Electrocardiosignal R wave identification method and device and electronic equipment

Abstract

The invention relates to the technical field of medical equipment, and provides an electrocardiosignal R wave identification method, device and equipment. The method comprises the steps of determining upper and lower limit thresholds of electrocardiosignal state transition, and determining a first state transition point and a second state transition point based on intersection points of the upper and lower limit thresholds and electrocardiosignals and signal trends on two sides of the intersection points; acquiring a plurality of groups of current continuous first and second state transition points, and determining an R wave starting point based on the time difference between the first and second state transition points in the plurality of groups; timing is started from the R wave starting point to the end of the ventricular refractory period, then a first state transition point closest to the R wave starting point is recognized, and the newly recognized first state transition point serves as a new R wave starting point. According to the scheme, the recognition accuracy of the R wave in the electrocardiosignal is improved, the probability that the R wave in the electrocardiosignal is mistakenly removed or the T wave is recognized as the R wave is reduced, and the problem that counterpulsation errors are generated in the IABP technical process is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to an R-wave recognition method, device and equipment for electrocardiogram signals. Background Art

[0002] The QRS complex is an important complex wave in the electrocardiogram (ECG), in which the R wave is the most prominent part, which reflects the potential change process of ventricular depolarization. The time range of the QRS complex under normal circumstances is 0.06-0.10 seconds, and this short period of time contains a series of complex electrophysiological activities. Ventricular premature beats (VPs) are a type of abnormal R wave. The R wave of ventricular premature beats is usually wide and deformed. The R wave of ventricular premature beats appears early, which will disrupt the normal RR interval. It will appear in the normal RR interval and prolong the RR interval after the premature beat. The T wave is an important component of the electrocardiogram (ECG). It represents the repolarization process of the ventricles. The normal T wave is generally a rounded wave with a relatively gentle ascending and descending branch, not as steep as the R wave, and the amplitude is generally smaller than the R wave in the QRS complex. Abnormal T waves include tall T waves (T wave amplitude is significantly higher than the normal range), flat or inverted T waves (flat T waves refer to a decrease in the amplitude of the T wave, which is less than 1 / 10 of the R wave in the same lead; inverted T waves refer to the direction of the T wave being opposite to that of normal), double peaks or notches in T waves (double peaks or notches in T waves may indicate myocardial disease or electrolyte imbalance).

[0003] In the IABP (Intra-aortic Balloon Pump) technology, when inflation and deflation are controlled by ECG, inflation and deflation are performed based on the detected R wave. After the R wave is detected, the device will inflate and inhale the balloon at the appropriate time according to the RR interval. In the prior art, T waves are generally filtered out by filtering to detect R waves. However, when premature ventricular contractions or tall T waves occur, due to the high amplitude of premature ventricular contractions and tall T waves, there is an overlap in the spectrum of premature ventricular contractions and tall T waves. This spectrum overlap makes the premature ventricular contraction signal also removed when the T wave interference is filtered out. As a special type of R wave, premature ventricular contraction will cause counterpulsation errors after being filtered out, making the balloon inflation and deflation time completely inconsistent with the actual contraction and relaxation cycle of the heart. For example, if the balloon is inflated too early, that is, it is inflated before the heart has fully entered the diastole, it will interfere with the normal relaxation process of the heart. When the balloon is inflated too late, for example, it is inflated after most of the diastole has passed, the best time for coronary artery perfusion will be missed.

[0004] Based on this, there is an urgent need for a method that can accurately and effectively identify the R wave of the electrocardiogram signal. Summary of the invention

[0005] In view of the method in the prior art of filtering out T waves to detect R waves, special R waves (such as premature ventricular contractions) are easily mistaken for T waves and filtered out together, making it difficult to accurately and effectively identify the R waves of electrocardiogram signals. The present disclosure provides a method, device and equipment for identifying R waves of electrocardiogram signals.

[0006] According to a first aspect of the present invention, there is provided a method for recognizing an R wave of an electrocardiogram signal, comprising: Determine upper and lower thresholds for the state transition of the ECG signal, and determine the first and second state transition points based on the intersections of the upper and lower thresholds with the ECG signal and the signal trends on both sides of the intersections; Acquire the current multiple continuous groups of first and second state transition points, and determine the R wave starting point based on the time difference between the first and second state transition points in the multiple groups; Timing starts from the R wave starting point and ends at the end of the ventricular refractory period, and then the first state transition point closest to the R wave starting point is identified, and the newly identified first state transition point is used as a new R wave starting point.

