CN117379062B

CN117379062B - Single-lead dry electrode electrocardiogram P wave identification method, device, equipment and medium

Info

Publication number: CN117379062B
Application number: CN202311696820.4A
Authority: CN
Inventors: 刘凯歌; 符灵建; 杨茂
Original assignee: Zhejiang Helowin Medical Technology Co ltd
Current assignee: Zhejiang Helowin Medical Technology Co ltd
Priority date: 2023-12-12
Filing date: 2023-12-12
Publication date: 2024-04-05
Anticipated expiration: 2043-12-12
Also published as: CN117379062A

Abstract

The invention discloses a single-lead dry electrode electrocardiogram P wave identification method, a single-lead dry electrode electrocardiogram P wave identification device, single-lead dry electrode electrocardiogram P wave identification equipment and a storage medium. The method comprises the following steps: determining a current detection wave band corresponding to a current cardiac cycle in an electrocardiogram, wherein the current detection wave band is positioned between a Q wave corresponding to the current cardiac cycle and a T wave corresponding to a previous cardiac cycle; determining a forward trend change curve and a reverse trend change curve of the current detection wave band; if the current detection wave band is determined to comprise at least one suspected P wave according to the forward trend change curve, the reverse trend change curve and a set reference line, determining whether the at least one suspected wave form comprises a target suspected P wave or not; and if the at least one suspected P wave comprises the target suspected P wave, determining a P wave corresponding to the target suspected P wave in the electrocardiogram. The technical scheme of the invention can accurately locate and identify the P wave from the electrocardiogram acquired by the dry electrode.

Description

Single-lead dry electrode electrocardiogram P wave identification method, device, equipment and medium

Technical Field

The invention relates to the technical field of physiological data processing, in particular to a single-lead dry electrode electrocardiogram P wave identification method, a single-lead dry electrode electrocardiogram P wave identification device, single-lead dry electrode electrocardiogram P wave identification equipment and a storage medium.

Background

An Electrocardiogram (ECG) is an important heart disease analysis tool, and has the characteristics of non-invasiveness, low cost and easy acquisition. The P-QRS-T waves of the ECG (P waves, QRS complexes, and T waves, respectively) reflect the atrial-ventricular mechanical activity of the heart, where the P waves reflect the depolarization of the atrium. The P-wave information is an important characteristic of arrhythmia based on ECG, is particularly important for atrial and ventricular lesions, and the accurate identification of the P-wave of an electrocardiogram is beneficial to analyzing arrhythmia diseases such as atrial flutter, atrial fibrillation, atrial premature and ventricular premature.

At present, single-lead wearable electrocardiograph monitoring equipment has become a research hot spot, has the characteristics of comfort in wearing, small size, portability and no influence on daily activities of patients, and adopts a dry electrode to collect electrocardiograph signals. The electrocardiosignals collected by the dry electrode belong to weak electric signals, are easy to be interfered by noise, and are greatly deformed P waves and noise false P waves, so that greater challenges are brought to P wave positioning.

Aiming at the electrocardiosignals collected by the dry electrode, the real P wave is difficult to accurately locate and identify from the electrocardiosignals in the prior art, namely the problem that the P wave cannot be accurately located and identified from the electrocardiosignals collected by the dry electrode exists in the prior art.

Disclosure of Invention

The invention provides a method, a device, equipment and a storage medium for identifying P waves of a single-lead dry electrode electrocardiogram, which are used for solving the problem that the P waves can not be accurately positioned and identified from electrocardiosignals acquired by a dry electrode in the prior art.

According to an aspect of the present invention, there is provided a single-lead dry electrode electrocardiogram P-wave recognition method, including:

determining a current detection wave band corresponding to a current cardiac cycle in an electrocardiogram, wherein the current detection wave band is positioned between a Q wave corresponding to the current cardiac cycle and a T wave corresponding to a previous cardiac cycle;

determining a forward trend change curve and a reverse trend change curve of the current detection wave band;

if the current detection wave band is determined to comprise at least one suspected P wave according to the forward trend change curve, the reverse trend change curve and a set reference line, determining whether the at least one suspected wave form comprises a target suspected P wave or not;

and if the at least one suspected P wave comprises the target suspected P wave, determining a P wave corresponding to the target suspected P wave in the electrocardiogram.

According to another aspect of the present invention, there is provided a single-lead dry electrode electrocardiogram P-wave recognition apparatus, including:

The wave band determining module is used for determining a current detection wave band corresponding to a current cardiac cycle in an electrocardiogram, wherein the current detection wave band is positioned between a Q wave corresponding to the current cardiac cycle and a T wave corresponding to a previous cardiac cycle;

the trend change curve module is used for determining a forward trend change curve and a reverse trend change curve of the current detection wave band;

the suspected P wave module is used for determining whether the at least one suspected wave form comprises a target suspected P wave or not if the current detection wave band comprises the at least one suspected P wave according to the forward trend change curve, the reverse trend change curve and a set datum line;

and the screening module is used for determining the P wave corresponding to the target suspected P wave in the electrocardiogram if the at least one suspected P wave comprises the target suspected P wave.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the single lead dry electrode electrocardiogram P-wave identification method according to any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the single-lead dry electrode electrocardiogram P-wave recognition method according to any one of the embodiments of the present invention when executed.

