second total area of ​​each lead; obtaining a high-frequency morphology index for each lead based on a ratio between the first total area and the corresponding second total area of ​​each lead; and calculating the number of first positive indicators based on the high-frequency morphology index for each lead and a first threshold.

[0010] In one embodiment, after the step of determining each amplitude reduced region corresponding to each lead based on the high frequency component of the static QRS waveform of each lead, the method further includes the steps of: calculating the area of ​​each amplitude reduced region corresponding to each lead; calculating the number of target areas for each lead based on the area of ​​each amplitude reduced region corresponding to each lead, where the target area is the area of ​​an amplitude reduced region larger than a fifth threshold; determining the number of target areas for each lead as the total number of corresponding leads; and determining the number of first target leads based on the total number of each lead and the second threshold.

[0011] In one embodiment, the step of evaluating and analyzing the risk assessment feature set to obtain a heart failure risk assessment score includes inputting the risk assessment feature set into a preset risk assessment function or a pre-trained risk assessment network model to obtain a heart failure risk assessment score.

[0012] In one embodiment, the method further includes determining a heart failure risk level based on the heart failure risk assessment score, and outputting heart failure monitoring alarm data in response to the heart failure risk level being greater than a level threshold.

[0013] According to a second aspect, there is provided an electrocardiographic signal processing device, said device comprising: a signal acquisition module for acquiring resting electrocardiogram signals of a first preset number of leads, the leads including a second preset number of limb leads, the second preset number being less than the first preset number; a signal processing module for performing data processing on each resting-state electrocardiogram signal to obtain a static high-frequency QRS waveform feature set, the static high-frequency QRS waveform feature set including a QRS time limit, a number of first positive indicators, a number of first target leads, and a number of target limb leads, the first positive indicator representing that the high-frequency morphology index of the corresponding lead is greater than a first threshold, the high-frequency morphology index is a ratio of a first total area to a second total area of ​​the corresponding lead, the first total area being a total area of ​​each amplitude reduction region of the corresponding resting-state electrocardiogram signal, the second total area being a total area below the envelope of the corresponding resting-state electrocardiogram signal, the first target lead being a lead whose total number of downward trends of the corresponding resting-state electrocardiogram signal exceeds a second threshold, and the target limb lead being a limb lead whose QRS complex voltage of the corresponding resting-state electrocardiogram signal is less than a third threshold; and an evaluation and analysis module that evaluates and analyzes the risk assessment feature set to obtain a heart failure risk assessment score, the heart failure risk assessment score being used to determine the degree of risk of developing heart failure, and the risk assessment feature set including a static high frequency QRS waveform feature set.

[0014] According to a third aspect, there is provided a computing device, the computing device including a memory and a processor, the memory storing computer-readable instructions, the computer-readable instructions, when executed by the processor, performing the method steps of any of the method embodiments described above.

[0015] According to a fourth aspect, there is provided a cardiac signal processing system, the system including an electrocardiogram signal collecting device and a computer device according to any of the above device embodiments, wherein the electrocardiogram signal collecting device is electrically connected to the computer device to collect electrocardiogram signals at each resting state.

[0016] According to a fifth aspect, there is provided a computer-readable storage medium having computer-readable instructions stored thereon that, when executed by a processor, perform the steps of any of the method embodiments described above.

[0017] The details of one or more embodiments of the application are set forth in the drawings and description which follow. Other features and advantages of the application will become apparent from the description, drawings, and claims. [Brief explanation of the drawings]

[0018] In order to more clearly explain the technical solutions of the embodiments of the present application, the following briefly introduces the necessary drawings of the embodiments. The drawings described below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without exerting any effort that amounts to inventive step. [Figure 1] 1 is a diagram illustrating an application environment of a method for processing an electrocardiogram signal according to one embodiment. [Figure 2] 1 is a first schematic flow diagram of a method for processing cardiac signals in one embodiment; [Figure 3] FIG. 1 is a first schematic flow diagram of the steps of performing data processing on each resting-state electrocardiogram signal to obtain a set of static high-frequency QRS waveform features in one embodiment. [Figure 4] FIG. 10 is a second schematic flow diagram of the steps of performing data processing on each resting-state electrocardiogram signal to obtain a static high-frequency QRS waveform feature set in one embodiment. [Figure 5] FIG. 4 is a second schematic flow diagram of a method for processing cardiac signals in one embodiment. [Figure 6] FIG. 10 is a third schematic flow diagram of a method for processing cardiac signals in one embodiment. [Figure 7] FIG. 10 is a fourth schematic flow diagram of a method for processing cardiac signals in one embodiment. [Figure 8] 1 is a structural block diagram of an electrocardiogram signal processing device according to one embodiment. [Figure 9] 1 is a diagram illustrating the internal structure of a computer device according to one embodiment. [Figure 10] 1 is a diagram showing the internal structure of an electrocardiogram signal processing system according to one embodiment. [Figure 11] FIG. 1 is a schematic diagram of an amplitude reduction region in one embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0019] In order to make the technical solutions and advantages of the present application more comprehensible, the present application will be described in detail below in conjunction with drawings and examples, wherein the specific examples described do not limit the present application but are merely used to interpret the present application.

[0020] In order to facilitate understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. The drawings illustrate examples of the present application. However, the present application is not limited to the examples set forth herein, and may be embodied in many different forms. These examples are provided to make the disclosure of the present application more thorough and complete.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terms used herein do not limit the present application, but are used merely to describe specific examples.

