Arrhythmia detection method, non-volatile readable storage medium and wearable device

Abstract

The application relates to the technical field of electrocardiosignal detection, and discloses an arrhythmia detection method, a nonvolatile readable storage medium and a wearable device. The method comprises the following steps: acquiring lead electrocardiosignal and acceleration collected by the wearable device; determining a heart beat area according to the lead electrocardiosignal; determining a target forgetting factor of the acceleration according to the heart beat time of the heart beat area; performing adaptive filtering processing on the lead electrocardiosignal according to the target forgetting factor and the acceleration, obtaining a first lead electrocardiosignal; performing band-pass filtering processing on the first lead electrocardiosignal, obtaining a second lead electrocardiosignal; and generating an arrhythmia detection result according to the second lead electrocardiosignal. The embodiment does not depend on matching the forgetting factor for the acceleration at a given current moment, but determines the target forgetting factor of the acceleration according to the heart beat time, so that the signal quality and effect of the adaptive filtering can be improved, and the detection precision of the arrhythmia is also improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrocardiosignal detection, and in particular to an arrhythmia detection method, a nonvolatile readable storage medium and a wearable device. BACKGROUND

[0002] An electrocardiosignal reflects an electrophysiological process of heart activity, and it is clinically considered that arrhythmia can be discovered in time and rescue can be performed in time through real-time monitoring of the electrocardiosignal. Figure 1 A typical electrocardiosignal waveform is shown. A normal electrocardiosignal is generally composed of a P wave, a QRS complex and a T wave.

[0003] A wearable device provided by the related technology can process an electrocardiosignal in combination with an arrhythmia detection algorithm, so as to be able to detect whether a user is in an arrhythmia state. In the process of processing the electrocardiosignal, the wearable device performs filtering processing on the electrocardiosignal according to a self-adaptive filtering algorithm. Generally, the self-adaptive filtering algorithm adopts a recursive least squares (RLS) algorithm. The RLS algorithm introduces a forgetting factor. The role of the forgetting factor is to configure a larger forgetting factor for an error closer to a current time and a smaller forgetting factor for an error farther from the current time. In this way, the convergence speed is improved, and the purpose of fast self-adaptive filtering is achieved. However, the electrocardiosignal analysis algorithm of the wearable device is generally performed at a fixed time. The time of the P wave, the QRS complex or the T wave of the electrocardiosignal and the current time of the forgetting factor are not necessarily matched. In this way, the forgetting factor corresponding to the P wave, the QRS complex or the T wave is relatively small, thereby reducing the signal quality and effect of the self-adaptive filtering, and further reducing the detection accuracy of the arrhythmia. SUMMARY

[0004] An object of an embodiment of the present application is to provide an arrhythmia detection method, a nonvolatile readable storage medium and a wearable device, and to solve the technical problem of low detection accuracy in arrhythmia detection in the related technology.

[0005] In a first aspect, an embodiment of the present application provides an arrhythmia detection method applied to a wearable device, and the method comprises the following steps.

[0006] obtaining a lead electrocardiosignal and an acceleration collected by the wearable device;

[0007] determining a heart beat region according to the lead electrocardiosignal;

[0008] determining a target forgetting factor of the acceleration according to a heart beat time of the heart beat region;

[0009] According to the target forgetting factor and the acceleration, the lead electrocardio signal is adaptively filtered to obtain a first lead electrocardio signal;

[0010] The first lead electrocardio signal is band-pass filtered to obtain a second lead electrocardio signal;

[0011] According to the second lead electrocardio signal, a heart rhythm detection result is generated.

[0012] Optionally, the target forgetting factor of the acceleration is determined according to the heart beat time of the heart beat region, including:

[0013] A signal time of the acceleration is determined;

[0014] According to the relative position between the signal time of the acceleration and the heart beat time of the heart beat region, the target forgetting factor of the acceleration is determined.

[0015] Optionally, the target forgetting factor of the acceleration is determined according to the relative position between the signal time of the acceleration and the heart beat time of the heart beat region, including:

[0016] When the signal time of the acceleration is within the heart beat time of the heart beat region, the target forgetting factor of the acceleration is determined as a first forgetting factor;

[0017] When the signal time of the acceleration is outside the heart beat time of the heart beat region, the target forgetting factor of the acceleration is determined as a second forgetting factor, and the second forgetting factor is smaller than the first forgetting factor.

[0018] Optionally, the heart beat time includes a P wave interval, a QRS interval and a T wave interval, the first forgetting factor includes a first factor, a second factor and a third factor, the second factor is greater than the first factor and the third factor, and when the signal time of the acceleration is within the heart beat time of the heart beat region, the target forgetting factor of the acceleration is determined as the first forgetting factor, including:

[0019] When the signal time of the acceleration is in the P wave interval of the heart beat region, the target forgetting factor of the acceleration is determined as the first factor;

[0020] When the signal time of the acceleration is in the QRS interval of the heart beat region, the target forgetting factor of the acceleration is determined as the second factor;

[0021] When the signal time of the acceleration is in the T wave interval of the heart beat region, the target forgetting factor of the acceleration is determined as the third factor.