According to the technical scheme of the single-lead dry electrode electrocardiogram P wave identification method provided by the embodiment of the invention, whether the current detection wave band comprises at least one suspected P wave or not is determined by adopting a mode of matching a forward trend change curve, a reverse trend change curve and a set datum line, and the at least one suspected P wave is determined under the condition that the current detection wave band comprises the at least one suspected P wave, so that the technical effect of determining the suspected P wave based on the trend change of the detection wave band is realized; if the target suspected P wave is screened out from the at least one suspected P wave, the P wave is accurately positioned in the electrocardiogram according to the target suspected P wave, and the technical effect of accurately positioning and identifying the P wave in the electrocardiogram by combining the trend change condition of the current detection wave band with waveform screening is realized.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a single-lead dry electrode electrocardiogram P-wave identification method provided according to an embodiment of the present invention;

FIG. 2 is an electrocardiogram including a current detection band provided in accordance with an embodiment of the present invention;

FIG. 3 is a schematic diagram of a forward trend curve and a reverse trend curve according to an embodiment of the present invention;

FIG. 4 is a further flowchart of a single lead dry electrode electrocardiogram P-wave identification method provided in accordance with an embodiment of the present invention;

fig. 5 is a flowchart of target suspected P-wave screening provided according to an embodiment of the present invention;

FIG. 6 is a further flowchart of a single lead dry electrode electrocardiogram P-wave identification method provided in accordance with an embodiment of the present invention;

FIG. 7 shows a current detection band, and normalization, averaging and amplification results corresponding to the current detection band according to an embodiment of the present invention;

Fig. 8 is a schematic structural diagram of a single-lead dry electrode electrocardiogram P-wave recognition device according to an embodiment of the present invention;

FIG. 9 is a schematic structural view of another single-lead dry electrode electrocardiogram P-wave recognition device according to an embodiment of the present invention;

fig. 10 is a schematic structural diagram of an electronic device implementing the single-lead dry electrode electrocardiogram P-wave recognition method according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1 is a flowchart of a single-lead dry electrode electrocardiogram P-wave identification method provided in an embodiment of the present invention, where the method is applicable to positioning and identifying P-waves in a dry electrode collected electrocardiogram, and the method may be performed by a single-lead dry electrode electrocardiogram P-wave identification device, where the single-lead dry electrode electrocardiogram P-wave identification device may be implemented in hardware and/or software, and the single-lead dry electrode electrocardiogram P-wave identification device may be configured in a processor of an electronic device. As shown in fig. 1, the method includes:

s110, determining a current detection wave band corresponding to a current cardiac cycle in an electrocardiogram, wherein the current detection wave band is positioned between a Q wave corresponding to the current cardiac cycle and a T wave corresponding to a previous cardiac cycle.

Wherein, the electrocardiogram is a record of the electrocardio activity generated by the target object in each electrocardio cycle through the dry electrode acquisition. In a normal electrocardiogram, each cardiac cycle includes a P wave, a QRS wave, and a T wave that occur in sequence. The QRS wave includes a pulsed R wave, and a Q wave located before the R wave. P-wave corresponds to atrial depolarization activity; the time elapsed between the P-wave starting point and the QRS-wave starting point is called PR interval, and the PR interval mainly reflects the conduction time of the electrocardiosignal between the atria and the rooms; QRS waves correspond to ventricular depolarization activity; the time elapsed between the R wave of the current cardiac cycle and the R wave of the previous cardiac cycle is referred to as the RR interval, which is the interval between each heart beat and the previous heart beat.

The current detection wave band is the area where the P wave corresponding to the current cardiac cycle is most likely to appear in the electrocardiogram.

In one embodiment, as shown in fig. 2, a front T wave end point and a rear Q wave start point are determined in an electrocardiogram, and the front T wave end point and the rear Q wave start point are used as the start point and the end point of a current detection wave band, wherein the front T wave is a T wave corresponding to a previous cardiac cycle, and the rear Q wave is a start point of a Q wave corresponding to a current cardiac cycle; it will be appreciated that this embodiment is applicable to the case where the front T wave end point and the rear Q wave start point can be accurately determined.

In one embodiment, a reference sampling instant corresponding to an R-wave vertex corresponding to the previous cardiac cycle is determined, as well as an RR interval between the previous cardiac cycle and the current cardiac cycle; determining a sampling point of which the sampling time is after the reference sampling time and the difference between the sampling time and the reference sampling time is half of the RR interval, and taking the sampling point as a starting point of the current detection wave band; and determining a sampling point with the sampling time after the reference sampling time and the difference value between the sampling time and the reference sampling time as a target time length, and taking the sampling point as an end point of the current detection wave band, wherein the target time length is the difference value between the RR interval and the sampling rate of a set multiple.

In fig. 2, the time difference between the sampling time of the R-wave vertex and the sampling time of the r+1-wave vertex is the RR interval between the previous cardiac cycle and the current cardiac cycle. For electrocardiographic data with a sampling rate of 500Hz, the multiple is set to be smaller than 0.03 and larger than 0.01, and specifically, the multiple can be selected to be 0.02, 0.15 and the like. According to the embodiment, the starting point and the end point of the current detection wave band are determined by taking the R wave peak and the RR interval as the reference, so that the method is suitable for the situation that the T wave end point and the Q wave starting point cannot be accurately determined, and the flexibility and the accuracy of determining the current detection wave band are improved.

S120, determining a forward trend change curve and a reverse trend change curve of the current detection wave band.

The forward trend change curve is used for reflecting the change trend of each sampling point value in the current detection wave band in the forward direction; the reverse trend change curve is used for reflecting the change trend of the values of all sampling points in the current detection wave band in the reverse direction.

In an electrocardiogram, the direction in which the sampling timing increases is defined as the forward direction, and the direction in which the sampling timing decreases is defined as the reverse direction.

In one embodiment, a forward trend curve (see curve T1 in fig. 3) and a reverse trend curve (see curve T2 in fig. 3) of the current detection band are determined using a man-kendel trend detection method.

