Arrhythmia detection method and apparatus, device, and medium

Abstract

Embodiments of the present application disclose a method and device for detecting arrhythmia, equipment and a storage medium. The method mainly comprises the following steps: acquiring an electrocardiosignal to be detected; extracting a target RR interval of a current cardiac cycle based on the electrocardiosignal, and acquiring a heartbeat type of the current cardiac cycle and a target T wave of the target RR interval; judging whether the electrocardiosignal appears RonT phenomenon according to the heartbeat type, the target RR interval and a T wave waveform feature of the target T wave, wherein the T wave waveform feature comprises a right edge width of the T wave, and the right edge width is a distance between a top point and a terminal point of the T wave. In addition to judging the RonT phenomenon of the RR interval of the electrocardiosignal, the present application also analyzes the T wave waveform feature on the electrocardiosignal, so that the result of judging the RonT phenomenon is more accurate, and the probability of false detection and missed detection is reduced.

Description

Technical Field

[0001] This invention relates to the technical field of heart rhythm detection, and more particularly to methods, devices, equipment and media for detecting arrhythmias. Background Technology

[0002] Monitoring equipment is mainly used to monitor a series of parameters, including electrocardiogram (ECG), blood pressure, blood oxygen saturation, respiration, and depth of anesthesia. Among these parameters, ECG is a crucial one. ECG monitoring includes at least arrhythmia analysis, and a significant alarm event in arrhythmia analysis is the Ron-T phenomenon. The Ron-T phenomenon refers to premature ventricular contractions occurring on the T wave of the preceding cardiac cycle, or in the anterior or posterior branch of the T wave. This occurs when ventricular repolarization is incomplete, and the ventricle is in a vulnerable period prone to repeated excitation. Currently, the detection of the Ron-T phenomenon in arrhythmias often results in numerous false positives and false negatives, leading to inaccurate test results. Summary of the Invention

[0003] Therefore, it is necessary to propose methods, devices, equipment, and media for detecting arrhythmias to address the aforementioned issues and solve the problem of inaccurate detection results.

[0004] To achieve the above objectives, the first aspect of this application provides a method for detecting arrhythmia, the method comprising:

[0005] Acquire the electrocardiogram signal to be detected;

[0006] Based on the ECG signal, the target RR interval of the current cardiac cycle is extracted, and the heartbeat type of the current cardiac cycle and the target T wave of the target RR interval are obtained.

[0007] Based on the heartbeat type, the target RR interval, and the T-wave waveform characteristics of the target T wave, it is determined whether the electrocardiogram signal exhibits the RonT phenomenon. The T-wave waveform characteristics include the right-side width of the T wave, which is the distance between the apex and the end point of the T wave.

[0008] Furthermore, the step of extracting the target RR interval of the current cardiac cycle based on the electrocardiogram signal, obtaining the heartbeat type of the current cardiac cycle, and the target T wave of the target RR interval specifically includes:

[0009] Extract the initial RR interval of the current cardiac cycle from the electrocardiogram signal;

[0010] The product of the preset interval coefficient and the initial RR interval is used as the target RR interval;

[0011] Get the heartbeat type of the current cardiac cycle;

[0012] If the current cardiac cycle's beat type is an abnormal beat, then the target T wave on the target RR interval is obtained, and the step of determining whether the ECG signal exhibits the RonT phenomenon based on the beat type, the target RR interval, and the T wave waveform characteristics of the target T wave continues.

[0013] Furthermore, obtaining the target T wave on the target RR interval specifically includes:

[0014] A peak-valley search is performed on the target RR interval to obtain target peak-valley information, which includes the amplitude and width of the target peak-valley. The target peak-valley is any one of all peaks and valleys on the target RR interval.

[0015] According to the preset template matching rules, the T-wave template in the preset storage area is matched with the target peak and valley information, and the peak and valley corresponding to the successfully matched target peak and valley information are used as the target T-wave of the target RR interval.

[0016] Furthermore, the step of matching the T-wave template in the preset storage area with the target peak-valley information according to the preset template matching rules, and taking the peak-valley corresponding to the successfully matched target peak-valley information as the target T-wave of the target RR interval, specifically includes:

[0017] Obtain the T-wave template from the preset storage area;

[0018] If the T-wave template is not obtained in the storage area, the target peak with the largest amplitude among the target peaks and valleys with an amplitude greater than a preset amplitude threshold and a width greater than a preset width threshold is taken as the target T-wave of the target RR interval.

