Method, device, system and storage medium for predicting risk of sudden cardiac death

Abstract

Disclosed are a sudden cardiac death risk prediction method, device, system and storage medium. The method comprises: acquiring resting electrocardiogram data output through a plurality of electrocardiogram leads, processing the resting electrocardiogram data to obtain high-frequency QRS complex data corresponding to each electrocardiogram lead, and obtaining high-frequency QRS features corresponding to each electrocardiogram lead according to the high-frequency QRS complex data; determining a lead positive index corresponding to each electrocardiogram lead according to a high-frequency morphology index corresponding to each electrocardiogram lead; determining whether there is a sudden cardiac death risk based on at least one of a plurality of conditions; and in the case of determining that there is a sudden cardiac death risk, predicting a sudden cardiac death risk level according to a sum of the high-frequency morphology indexes corresponding to each electrocardiogram lead. The scheme provided in the embodiments of the present application can quantitatively predict the sudden death risk based on the sum of the high-frequency morphology indexes of a plurality of (greater than or equal to 12) leads reflecting the myocardial injury volume in the case of qualitative determination based on a plurality of risk factors, and can take into account the misdiagnosis rate and accuracy.

Description

TECHNICAL FIELD

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

[0002] With the continuous improvement of people's living standards and the continuous increase of work pressure, heart disease is becoming more and more young and universal, and heart health problems are also attracting more and more attention and attention. Among them, sudden cardiac death (SCD) is one of the main causes of death of cardiovascular diseases, and early and accurate risk assessment is of great importance for prevention and intervention. The existing SCD risk assessment methods mainly rely on routine electrocardiogram, cardiac MRI, echocardiogram or biomarker detection, but these methods have limitations: the sensitivity of routine electrocardiogram is low, the cost of cardiac MRI is high and the operation is complex, and the detection of biomarkers may lack specificity. The Chinese patent application with publication number CN116649985A discloses a sudden cardiac death risk assessment method, which combines high-frequency features and low-frequency features of electrocardiogram data to assess the sudden cardiac death risk level. The assessment method still has room for improvement in improving sensitivity, reducing missed diagnosis rate, etc. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a heart health status assessment method, a processing device, a system and a computer readable storage medium.

[0004] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a sudden cardiac death risk prediction method, comprising:

[0005] obtaining resting electrocardiogram data output through a plurality of electrocardiogram leads;

[0006] processing the resting electrocardiogram data corresponding to each electrocardiogram lead to obtain high-frequency QRS complex data corresponding to each electrocardiogram lead;

[0007] obtaining high-frequency QRS feature corresponding to each electrocardiogram lead according to the high-frequency QRS complex data corresponding to each electrocardiogram lead, the high-frequency QRS feature including a high-frequency morphology index, and the high-frequency QRS feature further including at least one of a peak voltage and a waveform category, the waveform category including a multi-peak wave, a flat wave and a tailing;

[0008] determining a lead positive indicator corresponding to each electrocardiogram lead according to the high-frequency morphology index corresponding to each electrocardiogram lead;

[0009] determining whether there is a sudden cardiac death risk based on at least one of the following:

[0010] a first number of electrocardiogram leads corresponding to the waveform category being a multi-peak wave or a flat wave;

[0011] a third number of electrocardiogram leads corresponding to a waveform category of a trailing tail;

[0012] a third number of electrocardiogram leads corresponding to a waveform category of a trailing tail;

[0013] a fourth number of electrocardiogram leads corresponding to a lead positivity indicator being positive; and

[0014] a waveform category of an I lead among the plurality of electrocardiogram leads;

[0015] In a case where it is determined that there is a risk of sudden cardiac death, a risk level of sudden cardiac death is predicted according to a sum value of the high-frequency morphology indexes corresponding to each of the electrocardiogram leads.

[0016] In the embodiments of the present application, whether there is a risk of sudden cardiac death is determined based on at least one of the following:

[0017] In a case where any of the following conditions is met, it is determined that there is a risk of sudden cardiac death:

[0018] the first number is greater than or equal to a first number threshold;

[0019] the second number is greater than or equal to a second number threshold;

[0020] the third number is greater than or equal to a third number threshold;

[0021] the fourth number is greater than or equal to a fourth number threshold;

[0022] the waveform category of the I lead corresponds to a flat wave.

[0023] In the embodiments of the present application, whether there is a risk of sudden cardiac death is determined based on at least one of the following:

[0024] a risk value corresponding to each of the first number, the second number, the third number, and the fourth number is determined according to a number interval in which the first number, the second number, the third number, and the fourth number are located, wherein a plurality of number intervals are divided according to the numbers of the plurality of electrocardiogram leads;

[0025] In a case where any of the following conditions is met, it is determined that there is a risk of sudden cardiac death:

[0026] a sum of the risk values corresponding to the first number, the second number, the third number, and the fourth number is greater than or equal to a risk threshold;

[0027] the waveform type corresponding to the I lead is a flat wave.