[0022] Optionally, when the signal time of the acceleration is in the P-wave interval of the heart beat region, the closer the signal time of the acceleration is to the QRS interval, the greater the first factor corresponding to the acceleration is, and the farther the signal time of the acceleration is from the QRS interval, the smaller the first factor corresponding to the acceleration is; or,

[0023] When the signal time of the acceleration is in the T-wave interval of the heart beat region, the closer the signal time of the acceleration is to the QRS interval, the greater the third factor corresponding to the acceleration is, and the farther the signal time of the acceleration is from the QRS interval, the smaller the third factor corresponding to the acceleration is.

[0024] Optionally, the heart rhythm detection result includes a ventricular fibrillation detection result, and before the heart rhythm detection result is generated, the method further includes:

[0025] detecting whether a user wearing the wearable device is in a stationary state according to the acceleration;

[0026] if the user is in the stationary state, generating a ventricular fibrillation detection result according to the second lead electrocardio signal.

[0027] Optionally, the detection of whether the user wearing the wearable device is in the stationary state according to the acceleration includes:

[0028] calculating an acceleration value of the acceleration;

[0029] judging whether the acceleration value is greater than a preset threshold value;

[0030] if greater, determining that the user wearing the wearable device is in a motion state;

[0031] if less than or equal to, determining that the user wearing the wearable device is in the stationary state.

[0032] Optionally, the acceleration is a three-axis acceleration, the three-axis acceleration includes an x-axis acceleration, a y-axis acceleration and a z-axis acceleration, and the calculation of the acceleration value of the acceleration includes:

[0033] respectively calculating squares of the x-axis acceleration, the y-axis acceleration and the z-axis acceleration;

[0034] calculating a sum of the squares of the x-axis acceleration, the y-axis acceleration and the z-axis acceleration;

[0035] taking a square root of the sum to obtain the acceleration value of the three-axis acceleration.

[0036] In a second aspect, an embodiment of the present application provides a non-volatile readable storage medium, which stores computer executable instructions for causing a controller to perform the arrhythmia detection method.

[0037] In a third aspect, an embodiment of the present application provides a wearable device, comprising:

[0038] a heart rate sensor;

[0039] an acceleration sensor;

[0040] at least one processor, electrically connected with the heart rate sensor and the acceleration sensor respectively; and

[0041] a memory in communication connection with the at least one processor; wherein

[0042] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the arrhythmia detection method.

[0043] In the arrhythmia detection method provided by the embodiment of the present application, the lead electrocardiogram signal and the acceleration collected by the wearable device are acquired, the heart beat region is determined according to the lead electrocardiogram signal, the target forgetting factor of the acceleration is determined according to the heart beat time of the heart beat region, the lead electrocardiogram signal is adaptively filtered according to the target forgetting factor and the acceleration, the first lead electrocardiogram signal is obtained, the first lead electrocardiogram signal is band-pass filtered, the second lead electrocardiogram signal is obtained, and the heart rhythm detection result is generated according to the second lead electrocardiogram signal. The embodiment does not depend on the given current time to match the forgetting factor for the acceleration, but fully considers the importance of the heart beat region and the important influence of the heart beat region on the heart rhythm detection result, determines the target forgetting factor of the acceleration according to the heart beat time, so as to improve the signal quality and effect of adaptive filtering, and further improve the detection precision of the arrhythmia. BRIEF DESCRIPTION OF DRAWINGS

[0044] One or more embodiments are illustrated by way of example in the drawings, which are not intended to be limiting of the embodiments, and which do not constitute a definition of all possible embodiments, and wherein like reference numerals refer to like elements in the drawings and wherein the drawings are not necessarily to scale as proportions can have been exaggerated in order to clearly illustrate the embodiments.

[0045] Figure 1 A waveform diagram of a typical electrocardiogram signal provided by the related art;

[0046] Figure 2 A waveform diagram of an electrocardiogram signal before the onset of ventricular fibrillation provided by the related art;

[0047] Figure 3 Waveform diagram of non-fibrillation signal in low signal-to-noise ratio situation provided by the related art;

[0048] Figure 4 Waveform diagram of electrocardio signal when fibrillation occurs provided by the related art;

[0049] Figure 5 Circuit structure schematic diagram of a wearable device provided by an embodiment of the present application;

[0050] Figure 6 Flowchart of an arrhythmia detection method provided by an embodiment of the present application;

[0051] Figure 7a 、 Figure 7b and Figure 7c are waveform diagrams of x-axis acceleration a x in x direction, y-axis acceleration a y in y direction and z-axis acceleration a z in z direction respectively provided by an embodiment of the present application;

[0052] Figure 8 Structure schematic diagram of an arrhythmia detection device provided by an embodiment of the present application;

[0053] Figure 9 Circuit structure schematic diagram of a controller provided by an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0055] It should be noted that, if there is no conflict, each feature in the embodiments of the present application can be combined with each other, and all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flowchart. Furthermore, the "first", "second", "third" and the like used in the present application do not limit the data and execution order, but only distinguish the same items or similar items with basically the same function and effect.

[0056] According to the source of ectopic excitation, the arrhythmia can be divided into atrial arrhythmia and ventricular arrhythmia in the related art. According to the time of onset, the arrhythmia can also be divided into non-sustained arrhythmia and sustained arrhythmia. The non-sustained arrhythmia includes ventricular ectopic beats or atrial ectopic beats, and the sustained arrhythmia includes ventricular fibrillation or atrial fibrillation.

