System for determining probability of occurrence of ventricular fibrillation and monitor

Abstract

The embodiment of the invention discloses a ventricular fibrillation occurrence probability determination system and a monitor, the system comprises an electrode and a processor, an electrocardiosignal of a patient is obtained through the electrode, the processor determines a target parameter based on the electrocardiosignal, and the target parameter is used as an input parameter to be input into a hybrid rice algorithm to obtain a corresponding parameter threshold, the target parameter is a parameter value reflecting the ventricular fibrillation characteristic, and the probability that the electrocardiosignal generates ventricular fibrillation is determined according to the target parameter and a corresponding parameter threshold value. According to the system, the target parameter is input into the hybrid rice algorithm to obtain the corresponding parameter threshold value, the probability of occurrence of ventricular fibrillation of the electrocardiosignal is determined based on the target parameter and the corresponding parameter threshold value, a machine learning model is not needed to predict the occurrence of VF, and computing resources can be saved. Moreover, the target parameter has close correlation with the occurrence of the ventricular fibrillation, and the effectiveness of the occurrence probability of the ventricular fibrillation can be improved by predicting the occurrence probability of the ventricular fibrillation based on the target parameter.

Description

Technical Field

[0001] The present invention relates to the technical field of electrocardiogram signal processing, and in particular to a ventricular fibrillation occurrence probability determination system and a monitor. Background Art

[0002] Ventricular fibrillation (VF), also known as VF for short, is a common cardiovascular disease that can easily cause sudden cardiac death and greatly endangers people's health. If VF can be effectively predicted and effective intervention or treatment can be carried out on patients who are about to develop VF, accidents can be prevented to a great extent.

[0003] At present, some related studies have combined morphological features with heart rate variability features and used machine learning models such as K-nearest neighbor and BP neural network to predict the occurrence of VF. However, it requires large computing resources and the implementation process is cumbersome.

[0004] Therefore, it is of great significance to provide a system that can effectively determine the probability of occurrence of ventricular fibrillation while saving computing resources. Summary of the invention

[0005] The main purpose of the present invention is to provide a ventricular fibrillation probability determination system and a monitor, which can solve the problems of large computing resources consumed and complicated implementation process in the prior art ventricular fibrillation probability determination system.

[0006] To achieve the above-mentioned object, the present invention provides a system for determining the probability of occurrence of ventricular fibrillation in a first aspect, the system comprising electrodes and a processor;

[0007] The electrodes are used to collect the patient's electrocardiogram signals and transmit the electrocardiogram signals to the processor;

[0008] The processor is used to receive the ECG signal, determine the target parameter based on the ECG signal, input the target parameter as an input parameter into the hybrid rice algorithm to obtain a corresponding parameter threshold; the target parameter is a parameter value reflecting the characteristics of ventricular fibrillation; and determine the probability of ventricular fibrillation occurring in the ECG signal based on the target parameter and the corresponding parameter threshold.

[0009] In combination with the first aspect, in a possible implementation method, the above-mentioned processor is also used to determine whether the size relationship between the target parameter and the corresponding parameter threshold is to characterize the occurrence of ventricular fibrillation or to characterize the non-occurrence of ventricular fibrillation; if the size relationship characterizes the occurrence of ventricular fibrillation, then the target value corresponding to the target parameter is determined to be a first target value; if the size relationship characterizes the non-occurrence of ventricular fibrillation, then the target value corresponding to the target parameter is determined to be a second target value; wherein the second target value is less than the first target value; and the probability of ventricular fibrillation occurring in the electrocardiogram signal is determined based on the target value.

[0010] In combination with the first aspect, in a possible implementation method, the above-mentioned target parameter includes at least two different parameter values, and the processor is also used to respectively determine the weight values ​​corresponding to the target parameters; based on the target value corresponding to the target parameter and the weight value, a weighted sum is performed to obtain the probability of ventricular fibrillation occurring in the electrocardiogram signal.

[0011] In combination with the first aspect, in a possible implementation, the target parameters include at least any two parameter values ​​of the R wave duration of the electrocardiogram signal, the P wave amplitude of the electrocardiogram signal, and the singular value decomposition entropy of the electrocardiogram signal.