[0007] In some embodiments, the step of determining the first and second state transition points based on the intersection of the upper and lower thresholds and the electrocardiogram signal and the signal trends on both sides of the intersection includes: Determining multiple states of the electrocardiogram signal according to the magnitude relationship between the electrocardiogram signal value and the upper and lower thresholds; The intersection of the upper and lower thresholds and the electrocardiogram signal is obtained, the signal trends on both sides of the intersection are determined according to the multiple states, and the first and second state transition points are determined according to the signal trends on both sides of the intersection.

[0008] In some embodiments, the step of determining the multiple states of the electrocardiogram signal according to the magnitude relationship between the electrocardiogram signal value and the upper and lower thresholds includes: If the ECG signal value exceeds the upper threshold, determining that the ECG signal is in a rising state; If the ECG signal value is lower than a lower threshold, determining that the ECG signal is in a decreasing state; If the ECG signal value is between the upper and lower thresholds, it is determined that the ECG signal is in a transition state.

[0009] In some embodiments, the step of determining the signal trends on both sides of the intersection according to the multiple states includes: If the signal state on both sides of the intersection changes from the transition state to the rising or falling state, determining that the signal trend on both sides of the intersection is the first trend; If the signal states on both sides of the intersection are changed from the rising or falling state to the transition state, it is determined that the signal trends on both sides of the intersection are the second trend.

[0010] In some embodiments, the step of obtaining the current multiple continuous groups of first and second state transition points and determining the R wave starting point based on the time difference between the first and second state transition points in the multiple groups includes: Acquire multiple sets of current continuous first and second state transition points, each set comprising continuous first and second state transition points; The time difference between the first and second state transition points of each group is calculated, and the first state transition point corresponding to the group with the smallest time difference among the multiple groups is determined as the R wave starting point.

[0011] In some embodiments, the step of determining the first and second state transition points according to the signal trends on both sides of the intersection point includes: If the signal trends on both sides of the intersection are the first trends, determining a first state transition point; If the signal trends on both sides of the intersection are the second trend, a second state transition point is determined.

[0012] In some embodiments, the step of determining the upper and lower thresholds of the ECG signal state transition includes: The upper and lower thresholds of the electrocardiogram signal state transition are determined according to the median value of the electrocardiogram signal amplitude, wherein the upper and lower thresholds correspond to the baseline of the electrocardiogram signal.

[0013] In some embodiments, the ECG signal is obtained by preprocessing the original ECG signal, including: The original ECG signal is subjected to high-pass filtering to remove the baseline drift, so that the baseline of the obtained ECG signal is 0.

[0014] According to a second aspect of the present invention, there is provided an R wave recognition device for an electrocardiogram signal, the device comprising: The first module is used to determine the upper and lower thresholds of the ECG signal state transition, and determine the first and second state transition points based on the intersections of the upper and lower thresholds and the ECG signal and the signal trends on both sides of the intersections; The second module is used to obtain the current multiple continuous groups of first and second state transition points, and determine the R wave starting point based on the time difference between the first and second state transition points in the multiple groups; The third module starts timing from the R wave starting point to the end of the ventricular refractory period, and then identifies the first state transition point closest to the R wave starting point, and uses the newly identified first state transition point as the new R wave starting point.

[0015] According to a third aspect of the present invention, there is further provided an electronic device, the electronic device comprising: at least one processor; and The memory stores a computer program that can be run on the processor, and the processor executes the aforementioned R wave recognition method of the electrocardiogram signal when executing the program.