[0057] Figure 2 The waveform diagram of the electrocardio signal before the onset of ventricular fibrillation provided for the related art, Figure 3 The waveform diagram of the non-ventricular fibrillation signal in the case of low signal-to-noise ratio provided for the related art, Figure 4 The waveform diagram of the electrocardio signal when ventricular fibrillation occurs. In the arrhythmia, ventricular fibrillation (VF) is a kind of sustained arrhythmia that is more life-threatening. When VF occurs, the heart activity is fast and uncoordinated fibrillation, and the effective contraction ability is lost, which is equivalent to ventricular asystole in hemodynamics, and the electrocardio waveform is a series of rapid and amplitude varying fibrillation waves.

[0058] People can monitor the arrhythmia phenomenon by wearing a wearable device. The wearable device can measure the physical indicators such as heart rate and monitor the arrhythmia in the motion state. However, during the motion process, the electrocardio electrode of the wearable device often slips on the skin, causing the electrocardio signal collected by the wearable device to be submerged by irregular noise signals, which is similar to ventricular fibrillation, such as the waveform diagrams shown in Figure 3 and Figure 4 Subsequently, when the wearable device uses an algorithm to identify the electrocardio signal shown in Figure 4 , misjudgment is prone to occur.

[0059] In the related art, the electrocardio signal needs to be adaptively filtered when detecting the arrhythmia. In the current adaptive filter, the weight is an important parameter. According to the weight, the adaptive filter can be divided into three main types: least mean square (LMS), recursive least squares and affine projection (AP). For the least mean square algorithm, the new data is input into the algorithm for analysis sample by sample, and the error signal of each sample point has the same contribution weight to the objective function. The least mean square algorithm has the advantages of fast calculation speed, but the convergence speed is slow, and is only suitable for stationary signals with regular changes. Due to the influence of noise during the motion process, the electrocardio signal is in a non-stationary state, which not only further reduces the convergence speed, but also easily causes non-convergence.

[0060] The algorithm based on the recursive least square method adds a forgetting factor, the error signal contribution of which is greater the closer to the current time, thereby improving the convergence speed, but since the electrocardiogram signal analysis algorithm is usually performed at a fixed time, once the heart beat region is far from the current time, the signal quality is reduced, thereby affecting the analysis accuracy. Based on this, in the implementation process of the present application, the inventor finds that: combining the heart beat time of the heart beat region to determine the target forgetting factor of the acceleration is beneficial to improve the adaptive filtering effect, thereby being beneficial to improve the signal quality and detection accuracy, in addition, when the user is in a stationary state to monitor ventricular fibrillation, this detection method is more accurate and reliable.

[0061] As an aspect of an embodiment of the present application, an embodiment of the present application provides a wearable device, as shown in the figure, the wearable device 500 comprises a controller 51, a heart rate sensor 52, an acceleration sensor 53, a warning prompt circuit 54 and a wireless communication module 55. Figure 5 The controller 51 is the control core of the wearable device 500.

[0062] The controller 51 is the control core of the wearable device 500.

[0063] The heart rate sensor 52 is electrically connected with the controller 51 and is used for collecting electrocardiogram signals. The heart rate sensor 52 comprises a plurality of electrocardiogram electrodes, which can be closely attached to the skin of the user when the user wears the wearable device 500 to collect the electrocardiogram signals of the user. The user can wear the wearable device 500 on the wrist, elbow, leg, chest or head.

[0064] The acceleration sensor 53 is electrically connected with the controller 51 and is used for collecting the acceleration of the user. The acceleration sensor 53 can be a three-axis gyroscope or an inertial detection unit.

[0065] The warning prompt circuit 54 is electrically connected with the controller 51 and is used for generating warning information. The warning prompt circuit 54 can be a voice prompt circuit, a display screen or an LED light circuit, etc. The voice prompt circuit is used for generating voice type warning information, the display screen is used for generating text type warning information, and the LED light circuit is used for generating light type warning information.

[0066] The wireless communication module 55 is electrically connected with the controller 51 and is used for transmitting the heart rhythm detection report transmitted by the controller 51 to a designated terminal. For example, the controller 51 generates a heart rhythm detection report according to the electrocardiogram signals and the acceleration, and transmits the heart rhythm detection report to a designated terminal through the wireless communication module 55. The designated terminal can be a designated mobile phone, a designated computer or a designated server, etc. The wireless communication module 55 can be a Bluetooth module, a WIFI module, a 4G module or a 5G module, etc.

[0067] As another aspect of the embodiments of the present application, the embodiments of the present application provide a method for detecting arrhythmia, applied to a wearable device. Please refer to Figure 6 The method for detecting arrhythmia comprises the following steps:

[0068] S61: Obtain the lead electrocardio signal and acceleration collected by the wearable device.

[0069] In this step, the lead electrocardio signal is a series of electrocardio signals collected by a heart rate sensor. In the professional terms of electrocardiogram, the placement position of the electrocardio electrode on the human body surface and the connection mode of the electrocardio electrode and the amplifier when recording the electrocardiogram are called the lead of the electrocardiogram. The series of electrocardio signals collected through the lead can be regarded as the lead electrocardio signal. According to the number of lead channels, the lead electrocardio signal can be divided into single-lead electrocardio signal (i.e. the lead electrocardio signal collected through one lead) and multi-lead electrocardio signal (i.e. the lead electrocardio signal collected through multiple leads), wherein the multi-lead electrocardio signal can be considered to be composed of multiple single-lead electrocardio signals, and the number of leads of the more common multi-lead electrocardio signal is three leads, six leads, twelve leads, eighteen leads, etc.