[0028] In the embodiments of the present application, the division standards of the plurality of number intervals corresponding to each of the first number, the second number, the third number, and the fourth number are at least partially different.

[0029] In the embodiment of the present application, the high frequency morphology indexes corresponding to each electrocardiogram lead are weighted and summed to obtain a sum value.

[0030] In the embodiment of the present application, the sudden cardiac death risk prediction method further comprises:

[0031] determining a corresponding adjustment coefficient according to a specific condition;

[0032] adjusting the sum value using the adjustment coefficient.

[0033] In the embodiment of the present application, the specific condition comprises at least one of the following:

[0034] the waveform type corresponding to the I lead is flat wave;

[0035] the waveform category corresponding to at least one of the I lead, the V1 to V5 leads comprises tailing;

[0036] the first number is greater than or equal to a first preset value;

[0037] the second number is greater than or equal to a second preset value;

[0038] the third number is greater than or equal to a third preset value;

[0039] the fourth number is greater than or equal to a fourth preset value;

[0040] the QRS time limit is greater than a first time threshold but less than a second time threshold;

[0041] the QRS time limit is greater than the second time threshold.

[0042] In the embodiment of the present application, in the case where there are multiple specific conditions, adjusting the sum value using the adjustment coefficient comprises:

[0043] selecting the maximum adjustment coefficient from the multiple adjustment coefficients corresponding to the multiple specific conditions as a target adjustment coefficient, or multiplying the multiple adjustment coefficients corresponding to the multiple specific conditions to obtain the target adjustment coefficient;

[0044] adjusting the sum value using the target adjustment coefficient.

[0045] In the embodiment of the present application, the sudden cardiac death risk prediction method further comprises:

[0046] comparing the sum value of the currently determined high frequency morphology index with the sum value of the last determined high frequency morphology index;

[0047] adjusting the sudden cardiac death risk level according to the comparison result.

[0048] The second aspect of the present application provides a processing device, comprising a processor and a memory, the memory storing instructions, the processor being configured to call and execute the instructions from the memory to implement the above-mentioned sudden cardiac death risk prediction method.

[0049] The third aspect of the present application provides a sudden cardiac death risk prediction system, comprising:

[0050] An electrocardiosignal collection device, comprising at least one electrode forming at least one electrocardiogram lead for collecting electrocardiosignals of a subject; and

[0051] The above-mentioned processing device.

[0052] The fourth aspect of the present application provides a machine-readable storage medium, the machine-readable storage medium storing instructions for causing a machine to execute the above-mentioned sudden cardiac death risk prediction method.

[0053] The scheme provided by the embodiments of the present application quantifies the sudden death risk based on multiple (greater than or equal to 12) lead high-frequency morphology indexes and values reflecting the myocardial injury volume in the case of multiple risk factor qualification, which can take into account the misdiagnosis rate and accuracy. And adjusting the sudden death risk based on the risk factors can further improve the evaluation accuracy.

[0054] Other features and advantages of the embodiments of the present application will be described in detail in the following specific implementation part. BRIEF DESCRIPTION OF DRAWINGS

[0055] The accompanying drawings are included to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used together with the following specific implementation to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the drawings:

[0056] Figure 1 An example flowchart of a sudden cardiac death risk prediction method according to an embodiment of the present application is schematically shown.

[0057] Figure 2 An example block diagram of a sudden cardiac death risk prediction system according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0058] The specific implementation of the embodiments of the present application will be described in detail below in conjunction with the drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiments of the present application, and is not used to limit the embodiments of the present application.

[0059] It should be noted that the acquisition, transmission, storage, use, processing and the like of data in the technical solutions of the present application comply with the relevant provisions of laws and regulations. In the embodiments of the present application, some industry existing solutions such as software, components, models and the like may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solutions.

[0060] The heart sudden death risk prediction method provided in the embodiments of the present application can be applied to a terminal, a server, an interactive system including a terminal and a server, and is implemented through the interaction of the terminal and the server, which is not limited here. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, electrocardiogram monitoring devices and portable wearable devices, and the server can be implemented by an independent server or a server cluster composed of multiple servers.

[0061] The "resting electrocardiogram data" or its equivalent terms mentioned in the embodiments of the present application can refer to the electrocardiogram data collected in the resting electrocardiogram detection process. The subject is in a resting state during the resting electrocardiogram detection process. The resting electrocardiogram data can include multiple QRS complexes. The QRS complexes in the resting electrocardiogram data are sequentially aligned, averaged, and high-frequency filtered to obtain high-frequency QRS complex data, or the QRS complexes in the resting electrocardiogram data are sequentially high-frequency filtered, aligned, and averaged to obtain high-frequency QRS complex data, or high-frequency electrocardiogram data is extracted from the resting electrocardiogram data by analysis, and the QRS complexes in the high-frequency electrocardiogram data are sequentially aligned and averaged to obtain high-frequency QRS complex data, which is not limited here. The high-frequency QRS complex data corresponds to the high-frequency QRS envelope curve, and the high-frequency QRS envelope curve can be formed based on the high-frequency QRS complex data. As can be seen, the corresponding high-frequency QRS envelope curve can be obtained by processing the resting electrocardiogram data. It can be understood that when the high-frequency QRS complex is visualized based on the high-frequency QRS complex data, the envelope curve of the high-frequency QRS complex is the high-frequency QRS envelope curve.