[0022] As used in this specification, the singular forms "a," "an," and "said" may include the plural forms unless the context clearly dictates otherwise. Also, terms such as "comprises" or "comprising" specify the presence of stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not exclude the presence or possible addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. Also, as used herein, the term "and / or" includes any and all combinations of the associated items.

[0023] The electrocardiogram signal processing method provided in this application is applicable to the application environment shown in Fig. 1. The terminal 102 communicates with the server 104 via a network. The terminal 102 may be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices, and the server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0024] In the first aspect, as shown in FIG. 2, a method for processing an electrocardiogram signal is provided, and the method is described as being applied to the terminal of FIG. 1 as an example, and includes the following steps 202 to 206.

[0025] Step 202: Acquire resting electrocardiogram signals of a first preset number of leads.

[0026] The first preset number of leads includes a second preset number of limb leads, the second preset number being smaller than the first preset number. An electrocardiographic signal collecting device electrically connected to the terminal is arranged to collect electrocardiographic signals in a resting state of the first preset number of leads, so that the terminal can obtain the electrocardiographic signals in a resting state of the first preset number of leads through the electrocardiographic signal collecting device.

[0027] In a specific example, the first preset number of leads further includes a third preset number of chest leads, the third preset number being the difference between the first preset number and the second preset number. Here, the first preset number of leads may be 12 leads, the 12 leads including 6 chest leads and 6 limb leads, or the first preset number of leads may further be 18 leads, the 18 leads including 12 chest leads and 6 limb leads. The above are only specific examples and can be flexibly applied according to user needs in actual applications, and are not limited here.

[0028] Step 204: Perform data processing on each resting state electrocardiogram signal to obtain a static high frequency QRS waveform feature set.

[0029] The static high frequency QRS waveform feature set includes a QRS time limit, a number of first positive indicators, a number of first target leads, and a number of target limb leads.

[0030] Specifically, the QRS time limit is the time taken from the start to the end of the q wave, r wave, and s wave in an electrocardiogram generated based on the electrocardiogram signal of each lead in a resting state, and represents the overall cardiac function status corresponding to the electrocardiogram signal of each lead in a resting state.

[0031] In a specific example, the QRS time limit threshold may be, but is not limited to, 0.12 seconds, and if the QRS time limit is greater than the QRS time limit threshold, it indicates that there is an abnormality in the electrocardiogram generated based on the electrocardiogram signals in the resting state of each lead, and if the QRS time limit is equal to or less than the QRS time limit threshold, it indicates that the electrocardiogram generated based on the electrocardiogram signals in the resting state of each lead is normal. The above is only a specific example, and can be flexibly applied according to the needs of users in actual applications, and is not limited here.

[0032] Specifically, the high-frequency morphology index is the ratio of the first total area to the second total area of ​​the corresponding lead. The first total area is the total area of ​​each amplitude reduction region of the corresponding resting-state electrocardiogram signal, and the second total area is the total area under the envelope of the corresponding resting-state electrocardiogram signal. A first positive index indicates that the high-frequency morphology index of the corresponding lead is greater than a first threshold, indicating that the resting-state electrocardiogram signal of the corresponding lead is abnormal. Conversely, a first negative index indicates that the high-frequency morphology index of the corresponding lead is less than the first threshold, indicating that the resting-state electrocardiogram signal of the corresponding lead is normal. The number of first positive indexes indicates the overall degree of myocardial ischemia corresponding to the resting-state electrocardiogram signal of each lead. That is, a larger number of first positive indexes indicates a greater risk of myocardial ischemia overall corresponding to the resting-state electrocardiogram signal of each lead.

[0033] In a specific example, the first threshold is determined based on the age of the ECG signal collector. If the age of the ECG signal collector is over 50, the first threshold may be, but is not limited to, 8%. If the age of the ECG signal collector is under 50, the first threshold may be, but is not limited to, 15%. The first threshold may be the average value of the target high-frequency morphology index or 20% thereof, thereby further improving the accuracy of the heart failure risk assessment score. The target high-frequency morphology index is the top three high-frequency morphology indexes when each high-frequency morphology index is sorted in descending order. The above are only specific examples and can be flexibly applied according to user needs in actual applications, and are not limited herein.

[0034] Specifically, the first target lead is a lead for which the total number of times the corresponding resting electrocardiogram signal shows a downward trend exceeds a second threshold. That is, if the total number of times the corresponding resting electrocardiogram signal shows a downward trend exceeds the second threshold, the lead corresponding to the corresponding resting electrocardiogram signal is determined as the first target lead. The number of first target leads represents the overall heart failure risk corresponding to the resting electrocardiogram signal of each lead. Furthermore, a downward trend in the corresponding resting electrocardiogram signal indicates the appearance of a reduced amplitude zone (RAZ) in the QRS waveform of the corresponding resting electrocardiogram signal. As shown in FIG. 11 , the reduced amplitude zone refers to a concave region S formed between midpoint A and point B of the QRS waveform of the corresponding resting electrocardiogram signal. In a specific example, by collecting statistics of the peak values ​​of each amplitude reduction region of the corresponding electrocardiogram signal in the resting state, the total number of peak values ​​of the corresponding electrocardiogram signal in the resting state is determined as the total number of times the corresponding electrocardiogram signal in the resting state is on a downward trend. The total number of times the electrocardiogram signal in the resting state corresponding to each lead is on a downward trend is collected, and the total number of times the electrocardiogram signal in the resting state corresponding to each lead is on a downward trend is compared with a second threshold, and the number of leads in which the total number of times the corresponding electrocardiogram signal in the resting state is on a downward trend exceeds the second threshold, i.e., the number of first target leads, can be obtained. The above is merely a specific example, and can be flexibly applied according to user needs in actual applications, and is not limited herein.