Mann-Kendall (Mann-Kendall trend detection method) is a climate diagnosis and prediction technology, and whether climate mutation exists in a climate sequence can be judged by applying the Mann-Kendall detection method, and if the climate mutation exists, the occurrence time of the mutation can be determined. The Mann-Kendall test method is a nonparametric method. The non-parametric test method is also called no-distribution test, which has the advantage that the samples are not required to follow a certain distribution and are not disturbed by a few outliers.

The sampling points within the trend detection window, denoted (L1, L2.l3 … Lm), are samples of m independent random variables distributed together, and the statistics S of the test are calculated as follows:

wherein,、/>respectively marked asiSample point values and identifications of (2) are as followsjAnd i<j, sgn () is a sign function, which is specifically as follows: />

Specifically, the trend detection window is exemplified as sliding forward along the time axis. For each sampling point in the current detection band, determining L sample points in a target window behind the current sampling point; in the L sample points, along the moving direction of the detection window, the difference between the next sample point and the previous sample point is larger than 0,S value plus one, the difference between the next sample point and the previous sample point is smaller than 0,S value minus one, the difference between the next sample point and the previous sample point is 0,S value unchanged until the next sample point is the last sample point in the detection window, and the S value at the moment is taken as the S value corresponding to the current sample point.

The statistic S approximately follows a normal distribution, whose mean E (S) =0, variance Var (S) =m (m-1) (2m+5)/18, regardless of the presence of equivalent data points in the sequence. The normalized test statistic Z is calculated as follows:

it can be seen that the above formula is used to convert the S value corresponding to each sample point into the Z value. Z is positive and indicates that the trend corresponding to the sampling point is rising, and Z is negative in amplitude and indicates that the trend corresponding to the sampling point is falling. The absolute value of Z at greater than or equal to 1.645, 1.96, and 2.576 indicates that the confidence level 90%, 95%, and 99%, respectively, passed the significance test.

It can be understood that the setting reference line corresponding to the setting confidence coefficient is determined according to the predetermined correspondence between the trend change curve amplitude and the confidence coefficient. For example, the Z value of the baseline corresponding to 90% confidence is equal to 1.645; the Z value of the baseline corresponding to 95% confidence was 1.96.

S130, if the current detection wave band is judged to comprise at least one suspected P wave according to the forward trend change curve, the reverse trend change curve and a set reference line, determining whether the at least one suspected wave comprises a target suspected P wave.

In one embodiment, the baseline is set to the Z value corresponding to 90% confidence, i.e., 1.645. It can be understood that, in the trend change curve, compared with the sampling point with a lower Z value, the sampling point with a higher Z value corresponds to a higher confidence, and the accuracy of the corresponding trend change result is also higher. Therefore, the confidence corresponding to the set datum line can be determined according to actual conditions, such as the data acquisition characteristics of the sensor.

In one embodiment, if the number of first intersections of the forward trend change curve and the set reference line is greater than or equal to 1 and the number of second intersections of the reverse trend change curve and the set reference line is greater than or equal to 1, the first intersection is taken as a starting point, the second intersection is taken as an end point, and the current detection band is determined to include at least one suspected P-wave.

Referring to fig. 3, a curve T1 is a forward trend curve, a curve T2 is a reverse trend curve, and a curve p_ad is a current detection band. The Z value (1.645) corresponding to the confidence level of 90% is the set reference line, which is the transverse axis of the drawing with the amplitude of zero. Taking a first intersection point (see a solid circle in the figure) of the rising edge of the forward trend change curve and the set datum line as an endpoint of the suspected P wave, and short for endpoint; and taking a second intersection point (see a solid triangle in the figure) of the falling edge of the reverse trend change curve and the set reference line as a start point of the suspected P wave, and short for the start point. The figure shows 4 start points and 4 end points.

And after all the starting points and the ending points are determined, taking waveforms corresponding to adjacent starting points and ending points in at least one starting point and at least one ending point as suspected P waves according to the principle of starting from left to right (starting point at the left side and ending point at the right side) so as to obtain the at least one suspected P wave. The principle of the left starting point and the right ending point is determined based on the waveform characteristics that the P wave rises and then falls in the current detection wave band. After the at least one starting point and the at least one ending point are determined, all suspected P waves can be rapidly determined according to the waveform characteristics of the P waves.

In one embodiment, the suspected P-waves are determined in a back-to-front combination, as the P-waves are closer to the QRS waves. Specifically, for each of the at least one endpoint, determining a start point adjacent to and distributed before the current endpoint, and taking a waveform between the current endpoint and the start point as a suspected P-wave corresponding to the current endpoint, wherein the start point distributed between the current endpoint and the T-wave is the start point distributed before the current endpoint in the at least one start point; and taking all the suspected P waves as the at least one suspected P wave.

S140, if the at least one suspected P wave comprises the target suspected P wave, determining a P wave corresponding to the target suspected P wave in the electrocardiogram.

After the at least one suspected P wave is determined, P wave screening operation is carried out on the at least one suspected P wave, and if the suspected P wave meeting the set screening condition is screened out of the at least one suspected P wave, the suspected P wave is taken as a target suspected P wave. After the target suspected P wave is determined, a first sampling time and a second sampling time which respectively correspond to the starting point and the end point of the target suspected P wave are determined, and the P wave corresponding to the target suspected P wave is determined in the electrocardiogram according to the first sampling time and the second sampling time.

In one embodiment, after the P-wave is determined in the electrocardiogram, the electrocardiogram including a corresponding P-wave identification is displayed in a visual display interface, wherein the P-wave identification is identified at a set position of the P-wave corresponding to the current cardiac cycle, such as above or below the P-wave.