[0062] Figure 1 An example flowchart of the heart sudden death risk prediction method according to the embodiments of the present application is schematically shown. Specifically, as shown in Figure 1 The heart sudden death risk prediction method can include the following steps.

[0063] In step S101, resting electrocardiogram data output through multiple electrocardiogram leads is acquired.

[0064] Specifically, in the embodiments of the present application, the number of the plurality of electrocardiogram leads can be greater than or equal to 12. Taking the application of 12 electrocardiogram leads as an example, during the electrocardiogram acquisition process, 10 electrode pads can be used for signal acquisition for the subject. For example, the electrode pads can be distributed on the chest and limbs of the human body to form 12 electrocardiogram leads (such as V1, V2, V3, V4, V5, V6, I, II, III, aVL, aVF and aVR), corresponding to output 12 groups of electrocardiogram data.

[0065] In step S102, the resting electrocardiogram data corresponding to each electrocardiogram lead is processed to obtain high-frequency QRS complex data corresponding to each electrocardiogram lead.

[0066] In step S103, high-frequency QRS features corresponding to each electrocardiogram lead are obtained according to the high-frequency QRS complex data corresponding to each electrocardiogram lead, the high-frequency QRS features including a high-frequency morphology index, and at least one of a peak voltage and a waveform category, the waveform category can include a multi-peak wave, a flat wave and a tailing.

[0067] Specifically, the number of wave peaks can refer to the total number of wave peaks in the high-frequency QRS complex data (or on the high-frequency QRS envelope curve obtained according to the high-frequency QRS complex data), the number of wave peaks is associated with the myocardial cell activity corresponding to the corresponding electrocardiogram lead, and when the number of wave peaks is 1 (i.e. single-peak wave), it indicates that the myocardial cell activity is normal, and the more the number of wave peaks, the more the myocardial cell activity decreases. When the number of wave peaks is greater than or equal to a first threshold value, the waveform category is a multi-peak wave, and the first threshold value can be determined according to actual needs, for example, 4.

[0068] In the embodiments of the present application, the flat wave can refer to the amplitude of the high-frequency QRS envelope curve being significantly reduced and the morphology being flat, and the specific quantitative standard can be, for example: for any electrocardiogram lead, compared with the baseline voltage (which can be specifically the voltage average of the isopotential baseline segment corresponding to the high-frequency QRS complex of the electrocardiogram lead), the voltage fluctuation amplitude (the difference between the sampling point voltage and the baseline voltage) of the sampling points in the high-frequency QRS complex data (or the high-frequency QRS envelope curve) of the electrocardiogram lead is ≤ a voltage value (for example, 1 μV), and the proportion of the sampling points is greater than or equal to a preset threshold value (for example, 95% or 100%), that is, the high-frequency QRS envelope curve presents a horizontal or near-horizontal trend, then it is determined that the high-frequency QRS complex data corresponding to the lead exists a flat wave, that is, it is determined that the high-frequency QRS envelope curve corresponding to the lead exists a flat wave.

[0069] In the embodiments of the present application, the tailing (lead tailing) can refer to, in the physiological electrical activity interval of the high-frequency QRS complex, the termination section of the high-frequency QRS complex, that is, the interval after the end point (such as the J point) of the high-frequency QRS complex based on the conventional low-frequency electrocardiogram calibration and the immediately adjacent interval, the high-frequency QRS waveform (i.e., the high-frequency QRS envelope curve) corresponding to a certain electrocardiogram lead does not quickly return to the baseline with the main part of the high-frequency QRS complex, and there is still sustained voltage fluctuation, that is, there is still sustained low-amplitude irregular high-frequency electrical activity without fixed rhythm on the electrocardiogram lead. The specific quantitative standard can be, for example, that after the end point (such as the J point) of the high-frequency QRS complex based on the conventional low-frequency electrocardiogram calibration, a single electrocardiogram lead has sustained high-frequency signal fluctuation with a duration of ≥20 ms and an amplitude (also referred to as voltage) of between 0.1 μV and 1.2 μV (specifically, the amplitude is ≥0.1 μV and ≤1.2 μV relative to the baseline). This part of the sustained high-frequency signal is referred to as "tailing", and the electrocardiogram lead that appears this tailing feature can be referred to as a tailing lead. It can be understood that in the embodiments of the present application, another definition of high-frequency QRS complex data tailing (referred to as tailing) is given: tailing refers to the characteristic of sustained low-amplitude irregular fluctuation of high-frequency QRS complex data or its high-frequency QRS envelope curve at the end section of its time domain range; the core judgment basis is: whether the amplitude of the sampling point in the high-frequency QRS complex data or its high-frequency QRS envelope curve in the ending section time interval defined by taking the time sequence end point (the latest sampling point in time sequence) of the high-frequency QRS complex data as the interval end point and tracing back a preset time length, is in a preset amplitude interval, if the condition is met, it is determined that the high-frequency QRS complex data has tailing. The preset time length and the preset amplitude interval can be defined according to actual conditions, for example, the preset time length is 20 ms, and the preset amplitude interval is [0.1, 1.2], unit μV.