[0012] In combination with the first aspect, in a possible implementation method, the above-mentioned processor is also used to calculate the time interval from the beginning of the Q wave to the end of the S wave in the ECG signal to obtain the R wave time limit of the ECG signal; and / or calculate the difference between the P wave peak value and the baseline in the ECG signal to obtain the P wave amplitude of the ECG signal; and / or perform singular value decomposition on the ECG signal to obtain the singular value corresponding to the ECG signal, and calculate the singular value decomposition entropy of the ECG signal based on the singular value.

[0013] In combination with the first aspect, in a possible implementation manner, the processor is further configured to perform normalization processing on the singular values ​​according to the following formula:

[0014]

[0015] The subscript i represents the index of each singular value. Expressed as the normalized singular value, λ i represents the singular value, k represents the total number of singular values;

[0016] The singular value decomposition entropy is calculated according to the following formula:

[0017]

[0018] Among them, SVDE n represents the singular value decomposition entropy, Represented as normalized singular values.

[0019] In combination with the first aspect, in a possible implementation method, the above-mentioned processor is also used to indicate that ventricular fibrillation has occurred if the R wave time limit is greater than the parameter threshold corresponding to the R wave time limit, and that ventricular fibrillation has not occurred if the R wave time limit is less than or equal to the parameter threshold corresponding to the R wave time limit; if the P wave amplitude is less than the parameter threshold corresponding to the P wave amplitude, it indicates that ventricular fibrillation has occurred, and if the P wave amplitude is greater than or equal to the parameter threshold corresponding to the P wave amplitude, it indicates that ventricular fibrillation has not occurred; if the singular value decomposition entropy is greater than the parameter threshold corresponding to the singular value decomposition entropy, it indicates that ventricular fibrillation has occurred, and if the singular value decomposition entropy is less than or equal to the parameter threshold corresponding to the singular value decomposition entropy, it indicates that ventricular fibrillation has not occurred.

[0020] In combination with the first aspect, in a possible implementation, the processor is further used to determine the probability that the probability represents the possibility of ventricular fibrillation occurring in the electrocardiogram signal according to a preset probability range interval in which the probability lies.

[0021] In combination with the first aspect, in a possible implementation manner, the probability range interval includes a first interval, a second interval, and a third interval, the first interval is smaller than the second interval, and the second interval is smaller than the third interval;

[0022] The processor is also used to indicate that if the probability is in the first interval, the possibility of ventricular fibrillation in the ECG signal is small; if the probability is in the second interval, the possibility of ventricular fibrillation in the ECG signal is medium; if the probability is in the third interval, the possibility of ventricular fibrillation in the ECG signal is large.

[0023] To achieve the above object, the second aspect of the present invention provides a monitor, the monitor comprising any one of the systems described in the first aspect;

[0024] The monitor also includes an output device, which is used to display the probability of ventricular fibrillation occurring in the electrocardiogram signal.

[0025] The embodiments of the present invention have the following beneficial effects:

[0026] The present invention provides a system for determining the probability of ventricular fibrillation. The system includes electrodes and a processor. The patient's electrocardiogram (ECG) signal is obtained through the electrodes. The processor determines a target parameter based on the ECG signal, and inputs the target parameter as an input parameter into a hybrid rice algorithm to obtain a corresponding parameter threshold, wherein the target parameter is a parameter value reflecting the characteristics of ventricular fibrillation, and finally determines the probability of ventricular fibrillation in the ECG signal based on the target parameter and the corresponding parameter threshold. The system inputs the target parameter into the hybrid rice algorithm to obtain the corresponding parameter threshold, and determines the probability of ventricular fibrillation in the ECG signal based on the target parameter and the corresponding parameter threshold. The system does not require a machine learning model to predict the occurrence of VF, and can save computing resources. In addition, the target parameter is closely correlated with the occurrence of ventricular fibrillation. Predicting the probability of ventricular fibrillation based on the target parameter can improve the effectiveness of the probability of ventricular fibrillation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] in:

[0029] Figure 1 It is a structural block diagram of a system for determining the probability of occurrence of ventricular fibrillation in an embodiment of the present invention;