[0070] A lead electrocardio signal refers to a single-lead electrocardio signal, which can be a directly collected single-lead electrocardio signal or a single-lead electrocardio signal selected from a multi-lead electrocardio signal. For example, the wearable device can obtain at least one lead electrocardio signal collected through at least one lead, wherein the number of lead channels, the sampling time length and the sampling frequency can be set according to the actual situation. When multiple lead electrocardio signals are obtained, each lead electrocardio signal is a simultaneously collected electrocardio signal. The lead electrocardio signal is composed of each sample point obtained by sampling, wherein each sample point represents the electrocardio signal collected at the corresponding sampling time. For the lead electrocardio signal, the horizontal axis is the time axis, which is used to record the sampling time of the sample point in time units, at this time, the position of the sample point in the lead electrocardio signal refers to the sampling time of the sample point, and the vertical axis is the intensity of the electrocardio signal, which is often represented by voltage. Optionally, the characteristic waves in the lead electrocardio signal at least include P wave, QRS wave and T wave, and the number of each characteristic wave is not limited by the embodiments. Among them, an adjacent and continuous P wave, a QRS wave and a T wave form a heart beat, and multiple heart beats form a lead electrocardio signal.

[0071] The acceleration is collected by an acceleration sensor. When the acceleration is three-axis acceleration, the three-axis acceleration (a x , a y , a z ) includes x-axis acceleration a x , y-axis acceleration a y and z-axis acceleration a z . Please refer to Figure 7a ,Figure 7b and Figure 7c When the user wears the wearable device to exercise, the acceleration can be decomposed into x-axis acceleration a x , y-axis acceleration a y and z-axis acceleration a z in the x direction, y direction and z direction respectively.

[0072] S62: determining a heart beat region according to the lead electrocardio signal.

[0073] In this step, the heart beat region is the region of the electrocardio characteristic wave. In some embodiments, the heart beat region can be the QRS wave region, i.e. the region between the starting point of the QRS wave and the ending point of the QRS wave. In some embodiments, the heart beat region can be the region sequentially composed of the P wave region, the QRS wave region and the T wave region, i.e. the region between the starting point of the P wave and the ending point of the T wave.

[0074] Determining the heart beat region according to the lead electrocardio signal comprises inputting the lead electrocardio signal into a preset heart beat feature model to obtain the heart beat region. The heart beat feature model can be obtained by the designer in advance.

[0075] S63: determining a target forgetting factor of the acceleration according to the heart beat time of the heart beat region.

[0076] In this step, the heart beat time is the time corresponding to the heart beat region. In some embodiments, when the heart beat region is the QRS wave region, the heart beat time is the starting point of the QRS wave to the ending point of the QRS wave. In some embodiments, when the heart beat region is the region sequentially composed of the P wave region, the QRS wave region and the T wave region, the heart beat time is the starting point of the P wave to the ending point of the T wave.

[0077] The target forgetting factor is the forgetting factor determined by the heart beat time for the acceleration. In the subsequent adaptive filtering process, the embodiment needs to combine the forgetting factor of the acceleration and the acceleration to perform adaptive filtering processing on the lead electrocardio signal.

[0078] S64: performing adaptive filtering processing on the lead electrocardio signal according to the target forgetting factor and the acceleration to obtain a first lead electrocardio signal.

[0079] In this step, the first lead electrocardio signal is the lead electrocardio signal after adaptive filtering processing. Let the single-channel lead electrocardio signal be y, and the acceleration be (a x , a y , a z ). In each analysis process of the embodiment, the length of the obtained lead electrocardio signal and the acceleration is n. If the sampling rate of the lead electrocardio signal and the acceleration is not 250 Hz, the signal is resampled to 250 Hz before analysis.

[0080] In the adaptive filtering algorithm, the weight of the acceleration is w, and the dimension of the weight of the acceleration is equal to the channel number of the acceleration. e is an error signal of the adaptive filtering, and μ adap is a step size of the adaptive filtering weight update (μ adap = 0.01), and ε is a very small positive number (ε = 1e-3). When the i = 1,...,n sample points of the lead electrocardio signal and the acceleration are processed, the error of the adaptive filter, the weight, and the target optimization function are as shown in formula 1, formula 2, and formula 3:

[0081] e(i) = y bp (i) - w T (i)a(i) formula 1

[0082] w(i+1) = w(i) + 2μ adap / (ε + a T (i)a(i))a(i)e(i) formula 2

[0083]

[0084] wherein λ is a forgetting factor, 0 < λ ≤ 1, J n (w) is a target optimization function, and the target optimization function can be optimized according to the minimum mean square error method, so as to output the adaptive filtering result.

[0085] S65: performing a band-pass filtering process on the first lead electrocardio signal to obtain a second lead electrocardio signal.

[0086] In this step, the band-pass filtering process is an operation of retaining the first lead electrocardio signal in a specified frequency range, and the second lead electrocardio signal is the first lead electrocardio signal after the band-pass filtering process. In this embodiment, a 2-order Butterworth filter with a frequency range of 0.5 Hz to 35 Hz is selected as the band-pass filter to perform the band-pass filtering process on the first lead electrocardio signal.

[0087] S66: generating a heart rhythm detection result according to the second lead electrocardio signal.