[0070] The high-frequency morphology index (HFMI) and the QRS time can be obtained by analyzing the high-frequency QRS complex data (or high-frequency QRS envelope curve). For example, the high-frequency morphology index can be obtained by calculating the ratio of the amplitude decay area (RAZ) of the high-frequency QRS complex data (or high-frequency QRS envelope curve) to the area under the envelope curve, which can reflect the degree of myocardial injury. The calculation method of the high-frequency morphology index can be as follows: for each electrocardiogram lead, analyze the high-frequency QRS envelope curve corresponding to the electrocardiogram lead to obtain the total area of each amplitude decay area (also referred to as amplitude reduction area) on the high-frequency QRS envelope curve as a first total area, and the total area below the high-frequency QRS envelope curve as a second total area, and the ratio of the first total area to the second total area is taken as the high-frequency morphology index corresponding to the electrocardiogram lead. The QRS time is the duration from the QRS complex starting point to the QRS complex ending point, and the prolongation of the QRS time is related to the conduction block. The prolongation of the QRS time is an important predictor of sudden cardiac death, and the longer the QRS time, the higher the risk of sudden cardiac death.

[0071] In step S104, the lead positive indicators corresponding to each electrocardiogram lead are determined according to the high-frequency morphology index corresponding to each electrocardiogram lead.

[0072] Specifically, if the high-frequency morphology index corresponding to the electrocardiogram lead is greater than or equal to the second threshold value, which indicates the possibility of myocardial ischemia, the lead positive indicator corresponding to the electrocardiogram lead can be determined as positive, otherwise, the corresponding lead positive indicator is determined as negative. The second threshold value can be determined according to the actual situation, for example, 8%, or it can be dynamically determined according to the age of the subject or the high-frequency morphology index of multiple subjects, for example, if the subject is older than 50 years old, the second threshold value can be but is not limited to 8%, and if the subject is less than or equal to 50 years old, the second threshold value can be but is not limited to 15%. The number of electrocardiogram leads with positive lead positive indicators (which can be referred to as the number of positive leads) is positively correlated with the degree of myocardial ischemia in the resting state, and the more the number of positive leads, the greater the risk of myocardial ischemia or the higher the degree of myocardial ischemia in the resting state.

[0073] The peak voltage corresponding to each electrocardiogram lead can also be determined according to the high-frequency QRS complex data (or high-frequency QRS envelope curve) corresponding to each electrocardiogram lead.

[0074] In step S105, it is determined whether there is a risk of sudden cardiac death based on at least one of the following:

[0075] The first number of electrocardiogram leads corresponding to the waveform category of multi-peak wave or flat wave;

[0076] The second number of electrocardiogram leads corresponding to the peak voltage less than the first voltage threshold value;

[0077] a third quantity of electrocardiogram leads corresponding to the waveform category of tailing (quantity of tailing leads);

[0078] a fourth quantity of electrocardiogram leads corresponding to the lead positivity indicator being positive; and

[0079] a waveform category corresponding to the I lead among the plurality of electrocardiogram leads.

[0080] Specifically, in an embodiment of the present application, step S105 can include: determining that there is a risk of sudden cardiac death if any of the following conditions is met:

[0081] the first quantity is greater than or equal to a first quantity threshold value;

[0082] the second quantity is greater than or equal to a second quantity threshold value;

[0083] the third quantity is greater than or equal to a third quantity threshold value;

[0084] the fourth quantity is greater than or equal to a fourth quantity threshold value;

[0085] the waveform category corresponding to the I lead is flat wave.

[0086] Exemplarily, taking 12 electrocardiogram leads as an example, the first quantity threshold value may, for example, be 3, the second quantity threshold value may, for example, be 3, the third quantity threshold value may, for example, be 2, and the fourth quantity threshold value may, for example, be 5. Therefore, this example provides specific quantity threshold values, but those skilled in the art can understand that the values of these quantity threshold values can be determined according to actual conditions and the number of electrocardiogram leads used.