[0030] Figure 2 A monitor in an embodiment of the present invention;

[0031] Figure 3 4 is a structural block diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] The embodiment of the present invention provides a system for determining the probability of ventricular fibrillation, which is applicable to any scenario where the probability of ventricular fibrillation is predicted based on the patient's electrocardiogram signal. Figure 1 , Figure 1 A structural block diagram of a system for determining the probability of occurrence of ventricular fibrillation provided by an embodiment of the present invention is shown in FIG. Figure 1As shown, the system includes an electrode 10 and a processor 20, wherein the electrode 10 is used to collect the patient's electrocardiogram signal and transmit the electrocardiogram signal to the processor, and the processor is used to receive the electrocardiogram signal, determine the target parameter based on the electrocardiogram signal, and input the target parameter as an input parameter into the hybrid rice algorithm to obtain the corresponding parameter threshold, wherein the target parameter is a parameter value reflecting the characteristics of ventricular fibrillation, and the probability of ventricular fibrillation occurring in the electrocardiogram signal is determined based on the target parameter and the corresponding parameter threshold.

[0034] First, the electrode 10 collects the patient's ECG signal. The ECG signal is collected by attaching the electrode to the skin. For example, three electrodes can be used to collect the ECG signal, namely the RA (right arm) electrode, the LA (left arm) electrode and the LL (left leg) electrode.

[0035] The collected ECG signals are extremely small, usually ranging from a few microvolts to a few millivolts. In order to accurately measure and analyze these signals, the collected initial ECG signals need to be pre-processed by filtering, amplification, etc. Specifically, the initial ECG signals are first filtered. ECG signals may be mixed with various clutter interferences, such as power interference, poor electrode contact, etc. These interferences will affect the accuracy of ECG signals. Therefore, these interferences need to be filtered out and only ECG signals are retained. Common filtering methods include low-pass filtering and high-pass filtering. Low-pass filters will remove high-frequency noise, while high-pass filters will remove low-frequency interference. Next is the signal amplification processing. The voltage of ECG signals is small and needs to be amplified for better analysis and observation. Generally, multi-stage amplifiers are used for signal amplification to ensure that the amplification amplitude is appropriate and avoid signal distortion. The amplifier can also adjust the gain to make the waveform of the ECG signal clearer and easier to read. That is, the electrode can be connected to a low-pass filter, the low-pass filter is connected to a high-pass filter, the high-pass filter is connected to an amplifier, and the amplifier is connected to a processor.

[0036] After the processor obtains the preprocessed ECG signal, it determines the target parameters based on the ECG signal, where the target parameters are parameter values ​​that reflect the characteristics of ventricular fibrillation. The target parameters can be understood as parameters that are correlated with the occurrence of ventricular fibrillation, such as parameters that have obvious changes between ventricular fibrillation and non-ventricular fibrillation, such as morphological features in the ECG signal: R wave duration, P wave amplitude, etc.

[0037] The target parameter is input as an input parameter into the hybrid rice algorithm, and the optimal threshold corresponding to the target parameter is output to obtain the parameter threshold corresponding to the target parameter. The hybrid rice algorithm is less difficult to implement and consumes less computing resources, which can effectively save computing resources.

[0038] The probability of ventricular fibrillation occurring in the ECG signal is determined based on the target parameter and the corresponding parameter threshold. Specifically, the processor is used to determine whether the size relationship between the target parameter and the corresponding parameter threshold is to characterize the occurrence of ventricular fibrillation or to characterize the absence of ventricular fibrillation. If the size relationship characterizes the occurrence of ventricular fibrillation, the target value corresponding to the target parameter is determined to be a first target value. If the size relationship characterizes the absence of ventricular fibrillation, the target value corresponding to the target parameter is determined to be a second target value, wherein the second target value is less than the first target value. The probability of ventricular fibrillation occurring in the ECG signal is determined based on the target value.

[0039] In this embodiment, a first target value R1 and a second target value R2 are set, the first target value R1 represents the occurrence of ventricular fibrillation, the second target value R2 represents the absence of ventricular fibrillation, and 0≤R2<R1≤1, for example, R1 is 1 and R2 is 0.