In one embodiment, the method further comprises: and if the current detection wave band does not comprise suspected P waves according to the forward trend change curve, the reverse trend change curve and a set datum line, outputting prompt information in a visual interface, wherein the prompt information is used for indicating that the electrocardiogram does not comprise P waves corresponding to the current cardiac cycle. It can be understood that if the forward trend change curve and the set reference line have no first intersection point and/or the reverse trend change curve and the set reference line have no second intersection point, the current detection wave band is indicated to have no start point and/or end point for determining the suspected P-wave, and at this time, it can be determined that the current detection wave band does not include the suspected P-wave, and prompt information is directly output in the visual interface.

According to the technical scheme of the single-lead dry electrode electrocardiogram P wave identification method provided by the embodiment of the invention, if the current detection wave band comprises at least one suspected P wave by adopting a mode of matching a forward trend change curve and a reverse trend change curve with a set datum line, and if the current detection wave band comprises at least one suspected P wave, the at least one suspected P wave is determined, so that the technical effect of determining the suspected P wave based on the trend change of the detection wave band is realized; if the target suspected P wave is screened out from the at least one suspected P wave, the P wave is accurately positioned in the electrocardiogram according to the target suspected P wave, and the technical effect of accurately positioning and identifying the P wave in the electrocardiogram by combining the trend change condition of the current detection wave band with waveform screening is realized.

Fig. 4 is a flowchart of a single-lead dry electrode electrocardiogram P-wave identification method according to an embodiment of the present invention, where the embodiment is used to refine the target suspected P-wave screening step in the foregoing embodiment. As shown in fig. 4, the method includes:

s210, determining a current detection wave band corresponding to a current cardiac cycle in an electrocardiogram, wherein the current detection wave band is positioned between a Q wave corresponding to the current cardiac cycle and a T wave corresponding to a previous cardiac cycle.

S220, determining a forward trend change curve and a reverse trend change curve of the current detection wave band.

S230, if it is determined that the current detection wave band includes at least one suspected P wave according to the forward trend change curve, the reverse trend change curve and a set reference line, determining whether the at least one suspected wave includes a target suspected P wave.

S2401, determining the confidence of each suspected P wave in the at least one suspected P wave.

In one embodiment, the confidence level of each suspected P-wave is determined by:

step a1, determining at least one set feature score of the current suspected P wave according to each suspected P wave in the at least one suspected P wave, wherein the set feature score comprises at least one of a waveform feature score, a time limit feature score, an amplitude feature score and a PR interval feature score.

The waveform characteristic refers to the shape characteristic of the suspected P wave. The time limit feature refers to a time difference between a sampling time corresponding to a start point and a sampling time corresponding to an end point of the suspected P-wave. The amplitude characteristic refers to the difference between the peak amplitude and the starting point amplitude of the suspected P-wave. The PR interval characteristic refers to a time difference between a sampling time corresponding to a start point of a suspected P-wave and a sampling time corresponding to a start point of a target QRS-wave, wherein the target suspected QRS-wave is a QRS-wave corresponding to a current cardiac cycle.

In one embodiment, the step of determining the waveform feature score includes: determining a Gaussian function fitting result of the current suspected P wave for each suspected P wave in the at least one suspected P wave; determining fitting parameters according to the Gaussian function fitting result; determining a similarity result of the current suspected P wave and a set standard P wave according to the fitting parameters; and determining the waveform characteristic score of the current suspected P wave according to the similarity result and a preset similarity weight.

Specifically, in a normal electrocardiogram, the P wave is a curve with a blunt circle shape, and the gaussian function is a curve with a convex blunt circle shape, and the function expression is as follows:

wherein F is _p Is a fitting curve, and a, b and c are parameters of the fitting curve; a represents the amplitude of the fitting curve, b represents the symmetry axis of the fitting curve, and c represents the width of the waveform corresponding to the fitting curve. And optimizing the fitting curve by using a least square method, and updating parameters a, b and c of the fitting curve.

And determining the similarity between each suspected P wave and the standard P wave according to the parameters of the fitting curve of each suspected P wave and the predetermined standard P wave. In one embodiment, parameters of the fitted curve of each suspected P-wave are input into a trained similarity model to obtain the similarity of each suspected P-wave and the standard P-wave. The P-wave samples adopted in the similarity model training process comprise P-wave labels marked by electrocardiographs, and the P-wave labels comprise the similarity between waveforms in the training samples and standard P-waves. In the embodiment, the similarity between the fitting curve of each suspected P wave and the standard P wave is rapidly determined through the trained similarity model.

And after the similarity corresponding to each suspected P wave is determined, taking the product of the similarity and the set waveform characteristic weight as the waveform characteristic score of each suspected P wave. The method comprises the following steps:

wherein, P_m is the waveform characteristic score corresponding to the suspected P wave, pm is the similarity corresponding to the suspected P wave, and m1 is the set waveform characteristic weight.

Wherein the set waveform feature weights are related to the number of screening features included in the set screening conditions, e.g., if the set screening conditions include waveform features, time limit features, amplitude features, and PR interval features, the feature weights are selected asThe method comprises the steps of carrying out a first treatment on the surface of the If the set screening conditions include waveform characteristics and time limit characteristics, the characteristic weights can be selected as. Of course, in actual use, the data acquisition characteristics of the sensor can be determined according to specific conditionsThe weights of one or two of the waveform feature, the time limit feature, the amplitude feature and the PR interval feature are made higher than the weight average value, and the weights of the other of the waveform feature, the time limit feature, the amplitude feature and the PR interval feature are correspondingly made lower than the weight average value.