[0087] In another embodiment of the present application, a plurality of quantity intervals can be divided according to the number of electrocardiogram leads used, each quantity interval is assigned a different risk value, the risk values corresponding to the first quantity, the second quantity, the third quantity and the fourth quantity are determined according to the quantity interval in which the first quantity, the second quantity, the third quantity and the fourth quantity are located, and it is determined that there is a risk of sudden cardiac death if any of the following conditions is met:

[0088] the sum of the risk values corresponding to the first quantity, the second quantity, the third quantity and the fourth quantity is greater than or equal to a risk threshold value;

[0089] the waveform type corresponding to the I lead is flat wave.

[0090] For example, taking 12 ECG leads as an example, three intervals can be divided, respectively: [1, 2): corresponding to "prompt risk", [2, 6], corresponding to "highly suspected risk", and [7, 12], corresponding to "determined risk". According to the risk level from low to high, the three intervals can be assigned risk values, for example, 2, 3, 6, and the risk threshold can be set to 6. If any one of the first number, the second number, the third number and the fourth number falls into the interval corresponding to "determined risk", the risk value corresponding to this interval is 6, and the sum of the risk values has reached the risk threshold, at this time it can be determined that there is a risk of sudden cardiac death. If at least 2 of the first number, the second number, the third number and the fourth number fall into the "highly suspected risk" interval, the risk value corresponding to this interval is 3, and the sum of the risk values is 6, reaching the risk threshold, if only 1 falls into the "highly suspected risk" interval, then at least 2 of the remaining 3 items fall into the "prompt risk" interval, at this time the sum of the risk values is 7, greater than the risk value threshold 6, it can be determined that there is a risk of sudden cardiac death. Or at least 3 fall into the "prompt risk" interval, at this time the sum of the risk values reaches the risk threshold 6, it can also be determined that there is a risk of sudden cardiac death. It can be understood that different high-frequency QRS features can be divided into number intervals, taking three intervals as an example, the interval ranges or thresholds of the number intervals corresponding to the first number, the second number, the third number and the fourth number can be the same or different, and can be partially the same.

[0091] Therefore, in this embodiment, step S105 can include:

[0092] dividing a plurality of number intervals according to the number of ECG leads, each number interval corresponding to a different risk threshold;

[0093] determining risk values corresponding to the first number, the second number, the third number and the fourth number according to the number intervals in which the first number, the second number, the third number and the fourth number respectively fall;

[0094] calculating the sum of the risk values corresponding to the first number, the second number, the third number and the fourth number;

[0095] In the case where the sum is greater than or equal to the risk threshold, it is determined that there is a risk of sudden cardiac death.

[0096] In the embodiments of the present application, after it is determined that there is a risk of sudden cardiac death, the risk level can also be predicted according to the high-frequency morphology index.

[0097] Specifically, in step S106, in the case where it is determined that there is a risk of sudden cardiac death, the risk level of sudden cardiac death is predicted according to the sum of the high-frequency morphology indexes corresponding to each ECG lead.

[0098] Different threshold intervals can be divided according to risk levels. For example, five levels can be divided according to risk levels from low to high, such as low, existing, medium, high, and extremely high, and the threshold intervals corresponding to each level can be, for example, [0, 18%), [18%, 60%), [60%, 120%), [120%, 180%), and greater than or equal to 180%.

[0099] In the embodiments of the present application, the high-frequency morphology indexes corresponding to each electrocardiogram lead can be weighted and summed to obtain a sum value. The heart position / region corresponding to each electrocardiogram lead is different, so the weight value of each electrocardiogram lead can be different. The weight reflects the clinical correlation strength of the heart region corresponding to the electrocardiogram lead and sudden cardiac death, and its essence is a quantitative coefficient of the risk warning value of each electrocardiogram lead. Taking 12 leads as an example, the weight of lead I (covering the left ventricular lateral wall (SCD high-risk area), with strong signal stability and the highest warning value) and leads V1-V5 (covering the anterior wall, the anterior septal wall, and the lateral wall (core risk area), with high signal sensitivity) is higher than that of other electrocardiogram leads. For example, the weight of lead I can be, for example, 1.4-1.7 (preferably 1.5), the weight of leads V1-V5 can each be 1.2-1.4 (preferably 1.3), and the weight of leads II, III, aVR, aVL, aVF, and V6 (covering the inferior wall, the right ventricle, and the posterior wall (auxiliary risk area) to ensure comprehensive evaluation) can each be 1.0-1.2 (preferably 1). It can be understood that the weight can be updated adaptively on the training set through Logistic regression or machine learning (XGBoost) to further improve the evaluation accuracy.

[0100] In the embodiments of the present application, the sudden cardiac death risk level can be adjusted according to different situations.

