阅读说明：本技术 信号处理方法、装置、计算机设备、存储介质及标测系统 (Signal processing method, signal processing device, computer equipment, storage medium and mapping system ) 是由 杨翠微 何凯悦 钟高艳 王心怡 孙毅勇 宫晶晶 于 2020-05-29 设计创作，主要内容包括：本申请涉及一种心电信号的处理方法、装置、计算机设备、存储介质以及三维标测系统,由于各个心电信号之间的波形差与产生这些心电信号的位置差在一定程度上存在着映射关系,通过获取第一心律失常心电信号和多个电刺激心电信号,根据第一心律失常心电信号的波形与多个电刺激心电信号的波形,建立至少一个差值预测模型,并根据多个电刺激心电信号各自对应的起搏位置,建立各起搏位置的位置差矩阵,则根据各起搏位置的位置差矩阵,通过至少一个差值预测模型确定第一心律失常心电信号的起源位置。通过建立的差值预测模型可以快速定位心律失常起源点,避免多次起搏尝试,减少起搏次数,解决传统技术中定位心律失常起源点耗时较长的技术问题。(The application relates to an electrocardiosignal processing method, a device, a computer device, a storage medium and a three-dimensional mapping system, wherein a mapping relation exists between waveform differences among electrocardiosignals and position differences for generating the electrocardiosignals to a certain extent, at least one difference prediction model is established by acquiring a first arrhythmia electrocardiosignal and a plurality of electrostimulation electrocardiosignals, according to the waveform of the first arrhythmia signal and the waveforms of the plurality of electrostimulation electrocardiosignals, and a position difference matrix of each pacing position is established according to the respective corresponding pacing positions of the plurality of electrostimulation electrocardiosignals, so that the origin position of the first arrhythmia electrocardiosignal is determined through the at least one difference prediction model according to the position difference matrix of each pacing position. The arrhythmia origin point can be quickly positioned through the established difference prediction model, multiple pacing attempts are avoided, the pacing times are reduced, and the technical problem that the time for positioning the arrhythmia origin point in the traditional technology is long is solved.)

1. A method for processing an ecg signal, the method comprising:

obtaining a plurality of body surface electrocardiosignals, wherein the body surface electrocardiosignals comprise a first arrhythmia electrocardiosignal with unknown origin position and a plurality of electric stimulation electrocardiosignals generated by an intracardiac intervention device during pacing at each pacing position;

establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals;

establishing a position difference matrix of each pacing position according to the respective pacing positions corresponding to the plurality of electrical stimulation electrocardiosignals;

and determining the origin position of the first arrhythmia electrocardiosignal through at least one difference value prediction model according to the position difference matrix of each pacing position.

2. The method of claim 1, wherein said building at least one difference prediction model from said first arrhythmic cardiac signal waveform and a plurality of said electrical stimulation cardiac signals waveforms comprises:

establishing a waveform difference matrix of each pacing position according to the waveforms of the plurality of electrical stimulation electrocardiosignals;

establishing a waveform difference matrix of the origin position according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals;

and establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

3. The method of claim 1, wherein prior to said establishing at least one difference prediction model based on said first arrhythmic cardiac signal waveform and a plurality of said electrical stimulation cardiac signals waveforms, the method further comprises:

respectively carrying out waveform reconstruction on the plurality of obtained body surface electrocardiosignals to obtain a plurality of reconstructed waveform vectors of the body surface electrocardiosignals, wherein the plurality of reconstructed waveform vectors of the body surface electrocardiosignals comprise a plurality of reconstructed waveform vectors of the electric stimulation electrocardiosignals and a reconstructed waveform vector of the first arrhythmia electrocardiosignal;

establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals, wherein the difference prediction model comprises the following steps:

determining a waveform difference vector of each pacing position according to the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals;

determining a waveform difference vector of the origin position according to the reconstructed waveform vector of the first arrhythmia electrocardiosignal and the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals;

and establishing at least one difference prediction model according to the waveform difference vector of each pacing position and the waveform difference vector of the origin position.

4. The method according to claim 3, wherein the performing waveform reconstruction on the plurality of acquired body surface electrocardiosignals respectively to obtain a plurality of reconstructed waveform vectors of the body surface electrocardiosignals comprises:

detecting the peak position of each body surface electrocardiosignal, and aligning and intercepting each body surface electrocardiosignal through the peak position;

down-sampling each intercepted electrocardiosignal, and normalizing each electrocardiosignal obtained by down-sampling;

and respectively carrying out end-to-end connection on each electrocardiosignal obtained by normalization processing to obtain a reconstructed waveform vector of each body surface electrocardiosignal.

5. The method of claim 3, wherein establishing at least one of the difference prediction models based on the waveform difference vector for each of the pacing locations and the waveform difference vector for the originating location comprises:

establishing a waveform difference matrix of each pacing position and a waveform difference matrix of the origin position according to the waveform difference vector of each pacing position and the waveform difference vector of the origin position;

and establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

6. The method of claim 5, wherein establishing at least one of the difference prediction models based on the waveform difference matrix for each of the pacing sites and the waveform difference matrix for the originating site comprises:

calculating a conversion matrix between the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position by using a least square method;

and establishing at least one difference prediction model through each conversion matrix obtained by calculation.

7. The method of any one of claims 1 to 6, further comprising:

predicting a number of the pacing positions using each of the differential prediction models;

and determining a prediction error according to the pacing position and a prediction result corresponding to the pacing position, and performing optimization screening on each difference prediction model according to the prediction error.