In one embodiment, for each of the time limit feature, the amplitude feature, and the PR interval feature, a feature score for the current feature is determined by the steps comprising: determining a relation corresponding to the current characteristic value of the current suspected P wave according to the relation between the characteristic value range and the similarity of the current characteristic, which is created in advance, for each suspected P wave in the at least one suspected P wave; determining the similarity corresponding to the current characteristic value of the current suspected P wave according to the relation; and determining the current feature score of the current suspected P wave according to the similarity and the set current feature weight.

Specifically, regarding the time limit characteristics, the time limit corresponding to each suspected P-wave is determined by the following formula:

wherein, P_tb is the time limit corresponding to the suspected P wave, and the unit is millisecond (ms); p_s and p_e respectively represent the sampling time of the start point and the sampling time of the end point of the corresponding suspected P wave; sampling-rate is the Sampling frequency of the electrocardiographic data.

In one embodiment, the time limit feature score is determined by the following formula:

wherein, P_t is the time limit characteristic score of the corresponding suspected P wave; pt is a specific time limit corresponding to the suspected P-wave, and m2 is a set time limit characteristic weight.

If Pt is within the normal range, i.e., between the first boundary value (60 ms) and the second boundary value (110 ms), the time-limited similarity of Pt to the standard P-wave is 1, then the time-limited feature score for the corresponding suspected P-wave is m2. If Pt is greater than the third boundary value (300 ms) or less than the fourth boundary value (20 ms), the probability that the time limit belongs to a normal P-wave is considered to be 0, so the time limit feature score of the corresponding suspected P-wave is considered to be 0; if Pt is not in the normal range and is smaller than the third boundary value (300 ms) or larger than the fourth boundary value (20 ms), the ratio of the difference between the time limit of the suspected P-wave and the corresponding time limit boundary value to the corresponding time limit threshold value is used as the similarity between the time limit of the corresponding suspected P-wave and the time phase of the standard P-wave, and the product of the similarity and m2 is used as the time limit characteristic score of the corresponding suspected P-wave. Wherein, if Pt is greater than the second boundary value (110 ms), the corresponding time limit threshold is the difference between the third boundary value and the second boundary value; if Pt is less than the first boundary value, then the corresponding time limit threshold is the difference between the first boundary value and the fourth boundary value.

Regarding the amplitude characteristics, the amplitude of each suspected P-wave is determined by the following formula:wherein, P_al is the amplitude of the corresponding suspected P wave, and the unit millivolt (mv) of the P_al is the amplitude of the corresponding suspected P wave; p_wv is a voltage value corresponding to the vertex of the corresponding suspected P wave; p_sv is a voltage value corresponding to the start point of the corresponding suspected P wave.

In one embodiment, the amplitude characteristic score for each suspected P-wave is determined by the following equation:

wherein P_a is the amplitude characteristic score of the corresponding suspected P wave; pa represents the amplitude of the corresponding suspected P-wave; m3 is the set amplitude characteristic weight.

If Pa is within the normal range, that is, between the first boundary value (0.05 mv) and the second boundary value (0.25 mv), it is considered that the amplitude similarity with the standard P wave is 1, and if the amplitude feature weight is set to be m3, the amplitude feature weight score of the corresponding suspected P wave is m3. If Pa is greater than the upper limit third boundary value (1.0 mv) or less than the fourth boundary value (0 mv), the similarity between the corresponding suspected P-wave and the standard P-wave is considered to be 0, and thus the amplitude characteristic score of the corresponding suspected P-wave is considered to be 0. If Pa does not belong to the normal range and the amplitude is greater than the third boundary value (0 mv) or less than the fourth boundary value (1.0 mv), taking the ratio of the difference between the amplitude of the suspected P-wave and the corresponding amplitude boundary value to the corresponding amplitude threshold value as the similarity between the amplitude of the corresponding suspected P-wave and the amplitude of the standard P-wave, and taking the product of the similarity and m3 as the amplitude characteristic score of the corresponding suspected P-wave, wherein if Pa is greater than the second boundary value (0.25 mv), the corresponding amplitude threshold value is the difference between the third boundary value and the second boundary value; if Pa is less than the first boundary value, the corresponding amplitude threshold is the difference between the first boundary value and the fourth boundary value.

Regarding PR interval characteristics, PR intervals corresponding to each suspected P-wave are determined by the following formula:

PR_interval is PR interval corresponding to the corresponding suspected P wave and is unit ms; p_s represents a sampling time corresponding to the start point of the corresponding suspected P wave; qrs_s is the sampling instant corresponding to the start of the QRS wave corresponding to the current cardiac cycle.

In one embodiment, the PR interval feature score for each suspected P-wave is determined by the following equation:

PR_i is the PR interval characteristic score, PRI is the PRI interval corresponding to the suspected P wave, and m4 is the PRI interval characteristic weight.

If the PRI is within the normal range, i.e., between the first boundary value (120 ms) and the second boundary value (210 ms), the PR interval similarity between the PRI and the standard P wave is 1, and the PR interval characteristic score of the corresponding suspected P wave is m3. If the PRI is greater than the third boundary value (500 ms) or less than the fourth boundary value (20 ms), the probability that the PR interval belongs to the normal P wave is considered to be 0, so that the PR interval characteristic score of the corresponding suspected P wave is 0; if PRI is not in the normal range and is smaller than the third boundary value (500 ms) or larger than the fourth boundary value (0 ms), taking the ratio of the difference between the PR interval of the suspected P wave and the boundary value of the corresponding PR interval to the threshold value of the corresponding PR interval as the PR interval similarity between the PR interval of the corresponding suspected wave and the standard P wave, and taking the product of the similarity and m3 as the PR interval characteristic score of the corresponding suspected P wave; if PRI is greater than the second boundary value, the corresponding PR interval threshold is the difference between the third boundary value and the second boundary value; if PRI is less than the first boundary value, then the corresponding PR interval threshold is the difference between the first boundary value and the fourth boundary value.