[0016] The above-mentioned R wave recognition method of an ECG signal determines the upper and lower thresholds of the ECG signal state transition, determines the first and second state transition points of the ECG signal according to the intersection of the upper and lower thresholds and the ECG signal and the signal trends on both sides of the intersection, obtains the current multiple continuous groups of first and second state transition points, determines the R wave starting point in the current multiple continuous groups of first state transition points according to the time difference between the two, starts timing from the R wave starting point to the end of the ventricular refractory period, and then identifies the first state transition point closest to the R wave starting point, and uses the newly identified first state transition point as the R wave starting point. In this way, the accuracy of identifying the R wave starting point is improved, that is, the accuracy of R wave recognition in the ECG signal is improved, and the probability of erroneously removing the R wave (such as ventricular premature beats) in the ECG signal or identifying the T wave as the R wave is reduced, which can provide accurate R wave recognition results for subsequent IABP technology and reduce the problem of counterpulsation errors in the IABP technology process.

[0017] In addition, the present invention also provides an R-wave recognition device for an electrocardiogram signal and an electronic device, which can also achieve the above-mentioned technical effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flowchart of an R wave recognition method of an electrocardiogram signal provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the R wave in the ECG signal; Figure 3 It is a schematic diagram of the T wave in the ECG signal; Figure 4 It is a schematic diagram of premature ventricular contraction in the ECG signal; Figure 5 A schematic diagram of a first electrocardiogram signal provided by another embodiment of the present invention; Figure 6 A schematic diagram of a second electrocardiogram signal provided by another embodiment of the present invention; Figure 7 A schematic diagram of a third electrocardiogram signal provided by another embodiment of the present invention; Figure 8 A schematic diagram of a fourth electrocardiogram signal provided by another embodiment of the present invention; Fig. 9 A schematic diagram of a fifth electrocardiogram signal provided by another embodiment of the present invention; Fig.10 A schematic diagram of an R wave recognition device for an electrocardiogram signal provided by an embodiment of the present invention; Fig.11 FIG. 4 is a diagram showing the internal structure of an electronic device in another embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0021] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two non-identical entities with the same name or non-identical parameters. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. The subsequent embodiments will not explain this one by one.

[0022] In one embodiment, please refer to Figure 1 As shown, the present invention provides an R wave recognition method 100 of an electrocardiogram signal, specifically, comprising: Step 101, determining upper and lower thresholds of the ECG signal state transition, and determining the first and second state transition points based on the intersections of the upper and lower thresholds and the ECG signal and the signal trends on both sides of the intersections; Specifically, the ECG signal is obtained by preprocessing the original ECG signal, and the original ECG signal is filtered to remove power frequency interference, myoelectric interference and baseline drift. Through filtering, various interference factors are effectively removed, making the ECG signal purer. Combined with signal enhancement processing (for weak original ECG signals), normalization processing is further optimized, so that the ECG signal is within a suitable amplitude range and a unified scale, and the baseline of the ECG signal is 0, which facilitates the subsequent analysis and comparison of the signal.

[0023] Specifically, the ECG signal includes QRS complex, T wave, etc. The R wave in the QRS complex reflects the potential change process of ventricular depolarization, such as Figure 2 As shown in the figure, the bold part is the R wave in the ECG signal; the T wave reflects the repolarization process of the ventricle, such as Figure 3 As shown in the figure, the bold part is the T wave in the ECG signal; premature ventricular contraction is a special type of R wave, such as Figure 4As shown, the bold part is the premature ventricular depolarization in the ECG signal. The premature ventricular depolarization is caused by an ectopic beat from one ventricle. It is a ventricular event that occurs out of sequence, that is, there is no previous intervening atrial event (P wave or atrial pacemaker pulse) after the previous ventricular event.

[0024] Specifically, the process of determining the upper and lower thresholds of the ECG signal state transition is as follows: when the atrium is in a resting state, it is reflected in the ECG as a horizontal segment in the ECG signal, and the horizontal segment is determined as the baseline of the ECG signal, that is, baseline 0. Then, the amplitude of the ECG signal is obtained based on the baseline. The amplitude of the ECG signal refers to the maximum change value of the ECG signal relative to the baseline. The upper and lower thresholds of the ECG signal state transition are calculated based on the amplitude of the ECG signal. For example, half of the ECG signal amplitude (that is, the median) is taken as the upper and lower thresholds, or the average value of the ECG signal amplitude is taken as the upper and lower thresholds. The upper threshold and the lower threshold correspond to each other based on the baseline, such as Figure 5 As shown, Figure 5 A schematic diagram of a first type of ECG signal provided by another embodiment of the present invention, wherein the upper side of the baseline is the upper threshold, and the lower side of the baseline is the lower threshold. It can be understood that the upper and lower thresholds are dynamic thresholds as comparison criteria for judging the state of the ECG signal. The amplitudes of different ECG signals are different, and the upper and lower thresholds will also change accordingly.