[0019] When the T-wave template is obtained in the storage area, the Pearson correlation coefficient is calculated based on the target peak and valley information and the T-wave template to obtain the target correlation coefficient with the largest Pearson correlation coefficient among all the Pearson correlation coefficients.

[0020] When the target correlation coefficient is greater than the preset correlation coefficient threshold, it is determined that the peak and trough corresponding to the target correlation coefficient are successfully matched with the T-wave template, and the peak and trough corresponding to the target correlation coefficient are taken as the target T-wave of the target RR interval.

[0021] Furthermore, the T-wave waveform features also include: the electrocardiogram signal on the T-wave, the RT interval, and the amplitude of the T-wave, wherein the RT interval is the interval from the peak of the R-wave to the peak of the T-wave in the current cardiac cycle;

[0022] The method further includes:

[0023] If the heartbeat type of the current cardiac cycle is a normal heartbeat, then it is determined that the ECG signal does not show the RonT phenomenon, and the target T wave on the target RR interval is obtained;

[0024] Based on the T-wave waveform characteristics of the target T-wave, the T-wave template is updated according to the formula: Tmodel=1 / n×V(i)+(n-1) / n×Tmodel, and the updated T-wave template is saved to the storage area.

[0025] In the formula, Tmodel is the T-wave template, V(i) is the T-wave waveform feature, and n is a preset constant.

[0026] Furthermore, the types of abnormal heartbeats include ventricular premature beats and non-ventricular premature beats. Therefore, determining whether the electrocardiogram signal exhibits the RonT phenomenon based on the heartbeat type, the target RR interval, and the T-wave waveform characteristics of the target T wave specifically includes:

[0027] If the heartbeat type is non-ventricular premature beat, then it is determined that the electrocardiogram signal does not show the RonT phenomenon;

[0028] If the heartbeat type is ventricular premature beat, then determine whether the first interval is less than the second interval, wherein the first interval is the interval of the target RR interval, the second interval is the interval of the average RR interval multiplied by a preset interval coefficient, and the average RR interval is the average interval of the j RR intervals preceding the target RR interval;

[0029] If the first spacing is not less than the second spacing, it is determined that the electrocardiogram signal does not exhibit the RonT phenomenon;

[0030] When the first spacing is less than the second spacing, the ECG signal is judged to have RonT phenomenon based on the target T wave and the waveform characteristics of the target T wave.

[0031] Furthermore, determining whether the electrocardiogram signal exhibits the RonT phenomenon based on the target T wave and its waveform characteristics specifically includes:

[0032] If the target T wave of the target RR interval is not obtained, it is determined that the electrocardiogram signal exhibits the RonT phenomenon.

[0033] If a target T wave with the target RR interval is obtained, and the right width of the target T wave is less than a preset right width threshold, then it is determined that the electrocardiogram signal exhibits the RonT phenomenon.

[0034] If the target T wave of the target RR interval is obtained, and the right width of the target T wave is not less than the right width threshold, then it is determined that the electrocardiogram signal does not exhibit the RonT phenomenon.

[0035] To achieve the above objectives, a second aspect of this application provides a device for detecting arrhythmia, the device comprising: a signal acquisition unit, a signal processing unit, and a signal detection unit;

[0036] The signal acquisition unit is used to acquire the electrocardiogram signal to be detected;

[0037] The signal processing unit is used to extract the target RR interval of the current cardiac cycle based on the electrocardiogram signal, and to obtain the heartbeat type of the current cardiac cycle, as well as the target T wave of the target RR interval;

[0038] The signal detection unit is used to determine whether the electrocardiogram signal exhibits the RonT phenomenon based on the heartbeat type, the target RR interval, and the T-wave waveform characteristics of the target T wave. The T-wave waveform characteristics include the right-side width of the T wave, which is the distance between the apex and the end point of the T wave.

[0039] To achieve the above objectives, a third aspect of this application provides a computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the processor performs the steps of the method described in the first aspect.

[0040] To achieve the above objectives, a fourth aspect of this application provides a computer device including a memory and a processor, characterized in that the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method described in the first aspect.