[0035] Specifically, the target limb lead is a limb lead whose corresponding resting electrocardiogram signal has a QRS complex voltage smaller than a third threshold. That is, if the QRS complex voltage of the corresponding resting electrocardiogram signal is smaller than the third threshold, the lead corresponding to the corresponding resting electrocardiogram signal is determined as the target limb lead. The number of target limb leads indicates the overall risk of worsening heart failure corresponding to the resting electrocardiogram signal of each lead.

[0036] In a specific example, the third threshold is determined based on the QRS complex voltage of the electrocardiogram signal in a resting state corresponding to each chest lead. The above is only a specific example, and can be flexibly applied according to the needs of users in actual applications, and is not limited here.

[0037] Here, by performing data processing on each resting electrocardiogram signal, a static high-frequency QRS waveform feature set can be obtained, which includes the QRS limit time, the number of first positive indicators, the number of first target leads, and the number of target limb leads.

[0038] In one embodiment, as shown in FIG. 3, performing data processing on each resting-state electrocardiogram signal to obtain a static high-frequency QRS waveform feature set includes the following steps.

[0039] Step 301: Perform data extraction on each resting-state electrocardiogram signal to obtain the high-frequency components of the static QRS waveform of the corresponding lead.

[0040] Step 302: Determine each amplitude reduction region corresponding to each lead based on the high frequency components of the static QRS waveform of each lead, and calculate a first total area and a corresponding second total area of ​​each lead.

[0041] Step 303: Obtain a high frequency morphology index for each lead based on the ratio between the first total area of ​​each lead and the corresponding second total area.

[0042] Step 304: Calculate the number of first positive indicators based on the high frequency morphology index of each lead and the first threshold.

[0043] The terminal performs data extraction on the electrocardiogram signal in each resting state to obtain the high-frequency component of the static QRS waveform of the corresponding lead, and determines each amplitude reduction region corresponding to each lead based on the high-frequency component of the static QRS waveform of each lead, and calculates the first total area of ​​each lead and the corresponding second total area based on each amplitude reduction region corresponding to each lead, and then calculates the ratio between the first total area of ​​each lead and the corresponding second total area to obtain the high-frequency morphology index of each lead, and finally, calculates the number of first positive indicators based on the comparison result between the high-frequency morphology index of each lead and the first threshold.

[0044] In this embodiment, data extraction is performed on each resting electrocardiogram signal to obtain the high-frequency components of the static QRS waveform of the corresponding lead; that is, the accurate number of first positive indicators can be obtained from the high-frequency components of the static QRS waveform of each lead, and the number of leads in which abnormalities appear in the resting electrocardiogram signal of the corresponding lead can be known from the number of first positive indicators, so that the risk assessment feature set and heart failure risk assessment score can be easily obtained.

[0045] In one embodiment, as shown in FIG. 4, after the step of determining each amplitude reduction region corresponding to each lead based on the high frequency component of the static QRS waveform of each lead, the method further includes the following steps:

[0046] Step 401: Calculate the area of ​​each amplitude reduction region corresponding to each lead.

[0047] Step 402: Calculate the number of target areas for each lead based on the area of ​​each amplitude reduction region corresponding to each lead.

[0048] Step 403: Determine the number of target areas for each lead to the total number of corresponding leads.

[0049] Step 404: Determine the number of first target leads based on the total number of each lead and the second threshold.

[0050] The target area refers to the area of ​​the amplitude reduction region greater than the fifth threshold. The terminal determines each amplitude reduction region corresponding to each lead based on the high-frequency component of the static QRS waveform of each lead, calculates the area of ​​each amplitude reduction region corresponding to each lead, and determines the area of ​​the amplitude reduction region greater than the fifth threshold as the target area. Then, the terminal calculates the number of target areas for each lead based on the area of ​​each amplitude reduction region corresponding to each lead, and determines the number of target areas for each lead as the total number of times the electrocardiogram signal in the resting state of the corresponding lead is on a downward trend. Finally, the terminal determines the number of first target leads based on the result of comparing the total number of times for each lead with the second threshold.

[0051] In this embodiment, the number of target areas for each lead is calculated from the area of ​​each amplitude reduction region corresponding to each lead, thereby accurately obtaining the total number of times that the electrocardiogram signal in each resting state is on a downward trend, and then the number of first target leads is determined to evaluate and analyze the risk assessment feature set, thereby improving the convenience of obtaining a heart failure risk assessment score.

[0052] Step 206: Evaluate and analyze the risk assessment feature set to obtain a heart failure risk assessment score.

[0053] The heart failure risk assessment score is used to determine the degree of risk of developing heart failure, and the risk assessment feature set includes a static high-frequency QRS waveform feature set. The terminal evaluates and analyzes the risk assessment feature set to obtain a heart failure risk assessment score, thereby enabling the terminal to accurately understand the degree of risk of developing heart failure.