[0088] In this step, the heart rhythm detection result includes a ventricular beat detection result, an atrial beat detection result, a ventricular fibrillation detection result, and an atrial fibrillation detection result. The ventricular beat detection result includes a normal ventricular beat result and a ventricular ectopic beat result. The atrial beat detection result includes a normal atrial beat result and an atrial ectopic beat result. The ventricular fibrillation detection result includes a normal ventricular result and a ventricular fibrillation result. The atrial fibrillation detection result includes a normal atrial result and an atrial fibrillation result.

[0089] In general, the embodiment is not dependent on the current time to match the forgetting factor of the acceleration, and fully considers the importance of the heart beat region and the important influence of the heart beat region on the heart rhythm detection result, and determines the target forgetting factor of the acceleration according to the heart beat time, so as to improve the signal quality and effect of the adaptive filtering, and further improve the detection accuracy of the arrhythmia.

[0090] In some embodiments, determining the target forgetting factor of the acceleration according to the heart beat time of the heart beat region includes the following steps: determining the signal time of the acceleration, and determining the target forgetting factor of the acceleration according to the relative position of the signal time of the acceleration and the heart beat time of the heart beat region. The embodiment can distinguishively match the corresponding target forgetting factor of the acceleration according to the relative position of the signal time and the heart beat time, and fully integrates the importance of the heart beat region and the important influence of the heart beat region on the heart rhythm detection result into the selection of the forgetting factor, so as to improve the effect of the adaptive filtering, thereby helping to improve the detection accuracy.

[0091] In some embodiments, determining the target forgetting factor of the acceleration according to the relative position of the signal time of the acceleration and the heart beat time of the heart beat region includes: when the signal time of the acceleration is within the heart beat time of the heart beat region, determining the target forgetting factor of the acceleration as a first forgetting factor, and when the signal time of the acceleration is outside the heart beat time of the heart beat region, determining the target forgetting factor of the acceleration as a second forgetting factor, the second forgetting factor being smaller than the first forgetting factor.

[0092] For example, when the signal time of the acceleration is within the heart beat time of the heart beat region, the target forgetting factor of the acceleration appearing in the heart beat time is set as the first forgetting factor. When the signal time of the acceleration is outside the heart beat time of the heart beat region, the target forgetting factor of the acceleration appearing outside the heart beat time is set as the second forgetting factor.

[0093] It can be understood that the first forgetting factor and the second forgetting factor can be defined by the designer according to engineering experience, such as the first forgetting factor being 0.8 and the second forgetting factor being 0.2.

[0094] It can also be understood that, since the second forgetting factor is smaller than the first forgetting factor, the acceleration signal with the signal time in the heart beat region will be given a larger forgetting factor, that is, the forgetting of the acceleration signal with the signal time in the heart beat region is less, and the acceleration signal with the signal time outside the heart beat region will be given a smaller forgetting factor, that is, the forgetting of the acceleration signal with the signal time in the heart beat region is more, so as to facilitate fast convergence and improve the effect of the adaptive filtering.

[0095] In some embodiments, the heartbeat time comprises a P-wave interval, a QRS interval and a T-wave interval, the first forgetting factor comprises a first factor, a second factor and a third factor, and the second factor is greater than the first factor and the third factor. When the signal time of the acceleration is within the heartbeat time of the heartbeat region, determining the target forgetting factor of the acceleration as the first forgetting factor comprises the following steps: when the signal time of the acceleration is within the P-wave interval of the heartbeat region, determining the target forgetting factor of the acceleration as the first factor; when the signal time of the acceleration is within the QRS interval of the heartbeat region, determining the target forgetting factor of the acceleration as the second factor; and when the signal time of the acceleration is within the T-wave interval of the heartbeat region, determining the target forgetting factor of the acceleration as the third factor.

[0096] The QRS wave is an important characteristic wave of the electrocardiosignal, and the QRS interval is an important interval of the heartbeat time, so a relatively large forgetting factor can be matched for the QRS interval, and a relatively small forgetting factor can be matched for the P-wave interval or the T-wave interval, which is beneficial to improve the adaptive filtering effect, retain important waveform characteristics, and help the subsequent steps to reliably and accurately perform heart rhythm detection.

[0097] In some embodiments, when the signal time of the acceleration is within the P-wave interval of the heartbeat region, the closer the signal time of the acceleration is to the QRS interval, the greater the first factor corresponding to the acceleration, and the farther the signal time of the acceleration is from the QRS interval, the smaller the first factor corresponding to the acceleration. As described above, the QRS wave is an important characteristic wave of the electrocardiosignal, and the closer the P-wave electrocardiosignal is to the QRS wave, the more obvious the waveform characteristics carried, and the farther the P-wave electrocardiosignal is from the QRS wave, the less obvious the waveform characteristics carried, so this embodiment can monotonically increase or decrease the first factor according to the distance between the P-wave electrocardiosignal and the QRS wave, which is beneficial to improve the adaptive filtering effect and retain important waveform characteristics.

[0098] In some embodiments, when the signal time of the acceleration is within the T-wave interval of the heartbeat region, the closer the signal time of the acceleration is to the QRS interval, the greater the third factor corresponding to the acceleration, and the farther the signal time of the acceleration is from the QRS interval, the smaller the third factor corresponding to the acceleration. As described above, the QRS wave is an important characteristic wave of the electrocardiosignal, and the closer the T-wave electrocardiosignal is to the QRS wave, the more obvious the waveform characteristics carried, and the farther the T-wave electrocardiosignal is from the QRS wave, the less obvious the waveform characteristics carried, so this embodiment can monotonically increase or decrease the third factor according to the distance between the T-wave electrocardiosignal and the QRS wave, which is beneficial to improve the adaptive filtering effect and retain important waveform characteristics.