[0041] The embodiments of the present invention have the following beneficial effects:

[0042] This invention primarily acquires the electrocardiogram (ECG) signal to be detected; extracts the target RR interval of the current cardiac cycle based on the ECG signal, and obtains the heartbeat type of the current cardiac cycle, as well as the target T wave of the target RR interval; based on the heartbeat type, the target RR interval, and the T wave waveform characteristics of the target T wave, it determines whether the ECG signal exhibits the RonT phenomenon. The T wave waveform characteristics include the right-hand width of the T wave, which is the distance between the apex and the end of the T wave. In addition to determining the RonT phenomenon based on the RR interval of the ECG signal, this invention also incorporates the analysis of the T wave waveform characteristics on the ECG signal, making the determination of the RonT phenomenon more accurate and reducing the probability of false positives and false negatives. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] in:

[0045] Figure 1 This is a schematic flowchart of the method for detecting arrhythmia in an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of the process for obtaining parameters in an embodiment of the present invention;

[0047] Figure 3 This is a waveform diagram of the electrocardiogram signal according to an embodiment of the present invention;

[0048] Figure 4 This is a structural block diagram of the detection device for central rhythm aberration according to the present invention;

[0049] Figure 5 This is a diagram showing the internal structure of a computer device in an embodiment of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] The R-on-T phenomenon occurs when the R wave of a premature ventricular contraction (PVC) appears on the T wave of the preceding cardiac cycle. It happens when ventricular repolarization is incomplete, and the ventricles are in a vulnerable period prone to repeated excitation. Because the R-on-T phenomenon can lead to fatal arrhythmias such as ventricular tachycardia and ventricular fibrillation, its detection on an electrocardiogram should be considered a warning sign and should be taken seriously. Therefore, obtaining accurate detection results for the R-on-T phenomenon is crucial.

[0052] Based on this, the present invention proposes a method for detecting cardiac arrhythmias to obtain more accurate detection results of the RonT phenomenon, which can be found in [reference needed]. Figure 1 , Figure 1 This is a flowchart illustrating a method for detecting arrhythmia in an embodiment of the present invention. The method includes:

[0053] Step 100: Obtain the electrocardiogram signal to be detected.

[0054] Specifically, the electrical activity of the human heart is usually monitored by electrocardiogram (ECG) monitoring. During this monitoring process, the monitoring device receives ECG signals. In this embodiment of the invention, the ECG signals are acquired and analyzed to determine whether arrhythmia has occurred.

[0055] After acquiring the electrocardiogram (ECG) signal, the noise level may be high, affecting subsequent processing or detection results. Therefore, the ECG signal can be filtered to reduce noise. Preferably, the ECG signal data can be subjected to a 0.5Hz high-pass filter, a 40Hz low-pass filter, and a 50Hz or 60Hz power frequency filter to make the noise-reduced ECG signal easier to identify.

[0056] Step 200: Extract the target RR interval of the current cardiac cycle based on the electrocardiogram signal, and obtain the heartbeat type of the current cardiac cycle, as well as the target T wave of the target RR interval.

[0057] Specifically, a cardiac cycle refers to the period from the start of one heartbeat to the start of the next heartbeat. Each cardiac cycle includes at least the QRS complex and the T wave. The QRS complex includes the Q wave, R wave, and S wave. This embodiment of the invention mainly focuses on the analysis of the QRS complex and the T wave.

[0058] The interval between any two adjacent QRS waves is the RR interval. In this embodiment, the target RR interval refers to the interval between the peak of the QRS wave and the peak of the T wave in the current cardiac cycle. The target RR interval can be extracted from the electrocardiogram signal by the QRS wave detection algorithm.

[0059] After obtaining the current cardiac cycle, determine the type of heartbeat in the current cardiac cycle, and find the target T wave that meets the preset conditions on the target RR interval.

[0060] Step 300: Based on the heartbeat type, target RR interval, and T wave waveform characteristics of the target T wave, determine whether the ECG signal exhibits the RonT phenomenon. The T wave waveform characteristics include the right width of the target T wave, which is the distance between the peak and the end point of the target T wave.

[0061] After acquiring the target T-wave, its waveform features can be obtained, including at least the right-hand width. The right-hand width is the width between the peak and the endpoint of the target T-wave. The peak can be the highest point of a peak-valley pattern. The endpoint can be determined by searching to the right from the peak. The search ends when five consecutive signal points with amplitudes less than 1 / 10 of the peak amplitude are found, and the midpoint of these five points is taken as the endpoint. Using this method to obtain the endpoint of the target T-wave, more accurate T-wave waveform features can be obtained, providing more precise data for subsequent detection. The method for determining the endpoint can also be used to determine the starting point to obtain more waveform features, which will not be elaborated upon here.