[0054] Based on this, in the above-mentioned electrocardiogram signal processing method, a resting state electrocardiogram signal of a first preset number of leads is acquired, and data processing is performed on each resting state electrocardiogram signal to obtain a static high-frequency QRS waveform feature set, and then a risk assessment feature set is evaluated and analyzed to obtain a heart failure risk assessment score, thereby accurately understanding the degree of risk of developing heart failure.Furthermore, after processing the electrocardiogram signal, a complete and comprehensive static high-frequency QRS waveform feature set and a risk assessment feature set are obtained, and the degree of risk of developing heart failure is directly understood through the heart failure risk assessment score, thereby avoiding the need to jointly assess the risk of heart failure using multiple detection data as in traditional methods, reducing the time required for heart failure risk assessment, and improving the efficiency of heart failure risk assessment.

[0055] In one embodiment, the risk assessment feature set further includes a dynamic high frequency QRS waveform feature set, as shown in Figure 5. The above method further includes the following steps.

[0056] Step 501: Acquire an electrocardiogram signal in a load state for each lead.

[0057] Step 502: Data processing is performed on the electrocardiogram signals under each load condition to obtain corresponding high frequency waveform curves.

[0058] Step 503: Perform feature analysis on each high frequency waveform curve to obtain a dynamic high frequency QRS waveform feature set.

[0059] The electrocardiographic signals under stress conditions include electrocardiographic signals under resting conditions, exercise conditions, and recovery conditions. An electrocardiographic signal collecting device electrically connected to the terminal is arranged to collect electrocardiographic signals under stress conditions for a first preset number of leads. The terminal acquires the electrocardiographic signals under stress conditions for each lead using the electrocardiographic signal collecting device, and performs data processing on the electrocardiographic signals under stress conditions for each lead to obtain corresponding high-frequency waveform curves. Then, it performs feature analysis on each high-frequency waveform curve to obtain a dynamic high-frequency QRS waveform feature set.

[0060] In a specific example, the step of performing feature analysis on each high frequency waveform curve to obtain a dynamic high frequency QRS waveform feature set includes the steps of: performing feature point extraction on each high frequency waveform curve to obtain corresponding target feature points; and performing feature extraction based on the corresponding target feature points to obtain a dynamic high frequency QRS waveform feature set. The above is only a specific example, and can be flexibly applied according to user needs in actual applications, and is not limited here.

[0061] Specifically, the dynamic high-frequency QRS waveform feature set includes at least two of the number of second positive indicators, the initial mean voltage value, the maximum output power, and the number of second target leads, where the greater the number of features in the dynamic high-frequency QRS waveform feature set, the more comprehensive the data for evaluating and analyzing the risk assessment feature set and the more accurate the heart failure risk assessment score.

[0062] The amplitude drop relative value is the ratio of the amplitude absolute value to the maximum RMS voltage value, which is the difference between the maximum RMS voltage value and the target RMS voltage value, where the maximum RMS voltage value is the maximum RMS voltage value of the corresponding high-frequency waveform curve, and the target RMS voltage value is the minimum RMS voltage value after the time point corresponding to the maximum RMS voltage value of the corresponding high-frequency waveform curve. Here, the second positive indicator means that the amplitude drop relative value of the corresponding lead is greater than the fourth threshold, and conversely, the second negative indicator indicates that the amplitude drop relative value of the corresponding lead is equal to or less than the fourth threshold. The number of second positive indicators represents the overall degree of myocardial ischemia corresponding to the ECG signal under stress conditions in each lead, i.e., the higher the number of second positive indicators, the greater the risk of myocardial ischemia.

[0063] Specifically, the initial average voltage value is the average value of the initial voltage values ​​of each high-frequency waveform curve, and represents whether there is an abnormality in the overall cardiac pumping function corresponding to the ECG signal under the load state of each lead. The initial voltage value is the voltage value at the initial point of the high-frequency waveform curve. The maximum output power is determined based on the maximum root-mean-square voltage value of each high-frequency waveform curve, and represents the overall cardiac pumping ability corresponding to the ECG signal under the load state of each lead.

[0064] The second target leads are leads whose corresponding high-frequency waveform curves exhibit target waveforms, including U waves, L waves, and small V waves. The number of second target leads represents the severity of coronary artery stenosis corresponding to the ECG signal of each lead under stress.

[0065] In this embodiment, the electrocardiogram signals of each lead under stress conditions are obtained, and then data processing is performed on the electrocardiogram signals under each stress condition to obtain corresponding high-frequency waveform curves. Feature analysis is then performed on each high-frequency waveform curve to obtain a dynamic high-frequency QRS waveform feature set. This allows the static high-frequency QRS waveform feature set and the dynamic high-frequency QRS waveform feature set to be jointly evaluated and analyzed, and a more accurate heart failure risk assessment score is obtained from the electrocardiogram signals of each lead under stress conditions and at rest, further improving the accuracy and convenience of heart failure risk assessment.

[0066] In one embodiment, as shown in FIG. 6, evaluating and analyzing the risk assessment feature set to obtain a heart failure risk assessment score includes step 601 .

[0067] Step 601: Input the risk assessment feature set into a preset risk assessment function or a pre-trained risk assessment network model to obtain a heart failure risk assessment score.

[0068] The terminal pre-stores a preset risk assessment function or a pre-trained risk assessment network model, and when a set of risk assessment features is input into the preset risk assessment function, a corresponding heart failure risk assessment score can be output from the risk assessment function, and / or when a set of risk assessment features is input into the pre-trained risk assessment network model, a corresponding heart failure risk assessment score can be output from the risk assessment network model.

[0069] In a specific example, the first heart failure risk assessment subscore is obtained based on the following formula:

number

[0070] Obtain a second heart failure risk assessment subscore based on the following formula: α(c)=c α(c) is the second heart failure risk assessment subscore, and c is the number of first positive indicators.