8. The method according to claim 7, wherein determining the location of origin of the first arrhythmic cardiac signal by at least one of the difference prediction models based on the location difference matrix for each pacing location comprises:

selecting a difference value prediction model meeting a preset condition through the prediction error;

and determining the origin position of the first arrhythmia electrocardiosignal through the selected difference prediction model according to the position difference matrix of each pacing position.

9. The method according to claim 1, wherein determining the originating location of the first arrhythmic cardiac signal by at least one of the difference prediction models based on the location difference matrix for each pacing location comprises:

determining a position difference matrix of the origin position through at least one difference prediction model according to the position difference matrix of each pacing position;

and determining the origin position of the first arrhythmia electrocardiosignal according to the position information of each pacing position and the position difference matrix of the origin position.

10. The method according to any one of claims 1 to 6,

before the establishing of at least one difference prediction model according to the waveform of the first arrhythmic electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals, the method further comprises:

acquiring an intracardiac electrical stimulation signal; calculating the triggering lag time of each body surface electrocardiosignal relative to the intracardiac electrostimulation signal; judging whether each body surface electrocardiosignal is effective or not according to the trigger lag time;

establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals, wherein the difference prediction model comprises the following steps:

and if the body surface electrocardiosignals are judged to be effective, establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals.

11. The method of any one of claims 1 to 6, further comprising:

acquiring a plurality of second arrhythmia electrocardiosignals;

averaging a plurality of electrical stimulation electrocardiosignals used for establishing the difference value prediction model to obtain corresponding average waveform difference vectors;

comparing the obtained average waveform difference vector with the obtained waveform difference vectors of the second arrhythmia electrocardiosignals one by one to obtain a plurality of comparison parameters;

and determining a second arrhythmia electrocardiosignal matched with the characteristics of the difference prediction model according to the obtained multiple comparison parameters.

12. The method of claim 11, further comprising:

and displaying the origin position of the first arrhythmia electrocardiosignal and the origin position of the second arrhythmia electrocardiosignal.

13. An apparatus for processing an electrocardiographic signal, the apparatus comprising:

the body surface signal acquisition module is used for acquiring a plurality of body surface electrocardiosignals, wherein the body surface electrocardiosignals comprise a first arrhythmia electrocardiosignal with unknown origin position and a plurality of electric stimulation electrocardiosignals generated by the intracardiac intervention device during pacing at each pacing position;

the prediction model establishing module is used for establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals;

the position difference matrix establishing module is used for establishing a position difference matrix of each pacing position according to the respective corresponding pacing position of the plurality of electrical stimulation electrocardiosignals;

and the origin position prediction module is used for determining the origin position of the first arrhythmia electrocardiosignal through at least one difference value prediction model according to the position difference matrix of each pacing position.

14. A three-dimensional mapping system, comprising:

the electrical stimulation generation module is used for periodically electrically stimulating the heart through the intracardiac interventional device;

the signal acquisition module is used for acquiring body surface electrocardiosignals and intracardiac electrocardiosignals; the intracardiac cardiac electrical signals comprise intracardiac electrical stimulation signals;

a positioning module for acquiring a position of the intracardiac interventional device;

a data processing module, connected to the signal acquisition module and the positioning module respectively, for implementing the steps of the method for processing an electrocardiographic signal according to any one of claims 1 to 11.

15. The three-dimensional mapping system according to claim 14, further comprising:

and the display module is connected with the data processing module and is used for displaying the origin position of the arrhythmia electrocardiosignal.

16. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 11 when executing the computer program.

17. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 11.

Technical Field

The present application relates to the technical field of medical devices, and in particular, to a method and an apparatus for processing an electrocardiographic signal, a computer device, a storage medium, and a three-dimensional mapping system.

Background

Three-dimensional mapping systems are currently in wide use in the field of electrophysiology. Based on the existing medical theory, arrhythmia is often caused by the occurrence of abnormality in one or more regions in the heart. The three-dimensional mapping system may locate the one or more regions for treatment by intracardiac mapping.

In the case of ventricular arrhythmia, the pathological characteristics of ventricular arrhythmia are more obviously reflected in the waveform form of a 12-lead electrocardiogram. Some physicians incorporate a 12-lead electrocardiogram to locate the origin of the arrhythmia to a region before or during surgery. Some doctors use pacing devices to perform electrical stimulation in the heart during operation, and gradually locate the origin of arrhythmia to a more precise area by comparing the similarity of the 12-lead electrocardiogram generated by electrical stimulation and the spontaneous arrhythmia electrocardiogram of the patient for a plurality of times.

The existing problems are that different doctors can adopt different standards for judging origin positions, and some beginners are unskilled in operative operation of electrocardiographic waveform cognition and pacing similarity contrast, so that the operative type is complicated and not standard enough. Meanwhile, multiple pacing attempts are required in a waveform similarity comparison mode, the point with the highest similarity is found in a mode similar to 'blind guess', multiple pacing attempts are required, and the operation process is long. Namely, the technical problem of long time consumption exists in the method of positioning the arrhythmia origin point by means of waveform similarity contrast.

Disclosure of Invention

In view of the above, it is necessary to provide a processing method, an apparatus, a computer device, a storage medium, and a three-dimensional mapping system for cardiac electrical signals, which can quickly locate an arrhythmia origin.

The processing method of the electrocardiosignal provided by the invention comprises the following steps:

obtaining a plurality of body surface electrocardiosignals, wherein the body surface electrocardiosignals comprise a first arrhythmia electrocardiosignal with unknown origin position and a plurality of electric stimulation electrocardiosignals generated by an intracardiac intervention device during pacing at each pacing position; establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals; establishing a position difference matrix of each pacing position according to the respective pacing positions corresponding to the plurality of electrical stimulation electrocardiosignals; and determining the origin position of the first arrhythmia electrocardiosignal through at least one difference value prediction model according to the position difference matrix of each pacing position.