[0101] Specifically, in an embodiment, if the waveform type corresponding to lead I is a flat wave, that is, the waveform type obtained from the high-frequency QRS complex data corresponding to lead I is a flat wave, the sum value of the high-frequency morphology index obtained in step S106 can be multiplied by a first adjustment coefficient to adjust the sudden cardiac death risk level. Lead I corresponds to the SCD high-risk area, and flat wave indicates severe myocardial injury or even heart failure. The flat wave of lead I indicates that the local myocardial electrical activity is severely inhibited, and the coefficient needs to reflect the high-risk weight. For example, the value of the first adjustment coefficient can be, for example, 1.4 to 1.8, and preferably 1.6.

[0102] In one embodiment, the risk level of sudden cardiac death can be adjusted based on the location and number of ECG leads corresponding to the appearance of tails in the high-frequency QRS complex. Taking a 12-lead ECG as an example, if tails appear in at least one ECG lead (lead I, V1-V5), it indicates that the tailing in the core risk area leads suggests damage involving critical sites. In this case, the sum of the high-frequency morphological indices obtained in step S106 can be multiplied by a second adjustment coefficient to adjust the risk level of sudden cardiac death. For example, the value of the second adjustment coefficient can be, for example, 1.2 to 1.4, preferably 1.3. If the number of ECG leads corresponding to the appearance of tails is greater than or equal to a third preset value (e.g., 3), it indicates that the tailing range has expanded, reflecting damage spread. The risk weight needs to be further increased based on the single-region tailing. In this case, the sum of the high-frequency morphological indices obtained in step S106 can be multiplied by a third adjustment coefficient to adjust the risk level of sudden cardiac death. For example, the value of the third adjustment coefficient can be, for example, 1.5 to 1.7, preferably 1.6.

[0103] In one embodiment, the risk level of sudden cardiac death can be adjusted based on the number of ECG leads exhibiting multi-peaked and flat waveforms. Multiple leads showing waveform abnormalities can indicate widespread abnormal myocardial electrical activity. Taking a 12-lead ECG as an example, if the number of ECG leads exhibiting multi-peaked and flat waveforms is greater than or equal to a first preset value (e.g., 4), the sum of the high-frequency morphological indices obtained in step S106 can be multiplied by a fourth adjustment coefficient to adjust the risk level of sudden cardiac death. For example, the value of the fourth adjustment coefficient can be, for example, 1.2 to 1.4, preferably 1.3.

[0104] In this embodiment, the risk level of sudden cardiac death can be adjusted based on the number of ECG leads corresponding to positive positive leads (i.e., the number of positive leads). A higher number of positive leads indicates an expanded area of ​​injury / myocardial ischemia, reflecting overall abnormal high-frequency ECG activity, and the risk gradient matches with multiple waveform abnormalities. Taking a 12-lead ECG as an example, if the number of ECG leads corresponding to positive positive leads (the number of positive leads) is greater than or equal to a fourth preset value (e.g., 5), the sum of the high-frequency morphological indices obtained in step S106 can be multiplied by a fifth adjustment coefficient to adjust the risk level of sudden cardiac death. For example, the value of the fifth adjustment coefficient can be, for example, 1.2 to 1.4, preferably 1.3.

[0105] In the embodiments of the present application, the risk level of sudden cardiac death can be adjusted based on the number of ECG leads (low voltage leads) with peak voltage less than the first voltage threshold. Low voltage is related to impaired myocardial contractility, and the risk of SCD is high. The adjustment coefficient in this case can be slightly higher than that of multiple waveform abnormalities. For example, if the number of ECG leads (low voltage leads) with peak voltage less than the first voltage threshold is greater than or equal to a second preset value (for example, 3), the sum of the high frequency pattern indexes obtained in step S106 can be multiplied by a sixth adjustment coefficient to adjust the risk level of sudden cardiac death. For example, the sixth adjustment coefficient can be, for example, 1.4 to 1.8, preferably 1.5. Wherein the sixth adjustment coefficient is greater than the fourth adjustment coefficient.

[0106] In the embodiments of the present application, the risk level of sudden cardiac death can be adjusted based on the QRS time limit. If the QRS time limit is greater than a first time threshold (for example, 120 ms) but less than a second time threshold (for example, 150 ms), it indicates that mild conduction abnormalities occur, and the risk is slightly increased. At this time, the sum of the high frequency pattern indexes obtained in step S106 can be multiplied by a seventh adjustment coefficient to adjust the risk level of sudden cardiac death. For example, the seventh adjustment coefficient can be, for example, 1.1 to 1.3, preferably 1.2. If the QRS time limit is greater than the second time threshold, it indicates that severe conduction abnormalities occur, and the risk is significantly increased. At this time, the adjustment coefficient needs to reflect the gradient difference. The sum of the high frequency pattern indexes obtained in step S106 can be multiplied by an eighth adjustment coefficient to adjust the risk level of sudden cardiac death. For example, the eighth adjustment coefficient can be, for example, 1.3 to 1.5, preferably 1.4.