[0025] Specifically, the upper and lower thresholds are used as the upper and lower thresholds for the transition of the ECG signal state, that is, the different states of the ECG signal are defined by the upper and lower thresholds, and the intersection of the ECG signal and the upper and lower thresholds is the state transition point to achieve the transition of different states. There are multiple signal trends on both sides of the intersection of the ECG signal and the upper and lower thresholds. Based on the signal trends on both sides of the intersection, the first state transition point and the second state transition point can be determined. For example, in a specific example, the three states of the ECG signal are determined according to the size relationship between the ECG signal value and the upper and lower thresholds. When the ECG signal value exceeds the upper threshold, it is determined that the ECG signal is in an ascending state. When the ECG signal value is lower than the lower threshold, it is determined that the ECG signal is in a descending state. When the ECG signal value is between the upper and lower thresholds, it is determined that the ECG signal is in a transition state. It can be understood that whether it is an ascending state, a descending state, or a transition state, it reflects the signal trend presented by the ECG signal. By judging the signal trend on both sides of the intersection, the intersection is determined to be the first or second state transition point. When the signal state on both sides of a certain intersection changes from a transition state to an ascending or descending state, it is determined to be the first trend. The intersection is determined to be the first state transition point based on the first trend, which reflects ventricular depolarization (if it is an R wave) or ventricular repolarization (if it is a T wave), and the corresponding heartbeat is detected. However, this application requires accurate identification of the R wave. Therefore, if only based on the state transition as a constraint, the T wave may also be identified as an R wave. When the signal state on both sides of a certain intersection changes from an ascending or descending state to a transition state, it is determined to be the second trend. Based on the second trend, the intersection is determined to be the second state transition point, which reflects the end of the ventricular depolarization (if it is an R wave) or ventricular repolarization (if it is a T wave).

[0026] Step 102, obtaining a plurality of sets of current continuous first and second state transition points, and determining the R wave starting point based on the time difference between the first and second state transition points in the plurality of sets; Specifically, a plurality of first and second state transition points that are currently continuous are obtained. If the adjacent first state transition points and second state transition points are taken as a group, at least two groups are obtained. The time difference between the first and second state transition points corresponding to each group is calculated and compared. The first state transition point in a group corresponding to the minimum time difference is obtained and used as the R wave starting point. Since the time difference of the R wave is smaller than the time difference of the T wave, the R wave starting point is determined by the minimum time difference of each group, and the heart beat point that may detect the T wave later is filtered out, so that the determined R wave starting point is only used for the subsequent detection of the R wave, reducing the interference of the T wave detection, which is conducive to improving the accuracy of the R wave recognition. For example, if you want to detect the R wave from a certain moment, record the moment as time 0, and record the time difference of the adjacent first and second state transition points on the electrocardiogram signal within an initial period of time (for example, within 5 seconds from time 0) from time 0. The time corresponding to the transition of the ECG signal from the transition state to the rising or falling state (where the state transition point involved is the first state transition point) and then to the transition state (where the state transition point involved is the first state transition point) is counted, that is, the time difference between the adjacent first and second state transition points, and multiple continuous time differences within 5s starting from time 0 are counted, recorded as tt1, tt2, etc., and each time difference is compared. Since the R wave is narrower than the T wave, the first state transition point corresponding to the smallest of the multiple time differences is used as the R wave starting point (that is, the R wave's heartbeat point), which can effectively filter out the T wave's heartbeat point. Based on the R wave starting point, the R wave is identified in the subsequent time, thereby effectively reducing the situation where the T wave's heartbeat point is mistaken for the R wave's heartbeat point, laying the foundation for the subsequent accurate identification of the R wave, reducing the risk of the T wave being mistakenly determined as the R wave, and ensuring the accuracy and reliability of the ECG signal R wave identification.