[0099] In some embodiments, the heart rhythm detection result comprises a ventricular fibrillation result, and before the heart rhythm detection result is generated, the method further comprises the following steps: detecting whether the user wearing the wearable device is in a stationary state according to the acceleration, and if the user is in the stationary state, generating a ventricular fibrillation detection result according to the second-lead electrocardio signal, and if the user is in a motion state, generating a ventricular extrasystole detection result, an atrial extrasystole detection result or an atrial fibrillation detection result according to the second-lead electrocardio signal.

[0100] Among various main arrhythmia states, the electrocardio performance of ectopic beats and atrial fibrillation has regularity, and the performance of noise has obvious abnormality, while in ventricular fibrillation, the electrocardio performance has no regularity, thus leading to partial similarity with noise. When ventricular fibrillation occurs, due to severe hemodynamic disorder, the patient will have symptoms such as loss of consciousness and syncope, and stop moving, thus it can be considered that ventricular fibrillation usually does not occur when the user is in normal motion, and it is easy to misidentify ventricular fibrillation as non-ventricular fibrillation when the user is in a motion state.

[0101] The acceleration provided by the related art is usually used for fall detection or is only used in a filtering and noise reduction process, while in the present embodiment, the acceleration is not only applied to an adaptive filtering process, but also added to an arrhythmia identification process, thus reducing the misidentification of ventricular fibrillation.

[0102] In some embodiments, detecting whether the user wearing the wearable device is in a stationary state according to the acceleration comprises the following steps: calculating an acceleration value of the acceleration, judging whether the acceleration value is greater than a preset threshold, and if yes, determining that the user wearing the wearable device is in a motion state, and if no or equal, determining that the user wearing the wearable device is in a stationary state. The preset threshold is self-defined by a designer according to engineering experience.

[0103] In some embodiments, the acceleration is three-axis acceleration, which comprises x-axis acceleration, y-axis acceleration and z-axis acceleration, and calculating the acceleration value of the acceleration comprises the following steps: calculating the square of the x-axis acceleration, the square of the y-axis acceleration and the square of the z-axis acceleration respectively, calculating the sum of the square of the x-axis acceleration, the square of the y-axis acceleration and the square of the z-axis acceleration, and taking the square root of the sum to obtain the acceleration value of the three-axis acceleration.

[0104] For example, the present embodiment calculates the acceleration value of the three-axis acceleration according to the following formula: wherein a is the acceleration value of the three-axis acceleration.

[0105] The present embodiment can synthesize the acceleration values of multiple channels into three-axis acceleration, which is conducive to reliably judging whether the user is in a motion state, and thus reliably detecting whether ventricular fibrillation occurs.

[0106] In some embodiments, when the number of lead electrocardio signals is multiple, generating the heart rhythm detection result according to the second lead electrocardio signal comprises: determining the number of second lead electrocardio signals corresponding to the same type of heart rhythm detection result, and the total number of lead electrocardio signals, calculating the proportion of each type of number and the total number, determining the maximum proportion in the multiple proportions, judging whether the maximum proportion is greater than a preset proportion threshold, if greater, reporting the heart rhythm detection result corresponding to the maximum proportion to the background, if less than or equal to, re-performing the arrhythmia detection operation.

[0107] For example, the wearable device can detect 4-channel lead electrocardio signals at the same time, and the preset proportion threshold is 50%. If the lead electrocardio signals of the first channel to the third channel correspond to the atrial normal beat result, and the lead electrocardio signal of the fourth channel corresponds to the atrial fibrillation result, since the number of lead electrocardio signals of the same atrial normal beat result is 3, the total number is 4, the proportion is 3 / 4, and the number of lead electrocardio signals of the atrial fibrillation result is 1, the proportion is 1 / 4, therefore, the maximum proportion is 3 / 4, and 3 / 4 is greater than 50%, therefore, the atrial normal beat result is reported to the background in this embodiment, which can improve the detection robustness and avoid some noise factors to cause misidentification of the corresponding channel and make the final detection result not accurate and reliable.

[0108] It should be noted that in each of the above embodiments, there is no certain sequence between the above steps, and those skilled in the art can understand from the description of the embodiments of the present application that the above steps can have different execution sequences in different embodiments, that is, they can be executed in parallel, or they can be executed in exchange, etc.

[0109] As another aspect of the embodiments of the present application, the embodiments of the present application provide an arrhythmia detection device applied to a wearable device. The arrhythmia detection device can be a software module, the software module includes a plurality of instructions stored in a memory, and a processor can access the memory to call the instructions for execution to complete the arrhythmia detection method described in each of the above embodiments.

[0110] In some embodiments, the arrhythmia detection apparatus can also be built by hardware devices, for example, the arrhythmia detection apparatus can be built by one or more chips, and each chip can work in coordination with each other to complete the arrhythmia detection method described in each of the above embodiments. For another example, the arrhythmia detection apparatus can also be built by various logic devices, such as general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), single-chip microcomputers, ARM (Acorn RISC Machine), or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, or any combination of these components.