And a2, determining the confidence coefficient of the current suspected P wave according to the at least one set feature score.

And after the at least one feature score is determined, taking the sum value of the at least one feature score as the confidence of the current suspected P wave. The specific formula is as follows:

wherein, P_cl is the confidence of the suspected P wave; p_m is the waveform characteristic score of the suspected P wave; p_t is the time limit characteristic score of the suspected P wave; p_a is the amplitude characteristic score of the suspected P wave; PR_i is the PR interval feature score for the suspected P-wave.

S2402, if the at least one suspected P wave comprises the target suspected P wave according to the confidence degree of each suspected P wave, determining the P wave corresponding to the target suspected P wave in the electrocardiogram.

It can be appreciated that the higher the confidence of the suspected P-wave, the greater the likelihood that it belongs to the target suspected P-wave; conversely, the less likely it is that it belongs to the target suspected P-wave.

In one embodiment, the suspected P-wave with the highest confidence in the at least one suspected P-wave is taken as the target suspected P-wave. The embodiment can simply and directly screen out the target suspected P wave.

In one embodiment, according to the confidence of each suspected P-wave, removing the suspected P-waves which do not meet the confidence condition from the at least one suspected P-wave to obtain the rest suspected P-waves; if the remaining suspected P waves comprise a suspected P wave, the suspected P wave is taken as a target suspected P wave; and if the remaining suspected P waves comprise at least two suspected P waves, taking the suspected P wave with the highest confidence in the remaining suspected P waves as a target suspected P wave. Wherein the confidence condition may be selected as a confidence threshold.

Fig. 5 is a flowchart of screening a target suspected P-wave according to an embodiment of the present invention. In the drawing, the confidence coefficient threshold value is 50, and suspected P waves with the confidence coefficient smaller than 50 are deleted from all the suspected P waves to obtain residual suspected P waves, so that preliminary filtration of the suspected P waves is completed; if the number of the remaining suspected P waves is smaller than 1, the current detection wave band does not comprise the target suspected P waves, and if the number of the remaining suspected P waves is equal to 1, the remaining suspected P waves are used as the target suspected P waves; if the number of the remaining suspected P waves is greater than 1, the suspected P wave with the highest confidence in the remaining suspected P waves is used as the target suspected P wave, so that the accurate screening of the target suspected P wave is realized, and the overall screening speed is high.

And after the target suspected P wave is screened out, determining the P wave corresponding to the target suspected P wave in the electrocardiogram.

According to the method and the device for screening the target suspected P waves, the confidence coefficient of each suspected P wave in at least one suspected P wave is determined, and the target suspected P wave is screened from the at least one suspected P wave according to the confidence coefficient of each suspected P wave, so that accuracy of screening operation of the target suspected P waves is improved.

Fig. 6 is a flowchart of a single-lead dry electrode electrocardiogram P-wave identification method according to an embodiment of the present invention, where a step of preprocessing a current detection band is added on the basis of the foregoing embodiment. As shown in fig. 6, the method includes:

S3101, determining a current detection wave band corresponding to a current cardiac cycle in an electrocardiogram, wherein the current detection wave band is positioned between a Q wave corresponding to the current cardiac cycle and a T wave corresponding to a previous cardiac cycle.

S3102, preprocessing the current detection wave band to update the current detection wave band, wherein the preprocessing comprises averaging processing.

The averaging operation can be understood as determining, for any sampling point, the average value of all sampling point values in the corresponding set neighborhood, and replacing the sampling point value with the average value, so that the change of data is more uniform, and the interference of the burr noise on positioning is reduced.

Specifically, the averaging is to average the current sampling point value in the band to be detected and the current sampling point valueThe sum of r sampling point values and the following r sampling point values is divided by 2r+1, and r is the number of sampling points in the set neighborhood. Optionally, the radius of the neighborhood is set to a sampling rate of 0.02 times. The specific formula is as follows:

wherein P_ad (n) is an average result corresponding to a sampling point value marked as n in the current detection wave band, and Pad #i) Indicating that the identification in the neighborhood range corresponding to the set neighborhood radius isiIs a sampling point value of (a).

In one embodiment, the following steps are used to pre-process the current detection band:

And c1, performing a averaging operation on the current detection band to obtain an averaging result.

And c2, normalizing the averaged result to obtain a normalized result.

In one embodiment, after the averaged result is determined, normalization processing is performed on the averaged result. The normalization process is to normalize and adjust the sampling point value in the averaged result to be within the range of 0-1, so as to reduce the missing detection probability of the low-frequency P wave. Specifically, a maximum sampling point value and a minimum sampling point value in the averaged result are determined, and a difference value between the maximum sampling point value and the minimum sampling point value is used as a reference threshold value. And carrying out normalization processing on each sampling point value in the averaged result by adopting the reference threshold value. Specifically, for each sampling point in the result of the averaging process, a difference value between the sampling point value of the current sampling point and the minimum sampling point value is determined, and the ratio of the difference value to the reference threshold value is used as the normalized value of the current sampling point. The specific formula is as follows:

wherein p_ad (n) on the right side of the equation is a normalization result corresponding to a sampling point value identified as n, and Min and Max represent the maximum sampling point value and the minimum sampling point value in the averaged result, respectively.

And c3, amplifying the normalized result to update the current detection band.

The amplifying processing means that a set amplifying algorithm is adopted to perform amplifying operation on the current detection wave band, so that each sampling point value of the current detection wave band is correspondingly amplified.