[0027] Step 103, starting from the R wave starting point to the end of the ventricular refractory period, then identifying the first state transition point closest to the R wave starting point, and using the newly identified first state transition point as the new R wave starting point.

[0028] Specifically, the ventricular refractory period refers to the time interval between adjacent heartbeats, which is generally 200ms. The ventricular refractory period is timed from the determined R-wave starting point to the end. After the ventricular refractory period ends, a new first-state transition point closest to it is identified again, and the new first-state transition point is updated as the new R-wave starting point. The R wave continues to be identified based on the R-wave starting point in the subsequent period. In other words, after the ventricular refractory period ends, a new first-state transition point is identified (the signal trend on both sides of the intersection of the ECG signal and the upper and lower thresholds is the first trend, which means that the signal state on both sides of the intersection changes from a transitional state to a rising or falling state). Based on this, it can be confirmed that the R-wave starting point in the ECG signal has been identified. Otherwise, it is not considered that the R-wave starting point has been identified. For example Figure 5In the ventricular refractory period, although the first state transition point is detected, it is not identified as the starting point of the R wave because it is within the ventricular refractory period (the condition for the end of the ventricular refractory period is not met), and its corresponding T wave is not identified as an R wave. Based on this, the starting point of the R wave in the ECG signal is accurately identified, and the T wave beat point is marked as an invalid beat point, so that it is effectively excluded in the identification process, thereby ensuring that the final identification result only presents the R wave, and does not involve other waveforms such as the T wave. The probability of the T wave beat point being misjudged as the R wave beat point is significantly reduced, the accuracy of R wave identification is improved, the risk of misjudging the T wave as the R wave is effectively reduced, and the accuracy and reliability of R wave identification in the ECG signal are improved, which provides a basis for subsequent heart disease diagnosis based on R wave identification and related clinical decision-making.

[0029] According to some embodiments of the present invention, the step of determining the first and second state transition points based on the intersection of the upper and lower limit thresholds and the ECG signal and the signal trends on both sides of the intersection includes: determining multiple states of the ECG signal according to the size relationship between the ECG signal value and the upper and lower limit thresholds; obtaining the intersection of the upper and lower limit thresholds and the ECG signal, determining the signal trends on both sides of the intersection according to the multiple states, and determining the first and second state transition points according to the signal trends on both sides of the intersection.

[0030] According to some embodiments of the present invention, the steps of determining multiple states of an ECG signal based on the size relationship between the ECG signal value and the upper and lower thresholds include: if the ECG signal value exceeds the upper threshold, determining that the ECG signal is in a rising state; if the ECG signal value is lower than the lower threshold, determining that the ECG signal is in a falling state; if the ECG signal value is between the upper and lower thresholds, determining that the ECG signal is in a transition state.

[0031] Specifically, please refer to Figure 5 , the part of the ECG signal between the upper threshold and the lower threshold is in a transition state, and the part of the ECG signal exceeding the upper threshold is in a rising state. It is obvious that Figure 5 The central electrical signal is not in a falling state. Please continue to refer to Figure 6 , Figure 6 This is a schematic diagram of a second ECG signal provided by another embodiment of the present invention. The portion of the ECG signal between the upper threshold and the lower threshold is in a transition state, and the portion of the ECG signal exceeding the upper threshold is in a rising state. Obviously, Figure 6 The central electrical signal is not in a falling state. Please continue to refer to Figure 7 , Figure 7 A schematic diagram of a third type of ECG signal provided by another embodiment of the present invention, in which the portion of the ECG signal between the upper threshold and the lower threshold is in a transition state, and the portion of the ECG signal below the lower threshold is in a declining state. Obviously, Figure 7 The central electrical signal is not in the rising state. Please continue to refer to Figure 8 , Figure 8 This is a schematic diagram of a fourth type of ECG signal provided by another embodiment of the present invention. The portion of the ECG signal between the upper threshold and the lower threshold is in a transition state, and the portion of the ECG signal below the lower threshold is in a declining state. Obviously, Figure 8 The central electrical signal is not in the rising state. Please continue to refer to Fig. 9 , Fig. 9 A schematic diagram of a fifth type of ECG signal provided for another embodiment of the present invention, wherein a portion of the ECG signal between an upper threshold and a lower threshold is in a transition state, a portion of the ECG signal exceeding the upper threshold is in a rising state, and a portion of the ECG signal below the lower threshold is in a falling state.