[0071] Obtain a third heart failure risk assessment subscore based on the following formula: β(v)=5v β(v) is the third heart failure risk assessment subscore, and v is the number of the first target lead.

[0072] Obtain a fourth heart failure risk assessment subscore based on the following formula: χ(b)=3b χ(b) is the fourth heart failure risk assessment subscore, and b is the number of target limb leads.

[0073] Obtain a fifth heart failure risk assessment subscore based on the following formula: δ(n)=n δ(n) is the fifth heart failure risk assessment subscore, and n is the number of positive second indicators.

[0074] Obtain the sixth heart failure risk assessment subscore based on the following formula: ε(m)=10m(m>2) ε(m) is the sixth heart failure risk assessment subscore, and m is the initial mean voltage value.

[0075] Obtain a seventh heart failure risk assessment subscore based on the following formula:

number

[0076] Obtain an eighth heart failure risk assessment subscore based on the following formula:

number

[0077] Obtain a heart failure risk assessment score based on the following risk assessment function formula:

number

[0078] In a specific example, the eighth heart failure risk assessment subscore is further obtained based on the following formula:

number

[0079] In one embodiment, as shown in FIG. 7, the above method further includes step 701 and step 702.

[0080] Step 701: Determine a heart failure risk level based on a heart failure risk assessment score.

[0081] Step 702: In response to the heart failure risk level being greater than the level threshold, output heart failure monitoring alarm data.

[0082] The terminal evaluates and analyzes the risk assessment feature set to obtain a heart failure risk assessment score, and determines a heart failure risk level based on the heart failure risk assessment score, and then outputs heart failure monitoring alarm data in response to the heart failure risk level being greater than a level threshold.

[0083] In this embodiment, a heart failure risk level is determined based on the heart failure risk assessment score, and heart failure monitoring alarm data is output in response to the heart failure risk level being greater than the level threshold, thereby allowing the electrocardiogram signal collector to know his or her heart failure risk in a timely manner and improving the convenience of the electrocardiogram signal processing method.

[0084] In one embodiment, determining a heart failure risk level based on the heart failure risk assessment score includes determining a heart failure risk level based on an interval in which the heart failure risk assessment score is located.

[0085] The above ranges include a first preset score range, a second preset score range, and a third preset score range, wherein the upper limit of the first preset score range is equal to or less than the lower limit of the second preset score range, and the upper limit of the second preset score range is equal to or less than the lower limit of the third preset score range.

[0086] The heart failure risk levels include a first level, a second level, and a third level. If the heart failure risk assessment score falls within a first preset score interval, the terminal determines the heart failure risk level to be the first level, which indicates that the ECG signal collector has a low risk of heart failure and that rehabilitation exercise therapy is effective or the intensity of the rehabilitation exercise therapy program can be reduced. If the heart failure risk assessment score falls within a second preset score interval, the terminal determines the heart failure risk level to be the second level, which indicates that the ECG signal collector has a moderate risk of heart failure and that rehabilitation exercise therapy should be continued or the intensity of the rehabilitation exercise therapy program should be reduced until the heart failure risk assessment score falls within the first preset score interval. If the heart failure risk assessment score falls within the third preset score range, the terminal determines the heart failure risk level to be the third level, which indicates that the ECG signal collector has a high risk of heart failure and that rehabilitation exercise therapy is ineffective, or that the intensity of the rehabilitation exercise therapy program should be reduced for a while and then gradually increased after getting used to it.

[0087] In this embodiment, the heart failure risk level is determined based on the location of the heart failure risk assessment score, thereby accurately determining the heart failure risk level of the person whose electrocardiogram signal is collected, and conveniently knowing the effect of the rehabilitation exercise therapy and adjusting the intensity of the rehabilitation exercise therapy program.

[0088] Here, although the steps in the flowcharts of Figures 2 to 7 are displayed sequentially according to the direction of the arrows, these steps are not necessarily performed sequentially according to the order of the arrows. Unless explicitly stated herein, there are no strict order restrictions on the execution of these steps, and they may be performed in other orders. Furthermore, at least some of the steps in Figures 2 to 7 may include multiple substeps or multiple steps, and these substeps or steps may not necessarily be performed and completed at the same time but may be performed at different times. The order in which these substeps or steps are performed is also not necessarily sequential, and they may be performed in order or alternately with other steps, substeps of other steps, or at least some of the steps.

[0089] In one embodiment, as shown in FIG. 8, there is provided a cardiac signal processing device, the device comprising: a signal acquisition module 810 for acquiring resting electrocardiogram signals of a first preset number of leads, the leads including a second preset number of limb leads, the second preset number being less than the first preset number; a signal processing module 820 for performing data processing on each resting-state electrocardiogram signal to obtain a static high-frequency QRS waveform feature set, the static high-frequency QRS waveform feature set including a QRS time limit, a first number of positive indicators, a first number of target leads, and a number of target limb leads, the first positive indicator representing that the high-frequency morphology index of the corresponding lead is greater than a first threshold, the high-frequency morphology index being a ratio of a first total area to a second total area of ​​the corresponding lead, the first total area being a total area of ​​each amplitude reduction region of the corresponding resting-state electrocardiogram signal, the second total area being a total area under the envelope of the corresponding resting-state electrocardiogram signal, the first target lead being a lead whose total number of downward trends of the corresponding resting-state electrocardiogram signal exceeds a second threshold, and the target limb lead being a limb lead whose QRS complex voltage of the corresponding resting-state electrocardiogram signal is less than a third threshold; and an evaluation analysis module 830 that evaluates and analyzes the risk assessment feature set to obtain a heart failure risk assessment score, the heart failure risk assessment score being for determining the degree of risk of developing heart failure, and the risk assessment feature set including a static high frequency QRS waveform feature set.