An apparatus for processing cardiac electrical signals, the apparatus comprising: the body surface signal acquisition module is used for acquiring a plurality of body surface electrocardiosignals, wherein the body surface electrocardiosignals comprise a first arrhythmia electrocardiosignal with unknown origin position and a plurality of electric stimulation electrocardiosignals generated by the intracardiac intervention device during pacing at each pacing position; the prediction model establishing module is used for establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals; the position difference matrix establishing module is used for establishing a position difference matrix of each pacing position according to the respective corresponding pacing position of the plurality of electrical stimulation electrocardiosignals; and the origin position prediction module is used for determining the origin position of the first arrhythmia electrocardiosignal through at least one difference value prediction model according to the position difference matrix of each pacing position.

A three-dimensional mapping system, comprising: the electrical stimulation generation module is used for periodically electrically stimulating the heart through the intracardiac interventional device; the signal acquisition module is used for acquiring body surface electrocardiosignals and intracardiac electrocardiosignals; the intracardiac cardiac electrical signals comprise intracardiac electrical stimulation signals; a positioning module for acquiring a position of the intracardiac interventional device; and the data processing module is respectively connected with the signal acquisition module and the positioning module and is used for realizing the steps of the method in any embodiment.

A computer device comprising a memory storing a computer program and a processor implementing the method steps of any of the above embodiments when the processor executes the computer program.

A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any of the above embodiments.

According to the electrocardiosignal processing method, the electrocardiosignal processing device, the computer equipment, the storage medium and the three-dimensional mapping system, because the waveform difference between every two electrocardiosignals and the position difference for generating the electrocardiosignals have a mapping relation to a certain extent, at least one difference prediction model is established by acquiring a first arrhythmia electrocardiosignal and a plurality of electric stimulation electrocardiosignals according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electric stimulation electrocardiosignals, a position difference matrix of every pacing position is established according to the pacing positions corresponding to the plurality of electric stimulation electrocardiosignals, and the origin position of the first arrhythmia electrocardiosignal is determined through the at least one difference prediction model according to the position difference matrix of every pacing position. The arrhythmia origin point can be quickly positioned through the established difference prediction model, multiple pacing attempts are avoided, the pacing times are reduced, and the technical problem that the time for positioning the arrhythmia origin point in the traditional technology is long is solved.

Drawings

FIG. 1 is a schematic flow chart of a method for processing an ECG signal according to an embodiment;

FIG. 2 is a flowchart illustrating step S120 according to an embodiment;

FIG. 3 is a schematic flow chart illustrating a method for processing an ECG signal according to an embodiment;

FIG. 4a is a flowchart illustrating step S310 according to an embodiment;

FIG. 4b is a schematic diagram of the DDM model building in one embodiment;

FIG. 4c is a diagram of an example DDM model prediction in one embodiment;

FIG. 4d is a diagram illustrating a DDM model optimization prediction process in one embodiment;

FIG. 5 is a schematic flow chart illustrating a method for processing an ECG signal according to an embodiment;

FIG. 6 is a schematic flow chart illustrating a method for processing an ECG signal according to an embodiment;

FIG. 7 is a schematic diagram showing the location of the origin of an arrhythmia in one embodiment;

FIG. 8 is a block diagram of an apparatus for processing cardiac signals according to an embodiment;

fig. 9 is a block diagram of a structure of a three-dimensional mapping system in an embodiment;

FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

In one embodiment, as shown in fig. 1, a method for processing an electrocardiographic signal is provided, comprising the steps of:

and S110, acquiring a plurality of body surface electrocardiosignals.

The plurality of body surface electrocardiosignals comprise a first arrhythmia electrocardiosignal with unknown origin position and a plurality of electrical stimulation electrocardiosignals generated by the intracardiac interventional device during pacing at each pacing position. A series of well-coordinated electrical stimulation pulses generated within the heart excite the atrial and ventricular muscle cells to dilate and contract rhythmically, respectively. These movements form different potential differences at different parts of the body surface, and the body surface electrocardiosignals are the potential difference signals detected on the body surface. The body surface electrocardiosignals can macroscopically record the depolarization and repolarization processes of heart cells, and objectively reflect the physiological conditions of all parts of the heart to a certain extent. Pacing is the delivery of tiny electrical pulses to the heart by a pacemaker or pacing device to stimulate the heart to beat. The first arrhythmia electrocardiosignal is a body surface electrocardiosignal collected when the heart rate is abnormal. The electrical stimulation electrocardiosignals are body surface electrocardiosignals acquired when the intracardiac interventional device performs pacing or electrical stimulation on the heart.

Specifically, a section of 12-lead electrocardiosignals in arrhythmia is prestored, and the first arrhythmia electrocardiosignal is a spontaneous arrhythmia signal of the patient. And acquiring a first arrhythmia electrocardiosignal stored in advance when needed. The intracardiac interventional device can perform electrical stimulation on the heart for a period of time at fixed time intervals, and can synchronously cause the form of 12-lead electrocardiosignals to generate corresponding changes under normal conditions, so that a plurality of electrical stimulation electrocardiosignals can be obtained.

And S120, establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals.

Because the waveform difference between the cardiac electrical signals and the position difference for generating the cardiac electrical signals have a mapping relationship to a certain extent, a delta-pos delta-wave mapping method (DDM) can be established based on the waveform information corresponding to each pacing position and the arrhythmia origin position, so as to determine the position difference information between each pacing position and the arrhythmia origin position by combining the position difference information between each pacing position and the difference prediction model.