In one embodiment, the amplification process is a nonlinear amplification process, such as an exponential amplification process, to reduce the effect of noise on the positioning of the target suspected P-wave and to highlight the start and end characteristics of the P-wave, so that the P-wave in the current detection band is more distinguishable than other waveforms. The amplification process formula may be selected as:

wherein, to the right of the equal signIs the sample point value identified as n. Left +.>A value obtained by exponentially amplifying a sampling point value marked as n; e is a natural index.

Fig. 7 is a diagram of a current detection band and normalization processing results, averaging processing results, and amplification processing results of the current detection band according to an embodiment of the present invention. In the figure, the curve in the upper graph frame is the current detection band; in the three curves in the lower graph frame, the normalization processing result, the averaging processing result and the amplifying processing result are respectively from bottom to top. As can be seen from the figure, the averaging process removes the glitch noise in the current detection band; normalization weakens the smaller waveform in the averaged result; the amplification process intensifies the difference between the larger waveform and the smaller waveform in the normalization process result.

S320, determining the updated forward trend change curve and the updated reverse trend change curve of the current detection wave band.

S330, if it is determined that the updated current detection band includes at least one suspected P wave according to the forward trend change curve, the reverse trend change curve and the set reference line, determining whether the at least one suspected wave includes a target suspected P wave.

S340, if the at least one suspected P wave comprises the target suspected P wave, determining a P wave corresponding to the target suspected P wave in the electrocardiogram.

According to the embodiment of the invention, the pretreatment including normalization treatment is carried out on the current detection wave band, so that the burr noise in the current detection wave band is removed, the accuracy of determining the forward trend change curve and the reverse trend change curve is improved, and the accuracy of positioning and identifying the P wave in the electrocardiogram is improved.

Fig. 8 is a schematic structural diagram of a single-lead dry electrode electrocardiogram P-wave recognition device according to an embodiment of the present invention. As shown in fig. 8, the apparatus includes: a band determining module 41, configured to determine a current detection band corresponding to a current cardiac cycle in an electrocardiogram, where the current detection band is located between a Q wave corresponding to the current cardiac cycle and a T wave corresponding to a previous cardiac cycle; a trend change curve module 42, configured to determine a forward trend change curve and a reverse trend change curve of the current detection band; the suspected P-wave module 43 is configured to determine whether the at least one suspected waveform includes a target suspected P-wave if it is determined that the current detection band includes at least one suspected P-wave according to the forward trend change curve, the reverse trend change curve, and a set reference line; a screening module 44, configured to determine a P-wave corresponding to the target suspected P-wave in the electrocardiogram if the at least one suspected P-wave includes the target suspected P-wave.

In one embodiment, trend curve module 42 is specifically configured to:

and determining a forward trend change curve and a reverse trend change curve of the current detection wave band by adopting a Mancoldel trend detection method.

In one embodiment, the suspected P-wave module 43 specifically includes:

the datum line unit is used for determining a setting datum line corresponding to the setting confidence coefficient according to the corresponding relation between the preset trend change curve amplitude and the confidence coefficient;

and the boundary point unit is used for taking the first intersection point as a starting point and the second intersection point as an end point if the number of the first intersection points of the forward trend change curve and the set reference line is greater than or equal to 1 and the number of the second intersection points of the reverse trend change curve and the set reference line is greater than or equal to 1, and judging that the current detection wave band comprises at least one suspected P wave.

In one embodiment, the boundary point unit is for:

based on the principle of starting from the left to the right, waveforms corresponding to adjacent starting points and end points in the at least one starting point and the at least one end point are used as suspicious P waves, so that at least one suspicious P wave included in the current detection wave band is obtained.

In one embodiment, the suspected P-wave module 43 includes:

a confidence coefficient unit, configured to determine a confidence coefficient of each suspected P-wave in the at least one suspected P-wave;

and the screening unit is used for determining the P wave corresponding to the target suspected P wave in the electrocardiogram if the at least one suspected P wave comprises the target suspected P wave according to the confidence degree of each suspected P wave.

In one embodiment, the confidence unit specifically includes:

a feature score subunit, configured to determine, for each of the at least one suspected P-wave, at least one set feature score of a current suspected P-wave, where the set feature score includes at least one of a waveform feature score, a time limit feature score, an amplitude feature score, and a PR interval feature score;

and the confidence coefficient subunit is used for determining the confidence coefficient of the current suspected P wave according to the at least one set feature score.

In one embodiment, the feature score subunit is specifically configured to:

determining a Gaussian function fitting result of the current suspected P wave for each suspected P wave in the at least one suspected P wave;

determining fitting parameters according to the Gaussian function fitting result;

Determining the similarity between the current suspected P wave and a set standard P wave according to the fitting parameters;

and determining the waveform characteristic score of the current suspected P wave according to the similarity and the set waveform characteristic weight.

In one embodiment, the feature score subunit is specifically configured to:

determining a relation corresponding to the current characteristic value of the current suspected P wave according to the relation between the characteristic value range and the similarity of the current characteristic, which is created in advance, for each suspected P wave in the at least one suspected P wave;

determining the similarity corresponding to the current characteristic value of the current suspected P wave according to the relation;

and determining the current feature score of the current suspected P wave according to the similarity and the set current feature weight.

In one embodiment, as shown in fig. 9, the apparatus further comprises a preprocessing module 45 for:

and preprocessing the current detection wave band to update the current detection wave band, wherein the preprocessing comprises averaging processing.

In one embodiment, the preprocessing module is specifically configured to:

performing a averaging operation on the current detection band to obtain an averaging result;

performing normalization on the averaged result to obtain a normalized result;

And performing amplification processing on the normalization result to update the current detection band.