[0062] Since the characteristic of the RonT phenomenon is that the QRS complex of the premature ventricular contraction falls on the T wave of the previous cardiac cycle, after obtaining the heartbeat type and the T wave waveform characteristics of the target T wave in the current cardiac cycle, based on the characteristics of the RonT phenomenon, the ECG signal is judged to have the RonT phenomenon according to the heartbeat type, T wave waveform characteristics and the target RR interval.

[0063] Unlike existing methods for detecting the RonT phenomenon, the detection method proposed in this invention does not determine whether the RonT phenomenon has occurred based on the length of the RR interval. Instead, it determines whether the RonT phenomenon has occurred by combining the RR interval with the T-wave waveform characteristics of the target T wave, effectively reducing the probability of false detection and false negative detection when detecting the RonT phenomenon.

[0064] This invention provides methods for obtaining the target RR interval, the heartbeat type of the current cardiac cycle, and the target T wave with the target RR interval. See also: Figure 2 , Figure 2 This is a flowchart illustrating the parameter acquisition process in an embodiment of the present invention. It can be seen that step 200, extracting the target RR interval of the current cardiac cycle based on the electrocardiogram signal, and obtaining the heartbeat type of the current cardiac cycle, as well as the target T wave of the target RR interval, specifically includes:

[0065] Step 210: Extract the initial RR interval of the current cardiac cycle from the electrocardiogram signal, and use the product of the preset interval coefficient and the initial RR interval as the target RR interval.

[0066] This invention provides an embodiment of the method for obtaining the initial RR interval of the current cardiac cycle from the acquired electrocardiogram (ECG) signal to be detected. In addition, an interval coefficient is also obtained, which is pre-set according to the actual application scenario. After obtaining the interval coefficient and the initial RR interval, the initial RR interval is processed. Optionally, the interval coefficient is multiplied by the initial RR interval to obtain the target RR interval, and then low-pass filtered to obtain the processed target RR interval. This makes the obtained target RR interval easier to identify and facilitates subsequent analysis. For example, if the interval coefficient is pre-set to 0.75, then the target RR interval is 0.75 times the initial RR interval.

[0067] Step 220: Obtain the heartbeat type of the current cardiac cycle.

[0068] In this embodiment of the invention, it is also necessary to obtain the heartbeat type of the current cardiac cycle and determine how to proceed to the next step based on the heartbeat type. Before determining whether the electrocardiogram signal exhibits the RonT phenomenon based on the heartbeat type, T wave waveform characteristics, and target RR interval, preliminary screening can be performed by the heartbeat type, making the detection more efficient.

[0069] Step 230a: If the heartbeat type of the current cardiac cycle is a normal heartbeat, then it is determined that the ECG signal does not show the RonT phenomenon.

[0070] Step 230b: If the heartbeat type of the current cardiac cycle is an abnormal heartbeat, then obtain the target T wave on the target RR interval, and continue to execute the step of determining whether the ECG signal has RonT phenomenon based on the heartbeat type, target RR interval and target T wave T wave waveform characteristics.

[0071] Specifically, when the heartbeat type of the current cardiac cycle is abnormal, it indicates that there is an abnormality in the electrocardiogram signal. This may be due to the RonT phenomenon, and an abnormal heartbeat warning should be issued so that the abnormality can be investigated in time.

[0072] When an abnormality in the electrocardiogram signal is detected, the target T wave and its waveform characteristics are acquired for further analysis. Specifically, in step 230b, acquiring the target T wave within the target RR interval includes:

[0073] Step 1: Perform a peak-valley search on the target RR interval to obtain target peak-valley information. The target peak-valley information includes the amplitude and width of the target peak-valley. The target peak-valley is any one of the peaks and valleys on the target RR interval.

[0074] Specifically, searching for peak and trough information on the target RR interval is to find all possible T-wave targets on the target RR interval. Therefore, searching for all peaks and troughs on the target RR interval and obtaining the amplitude and width of all peaks and troughs can be understood as follows: the amplitude of a peak or trough refers to the distance between the peak and the lowest point of the peak or trough, and the width of a peak or trough is the distance between the beginning and the end point of the peak or trough.

[0075] Step 2: According to the preset template matching rules, match the T-wave template in the preset storage area with the target peak and valley information, and take the peak and valley corresponding to the successfully matched target peak and valley information as the target T-wave of the target RR interval.