In particular, the origin position of the first arrhythmic cardiac signal is unknown. The method includes the steps that a plurality of electrocardiosignals are randomly selected from the electric stimulation electrocardiosignals corresponding to a plurality of known pacing positions, each selected electric stimulation electrocardiosignal has a corresponding waveform difference relative to any electric stimulation electrocardiosignal, and each selected electric stimulation electrocardiosignal also has a corresponding waveform difference relative to the first arrhythmia electrocardiosignal. And determining a conversion relation between the waveform difference corresponding to the first arrhythmic electrocardiosignal relative to each selected electric stimulation electrocardiosignal and the waveform difference corresponding to each selected electric stimulation electrocardiosignal relative to any selected electric stimulation electrocardiosignal by combining the two waveform differences, thereby determining the conversion relation corresponding to the unknown position of the first arrhythmic electrocardiosignal and the known position of each selected electric stimulation electrocardiosignal, namely establishing at least one corresponding difference value prediction model.

And S130, establishing a position difference matrix of each pacing position according to the respective pacing positions corresponding to the plurality of electrical stimulation electrocardiosignals.

Specifically, the sensing element of the intracardiac intervention device moves in the heart, outputs electrical stimulation signals at different positions, electrically stimulates the heart, and can acquire corresponding electrical stimulation electrocardiosignals on the surface of the body at a plurality of known pacing positions. At least one difference value prediction model is established based on waveform difference information corresponding to each pacing position and an arrhythmia origin position, and a mapping relation exists between the waveform difference between the electrocardiosignals and the position difference for generating the electrocardiosignals to a certain extent, so that the position difference information between the pacing positions corresponding to the electrostimulation electrocardiosignals needs to be known. Therefore, the difference of each pacing position of the electrical stimulation electrocardiosignal used for establishing the difference prediction model relative to any one pacing position is calculated. Any pacing position can be selected as a reference point, the position difference of other pacing positions relative to the reference point is calculated, a position difference matrix of each pacing position relative to the reference point is established, and the like, and a position difference matrix of each pacing position is established.

And S140, determining the origin position of the first arrhythmia electrocardiosignal through at least one difference prediction model according to the position difference matrix of each pacing position.

Specifically, since the waveform difference between the electrocardiographic signals and the position difference for generating the electrocardiographic signals have a mapping relationship to a certain extent, at least one difference prediction model has been established based on the waveform difference information corresponding to each pacing position and the arrhythmia origin position, and the position difference matrix of each pacing position is determined according to each pacing position, therefore, the position difference matrix of each pacing position is transformed by the established difference prediction model, the position difference matrix between each pacing position and the origin position of the first arrhythmia electrocardiographic signal is determined, and the origin position of the first arrhythmia electrocardiographic signal is calculated based on the position difference matrix.

According to the method for processing the electrocardiosignals, because the waveform difference between every two electrocardiosignals and the position difference for generating the electrocardiosignals have a mapping relation to a certain extent, at least one difference prediction model is established according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the electrostimulation electrocardiosignals by acquiring the first arrhythmia electrocardiosignal and the plurality of electrostimulation electrocardiosignals, a position difference matrix of each pacing position is established according to the pacing positions corresponding to the plurality of electrostimulation electrocardiosignals, and the origin position of the first arrhythmia electrocardiosignal is determined through the at least one difference prediction model according to the position difference matrix of each pacing position. The arrhythmia origin point can be quickly positioned through the established difference prediction model, multiple pacing attempts are avoided, the pacing times are reduced, and the technical problem that the time for positioning the arrhythmia origin point in the traditional technology is long is solved.

In one embodiment, as shown in fig. 2, the establishing of at least one difference prediction model according to the waveform of the first arrhythmic electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals comprises the following steps:

s210, establishing a waveform difference matrix of each pacing position according to the waveforms of the plurality of electrical stimulation electrocardiosignals.

Specifically, for any pacing position, waveform differences between the electrical stimulation electrocardiosignal waveforms of other pacing positions and the electrical stimulation electrocardiosignal waveforms of the pacing position are calculated, and a waveform difference matrix of the pacing position is established. And calculating a waveform difference matrix of each pacing position relative to other pacing positions by analogy. Illustratively, if the number of pacing positions is 4, which are respectively denoted as pacing position 1, pacing position 2, pacing position 3, and pacing position 4, waveform difference matrices of pacing position 2, pacing position 3, and pacing position 4 with respect to pacing position 1 are calculated; calculating waveform difference matrixes of pacing positions 2, 3 and 1 relative to pacing position 4; calculating waveform difference matrixes of the pacing positions 1, 3 and 4 relative to the pacing position 2; waveform difference matrices for pacing site 1, pacing site 2, pacing site 4 relative to pacing site 3 are calculated.

S220, establishing a waveform difference matrix of an origin position according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals.

Specifically, for the origin position (unknown) of the first arrhythmia electrocardiosignal, the waveform difference between the electrical stimulation electrocardiosignal waveform of each pacing position and the first arrhythmia electrocardiosignal waveform of the unknown position is calculated, and the waveform difference matrix of the origin position is established. Illustratively, if the number of pacing positions is 4, namely pacing position 1, pacing position 2, pacing position 3 and pacing position 4, respectively, waveform difference matrices of pacing position 1, pacing position 2, pacing position 3 and pacing position 4 with respect to the origin position (unknown) of the first arrhythmia cardiac signal are calculated.

And S230, establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

Specifically, a conversion matrix between a waveform difference matrix corresponding to the first arrhythmia electrocardiosignal and waveform difference matrices corresponding to the plurality of electrical stimulation electrocardiosignals is determined by combining the waveform difference matrix corresponding to the first arrhythmia electrocardiosignal and the waveform difference matrices corresponding to the plurality of electrical stimulation electrocardiosignals, so that a conversion matrix corresponding to an unknown position of the first arrhythmia electrocardiosignal and known positions of the plurality of electrical stimulation electrocardiosignals can be determined, that is, at least one corresponding difference prediction model is established.