[0040] The target parameter is compared with the corresponding parameter threshold value. If the magnitude relationship of the comparison indicates that ventricular fibrillation has occurred, the target value corresponding to the target parameter is determined to be the first target value R1. If the magnitude relationship indicates that ventricular fibrillation has not occurred, the target value corresponding to the target parameter is determined to be the second target value R2. For example, the target parameter is P, and the corresponding parameter threshold value is T. When P<T, it indicates that ventricular fibrillation has occurred, and when P≥T, it indicates that ventricular fibrillation has not occurred. If P<T, the target value Ret corresponding to the target parameter P is R1, and if P≥T, the target value Ret corresponding to the target parameter P is R2.

[0041] The probability of ventricular fibrillation occurring in the electrocardiogram signal is determined according to the target value. Specifically, the processor is used to determine the weight values ​​corresponding to the target parameters respectively, wherein the weight value is less than 1, and a weighted sum is performed based on the target value corresponding to the target parameter and the weight value to obtain the probability of ventricular fibrillation occurring in the electrocardiogram signal.

[0042] In this embodiment, in order to improve the accuracy of the predicted probability, the target parameter includes at least two different parameter values. For example, the target parameter may include at least any two parameter values ​​of the R wave duration of the ECG signal, the P wave amplitude of the ECG signal, and the singular value decomposition entropy of the ECG signal.

[0043] The weight values ​​corresponding to each target parameter are determined respectively, where the weight value is less than 1. The target value corresponding to the target parameter and the weight value are weighted and summed to obtain the probability of ventricular fibrillation in the ECG signal. The probability can be calculated by the following formula:

[0044] Result=a1*Ret1+a2*Ret2+a i *Ret i +...+a n *Ret n

[0045] Among them, Result represents the probability, i represents the serial number of the parameter value, n is the total number of parameter values, and a i Represents the weight value, Ret i Represents the target value, a1+a2+a i +...+a n =1.

[0046] For example, the target parameter includes three parameter values, the corresponding target values ​​are Ret1, Ret2, and Ret3, and the corresponding weights are a1, a2, and a3, respectively. Then the probability Result = a1*Ret1+a2*Ret2+a3*Ret3.

[0047] In a possible implementation, the weight value may be assigned according to the degree of correlation between the parameter value and the ventricular fibrillation signal. A higher weight value may be assigned to a parameter value with a greater degree of correlation, and a smaller weight value may be assigned to a parameter value with a lesser degree of correlation.

[0048] In one possible implementation, the target parameters include at least any two parameter values ​​of the R wave duration of the ECG signal, the P wave amplitude of the ECG signal, and the singular value decomposition entropy of the ECG signal. The processor is used to calculate the time interval from the start of the Q wave to the end of the S wave in the ECG signal to obtain the R wave duration of the ECG signal, and / or calculate the difference between the P wave peak and the baseline in the ECG signal to obtain the P wave amplitude of the ECG signal, and / or perform singular value decomposition on the ECG signal to obtain the singular value corresponding to the ECG signal, and calculate the singular value decomposition entropy of the ECG signal based on the singular value.

[0049] The time interval from the start of the Q wave to the end of the S wave in the ECG signal is calculated to obtain the R wave duration of the ECG signal. The difference between the P wave peak value and the baseline in the ECG signal is calculated to obtain the P wave amplitude of the ECG signal.

[0050] And perform singular value decomposition on the ECG signal to obtain the singular value corresponding to the ECG signal, and calculate the singular value decomposition entropy of the ECG signal according to the singular value. For the ECG signal matrix A, there must be matrices U and V to make the following equations hold:

[0051] A=USV T

[0052] Among them, S is a diagonal matrix, S=diag(λ1, λ2, λ3, ...λk), and the elements (λ1, λ2, λ3, ...λk) are the singular values ​​of A.

[0053] The singular values ​​are standardized according to the following formula:

[0054]

[0055] The subscript i represents the index of each singular value. Expressed as the normalized singular value, λ i represents the singular value, k represents the total number of singular values;

[0056] The calculation formula of singular value decomposition entropy is as follows:

[0057]

[0058] Among them, SVDE n represents the singular value decomposition entropy, Represented as normalized singular values.