[0076] Specifically, after finding the peak and trough information, the information of each peak and trough is matched with the T-wave template in the preset storage area. If the match is successful, the matched peak and trough is taken as the target T-wave; if the match is unsuccessful, the target T-wave is not obtained, that is, the target T-wave does not exist on the target RR interval.

[0077] This invention provides a method for obtaining an optimal target T-wave by matching a T-wave template with peak and valley information. The method specifically includes:

[0078] 1. Obtain the T-wave template from the preset storage area.

[0079] 2a. If a T-wave template is not obtained in the storage area, the target peak with the largest amplitude among the target peaks and valleys with an amplitude greater than the preset amplitude threshold and a width greater than the preset width threshold shall be taken as the target T-wave of the target RR interval.

[0080] 2b. When the T-wave template is obtained in the storage area, the Pearson correlation coefficient is calculated based on the peak and valley information of each target and the T-wave template, and the target correlation coefficient with the largest Pearson correlation coefficient is obtained.

[0081] When the target correlation coefficient is greater than the preset correlation coefficient threshold, it is determined that the peak and trough corresponding to the target correlation coefficient are successfully matched with the T-wave template, and the peak and trough corresponding to the target correlation coefficient are taken as the target T-wave of the target RR interval.

[0082] Specifically, T-wave templates can be pre-set and stored in the preset storage area, or they can be left unset and unstored. The following describes how to perform T-wave matching in both cases:

[0083] (1) If a T-wave template is not pre-set and stored in the storage area, then the T-wave template cannot be obtained from the storage area. In this case, among all the target peaks and valleys searched, the target peak and valley with the largest amplitude that is greater than the preset amplitude threshold and the width that is greater than the preset width threshold is taken as the target T-wave, and the target T-wave is saved as the T-wave template in the storage area to provide a T-wave template for the next matching. Preferably, the amplitude threshold can be 1 / 10 of the average QRS wave amplitude, and the average QRS wave amplitude is the average amplitude of all the QRS waves searched. The width threshold can be pre-set according to the actual application scenario. For example, the width threshold can be set to 20ms. Conversely, if there is no peak or valley that meets the above conditions from all the peak and valley information, then it is considered that there is no target T-wave in the target RR interval.

[0084] (2) When a T-wave template is pre-set and stored in the storage area, the T-wave template can be obtained from the storage area. At this time, the information of each peak and valley is matched with the T-wave template. The matching method can be to calculate the Pearson correlation coefficient between the information of each peak and valley and the T-wave template, select the largest correlation coefficient among all Pearson correlation coefficients as the target correlation coefficient, and compare the target correlation coefficient with the preset correlation coefficient threshold. If the comparison result is that the target correlation coefficient is greater than the correlation coefficient threshold, then it is determined that the peak and valley corresponding to the target correlation coefficient are successfully matched with the T-wave template, and the peak and valley corresponding to the target correlation coefficient are taken as the target T-wave. If the comparison result is that the target correlation coefficient is not greater than the correlation coefficient threshold, then it is determined that the peak and valley corresponding to the target correlation coefficient are not successfully matched with the T-wave template, that is, there is no target T-wave on the target RR interval.

[0085] The above-described method for obtaining the target T-wave combines the peak and trough information of the target RR interval with the T-wave template for analysis, thereby obtaining the target T-wave that meets the preset conditions on the target RR interval. Setting the preset conditions in the above method is to obtain more accurate target T-wave information on the target RR interval.

[0086] This invention combines the T-wave template with the peak and trough information on the target RR interval for analysis, sets preset conditions, and uses the peak and trough on the target RR interval that meet the preset conditions as the target T-wave, so as to obtain a more accurate target T-wave and thus improve the accuracy of the detection results.

[0087] After obtaining the accurate waveform characteristics of the target T wave, the ECG signal can be analyzed to determine whether the RonT phenomenon occurs, based on the heartbeat type and the waveform characteristics of the target RR interval. It is understood that abnormal heartbeats include ventricular premature beats and non-ventricular premature beats. Therefore, step 300, based on the heartbeat type, the target RR interval, and the T wave waveform characteristics of the target T wave, determines whether the ECG signal exhibits the RonT phenomenon, specifically including:

[0088] 1. If the heartbeat type is non-ventricular premature beat, then the RonT phenomenon is not present in the electrocardiogram signal. When the detected heartbeat type is non-ventricular premature beat, it can be considered that no abnormality has occurred or the possibility of RonT phenomenon has been ruled out.