In this embodiment, a waveform difference matrix of each pacing position is established according to waveforms of a plurality of electrical stimulation electrocardiographic signals, and a waveform difference matrix of an origin position is established according to a waveform of a first arrhythmia electrocardiographic signal and waveforms of a plurality of electrical stimulation electrocardiographic signals.

In one embodiment, as shown in fig. 3, before establishing at least one difference prediction model based on the waveform of the first arrhythmic cardiac signal and the waveforms of the plurality of electrical stimulation cardiac signals, the method further comprises:

s310, respectively carrying out waveform reconstruction on the obtained plurality of body surface electrocardiosignals to obtain reconstructed waveform vectors of the plurality of body surface electrocardiosignals;

establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals, wherein the difference prediction model comprises the following steps:

s320, determining a waveform difference vector of each pacing position according to the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals;

s330, determining a waveform difference vector of an origin position according to the reconstructed waveform vector of the first arrhythmia electrocardiosignal and the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals;

and S340, establishing at least one difference prediction model according to the waveform difference vector of each pacing position and the waveform difference vector of the origin position.

Further, a waveform difference matrix of each pacing position and a waveform difference matrix of an origin position can be established according to the waveform difference vector of each pacing position and the waveform difference vector of the origin position; at least one difference prediction model is thus established based on the waveform difference matrix for each pacing site and the waveform difference matrix for the originating site.

For convenience of calculation, the acquired body surface electrocardiosignals can be reconstructed to obtain a one-dimensional waveform vector. The plurality of reconstructed waveform vectors of the body surface electrocardiosignals comprise a plurality of reconstructed waveform vectors of the electric stimulation electrocardiosignals and a reconstructed waveform vector of the first arrhythmia electrocardiosignal. For example, the obtained body surface electrocardiosignals can be 12-lead electrocardiosignals, and the 12-lead electrocardiosignals are reconstructed and recombined into a single-dimensional vector from a 12-dimensional matrix. For ease of calculation, a difference prediction matrix may be established based on the reconstructed waveform vector. Specifically, waveform reconstruction is performed on the obtained plurality of electrical stimulation electrocardiosignals, and a reconstructed waveform vector of the electrical stimulation electrocardiosignals corresponding to each pacing position is obtained. And performing waveform reconstruction on the obtained first arrhythmia electrocardiosignal to obtain a reconstructed waveform vector of the first arrhythmia electrocardiosignal. For any pacing position, the difference value between the reconstructed waveform vector of other pacing positions and the reconstructed waveform vector of the pacing position is calculated, and the waveform difference vector of the pacing position is determined. And calculating waveform difference vectors of each pacing position relative to other pacing positions by analogy. For the origin position (unknown) of the first arrhythmia electrocardiosignal, calculating the difference value between the reconstructed waveform vector of each pacing position and the reconstructed waveform vector of the origin position, and determining the waveform difference vector of the origin position. And establishing a waveform difference matrix of each pacing position and a waveform difference matrix of the origin position according to the waveform difference vector of each pacing position and the waveform difference vector of the origin position. And determining a conversion matrix between the waveform difference vector corresponding to the first arrhythmia electrocardiosignal and the waveform difference vectors corresponding to the plurality of electrical stimulation electrocardiosignals by combining the waveform difference matrix of the origin position and the waveform difference matrices of the pacing positions, thereby determining the conversion matrix corresponding to the origin position of the first arrhythmia electrocardiosignal and the pacing positions of the plurality of electrical stimulation electrocardiosignals, namely establishing at least one corresponding difference prediction model.

In this embodiment, waveform reconstruction is performed on the obtained plurality of body surface electrocardiographic signals respectively to obtain reconstructed waveform vectors of the plurality of body surface electrocardiographic signals, so that the operation is simplified, and at least one difference prediction model is established according to the reconstructed waveform vectors of the plurality of body surface electrocardiographic signals, thereby reducing the pacing frequency to a certain extent and accelerating the positioning of the arrhythmia origin point.

In one embodiment, as shown in fig. 4a, performing waveform reconstruction on each of the obtained plurality of body surface electrocardiographic signals to obtain a reconstructed waveform vector of the plurality of body surface electrocardiographic signals includes:

s410, detecting the peak position of each body surface electrocardiosignal, and aligning and intercepting each body surface electrocardiosignal through the peak position;

s420, performing down-sampling on each intercepted electrocardiosignal, and performing normalization processing on each electrocardiosignal obtained by the down-sampling;

and S430, respectively carrying out end-to-end connection on each electrocardiosignal obtained by normalization processing to obtain a reconstructed waveform vector of each body surface electrocardiosignal.

Specifically, after pacing is started, a body surface electrocardiosignal within a period of time is acquired. Firstly, detecting the peak position of each acquired body surface electrocardiosignal, and aligning and intercepting each body surface electrocardiosignal through the peak position. Generally, the sampling rate of the electrocardiograph signal is several kilohertz, for example 3000Hz, 36000 sampling points exist in data acquired in one second, the data volume is large, and interference data can be removed in a down-sampling mode and the data volume is reduced to be below 6000. Because the electrocardiosignals acquired by the body surface have different amplitudes and may influence the result, normalization processing is carried out on each electrocardiosignal obtained by down-sampling, finally, each electrocardiosignal obtained by normalization processing is connected end to end, and the electrocardiosignals are recombined into a single-dimensional vector from a multi-dimensional matrix to obtain a reconstructed waveform vector of each body surface electrocardiosignal.