[0111] Referring to Figure 8 The arrhythmia detection apparatus 800 includes a signal acquisition module 81, a heartbeat determination module 82, a weight adjustment module 83, an adaptive filtering module 84, a band-pass filtering module 85, and a result generation module 86.

[0112] The signal acquisition module 81 is configured to acquire the lead electrocardio signal and the acceleration collected by the wearable device. The heartbeat determination module 82 is configured to determine a heartbeat region according to the lead electrocardio signal. The weight adjustment module 83 is configured to determine a target forgetting factor of the acceleration according to a heartbeat time of the heartbeat region. The adaptive filtering module 84 is configured to perform adaptive filtering processing on the lead electrocardio signal according to the target forgetting factor and the acceleration, to obtain a first lead electrocardio signal. The band-pass filtering module 85 is configured to perform band-pass filtering processing on the first lead electrocardio signal, to obtain a second lead electrocardio signal. The result generation module 86 is configured to generate an arrhythmia detection result according to the second lead electrocardio signal.

[0113] The embodiment does not rely on matching the forgetting factor for the acceleration at a given current time, but fully considers the importance of the heartbeat region and the important influence of the heartbeat region on the arrhythmia detection result. The target forgetting factor of the acceleration is determined according to the heartbeat time, so that the signal quality and effect of the adaptive filtering can be improved, and the detection accuracy of the arrhythmia can also be improved.

[0114] In some embodiments, the weight adjustment module 83 is specifically configured to determine a signal time of the acceleration, and determine the target forgetting factor of the acceleration according to the relative position between the signal time of the acceleration and the heartbeat time of the heartbeat region.

[0115] In some embodiments, the weight adjustment module 83 is further specifically configured to determine the target forgetting factor of the acceleration as a first forgetting factor when the signal time of the acceleration is within the heartbeat time of the heartbeat region, and determine the target forgetting factor of the acceleration as a second forgetting factor when the signal time of the acceleration is outside the heartbeat time of the heartbeat region, the second forgetting factor being smaller than the first forgetting factor.

[0116] In some embodiments, the heart beat time comprises a P-wave interval, a QRS interval and a T-wave interval, the first forgetting factor comprises a first factor, a second factor and a third factor, the second factor is greater than the first factor and the third factor, and in some embodiments, the weight adjusting module 83 is further specifically configured to: when the signal time of the acceleration is in the P-wave interval of the heart beat region, determine the target forgetting factor of the acceleration as the first factor, when the signal time of the acceleration is in the QRS interval of the heart beat region, determine the target forgetting factor of the acceleration as the second factor, and when the signal time of the acceleration is in the T-wave interval of the heart beat region, determine the target forgetting factor of the acceleration as the third factor.

[0117] In some embodiments, when the signal time of the acceleration is in the P-wave interval of the heart beat region, the closer the signal time of the acceleration to the QRS interval, the greater the first factor corresponding to the acceleration, and the farther the signal time of the acceleration to the QRS interval, the smaller the first factor corresponding to the acceleration.

[0118] In some embodiments, when the signal time of the acceleration is in the T-wave interval of the heart beat region, the closer the signal time of the acceleration to the QRS interval, the greater the third factor corresponding to the acceleration, and the farther the signal time of the acceleration to the QRS interval, the smaller the third factor corresponding to the acceleration.

[0119] In some embodiments, the heart rhythm detection result comprises a ventricular fibrillation detection result, and before the heart rhythm detection result is generated, the result generating module 86 is specifically configured to: detect whether a user wearing the wearable device is in a stationary state according to the acceleration, and if the user is in the stationary state, generate the ventricular fibrillation detection result according to the second lead electrocardio signal.

[0120] In some embodiments, the result generating module 86 is further specifically configured to: calculate an acceleration value of the acceleration, judge whether the acceleration value is greater than a preset threshold, if yes, determine that the user wearing the wearable device is in a motion state, and if no or equal, determine that the user wearing the wearable device is in a stationary state.

[0121] In some embodiments, the acceleration is a three-axis acceleration, the three-axis acceleration comprises an x-axis acceleration, a y-axis acceleration and a z-axis acceleration, and the result generating module 86 is further specifically configured to: calculate the square of the x-axis acceleration, the square of the y-axis acceleration and the square of the z-axis acceleration respectively, calculate the sum of the square of the x-axis acceleration, the square of the y-axis acceleration and the square of the z-axis acceleration, and take the square root of the sum to obtain the acceleration value of the three-axis acceleration.

[0122] It should be noted that the above-mentioned arrhythmia detection device can execute the arrhythmia detection method provided by the embodiments of the present application, has the function modules and beneficial effects corresponding to the execution method. The technical details not described in detail in the embodiment of the arrhythmia detection device can be referred to the arrhythmia detection method provided by the embodiments of the present application.

[0123] Please refer to Figure 9 , Figure 9 The circuit structure schematic diagram of a controller provided by the embodiments of the present application is shown in the figure. As shown in the figure, Figure 9 The controller 900 includes one or more processors 91 and a memory 92. Among them, Figure 9 The processor 91 is taken as an example.

[0124] The processor 91 and the memory 92 can be connected through a bus or other means, Figure 9 The connection through the bus is taken as an example.

[0125] The memory 92 is a kind of non-volatile computer readable storage medium, which can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the arrhythmia detection method in the embodiments of the present application. The processor 91 executes the non-volatile software program, instruction and module stored in the memory 92, thereby executing various functional applications and data processing of the arrhythmia detection device, i.e. realizing the functions of the arrhythmia detection method provided by the above-mentioned method embodiments and the modules or units of the above-mentioned device embodiments.