[0089] 2. If the heartbeat type is ventricular premature beat (PVC), then determine whether the first interval is less than the second interval. The first interval is the interval of the target RR interval, and the second interval is the interval of the average RR interval multiplied by a preset interval coefficient. The average RR interval is the average interval of the j preceding RR intervals of the target RR interval. When the detected heartbeat type is PVC, it can be considered that the ECG signal may exhibit the RonT phenomenon, but further analysis is needed to determine whether the RonT phenomenon has occurred. Therefore, if the heartbeat type is PVC, the ECG signal is judged to have the RonT phenomenon based on the target RR interval, average RR interval, and T wave waveform characteristics. The specific judgment process may include:

[0090] (1) If the first interval is not less than the second interval, it is determined that the electrocardiogram signal does not show the RonT phenomenon.

[0091] (2) When the first interval is less than the second interval, the ECG signal does not show the RonT phenomenon based on the target T wave and the waveform characteristics of the target T wave.

[0092] (2a) If the target T wave of the target RR interval is not obtained, it is determined that the ECG signal shows the RonT phenomenon.

[0093] (2b) If the target T wave of the target RR interval is obtained and the right width of the target T wave is less than the preset right width threshold, then the RonT phenomenon is determined to have occurred in the ECG signal.

[0094] (2c) If the target T wave of the target RR interval is obtained and the right width of the target T wave is not less than the right width threshold, then it is determined that the ECG signal does not show the RonT phenomenon.

[0095] Specifically, based on a comparison between the first and second intervals, it is determined whether the ECG signal exhibits the RonT phenomenon. If the first interval is not less than the second interval, the ECG signal does not exhibit the RonT phenomenon; if the first interval is less than the second interval and the target T wave is absent, the ECG signal exhibits the RonT phenomenon; if the first interval is less than the second interval and the right width of the target T wave is less than a preset right width threshold, the ECG signal exhibits the RonT phenomenon; if the first interval is less than the second interval and the right width of the target T wave is not less than the right width threshold, the ECG signal does not exhibit the RonT phenomenon.

[0096] Based on the above judgment method, in addition to judging whether the RonT phenomenon occurs based on the target RR interval interval, the target RR interval and T wave waveform characteristics are also analyzed to judge whether the ECG signal has the RonT phenomenon, which reduces the probability of false detection and false negative detection.

[0097] To make the T-wave template more accurate and reduce errors, in addition to obtaining the T-wave waveform characteristics of the right width of the target T-wave, other T-wave waveform characteristics can also be obtained. (See reference...) Figure 3 , Figure 3 The waveform diagram of the electrocardiogram signal in an embodiment of the present invention is shown below. Figure 3 As shown, Tpk is the T-wave apex, Ton is the T-wave start point, Toff is the T-wave end point, Ta is the T-wave amplitude, and Tr is the right-side width of the T-wave. Therefore, the T-wave waveform characteristics can also include: the electrocardiogram signal on the T-wave, the RT interval, and the T-wave amplitude, where the RT interval is the interval from the R-wave apex to the T-wave apex of the current cardiac cycle. If the above T-wave waveform characteristics are obtained, then after determining that the heartbeat type of the current cardiac cycle is a normal heartbeat, the target T-wave on the target RR interval can be obtained, and the T-wave template can be updated according to the formula: Tmodel=1 / n×V(i)+(n-1) / n×Tmodel, and the updated T-wave template can be saved to the storage area; where Tmodel is the T-wave template, V(i) is the T-wave waveform characteristic, and n is a preset constant. For example, the T-wave waveform characteristics during the target RR interval can be V(i) = {Si0, Si1, Si2, ..., Sie, RTIi, Tai, Tri}, where {Si0, Si1, Si2, ..., Sie} represent the amplitudes of all signal points between the start and end points of the target T-wave, RTIi is the RT interval, Tai is the amplitude of the target T-wave, and Tri is the right-hand width of the target T-wave. Based on this, an adaptive process of updating the T-wave template using the obtained T-wave waveform characteristics can achieve more accurate T-wave detection in subsequent tests, thereby further improving the accuracy of the detection results.

[0098] This invention provides a device for detecting cardiac arrhythmia, which can be referred to. Figure 4 , Figure 4 This is a structural block diagram of the detection device for central rhythm disorder of the present invention. The device includes: a signal acquisition unit 401, a signal processing unit 402, and a signal detection unit 403.