[0032] According to several embodiments of the present invention, the step of determining the signal trend on both sides of the intersection based on multiple states includes: if the signal state on both sides of the intersection changes from a transition state to a rising or falling state, then determining the signal trend on both sides of the intersection to be a first trend; if the signal state on both sides of the intersection changes from a rising or falling state to a transition state, then determining the signal trend on both sides of the intersection to be a second trend.

[0033] According to some embodiments of the present invention, the step of determining the first and second state transition points based on the signal trends on both sides of the intersection includes: if the signal trend on both sides of the intersection is the first trend, determining the first state transition point; if the signal trend on both sides of the intersection is the second trend, determining the second state transition point.

[0034] Specifically, please refer to Figure 5-9 , the ECG signal is divided into three states according to the upper and lower thresholds, namely the rising state, the transition state and the falling state. When transitioning between different states (the transition point is the intersection of the ECG signal and the upper and lower thresholds), two types of state transition points will appear, namely the first state transition point and the second state transition point. The intersection is determined to be the first state transition point or the second state transition point by judging the signal trend on both sides of the intersection. Specifically, if the signal state on both sides of the intersection changes from the transition state to the rising or falling state, the signal trend on both sides of the intersection is determined to be the first trend. If the signal state on both sides of the intersection changes from the rising or falling state to the transition state, the signal trend on both sides of the intersection is determined to be the second trend. If the signal trend on both sides of the intersection is the first trend, the intersection is determined to be the first state transition point. If the signal trend on both sides of the intersection is the second trend, the intersection is determined to be the second state transition point. For example Figure 5 In the example, if the signal state on both sides of the intersection changes from the transition state to the rising state, which is the first trend, the intersection is determined as the first state transition point; if the signal state on both sides of the intersection changes from the rising state to the transition state, which is the second trend, the intersection is determined as the second state transition point. Figure 7In the example, if the signals on both sides of the intersection change from the transition state to the falling state, which is the first trend, it is determined as the first state transition point. If the signals on both sides of the intersection change from the falling state to the transition state, which is the first trend, it is determined as the second state transition point. Based on the first state transition point, the starting point of the R wave can be detected, but at the same time, the T wave heart beat point may also be detected, and it is mistakenly believed that the R wave is detected, which will lead to subsequent R wave detection errors and even continuous misdetection problems (continuously mistaking T waves for R waves). Therefore, only relying on the first state transition point to determine the starting point of the R wave will have the risk of misdetecting the T wave when determining the starting point of the first R beat. Since the width of the T wave is greater than the width of the R wave, based on the time difference between several groups of continuous first state transition points and second state transitions, the group with the smallest time difference is taken, and the first state transition point is used as the starting point of the R wave. This can avoid the problem of incorrect identification of the starting point of the first R beat, so as to fully ensure the accuracy of R wave identification and improve the reliability of R wave identification.

[0035] According to some embodiments of the present invention, the steps of obtaining the current multiple continuous groups of first and second state transition points, and determining the R-wave starting point based on the time difference between the first and second state transition points in the multiple groups include: obtaining the current multiple continuous groups of first and second state transition points, each group including continuous first and second state transition points; calculating the time difference between the first and second state transition points of each group, and determining the first state transition point corresponding to the one with the smallest time difference in the multiple groups as the R-wave starting point.