In one implementation, determining the origin position of the first arrhythmic cardiac signal by at least one of the difference prediction models according to the position difference matrix of each pacing position includes: determining a position difference matrix of the origin position through at least one difference prediction model according to the position difference matrix of each pacing position; and determining the origin position of the first arrhythmia electrocardiosignal according to the position information of each pacing position and the position difference matrix of the origin position.

In one embodiment, establishing at least one difference prediction model based on the waveform difference matrix for each pacing site and the waveform difference matrix for the originating site includes: calculating a conversion matrix between the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position by using a least square method; and establishing at least one difference prediction model through each conversion matrix obtained by calculation.

Specifically, each pacing location is noted as 1, 2, 3 … … J; the waveform difference matrix for each pacing site may be written as [ Δ W]Then, then The origin position is recorded as O, and the waveform difference matrix of the origin position is recorded as [ Delta W^*]Then, then

[ΔW]And [ Δ W^*]Transformation matrix [ theta ] between]The method can be calculated by a least square method, and the process is as follows:

[Δw^*]＝[ΔW_J]×[0]

[θ]＝([ΔW_J]^T×[ΔW_J])^-1×[ΔW_J]^T×[Δw^*]

wherein, [ Delta W [ ]]^THas the meaning of [ Δ W]Transposing of the matrix.

Thus, one or more transformation matrices [ theta ] are computed₁]，[θ₂]，……，[θ_J]. And establishing one or more difference prediction models through each conversion matrix obtained through calculation.

An exemplary differential prediction model building process is illustrated: p_IPacing position in the heart for pacing device I_IFor a 12 lead reconstructed waveform over a period of time (e.g., 150ms) at the time of the I-th pacing, P_JPacing position at the J-th pacing, W_JThe reconstructed waveform for 12 leads at jth pacing.

As shown in fig. 4b, in space, there are:

representing a position difference vector between the I-th pace and the J-th pace,

then the reconstructed waveform difference vector also has:

for the reconstructed waveform difference vector between the I-th and J-th paces,θ_Iand theta_JI and J transfer coefficients.

As shown in fig. 4c, where there are multiple known pacing locations and electrocardiographic waveforms, [ΔW]and [ Delta P ]]A waveform difference matrix and a position difference matrix are established for four known points (pacing points), respectively. If there is a point O (origin position of arrhythmia signal) whose position is unknown but electrocardiographic waveform is known, the corresponding waveform difference vector can be obtained, then the following calculation is made:

[ΔW^*]is a waveform difference matrix between the pacing points 1, 2, 3, 4 and the origin point O, namely a waveform difference matrix of the origin position; [ Delta W]And [ Δ W^*]Transformation matrix [ theta ] between]The method can be calculated by a least square method, and the process is as follows:

[ΔW^*]＝[ΔW]×[θ]

[θ]＝([ΔW]^T×[ΔW])^-1×[ΔW]^T×[ΔW^*]

wherein, [ Delta W [ ]]^THas the meaning of[ΔW]Transposing of the matrix. The following formula can be obtained:

[ΔP^*]＝[ΔP]×[θ]

wherein the content of the first and second substances,

[ΔP^*]is a new matrix (i.e., a position difference matrix of the origin position) composed of the position difference between the position P of each pacing point and the origin point O. Then, the predicted location of the origin point OCan be obtained according to the following formula:

the above process of establishing and completing the prediction of the unknown point position (namely the origin position of the arrhythmia signal) for a small DDM model.

In one embodiment, the method further comprises: predicting a plurality of pacing positions by utilizing each difference prediction model; and determining a prediction error according to the pacing position and a prediction result corresponding to the pacing position, and performing optimization screening on each difference prediction model according to the prediction error.

Specifically, a plurality of differential prediction models have been established, with each differential prediction model being used to predict a pacing site, the differential prediction models outputting corresponding predicted sites. Comparing the real position of the pacing position with the predicted position, calculating a prediction error according to the coordinates of the real position and the coordinates of the predicted position, screening all the established difference prediction models by combining the magnitude of the prediction error, filtering the difference prediction models with larger prediction errors, and screening the difference prediction models with smaller prediction errors.

Illustratively, assume that there are 4 pacing sites, pacing site 1, pacing site 2, pacing site 3, and pacing site 4. The difference prediction model A established by the signal waveforms corresponding to the pacing position 1, the pacing position 2 and the pacing position 3 can be used for predicting the pacing position 4 by using the difference prediction model A to obtain a prediction position coordinate, and the prediction position coordinate is compared with the real position of the pacing position 4 to determine the prediction error of the difference prediction model A. And predicting the pacing position 3 by using a difference prediction model B established by signal waveforms corresponding to the pacing position 1, the pacing position 2 and the pacing position 4 respectively to obtain a predicted position coordinate, comparing the predicted position coordinate with the real position of the pacing position 3, and determining a prediction error of the difference prediction model B. And predicting the pacing position 1 by using a difference prediction model C established by signal waveforms corresponding to the pacing position 2, the pacing position 3 and the pacing position 4 respectively to obtain a predicted position coordinate, comparing the predicted position coordinate with the real position of the pacing position 1, and determining a prediction error of the difference prediction model C. And predicting the pacing position 2 by using a difference prediction model D established by signal waveforms corresponding to the pacing position 1, the pacing position 3 and the pacing position 4 respectively to obtain a predicted position coordinate, comparing the predicted position coordinate with the real position of the pacing position 2, and determining a prediction error of the difference prediction model D. The prediction errors of the difference prediction models A, B, C, D are compared, and a difference prediction model having a smaller prediction error is selected.