[0059] It should be noted that, for R wave duration, if the R wave duration is greater than the parameter threshold corresponding to the R wave duration, it indicates that ventricular fibrillation has occurred; if the R wave duration is less than or equal to the parameter threshold corresponding to the R wave duration, it indicates that ventricular fibrillation has not occurred. For P wave amplitude, if the P wave amplitude is less than the parameter threshold corresponding to the P wave amplitude, it indicates that ventricular fibrillation has occurred; if the P wave amplitude is greater than or equal to the parameter threshold corresponding to the P wave amplitude, it indicates that ventricular fibrillation has not occurred. For singular value decomposition entropy, if the singular value decomposition entropy is greater than the parameter threshold corresponding to the singular value decomposition entropy, it indicates that ventricular fibrillation has occurred; if the singular value decomposition entropy is less than or equal to the parameter threshold corresponding to the singular value decomposition entropy, it indicates that ventricular fibrillation has not occurred.

[0060] In this embodiment, in a possible implementation, after determining the probability of ventricular fibrillation of the patient, the processor is further configured to determine the probability of ventricular fibrillation of the ECG signal according to a preset probability range in which the probability lies.

[0061] The probability range includes a first interval, a second interval and a third interval. The first interval is smaller than the second interval, and the second interval is smaller than the third interval. If the probability is in the first interval, it means that the possibility of ventricular fibrillation in the ECG signal is small. If the probability is in the second interval, it means that the possibility of ventricular fibrillation in the ECG signal is medium. If the probability is in the third interval, it means that the possibility of ventricular fibrillation in the ECG signal is large. The first interval can be 0-34%, the second interval can be 34-67%, and the third interval can be 67-100%.

[0062] Based on the above system, the target parameters can be input into the hybrid rice algorithm to obtain the corresponding parameter thresholds. The probability of ventricular fibrillation in the ECG signal can be determined based on the target parameters and the corresponding parameter thresholds. There is no need for a machine learning model to predict the occurrence of VF, which can save computing resources. In addition, the morphological changes of the R wave and P wave in the QRS wave in the electrocardiograph (ECG) signal are closely related to the occurrence of ventricular fibrillation. Predicting the probability of ventricular fibrillation based on the morphological characteristic parameters of the ECG signal can improve the effectiveness of the probability of ventricular fibrillation.

[0063] The embodiment of the present invention provides a monitor, referring to Figure 2 , Figure 2 A monitor provided by an embodiment of the present invention includes the above system, and the monitor also includes an output device 30, the output device 30 is used to output and display the probability of ventricular fibrillation of the electrocardiogram signal, and can also output and display the possibility of ventricular fibrillation of the electrocardiogram signal. The monitor can input the target parameter into the hybrid rice algorithm to obtain the corresponding parameter threshold, and determine the probability of ventricular fibrillation of the electrocardiogram signal based on the target parameter and the corresponding parameter threshold. There is no need for a machine learning model to predict the occurrence of VF, which can save computing resources. In addition, the morphological changes of the R wave and the P wave in the QRS wave in the electrocardiogram (ECG) signal are closely related to the occurrence of ventricular fibrillation. Predicting the probability of ventricular fibrillation based on the morphological characteristic parameters of the electrocardiogram signal can improve the effectiveness of the probability of ventricular fibrillation.

[0064] Figure 3 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 3 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement all the functions of the above system. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement all the functions of the above system. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0065] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes all functions of the aforementioned system.

[0066] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor executes all functions of the aforementioned system.

[0067] Those skilled in the art will appreciate that the full functionality of the above-described embodiment system can be accomplished by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium, and the program, when executed, can include the full functionality of the above-described system. Among them, any reference to memory, storage, database, or other medium used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0068] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0069] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A system for determining the probability of ventricular fibrillation, characterized in that: The system includes an electrode and a processor; The electrodes are used to collect the patient's electrocardiogram signals and transmit the electrocardiogram signals to the processor; The processor is used to receive the electrocardiogram signal, determine the target parameter based on the electrocardiogram signal, input the target parameter as an input parameter into the hybrid rice algorithm, and obtain a corresponding parameter threshold; The target parameter is a parameter value reflecting the characteristics of ventricular fibrillation; the probability of ventricular fibrillation occurring in the electrocardiogram signal is determined based on the target parameter and the corresponding parameter threshold.