[0090] In one embodiment, the risk assessment feature set further includes a dynamic high-frequency QRS waveform feature set, and the signal acquisition module 810 further acquires electrocardiogram signals in stress states of each lead. The signal processing module 820 further performs data processing on the electrocardiogram signals in each stress state to obtain corresponding high-frequency waveform curves, and the signal processing module 820 further performs feature analysis on each high-frequency waveform curve to obtain a dynamic high-frequency QRS waveform feature set, the dynamic high-frequency QRS waveform feature set including the number of second positive indicators, an initial average voltage value, a maximum output power, and the number of second target leads, the second positive indicators representing that the amplitude drop relative value of the corresponding lead is greater than a fourth threshold, the amplitude drop relative value is the ratio of the amplitude absolute value to the maximum RMS voltage value, and the amplitude absolute value is the difference between the maximum RMS voltage value and the target RMS voltage value, where the maximum RMS voltage value is the maximum value of the RMS voltage of the corresponding high-frequency waveform curve, the target RMS voltage value is the minimum value of the RMS voltage after the time point corresponding to the maximum RMS voltage value of the corresponding high-frequency waveform curve, the initial average voltage value is the average value of the initial voltage values ​​of each high-frequency waveform curve, the maximum output power is determined based on the maximum root-mean-square voltage values ​​of each high-frequency waveform curve, and the second target lead is the lead at which the corresponding high-frequency waveform curve exhibits the target waveform, which includes a U wave, an L wave, and a small V wave.

[0091] In one embodiment, the signal processing module 820 includes a signal processing unit, which performs data extraction on the electrocardiogram signal in each resting state to obtain high-frequency components of the static QRS waveform of the corresponding lead; the signal processing unit further determines each amplitude reduction region corresponding to each lead based on the high-frequency components of the static QRS waveform of each lead to calculate a first total area and a corresponding second total area of ​​each lead; the signal processing unit further obtains a high-frequency morphology index of each lead based on the ratio of the first total area to the corresponding second total area of ​​each lead; and the signal processing unit further calculates the number of first positive indicators based on the high-frequency morphology index of each lead and a first threshold.

[0092] In one embodiment, the signal processing unit further calculates the area of ​​each amplitude reduction region corresponding to each lead, and the signal processing unit further calculates the number of target areas of each lead based on the area of ​​each amplitude reduction region corresponding to each lead, where the target area is the area of ​​the amplitude reduction region larger than a fifth threshold, and the signal processing unit further determines the number of target areas of each lead to be the total number of corresponding leads, and the signal processing unit further determines the number of first target leads based on the total number of each lead and the second threshold.

[0093] In one embodiment, the assessment analysis module 830 includes an assessment analysis unit that inputs the risk assessment feature set into a preset risk assessment function or a pre-trained risk assessment network model to obtain a heart failure risk assessment score.

[0094] In one embodiment, the device comprises: a risk level determination module that determines a heart failure risk level based on the heart failure risk assessment score; and a risk alert module that outputs heart failure monitoring alert data in response to the heart failure risk level being greater than the level threshold.

[0095] For specific limitations of the electrocardiogram signal processing device, please refer to the limitations of the electrocardiogram signal processing method above, and no further details will be provided here. Each module in the above electrocardiogram signal processing device may be realized in whole or in part by software, hardware, or a combination thereof. Each module may be embedded in a processor in a computer device in the form of hardware, or may be independent of the processor in a computer device, or may be stored in a memory in a computer device in the form of software and called by the processor to perform the operations corresponding to each module.

[0096] In one embodiment, a computer device 900 is provided, which may be a terminal. The internal structure of the computer device 900 is shown in FIG. 9. The computer device 900 includes a processor, memory, a network interface, a display, and an input device, all connected by a system bus. The processor of the computer device 900 provides computing and control functions. The memory of the computer device 900 includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer-readable instructions. The internal memory provides an environment for the execution of the operating system and computer-readable instructions in the non-volatile storage medium. The network interface of the computer device 900 connects to and communicates with an external terminal via a network. When the computer-readable instructions are executed by the processor, a method for processing electrocardiogram signals is realized. The display of the computer device 900 may be a liquid crystal display or an electronic paper display. The input device of the computer device 900 may be a touch panel covering the display, or a button, trackball, or touch panel mounted on the housing of the computer device 900. It may also be an external keyboard, touch panel, mouse, etc.

[0097] As can be understood by those skilled in the art, the structure of FIG. 9 is merely a block diagram of some structures related to the solution of the present application, and does not limit the computer device 900 to which the solution of the present application is applied. In particular, the computer device 900 may include more or fewer components than those shown, or may combine some components, or may have a different component arrangement.

[0098] According to a third aspect, there is provided a computing device 900, the computing device including a memory and a processor, the memory storing computer-readable instructions, the processor executing the computer-readable instructions to implement the steps of any of the method embodiments described above.

[0099] According to a fourth aspect, there is provided a cardiac signal processing system, as shown in FIG. 10, said system including a cardiac signal collecting device 1010 and a computing device 900 of any of the device embodiments described above. The electrocardiogram signal collecting device 1010 is electrically connected to the computer device 900 to collect electrocardiogram signals at each resting state.