In this embodiment, the known pacing positions are mutually predicted by the plurality of difference prediction models, prediction errors are calculated, and an optimized screening mode is performed on each difference prediction model, so that the prediction accuracy of the difference prediction models is improved.

In one embodiment, determining the location of origin of the first arrhythmic cardiac signal by at least one difference prediction model based on a location difference matrix for each pacing location comprises: selecting a difference value prediction model meeting a preset condition through a prediction error; and determining the origin position of the first arrhythmia electrocardiosignal through the selected difference prediction model according to the position difference matrix of each pacing position.

Specifically, a plurality of pacing positions are predicted by utilizing each difference prediction model; and determining a prediction error according to the pacing position and a prediction result corresponding to the pacing position, and setting a preset condition to judge whether each difference value prediction model can be used for predicting the origin position of the first arrhythmia electrocardiosignal. Screening the prediction error, selecting a difference prediction model meeting preset conditions, and determining the origin position of the first arrhythmia electrocardiosignal by using the screened difference prediction model.

Illustratively, as shown in FIG. 4d, several difference prediction models are built. The 4 difference prediction models shown in fig. 4d have the smallest prediction error for other known pacing point positions, and the 4 difference prediction models are selected first to predict the origin position of the first arrhythmia electrocardiosignal. The prediction process may be a single prediction or a process in which multiple predictions converge. The dots 1, 2, 3, and 4 in the figure are the prediction results of the four difference prediction models. Although the error of the selected difference prediction model is small, a certain error may exist in a large range, so that the prediction results of a plurality of models still have a certain distance from the actual origin position. However, the four prediction results can be finally aggregated into one direction information, and the operator can perform a new round of electrical stimulation through the direction information, so that the predicted position can be finally converged into an acceptable area.

In one embodiment, as shown in fig. 5, before establishing at least one difference prediction model based on the waveform of the first arrhythmic cardiac signal and the waveforms of the plurality of electrical stimulation cardiac signals, the method further comprises the steps of:

s510, acquiring an intracardiac electrical stimulation signal;

s520, calculating the trigger lag time of each body surface electrocardiosignal relative to the intracardiac electrical stimulation signal;

s530, judging whether the electrocardiosignals of all the body surfaces are effective or not according to the trigger lag time;

establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals, wherein the difference prediction model comprises the following steps:

and S540, if the body surface electrocardiosignal is judged to be effective, establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals.

The heart is electrically stimulated through the intracardiac interventional device, the electrical stimulation can be carried out for a period of time at fixed time intervals, and the 12-lead electrocardiosignal forms are synchronously caused to generate corresponding changes under normal conditions. The time interval of the electrical stimulation is generally 400-600 ms, preferably 500 ms. However, in some cases, the morphology of the 12-lead ECG signal is not significantly changed. For example, the intracardiac interventional devices are not firmly attached; the output voltage of the electrical stimulation is low; the stimulated pacing site has a lower voltage on the myocardium itself. In addition, some instances where more abnormal electrocardiographic waveforms occur may be due to sudden wall contact by an intracardiac interventional device. The electrical stimulation in the above cases cannot be used to build a difference prediction model, and therefore, before building a model, the effectiveness of the electrical stimulation needs to be judged. Determining the effectiveness of electrical stimulation may be considered from the lag time of the 12-lead trigger. Specifically, when performing electrical stimulation, the start time of the intracardiac electrical stimulation signal may be 30ms to 60ms earlier than the triggering cardiac electrical signal of the body surface 12 leads. The initial time of the electrical stimulation signals in the heart and the initial time of each body surface electrocardiosignal can be obtained through the signal detection module, and the triggering lag time of each body surface electrocardiosignal relative to the electrical stimulation signals in the heart is calculated; electrical stimulation may be considered effective if its trigger lag time is within a certain acceptable range and is not morphologically standard sinus rhythm. And if the body surface electrocardiosignals are judged to be effective, establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals. It should be noted that, if the body surface electrocardiosignal is judged to be invalid, a prompt indicating that the signal is invalid can be given to acquire an effective body surface electrocardiosignal.

In the embodiment, whether the electrical stimulation is effective or not is judged through the trigger lag time, and the electrical stimulation electrocardiosignal used for establishing the model is determined to be effective, so that the accuracy of the difference value prediction model is ensured, and the prediction precision of the difference value prediction model is improved.

In one embodiment, as shown in fig. 6, the method further comprises the steps of:

s610, acquiring a plurality of second arrhythmia electrocardiosignals;

s620, averaging a plurality of electrical stimulation electrocardiosignals used for establishing the difference prediction model to obtain corresponding average waveform difference vectors;

s630, comparing the obtained average waveform difference vector with the obtained waveform difference vectors of the second arrhythmia electrocardiosignals one by one to obtain a plurality of comparison parameters;

and S640, determining a second arrhythmia electrocardiosignal matched with the characteristics of the difference prediction model according to the obtained multiple comparison parameters.

In the case of more complicated cases, there may be many different types of arrhythmia signals, and spontaneous arrhythmia body surface electrocardiosignals can be stored at any time in the operation process. Each second arrhythmic cardiac signal corresponds to an origin position and is different from arrhythmia origin positions of other second arrhythmic cardiac signals. After the plurality of difference prediction models are established, the positions of the second arrhythmia electrocardiosignals at a plurality of unknown origin positions can be respectively predicted, and one of the second arrhythmia electrocardiosignals can also be predicted. Preferably, the position of one second arrhythmic cardiac signal among the plurality of second arrhythmic cardiac signals is predicted. Therefore, it is necessary to select an arrhythmic cardiac signal matching the characteristics of the difference prediction model. The embodiment provides a method for automatically selecting corresponding arrhythmia electrocardiosignals according to the characteristics of a difference prediction model.