[0099] The signal acquisition unit 401 is used to acquire the electrocardiogram signal to be detected.

[0100] The signal processing unit 402 is used to extract the target RR interval of the current cardiac cycle based on the electrocardiogram signal, and to obtain the heartbeat type of the current cardiac cycle, as well as the target T wave of the target RR interval.

[0101] The signal detection unit 403 is used to determine whether the electrocardiogram signal has the RonT phenomenon based on the heartbeat type, the target RR interval and the T wave waveform characteristics of the target T wave. The T wave waveform characteristics include the right width of the target T wave, which is the distance between the peak and the end point of the target T wave.

[0102] The detection device proposed in this invention, in addition to judging the RonT phenomenon by the RR interval of the electrocardiogram signal, also combines the analysis of the T wave waveform characteristics on the electrocardiogram signal, making the judgment of the occurrence of the RonT phenomenon more accurate and reducing the probability of false detection and missed detection.

[0103] Figure 5 An internal structural diagram of a computer device according to one embodiment of the present invention is shown. This computer device can specifically be a terminal or a system. Figure 5 As shown, the computer device includes a processor, memory, and network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program causes the processor to perform the steps in the above-described method embodiments. The internal memory may also store a computer program, which, when executed by the processor, causes the processor to perform the steps in the above-described method embodiments. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0104] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps in the above method embodiments.

[0105] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the steps in the above method embodiments.

[0106] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can 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. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0107] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for detecting cardiac arrhythmia, characterized in that, The method includes: Acquire the electrocardiogram signal to be detected; Based on the ECG signal, the target RR interval of the current cardiac cycle is extracted, and the heartbeat type of the current cardiac cycle and the target T wave of the target RR interval are obtained. Based on the heartbeat type, the target RR interval, and the T-wave waveform characteristics of the target T wave, it is determined whether the electrocardiogram signal exhibits the RonT phenomenon. The T-wave waveform characteristics include the right-side width of the T wave, which is the distance between the apex and the end of the T wave. Specifically, the step of extracting the target RR interval of the current cardiac cycle based on the electrocardiogram signal, obtaining the heartbeat type of the current cardiac cycle, and the target T wave of the target RR interval includes: Extract the initial RR interval of the current cardiac cycle from the electrocardiogram signal; The product of the preset interval coefficient and the initial RR interval is used as the target RR interval; Get the heartbeat type of the current cardiac cycle; If the current cardiac cycle heartbeat type is an abnormal heartbeat, then the target T wave on the target RR interval is obtained, and the step of determining whether the electrocardiogram signal has RonT phenomenon based on the heartbeat type, the target RR interval and the T wave waveform characteristics of the target T wave is continued; The abnormal heartbeats include ventricular premature beats and non-ventricular premature beats. The step of determining whether the electrocardiogram signal exhibits the RonT phenomenon based on the heartbeat type, the target RR interval, and the T-wave waveform characteristics of the target T wave specifically includes: If the heartbeat type is non-ventricular premature beat, then it is determined that the electrocardiogram signal does not show the RonT phenomenon; If the heartbeat type is ventricular premature beat, then determine whether the first interval is less than the second interval, wherein the first interval is the interval of the target RR interval, and the second interval is the interval of the average RR interval multiplied by a preset interval coefficient, wherein the average RR interval is the average interval of the first j RR intervals of the target RR interval; If the first spacing is not less than the second spacing, it is determined that the electrocardiogram signal does not exhibit the RonT phenomenon; When the first spacing is less than the second spacing, the ECG signal is judged to have RonT phenomenon based on the target T wave and the waveform characteristics of the target T wave.

2. The method according to claim 1, characterized in that, The acquisition of the target T wave on the target RR interval specifically includes: A peak-valley search is performed on the target RR interval to obtain target peak-valley information, which includes the amplitude and width of the target peak-valley. The target peak-valley is any one of all peaks and valleys on the target RR interval. According to the preset template matching rules, the T-wave template in the preset storage area is matched with the target peak and valley information, and the peak and valley corresponding to the successfully matched target peak and valley information are used as the target T-wave of the target RR interval.