[0100] In this embodiment, the heart failure risk assessment system described above can directly obtain a heart failure risk assessment score, that is, accurately understand the degree of risk of developing heart failure. Furthermore, directly understanding the degree of risk of developing heart failure through the heart failure risk assessment score avoids the need for joint heart failure risk assessment using multiple detection data as in the traditional method, thereby reducing the time required for heart failure risk assessment and improving the efficiency of heart failure risk assessment.

[0101] In one embodiment, the cardiac signal acquisition device 1010 further acquires cardiac signals at each loading condition.

[0102] According to a fifth aspect, there is provided a computer-readable storage medium having computer-readable instructions stored thereon that, when executed by a processor, perform the steps of any of the method embodiments described above.

[0103] As will be understood by those skilled in the art, all or part of the steps in the above-described method embodiments can be achieved by instructing relevant hardware with computer-readable instructions, which are stored in a non-volatile computer-readable storage medium and, when executed, produce the steps of the above-described method embodiments. Any references to memory, storage devices, databases, or other media used in the embodiments provided in this application include both non-volatile and / or volatile memory. Non-volatile memory includes read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), and flash memory. Volatile memory includes random access memory (RAM) and external cache memory. By way of illustration and not limitation, RAM may be in several forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0104] The technical features of the above embodiments may be combined in any manner. For the sake of simplicity, not all possible combinations of the technical features in the above embodiments are described. However, any combination of these technical features that is not contradictory should fall within the scope of this specification.

[0105] The above examples only represent some embodiments of the present application, and the descriptions are specific and detailed, but do not limit the patent scope of the invention. Those skilled in the art may make some modifications and improvements without departing from the concept of the present application, and all of these fall within the scope of protection of the present application. Therefore, the patent scope of the present application should be determined based on the appended claims.

Claims

1. 1. A method for processing an electrocardiogram signal, said method comprising: acquiring resting electrocardiogram signals for a first preset number of leads, the leads including a second preset number of limb leads, the second preset number being less than the first preset number; performing data processing on each of the resting-state electrocardiogram signals to obtain a static high frequency QRS waveform feature set, the static high frequency QRS waveform feature set including a QRS time limit, a first number of positive indicators, a first number of target leads, and a number of target limb leads, the first positive indicator representing that a high frequency morphology index corresponding to the lead is greater than a first threshold, the high frequency morphology index being a ratio of a first total area to a second total area of ​​the corresponding lead, the first total area being a total area of ​​each amplitude reduction region of the corresponding resting-state electrocardiogram signal, the second total area being a total area below an envelope of the corresponding resting-state electrocardiogram signal, the first target lead being the lead for which the total number of times the corresponding resting-state electrocardiogram signal is on a downward trend exceeds a second threshold, and the target limb lead being the limb lead for which a QRS complex voltage of the corresponding resting-state electrocardiogram signal is less than a third threshold; evaluating and analyzing a risk assessment feature set to obtain a heart failure risk assessment score, the heart failure risk assessment score being used to determine a degree of risk of developing heart failure, the risk assessment feature set including the static high frequency QRS waveform feature set; performing data processing on each of the resting-state electrocardiogram signals to obtain a set of static high-frequency QRS waveform features; performing data extraction on each of the resting-state electrocardiogram signals to obtain high frequency components of a static QRS waveform in the corresponding lead; determining each of the amplitude-reduced regions corresponding to each of the leads based on high-frequency components of a static QRS waveform of each of the leads, and calculating the first total area and the corresponding second total area of ​​each of the leads; obtaining the high frequency morphology index for each of the leads based on a ratio between the first total area of ​​each of the leads and the corresponding second total area; Counting the number of first positive indicators based on the high frequency morphology index of each lead and the first threshold; calculating the area of ​​each of the amplitude reduction regions corresponding to each of the leads; Counting the number of target areas of each of the leads based on the area of ​​each of the amplitude reduction regions corresponding to each of the leads, wherein the target areas are areas of the amplitude reduction regions that are greater than a fifth threshold; determining the number of target areas for each of the leads to the total number of the corresponding leads; determining the number of the first target leads based on the total number of each lead and the second threshold.

2. The risk assessment feature set further comprises a dynamic high frequency QRS waveform feature set, and the method further comprises: acquiring an electrocardiogram signal in a load state for each of the leads; performing data processing on the electrocardiogram signals under each of the stress conditions to obtain corresponding high frequency waveform curves; and performing a feature analysis on each of the high frequency waveform curves to obtain the dynamic high frequency QRS waveform feature set, wherein the dynamic high frequency QRS waveform feature set includes at least two of a number of second positive indicators, an initial mean voltage value, a maximum output power, and a number of second target leads, wherein the second positive indicator represents that a relative amplitude drop value of a corresponding lead is greater than a fourth threshold, the relative amplitude drop value is a ratio of an absolute amplitude value to a maximum RMS voltage value, the absolute amplitude value is a difference between the maximum RMS voltage value and a target RMS voltage value, and the maximum RMS voltage value is a value greater than a fourth threshold. the target RMS voltage value is the minimum RMS voltage value after a time point corresponding to the maximum RMS voltage value of the corresponding high frequency waveform curve; the initial average voltage value is the average of the initial voltage values ​​of each of the high frequency waveform curves; the maximum output power is determined based on the maximum root mean square voltage value of each of the high frequency waveform curves; the second target lead is the lead at which the corresponding high frequency waveform curve exhibits a target waveform, the target waveform including a U wave, an L wave, and a small V wave.