In one embodiment, the band determining module is specifically configured to:

determining a reference sampling time corresponding to an R-wave vertex corresponding to the previous cardiac cycle and an RR interval between the previous cardiac cycle and the current cardiac cycle;

determining a sampling point of which the sampling time is after the reference sampling time and the difference between the sampling time and the reference sampling time is half of the RR interval, and taking the sampling point as a starting point of the current detection wave band;

and determining a sampling point with the sampling time after the reference sampling time and the difference value between the sampling time and the reference sampling time as a target time length, and taking the sampling point as an end point of the current detection wave band, wherein the target time length is the difference value between the RR interval and the sampling rate of a set multiple.

In one embodiment, the system further comprises a prompt module for:

if the current detection wave band does not comprise suspected P waves according to the forward trend change curve, the reverse trend change curve and the set datum line, outputting prompt information in a visual interface, wherein the prompt information is used for indicating that the electrocardiogram does not comprise P waves corresponding to the current cardiac cycle.

According to the technical scheme of the single-lead dry electrode electrocardiogram P wave identification device, if the current detection wave band comprises at least one suspected P wave by adopting a mode that a forward trend change curve and a reverse trend change curve are matched with a set datum line, and if the current detection wave band comprises at least one suspected P wave, the at least one suspected P wave is determined, so that the technical effect of determining the suspected P wave based on the trend change of the detection wave band is realized; if the target suspected P wave is screened out from the at least one suspected P wave, the P wave is accurately positioned in the electrocardiogram according to the target suspected P wave, and the technical effect of accurately positioning and identifying the P wave in the electrocardiogram by combining the trend change condition of the current detection wave band with waveform screening is realized.

The P wave identification method and the P wave identification device for the single-lead dry electrode electrocardiogram provided by the embodiment of the invention can execute the P wave identification method for the single-lead dry electrode electrocardiogram provided by any embodiment of the invention, and have the corresponding functional modules and beneficial effects of the execution method.

Fig. 10 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 10, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the single lead dry electrode electrocardiogram P-wave recognition method.

In some embodiments, the single-lead dry electrode electrocardiogram P-wave identification method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the single lead dry electrode electrocardiogram P-wave identification method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the single-lead dry electrode electrocardiogram P-wave identification method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. The method for identifying the P wave of the single-lead dry electrode electrocardiogram is characterized by comprising the following steps of:

if the current detection wave band is judged to comprise at least one suspected P wave according to the forward trend change curve, the reverse trend change curve and a set reference line, determining whether the at least one suspected wave form comprises a target suspected P wave or not;

If the at least one suspected P wave comprises the target suspected P wave, determining a P wave corresponding to the target suspected P wave in the electrocardiogram;

wherein, according to the forward trend change curve, the reverse trend change curve and a set reference line, determining that the current detection band includes at least one suspected P-wave includes:

according to the corresponding relation between the preset trend change curve amplitude and the confidence coefficient, a setting datum line corresponding to the setting confidence coefficient is determined;

if the number of the first intersection points of the forward trend change curve and the set reference line is greater than or equal to 1 and the number of the second intersection points of the reverse trend change curve and the set reference line is greater than or equal to 1, taking the first intersection points as a starting point and the second intersection points as an end point, and judging that the current detection wave band comprises at least one suspected P wave;

wherein the determining whether the at least one suspected waveform includes a target suspected P-wave includes:

determining the confidence of each suspected P wave in the at least one suspected P wave;

and determining whether the at least one suspected P wave comprises the target suspected P wave according to the confidence degree of each suspected P wave.

2. The method of claim 1, wherein said determining a forward trend curve and a reverse trend curve for said current detection band comprises:

3. The method of claim 1, wherein determining the at least one suspected P-wave comprises:

based on the principle of starting from the left to the right, waveforms corresponding to adjacent starting points and end points in at least one starting point and at least one end point are used as the suspected P waves, so that the at least one suspected P waves are obtained.

4. The method of claim 1, wherein said determining a confidence level for each of said at least one suspected P-wave comprises:

determining at least one set feature score of the current suspected P wave for each suspected P wave in the at least one suspected P wave, wherein the set feature score comprises at least one of a waveform feature score, a time limit feature score, an amplitude feature score and a PR interval feature score;

and determining the confidence of the current suspected P wave according to the at least one set feature score.

5. The method of claim 4, wherein determining a waveform characteristic score for each of the suspected P-waves comprises:

6. The method of claim 4, wherein determining the feature score of the current feature for each of the time limit feature, the amplitude feature, and the PR interval feature comprises:

7. The method of claim 1, wherein prior to determining the forward trend curve and the reverse trend curve for the current detection band, further comprising:

preprocessing the current detection band to update the current detection band, wherein the preprocessing comprises averaging.

8. The method of claim 7, wherein the preprocessing the current detection band to update the current detection band comprises:

performing normalization on the averaged result to obtain a normalized result;

9. The method of claim 1, wherein the current detection band is determined by:

10. The method as recited in claim 1, further comprising:

if the current detection wave band is determined to not comprise suspected P waves according to the forward trend change curve, the reverse trend change curve and the set reference line, outputting prompt information in a visual interface, wherein the prompt information is used for indicating that the electrocardiogram does not comprise P waves corresponding to the current cardiac cycle.

11. A single-lead dry electrode electrocardiogram P-wave recognition device, comprising:

the screening module is used for determining a P wave corresponding to the target suspected P wave in the electrocardiogram if the at least one suspected P wave comprises the target suspected P wave;

the suspected P-wave module is specifically configured to:

the suspected P-wave module is further specifically configured to:

12. An electronic device, the electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the single lead dry electrode electrocardiogram P-wave identification method of any one of claims 1-10.

13. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the single-lead dry electrode electrocardiogram P-wave identification method according to any one of claims 1-10 when executed.