[0107] In the embodiments of the present application, if multiple conditions occur, in one example, the largest adjustment coefficient among the adjustment coefficients corresponding to the multiple conditions can be selected as the target adjustment coefficient. In another example, the adjustment coefficients corresponding to the conditions can be multiplied to obtain the target adjustment coefficient. The risk level of sudden cardiac death is adjusted by the target adjustment coefficient.

[0108] In the embodiments of the present application, the sum of the currently determined high frequency pattern indexes can be compared with the sum of the last determined high frequency pattern indexes, and the risk level of sudden cardiac death is adjusted according to the comparison result to correct the risk of sudden death based on the development speed. This method is especially suitable for dynamic monitoring scenarios. Specifically, the ratio ΔH of the sum of the currently determined high frequency pattern indexes to the sum of the last determined high frequency pattern indexes can be calculated as follows:

[0109] ΔH = (H2 - H1) / H1

[0110] Wherein, H2 is the sum of the currently determined high frequency pattern indexes, and H1 is the sum of the last determined high frequency pattern indexes.

[0111] If the third threshold (e.g. 15%) < AH < the fourth threshold (e.g. 20%), it indicates that the short-term risk is rapidly rising, and intervention is needed, in which case the sum of the high-frequency morphology indexes obtained in step S106 can be multiplied by a ninth adjustment coefficient to adjust the cardiac sudden death risk level. For example, the ninth adjustment coefficient can be, for example, 1.2 to 1.4, preferably 1.3. If AH is greater than or equal to the fourth threshold, it indicates that the short-term risk is sharply rising, and urgent intervention is needed, in which case the sum of the high-frequency morphology indexes obtained in step S106 can be multiplied by a tenth adjustment coefficient to adjust the cardiac sudden death risk level. For example, the tenth adjustment coefficient can be, for example, 1.4 to 1.6, preferably 1.5. In an example, the sum of the currently determined high-frequency morphology indexes can be spaced apart from the sum of the last determined high-frequency morphology indexes by a time period, which can be, for example, 1 to 7 days.

[0112] Those skilled in the art can understand that the values of the adjustment coefficients involved in the above embodiments can be determined by a limited number of experiments according to the actual application scenario, and the values of the thresholds are also exemplary, and appropriate threshold values can be selected according to the actual application.

[0113] In the embodiments of the present application, a processing device is provided, which includes a processor and a memory, the memory stores instructions, and the processor is configured to call and execute the instructions from the memory to implement the cardiac sudden death risk prediction method described in the above embodiments.

[0114] Figure 2 An example block diagram of an electrocardio data processing system according to an embodiment of the present application is schematically shown. As shown in the figure, in the embodiments of the present application, a cardiac sudden death risk prediction system is provided, which can include: Figure 2

[0115] An electrocardio signal acquisition device 100, which includes at least one electrode forming at least one electrocardio lead for acquiring electrocardio signals of a subject; and

[0116] The processing device 200 described above.

[0117] The electrocardio signal acquisition device 100 can further include a display configured to display various data and information, including but not limited to, for example, electrocardio data, cardiac sudden death risk prediction results, etc.

[0118] In the embodiments of the present application, a machine-readable storage medium is provided, which stores instructions for causing a machine to execute the coronary heart disease risk prediction method described in the above embodiments.

[0119] ​Examples of a processor can include, but are not limited to, a single-chip microcomputer, a microprocessor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), and the like.

[0120] The memory can include a non-transitory memory in a computer readable medium, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

[0121] The scheme provided by the embodiments of the present application can quantify the sudden death risk based on a plurality of (greater than or equal to 12) lead high-frequency morphology indexes and values reflecting the myocardial injury volume in the case of multiple risk factor qualification, and can take into account the misdiagnosis rate and accuracy. Further, the sudden death risk is adjusted based on the risk factors, and the evaluation accuracy can be further improved.

[0122] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0123] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1 The functions specified in one or more flows and / or blocks.

[0124] These computer program instructions can also be stored in a computer readable memory capable of directing the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including instruction devices that implement the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1 The functions specified in one or more flows and / or blocks.

[0125] These computer program instructions can also be loaded into computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices, to generate computer-implemented processes, in order to achieve the flow Figure 1 one or more flows and / or blocks Figure 1 one or more blocks or multiple blocks.

[0126] In one typical arrangement, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0127] The memory can include non-persistent memory and / or volatile memory, such as a random access memory (RAM) including a cache area for the temporary storage of data. The memory can also include non-volatile memory, such as

[0128] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for the storage of information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0129] It should also be noted that the terms "comprising", "containing", or any other variant thereof, are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a list of elements not only includes those elements, but also includes other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0130] The above merely provides an example of the present application, and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall fall into the scope of claims of the present application.