[0036] Specifically, please refer to Figure 5-9, assuming that the R wave of the ECG signal is detected from the current time (time 0), when the R wave starting point is initially detected, it is necessary to ensure that the R wave starting point is accurately identified, and the initial multiple continuous groups of first and second state transition points are obtained, each group contains continuous first and second state transition points, such as obtaining two initial continuous groups, calculating the time difference of each group, taking the group with the smaller time difference as the group where the R wave starting point is located, and taking the first state transition point as the R wave starting point, that is, the effective heartbeat point for detecting the R wave, from the R wave starting point to the end of the ventricular refractory period, and then identifying the first state transition point closest to the R wave starting point, and taking it as the new R wave starting point, and then continuously identifying new R wave starting points. In this way, the T wave heartbeat point can be effectively filtered out, ensuring that when detecting the R wave, the detection is correct from the first R wave starting point. The end of the ventricular refractory period is timed from the correct first R wave starting point, and the first state transition point closest to the first R wave starting point is identified after the end of the ventricular refractory period, and the new first state transition point is used as the new R wave starting point; then the time is counted from the new R wave starting point to the end of the ventricular refractory period, and the first state transition point closest to it is identified again after the end of the ventricular refractory period, and the new first state transition point identified again is used as the new R wave starting point; then the R wave starting point of the ECG signal is continuously detected according to this step, so as to continuously detect the R wave based on the R wave starting point. It can be seen that it is only necessary to perform a time difference judgment when identifying the first R wave starting point to determine the accurate R wave starting point, and subsequently it is only necessary to identify the first state transition point closest to the R wave starting point after the time is counted from the R wave starting point to the end of the ventricular refractory period, and use it as the new R wave starting point, without the need for further time difference judgment, which ensures the overall accuracy and effectiveness of the ECG signal R wave detection, while improving the efficiency of the R wave detection.

[0037] Specifically, for example Figure 5 In the process, the ventricular refractory period is timed after the R wave starting point is detected. After the R wave starting point (still in the ventricular refractory period), the signal state on both sides of the intersection is detected to change from the transition state to the rising state, that is, the first trend. The intersection is determined as the first state transition point. The first state transition point is T1 away from the R wave starting point, but because it is in the ventricular refractory period, it will not be detected as an R wave (actually a T wave). For example Figure 6In the process, the ventricular refractory period is timed after the R wave starting point is detected. After the R wave starting point, the signal states on both sides of the intersection are detected to change from the transition state to the rising state, that is, the first trend. The intersection is determined as the first state transition point. The first state transition point is T2 away from the R wave starting point. Since it is after the end of the ventricular refractory period (not within the ventricular refractory period), the first state transition point is the next R wave starting point detected, based on which the R wave can be detected. This fully ensures the accuracy of R wave recognition and reduces the possibility of misidentifying T waves as R waves.

[0038] According to some embodiments of the present invention, the step of determining the upper and lower thresholds of the ECG signal state transition includes: determining the upper and lower thresholds of the ECG signal state transition according to the median of the ECG signal amplitude, wherein the upper and lower thresholds correspond to the baseline of the ECG signal.

[0039] Specifically, please refer to Figure 5-9 , the median amplitude of the ECG signal is used as the upper and lower thresholds of the ECG signal state transition, and the ventricular resting state is used as the baseline of the ECG signal, so that the upper threshold and the lower threshold correspond to each other with respect to the baseline.

[0040] In some embodiments, please refer to Fig.10 As shown, the present invention also provides an R-wave identification device 200 for an electrocardiogram signal, the device comprising: a first module 201, used to determine the upper and lower limit thresholds of the electrocardiogram signal state transition, and determine the first and second state transition points based on the intersection of the upper and lower limit thresholds and the electrocardiogram signal and the signal trends on both sides of the intersection; a second module 202, used to obtain the current continuous multiple groups of first and second state transition points, and determine the R-wave starting point based on the time difference between the first and second state transition points in the multiple groups; a third module 203, used to start timing from the R-wave starting point to the end of the ventricular refractory period, and then identify the first state transition point closest to the R-wave starting point, and use the newly identified first state transition point as the new R-wave starting point.

[0041] It should be noted that each module in the above-mentioned R wave recognition device of the electrocardiogram signal can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory in the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0042] According to another aspect of the present invention, an electronic device is provided. The electronic device may be a server. Fig.11As shown. The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the R wave recognition method of the electrocardiogram signal described above is implemented.

[0043] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this 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. By way of illustration and not limitation, RAM is available in many 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), etc.

[0044] 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.

[0045] 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 invention patent. 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 patent of the present application shall be subject to the attached claims.