[0126] The memory 92 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 92 can optionally include a memory remotely arranged relative to the processor 91, and these remote memories can be connected to the processor 91 through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0127] The program instructions / modules are stored in the memory 92, and when executed by the one or more processors 91, the arrhythmia detection method in any of the above-mentioned method embodiments is executed.

[0128] The embodiments of the present application also provide a non-volatile computer storage medium, which stores computer executable instructions. The computer executable instructions are executed by one or more processors, for example Figure 9 The one processor 91 in the above-mentioned embodiment, so that the above-mentioned one or more processors can execute the arrhythmia detection method in any of the above-mentioned method embodiments.

[0129] The embodiment of the present application also provides a computer program product, which comprises a computer program stored on a nonvolatile computer readable storage medium, the computer program comprising program instructions, which, when executed by a controller, cause the controller to perform any of the heartbeat disorder detection methods.

[0130] The device or equipment embodiments described above are merely illustrative, wherein the unit modules described as separate components can or can not be physically separated, and the components shown as module units can or can not be physical units, i.e., can be located in one place or distributed on multiple network module units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0131] Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0132] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; under the idea of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of the different aspects of the present application as described above; for the sake of simplicity, they are not provided in detail; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for arrhythmia detection, applied to a wearable device, characterized in that, The method comprises the following steps: obtaining a lead electrocardio signal and acceleration collected by the wearable device; determining a heart beat region according to the lead electrocardio signal; determining a target forgetting factor of the acceleration according to a heart beat time of the heart beat region; performing adaptive filtering processing on the lead electrocardio signal according to the target forgetting factor and the acceleration to obtain a first lead electrocardio signal; performing band-pass filtering processing on the first lead electrocardio signal to obtain a second lead electrocardio signal; generating a heart rhythm detection result according to the second lead electrocardio signal.

2. The method of claim 1, wherein, The step of determining the target forgetting factor of the acceleration according to the relative position between the signal time of the acceleration and the heart beat time of the heart beat region comprises the following steps: when the signal time of the acceleration is within the heart beat time of the heart beat region, determining the target forgetting factor of the acceleration as a first forgetting factor; when the signal time of the acceleration is outside the heart beat time of the heart beat region, determining the target forgetting factor of the acceleration as a second forgetting factor, the second forgetting factor being smaller than the first forgetting factor.

3. The method of claim 2, wherein, The heart beat time comprises a P wave interval, a QRS interval and a T wave interval, the first forgetting factor comprises a first factor, a second factor and a third factor, the second factor being larger than the first factor and the third factor, and the step of determining the target forgetting factor of the acceleration as the first forgetting factor when the signal time of the acceleration is within the heart beat time of the heart beat region comprises the following steps: when the signal time of the acceleration is within the P wave interval of the heart beat region, determining the target forgetting factor of the acceleration as the first factor; when the signal time of the acceleration is within the QRS interval of the heart beat region, determining the target forgetting factor of the acceleration as the second factor; 4. The method of claim 3, wherein, when the signal time of the acceleration is within the T wave interval of the heart beat region, determining the target forgetting factor of the acceleration as the third factor.

5. The method according to claim 4, wherein: when the signal time of the acceleration is within the P wave interval of the heart beat region, the closer the signal time of the acceleration is to the QRS interval, the larger the first factor corresponding to the acceleration, and the farther the signal time of the acceleration is from the QRS interval, the smaller the first factor corresponding to the acceleration; or when the signal time of the acceleration is within the T wave interval of the heart beat region, the closer the signal time of the acceleration is to the QRS interval, the larger the third factor corresponding to the acceleration, and the farther the signal time of the acceleration is from the QRS interval, the smaller the third factor corresponding to the acceleration. The heart rhythm detection result comprises a ventricular fibrillation detection result, and before the heart rhythm detection result is generated, the method further comprises the following steps: detecting whether a user wearing the wearable device is in a stationary state according to the acceleration; ​ 6. The method according to any one of claims 1 to 5, characterized in that, ​ ​ If the user is in a stationary state, a ventricular fibrillation detection result is generated according to the second lead electrocardio signal.

7. The method of claim 6, wherein, The method comprises: calculating an acceleration value of the acceleration; judging whether the acceleration value is greater than a preset threshold value; if greater, determining that the user wearing the wearable device is in a motion state; if less than or equal to, determining that the user wearing the wearable device is in a stationary state.

8. The method of claim 7, wherein, The acceleration is a three-axis acceleration, which comprises an x-axis acceleration, a y-axis acceleration and a z-axis acceleration, and the calculation of the acceleration value of the acceleration comprises: respectively calculating squares of the x-axis acceleration, the y-axis acceleration and the z-axis acceleration; calculating a sum of the squares of the x-axis acceleration, the y-axis acceleration and the z-axis acceleration; taking a square root of the sum to obtain the acceleration value of the three-axis acceleration.

9. A non-volatile readable storage medium, characterized by The non-volatile readable storage medium stores computer executable instructions for causing the controller to execute the arrhythmia detection method according to any one of claims 1 to 8.

10. A wearable device, comprising: comprises: a heart rate sensor; an acceleration sensor; at least one processor electrically connected with the heart rate sensor and the acceleration sensor respectively; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the arrhythmia detection method according to any one of claims 1 to 8.

Images