Claims

1. A sudden cardiac death risk prediction device, characterized in that, A method for predicting risk of sudden cardiac death is configured to implement a method for predicting risk of sudden cardiac death, the method comprising: obtaining resting electrocardiogram data output by a plurality of electrocardiogram leads; processing the resting electrocardiogram data corresponding to each electrocardiogram lead to obtain high-frequency QRS complex data corresponding to each electrocardiogram lead; obtaining high-frequency QRS features corresponding to each electrocardiogram lead according to the high-frequency QRS complex data corresponding to each electrocardiogram lead, the high-frequency QRS features including a high-frequency morphology index, and the high-frequency QRS features further including at least one of a peak voltage and a waveform category, the waveform category including a multi-peak wave, a flat wave, and a tailing; determining a lead positive indicator corresponding to each electrocardiogram lead according to the high-frequency morphology index corresponding to each electrocardiogram lead; determining whether there is a risk of sudden cardiac death based on at least one of the following: a first number of electrocardiogram leads corresponding to the waveform category being a multi-peak wave or a flat wave; a second number of electrocardiogram leads corresponding to the peak voltage being less than a first voltage threshold; a third number of electrocardiogram leads corresponding to the waveform category being a tailing; a fourth number of electrocardiogram leads corresponding to the lead positive indicator being positive; a waveform category corresponding to an I lead among the plurality of electrocardiogram leads; in a case where it is determined that there is a risk of sudden cardiac death, predicting a risk level of sudden cardiac death according to a sum value of the high-frequency morphology index corresponding to each electrocardiogram lead; determining a corresponding adjustment coefficient according to a specific condition; adjusting the sum value using the adjustment coefficient; wherein the specific condition includes at least one of the following: the waveform type corresponding to the I lead being a flat wave; the waveform category corresponding to at least one of the I lead, V1 to V5 leads, including a tailing; the first number being greater than or equal to a first preset value; the second number being greater than or equal to a second preset value; the third number being greater than or equal to a third preset value; the fourth number being greater than or equal to a fourth preset value; the QRS time interval being greater than a first time threshold but less than a second time threshold; the QRS time interval being greater than the second time threshold.

2. The sudden cardiac death risk predictor device according to claim 1, characterized in that, The determining whether there is a risk of sudden cardiac death based on at least one of the following includes: in a case where any of the following conditions is met, it is determined that there is a risk of sudden cardiac death: the first number being greater than or equal to a first number threshold; the second number being greater than or equal to a second number threshold; the third number being greater than or equal to a third number threshold; the fourth number being greater than or equal to a fourth number threshold; the waveform category corresponding to the I lead being a flat wave.

3. The sudden cardiac death risk prediction device according to claim 1, characterized in that, The determining whether there is a risk of sudden cardiac death based on at least one of the following includes: determining a risk value corresponding to each of the first number, the second number, the third number, and the fourth number, respectively, according to a number interval in which the first number, the second number, the third number, and the fourth number are located, wherein a plurality of number intervals are divided according to the number of electrocardiogram leads; in a case where any of the following conditions is met, it is determined that there is a risk of sudden cardiac death: a sum of the risk values corresponding to the first number, the second number, the third number, and the fourth number being greater than or equal to a risk threshold; the waveform type corresponding to the I lead being a flat wave.

4. The sudden cardiac death risk prediction device according to claim 3, characterized in that, The first number, the second number, the third number and the fourth number each correspond to a plurality of number intervals, and the division standards of the plurality of number intervals are different at least in part.

5. The sudden cardiac death risk prediction device according to claim 1, characterized in that, The high frequency morphology indexes corresponding to each electrocardiogram lead are weighted and summed to obtain the sum value.

6. The sudden cardiac death risk prediction device of claim 1, wherein, In the presence of a plurality of specific conditions, adjusting the sum value using the adjustment coefficient comprises: Selecting the largest adjustment coefficient from a plurality of adjustment coefficients corresponding to a plurality of specific conditions as a target adjustment coefficient, or multiplying a plurality of adjustment coefficients corresponding to a plurality of specific conditions to obtain a target adjustment coefficient; Adjusting the sum value using the target adjustment coefficient.

7. The sudden cardiac death risk prediction device of claim 1, wherein, The cardiac sudden death risk prediction method further comprises: Comparing the sum value of the currently determined high frequency morphology index with the sum value of the last determined high frequency morphology index; Adjusting the cardiac sudden death risk level according to the comparison result.

8. A sudden cardiac death risk prediction system, characterized in that, Comprise: An electrocardiosignal acquisition device comprising at least one electrode forming at least one electrocardiogram lead for acquiring electrocardiosignals of a subject; And The cardiac sudden death risk prediction device according to any one of claims 1 to 7.

9. A machine-readable storage medium, characterized in that, The machine readable storage medium has instructions stored thereon for causing a machine to perform the cardiac sudden death risk prediction method according to any one of claims 1 to 7.

Images