3. The step of evaluating and analyzing the risk assessment feature set to obtain a heart failure risk assessment score includes: The method of any one of claims 1 to 2, characterized in that it includes a step of inputting the risk assessment feature set into a preset risk assessment function or a pre-trained risk assessment network model to obtain the heart failure risk assessment score.

4. The method comprises: determining a heart failure risk level based on the heart failure risk assessment score; The method according to any one of claims 1 to 2, further comprising the step of outputting heart failure monitoring alarm data in response to the heart failure risk level being greater than a level threshold.

5. 1. An electrocardiogram signal processing device, comprising: a signal acquisition module for acquiring resting state electrocardiogram signals for a first preset number of leads, the leads including a second preset number of limb leads, the second preset number being less than the first preset number; a signal processing module that performs data processing on each of the resting-state electrocardiogram signals to obtain a static high frequency QRS waveform feature set, the static high frequency QRS waveform feature set including a QRS time limit, a first number of positive indicators, a first number of target leads, and a number of target limb leads, the first positive indicator representing that a high frequency morphology index of the corresponding lead is greater than a first threshold, the high frequency morphology index being a ratio of a first total area to a second total area of ​​the corresponding lead, the first total area being a total area of ​​each amplitude reduction region of the corresponding resting-state electrocardiogram signal, the second total area being a total area below an envelope of the corresponding resting-state electrocardiogram signal, the first target lead being the lead in which the total number of times the corresponding resting-state electrocardiogram signal is on a downward trend exceeds a second threshold, and the target limb lead being the limb lead in which a QRS complex voltage of the corresponding resting-state electrocardiogram signal is less than a third threshold; an evaluation and analysis module that evaluates and analyzes the risk assessment feature set to obtain a heart failure risk assessment score, the heart failure risk assessment score being used to determine a degree of risk of developing heart failure, and the risk assessment feature set including the static high frequency QRS waveform feature set; The signal processing module includes a signal processing unit, and the signal processing unit performs data extraction on the electrocardiogram signal in the resting state to obtain a high frequency component of a static QRS waveform of the corresponding lead. The signal processing unit further determines each of the amplitude reduction regions corresponding to each of the leads based on the high frequency component of the static QRS waveform of each of the leads to calculate the first total area and the corresponding second total area of ​​each of the leads. The signal processing unit further obtains the high frequency morphology index of each of the leads based on a ratio of the first total area to the corresponding second total area of ​​each of the leads. the signal processing unit further calculates the area of ​​each of the amplitude reduction regions corresponding to each of the leads, the signal processing unit further calculates the number of target areas for each of the leads based on the area of ​​each of the amplitude reduction regions corresponding to each of the leads, the target areas being areas of the amplitude reduction regions that are greater than a fifth threshold; the signal processing unit further determines the number of target areas for each of the leads to be the total number of times for the corresponding lead; and the signal processing unit further determines the number of the first target leads based on the total number of times for each of the leads and the second threshold.

6. The risk assessment feature set further includes a dynamic high-frequency QRS waveform feature set, the signal acquisition module further acquires an electrocardiogram signal in a stress state of each of the leads, the signal processing module further performs data processing on the electrocardiogram signal in each of the stress states to obtain a corresponding high-frequency waveform curve, and performs feature analysis on each of the high-frequency waveform curves to obtain the dynamic high-frequency QRS waveform feature set, the dynamic high-frequency QRS waveform feature set including at least two of a number of second positive indicators, an initial average voltage value, a maximum output power, and a number of second target leads, the second positive indicator indicating that a relative value of amplitude decline of a corresponding lead is greater than a fourth threshold, and the relative value of amplitude decline is determined by an absolute amplitude value and a maximum RMS voltage. the maximum RMS voltage value of the corresponding high frequency waveform curve is a ratio of the RMS voltage value to the corresponding RMS voltage value, the absolute amplitude value is a difference between the maximum RMS voltage value and a target RMS voltage value, the maximum RMS voltage value is a maximum value of the RMS voltage of the corresponding high frequency waveform curve, the target RMS voltage value is a minimum value of the RMS voltage after a time point corresponding to the maximum RMS voltage value of the corresponding high frequency waveform curve, the initial average voltage value is an average value of the initial voltage values ​​of each of the high frequency waveform curves, the maximum output power is determined based on the maximum root mean square voltage value of each of the high frequency waveform curves, and the second target lead is the lead in which the corresponding high frequency waveform curve exhibits a target waveform, the target waveform including a U wave, an L wave, and a small V wave.

7. The device of any one of claims 5 to 6, characterized in that the assessment analysis module includes an assessment analysis unit, which inputs the risk assessment feature set into a preset risk assessment function or a pre-trained risk assessment network model to obtain the heart failure risk assessment score.

8. a risk level determination module that determines a heart failure risk level based on the heart failure risk assessment score; The device of any one of claims 5 to 6, further comprising a risk warning module that outputs heart failure monitoring warning data in response to the heart failure risk level being greater than a level threshold.

9. A computing device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable by the processor, the computing device implementing the steps of the method of any one of claims 1 to 4 when the processor executes the computer-readable instructions.

10. 10. An electrocardiogram signal processing system, comprising an electrocardiogram signal collecting device and the computer device according to claim 9, wherein the electrocardiogram signal collecting device is electrically connected to the computer device to collect electrocardiogram signals in each of the resting states.

11. A computer-readable storage medium having stored thereon computer-readable instructions, the computer-readable instructions being adapted to implement the steps of the method of any one of claims 1 to 4 when executed by a processor.

Images