Claims

1. A method for recognizing R waves of electrocardiogram signals, characterized in that: include: Determine upper and lower thresholds for the state transition of the ECG signal, and determine the first and second state transition points based on the intersections of the upper and lower thresholds with the ECG signal and the signal trends on both sides of the intersections; Acquire the current multiple continuous groups of first and second state transition points, and determine the R wave starting point based on the time difference between the first and second state transition points in the multiple groups; Timing starts from the R wave starting point and ends at the end of the ventricular refractory period, and then the first state transition point closest to the R wave starting point is identified, and the newly identified first state transition point is used as a new R wave starting point.

2. The R wave recognition method of the electrocardiogram signal according to claim 1, characterized in that: The step of determining the first and second state transition points based on the intersection of the upper and lower thresholds and the electrocardiogram signal and the signal trends on both sides of the intersection includes: Determining multiple states of the electrocardiogram signal according to the magnitude relationship between the electrocardiogram signal value and the upper and lower thresholds; The intersection of the upper and lower thresholds and the electrocardiogram signal is obtained, the signal trends on both sides of the intersection are determined according to the multiple states, and the first and second state transition points are determined according to the signal trends on both sides of the intersection.

3. The R wave recognition method of the electrocardiogram signal according to claim 2, characterized in that: The step of determining the multiple states of the electrocardiogram signal according to the magnitude relationship between the electrocardiogram signal value and the upper and lower thresholds comprises: If the ECG signal value exceeds the upper threshold, it is determined that the ECG signal is in a rising state; If the ECG signal value is lower than the lower threshold, determining that the ECG signal is in a decreasing state; If the ECG signal value is between the upper and lower thresholds, it is determined that the ECG signal is in a transition state.

4. The R wave recognition method of the electrocardiogram signal according to claim 3, characterized in that: The step of determining the signal trends on both sides of the intersection according to the multiple states includes: If the signal state on both sides of the intersection changes from the transition state to the rising or falling state, determining that the signal trend on both sides of the intersection is the first trend; If the signal states on both sides of the intersection are changed from the rising or falling state to the transition state, it is determined that the signal trends on both sides of the intersection are the second trend.

5. The R wave recognition method of the electrocardiogram signal according to claim 4, characterized in that: The step of determining the first and second state transition points according to the signal trends on both sides of the intersection point comprises: If the signal trends on both sides of the intersection are the first trends, determining a first state transition point; If the signal trends on both sides of the intersection are the second trend, a second state transition point is determined.

6. The R wave recognition method of electrocardiogram signal according to claim 1, characterized in that: The step of obtaining the current multiple continuous groups of first and second state transition points and determining the R wave starting point based on the time difference between the first and second state transition points in the multiple groups includes: Acquire multiple sets of current continuous first and second state transition points, each set comprising continuous first and second state transition points; The time difference between the first and second state transition points of each group is calculated, and the first state transition point corresponding to the group with the smallest time difference among the multiple groups is determined as the R wave starting point.

7. The R wave recognition method of an electrocardiogram signal according to claim 1, characterized in that: The step of determining the upper and lower thresholds of the electrocardiogram signal state transition includes: The upper and lower thresholds of the electrocardiogram signal state transition are determined according to the median value of the electrocardiogram signal amplitude, wherein the upper and lower thresholds correspond to the baseline of the electrocardiogram signal.

8. The R wave recognition method of electrocardiogram signal according to claim 1, characterized in that: The electrocardiogram signal is obtained by preprocessing the original electrocardiogram signal, including: The original ECG signal is subjected to high-pass filtering to remove the baseline drift, so that the baseline of the obtained ECG signal is 0.

9. An R wave recognition device for an electrocardiogram signal, characterized in that: The device comprises: The first module is used to determine the upper and lower thresholds of the ECG signal state transition, and determine the first and second state transition points based on the intersections of the upper and lower thresholds and the ECG signal and the signal trends on both sides of the intersections; The second module is used to obtain the current multiple continuous groups of first and second state transition points, and determine the R wave starting point based on the time difference between the first and second state transition points in the multiple groups; The third module is used to start timing from the R wave starting point to the end of the ventricular refractory period, and then identify the first state transition point closest to the R wave starting point, and use the newly identified first state transition point as the new R wave starting point.

10. An electronic device, characterized in that: include: at least one processor; as well as A memory storing a computer program executable in the processor, wherein the processor executes the R wave recognition method of the electrocardiogram signal according to any one of claims 1 to 7 when executing the program.

Images