3. The method according to claim 2, characterized in that, The step of matching the T-wave template in the preset storage area with the target peak-valley information according to the preset template matching rules, and taking the peak-valley corresponding to the successfully matched target peak-valley information as the target T-wave of the target RR interval, specifically includes: Obtain the T-wave template from the preset storage area; If the T-wave template is not obtained in the preset storage area, the target peak with the largest amplitude among the target peaks and valleys with an amplitude greater than a preset amplitude threshold and a width greater than a preset width threshold is taken as the target T-wave of the target RR interval. When the T-wave template is obtained in the preset storage area, the Pearson correlation coefficient is calculated based on the target peak and valley information and the T-wave template to obtain the target correlation coefficient with the largest Pearson correlation coefficient among all the Pearson correlation coefficients. When the target correlation coefficient is greater than the preset correlation coefficient threshold, it is determined that the peak and trough corresponding to the target correlation coefficient are successfully matched with the T-wave template, and the peak and trough corresponding to the target correlation coefficient are taken as the target T-wave of the target RR interval.

4. The method according to claim 2, characterized in that, The T-wave waveform features also include: the electrocardiogram signal on the T-wave, the RT interval, and the amplitude of the T-wave, wherein the RT interval is the interval from the peak of the R-wave to the peak of the T-wave in the current cardiac cycle; The method further includes: If the heartbeat type of the current cardiac cycle is a normal heartbeat, then it is determined that the ECG signal does not show the RonT phenomenon, and the target T wave on the target RR interval is obtained; Based on the T-wave waveform characteristics of the target T-wave, the T-wave template is updated according to the formula: Tmodel=1 / n×V(i)+(n-1) / n×Tmodel, and the updated T-wave template is saved to the preset storage area. In the formula, Tmodel is the T-wave template, V(i) is the T-wave waveform feature, and n is a preset constant.

5. The method according to claim 1, characterized in that, The step of determining whether the electrocardiogram signal exhibits the RonT phenomenon based on the target T wave and the waveform characteristics of the target T wave specifically includes: If the target T wave of the target RR interval is not obtained, it is determined that the electrocardiogram signal exhibits the RonT phenomenon. If a target T wave with the target RR interval is obtained, and the right width of the target T wave is less than a preset right width threshold, then it is determined that the electrocardiogram signal exhibits the RonT phenomenon. If the target T wave of the target RR interval is obtained, and the right width of the target T wave is not less than the right width threshold, then it is determined that the electrocardiogram signal does not exhibit the RonT phenomenon.

6. A device for detecting cardiac arrhythmia, characterized in that, The device includes: a signal acquisition unit, a signal processing unit, and a signal detection unit; The signal acquisition unit is used to acquire the electrocardiogram signal to be detected; The signal processing unit is used to extract the target RR interval of the current cardiac cycle based on the electrocardiogram signal, and to obtain the heartbeat type of the current cardiac cycle, as well as the target T wave of the target RR interval; The signal detection unit is used to determine whether the electrocardiogram signal exhibits RonT phenomenon based on the heartbeat type, the target RR interval, and the T wave waveform characteristics of the target T wave. The T wave waveform characteristics include the right width of the T wave, which is the distance between the apex and the end of the T wave. The signal processing unit is further configured to extract the initial RR interval of the current cardiac cycle from the electrocardiogram signal; use the product of a preset interval coefficient and the initial RR interval as the target RR interval; obtain the heartbeat type of the current cardiac cycle; if the heartbeat type of the current cardiac cycle is an abnormal heartbeat, obtain the target T wave on the target RR interval, and continue to execute the step of determining whether the electrocardiogram signal exhibits the RonT phenomenon based on the heartbeat type, the target RR interval, and the T wave waveform characteristics of the target T wave; The abnormal heartbeat types include ventricular premature beats and non-ventricular premature beats. The signal detection unit is further configured to: if the heartbeat type is a non-ventricular premature beat, determine that the electrocardiogram signal does not exhibit the RonT phenomenon; if the heartbeat type is a ventricular premature beat, determine whether a first interval is less than a second interval, wherein the first interval is the interval of the target RR interval, and the second interval is the interval of the average RR interval multiplied by a preset interval coefficient, where the average RR interval is the average interval of the first j RR intervals of the target RR interval; if the first interval is not less than the second interval, determine that the electrocardiogram signal does not exhibit the RonT phenomenon; if the first interval is less than the second interval, determine whether the electrocardiogram signal exhibits the RonT phenomenon based on the target T wave and the T wave waveform characteristics of the target T wave.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, the processor performs the steps of the method as described in any one of claims 1 to 5.

8. A computer device, comprising a memory and a processor, characterized in that, The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 5.

Images