2. The system according to claim 1, characterized in that The processor is further configured to determine whether the magnitude relationship between the target parameter and the corresponding parameter threshold is indicative of the occurrence of ventricular fibrillation or the absence of ventricular fibrillation; if the magnitude relationship is indicative of the occurrence of ventricular fibrillation, determining the target value corresponding to the target parameter to be a first target value; If the magnitude relationship indicates that ventricular fibrillation has not occurred, the target value corresponding to the target parameter is a second target value; wherein the second target value is less than the first target value; and the probability of ventricular fibrillation occurring in the electrocardiogram signal is determined based on the target value.

3. The system according to claim 2, characterized in that The target parameter includes at least two different parameter values, and the processor is further used to determine the weight values ​​corresponding to the target parameters respectively; based on the target value corresponding to the target parameter and the weight value, a weighted sum is performed to obtain the probability of ventricular fibrillation occurring in the electrocardiogram signal.

4. The system according to claim 3, characterized in that The target parameters include at least any two parameter values ​​of the R wave duration of the electrocardiogram signal, the P wave amplitude of the electrocardiogram signal, and the singular value decomposition entropy of the electrocardiogram signal.

5. The system according to claim 4, characterized in that The processor is also used to calculate the time interval from the start of the Q wave to the end of the S wave in the ECG signal to obtain the R wave time limit of the ECG signal; and / or calculate the difference between the P wave peak and the baseline in the ECG signal to obtain the P wave amplitude of the ECG signal; and / or perform singular value decomposition on the ECG signal to obtain the singular value corresponding to the ECG signal, and calculate the singular value decomposition entropy of the ECG signal based on the singular value.

6. The system according to claim 5, characterized in that The processor is further configured to perform standardization processing on the singular values ​​according to the following formula: The subscript i represents the index of each singular value. Expressed as the normalized singular value, λ i represents the singular value, k represents the total number of singular values; The singular value decomposition entropy is calculated according to the following formula: Among them, SVDE n represents the singular value decomposition entropy, Represented as normalized singular values.

7. The system according to claim 4, characterized in that The processor is also used to indicate the occurrence of ventricular fibrillation if the R wave time limit is greater than the parameter threshold corresponding to the R wave time limit, and to indicate that ventricular fibrillation has not occurred if the R wave time limit is less than or equal to the parameter threshold corresponding to the R wave time limit; if the P wave amplitude is less than the parameter threshold corresponding to the P wave amplitude, it indicates the occurrence of ventricular fibrillation, and if the P wave amplitude is greater than or equal to the parameter threshold corresponding to the P wave amplitude, it indicates that ventricular fibrillation has not occurred; if the singular value decomposition entropy is greater than the parameter threshold corresponding to the singular value decomposition entropy, it indicates the occurrence of ventricular fibrillation, and if the singular value decomposition entropy is less than or equal to the parameter threshold corresponding to the singular value decomposition entropy, it indicates that ventricular fibrillation has not occurred.

8. The system according to claim 1, characterized in that The processor is further configured to determine, based on a preset probability range within which the probability lies, the degree of possibility that the probability represents ventricular fibrillation of the electrocardiogram signal.

9. The system according to claim 8, characterized in that The probability range interval includes a first interval, a second interval and a third interval, the first interval is smaller than the second interval, and the second interval is smaller than the third interval; The processor is also used to indicate that if the probability is in the first interval, the possibility of ventricular fibrillation in the ECG signal is small; if the probability is in the second interval, the possibility of ventricular fibrillation in the ECG signal is medium; if the probability is in the third interval, the possibility of ventricular fibrillation in the ECG signal is large.

10. A monitor, characterized in that: The monitor comprises any system according to claim 1 to claim 9; The monitor also includes an output device, which is used to display the probability of ventricular fibrillation occurring in the electrocardiogram signal.

Images