Assuming that m spontaneous arrhythmic electrocardiographic signals are stored in advance, in the prediction stage, if the difference prediction model screened out by the error is established by n electrical stimulation signals, the n electrical stimulation signals can be averaged and processed according to the following formula:

ΔW_meanaverage waveform difference vector, Δ W, after averaging of electrical stimulation signals for use in building a difference prediction model_ITo build the waveform difference vector of the I-th electrical stimulation signal used for the difference prediction model, I is 1, 2, 3, … … n.

Arrhythmia electrocardiosignals corresponding to the model can be selected preferably in a mode of waveform difference vector comparison. The comparison of waveform difference vectors can be performed according to the following formula:

wherein, I is 1, 2, 3, …, length, length is the length of the waveform difference vector,is the waveform difference vector of the J-th arrhythmia electrocardiosignal, namely the waveform difference vector of the second origin position, J is 1, 2, …, m, delta W_meanThe average waveform difference vector after the difference prediction model is subjected to the averaging processing is shown, Coeff is an alignment parameter, and J is 1, …, m.

After the comparison parameters are calculated, the arrhythmia electrocardiosignal with the minimum comparison parameter can be determined as a second arrhythmia electrocardiosignal matched with the characteristics of the difference prediction model.

Further, as shown in fig. 7, the method further includes: and displaying the origin position of the first arrhythmia electrocardiosignal and the origin position of the second arrhythmia electrocardiosignal. Therefore, the intracardiac access device can be controlled to perform treatment, for example, the intracardiac access device is controlled to the prompted origin position to perform ablation treatment by adopting common operation modes such as radio frequency ablation or cryoballoon ablation.

In the embodiment, the arrhythmia electrocardiosignals to be predicted are automatically selected by utilizing the characteristics of the established difference prediction model, so that the accuracy of the prediction result is improved. And the focus position predicted by the model is visually displayed.

In one embodiment, the present application provides a method for processing an electrocardiographic signal, comprising the following steps:

s702, obtaining a plurality of body surface electrocardiosignals.

The plurality of body surface electrocardiosignals comprise a first arrhythmia electrocardiosignal with unknown origin position and a plurality of electrical stimulation electrocardiosignals generated by the intracardiac interventional device during pacing at each pacing position.

And S704, acquiring an intracardiac electrical stimulation signal.

And S706, calculating the trigger lag time of each body surface electrocardiosignal relative to the intracardiac electrical stimulation signal.

And S708, judging whether the electrocardiosignals of all the body surfaces are effective or not according to the trigger lag time.

And S710, if the body surface electrocardiosignals are judged to be effective, respectively carrying out waveform reconstruction on the obtained body surface electrocardiosignals to obtain reconstructed waveform vectors of the body surface electrocardiosignals.

Detecting the peak position of each body surface electrocardiosignal, and aligning and intercepting each body surface electrocardiosignal through the peak position; down-sampling each intercepted electrocardiosignal, and normalizing each electrocardiosignal obtained by down-sampling; and respectively carrying out end-to-end connection on each electrocardiosignal obtained by the normalization processing to obtain a reconstructed waveform vector of each body surface electrocardiosignal.

And S712, determining a waveform difference vector of each pacing position according to the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals.

And S714, determining a waveform difference vector of an origin position according to the reconstructed waveform vector of the first arrhythmia electrocardiosignal and the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals.

S716, establishing a waveform difference matrix of each pacing position and a waveform difference matrix of an origin position according to the waveform difference vector of each pacing position and the waveform difference vector of the origin position;

s718, establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

Calculating a conversion matrix between the waveform difference vector of each pacing position and the waveform difference vector of the origin position by using a least square method; and establishing at least one difference prediction model through each conversion matrix obtained by calculation.

And S720, selecting a difference value prediction model meeting a preset condition through the prediction error.

And S722, determining a position difference matrix of the origin position through at least one difference value prediction model according to the position difference matrix of each pacing position.

S724, according to the position information of each pacing position, determining the origin position of the first arrhythmia electrocardiosignal through the position difference matrix of the origin position.

And S726, acquiring a plurality of second arrhythmia electrocardiosignals.

And S728, averaging the plurality of electrical stimulation electrocardiosignals used for establishing the difference prediction model to obtain corresponding average waveform difference vectors.

And S730, comparing the obtained average waveform difference vector with the obtained waveform difference vectors of the plurality of second arrhythmia electrocardiosignals one by one to obtain a plurality of comparison parameters.

And S732, determining a second arrhythmia electrocardiosignal matched with the characteristics of the difference prediction model according to the obtained comparison parameters.

And further, processing the second arrhythmia electrocardiosignal through the difference value prediction model, and determining the origin position of the second arrhythmia electrocardiosignal.

S734, displaying the origin of the first arrhythmic cardiac signal and the origin of the second arrhythmic cardiac signal.

It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the above embodiments may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or the stages is not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a part of the sub-steps or the stages of other steps.

In one embodiment, as shown in fig. 8, there is provided a device 800 for processing cardiac electrical signals, comprising: a body surface signal obtaining module 810, a prediction model establishing module 820, a position difference matrix establishing module 830 and an origin position predicting module 840, wherein:

a body surface signal obtaining module 810, configured to obtain a plurality of body surface electrocardiographic signals, where the plurality of body surface electrocardiographic signals include a first arrhythmia electrocardiographic signal with an unknown origin position and a plurality of electrical stimulation electrocardiographic signals generated by the intracardiac intervention device during pacing at each pacing position;

a prediction model establishing module 820, configured to establish at least one difference prediction model according to the waveform of the first arrhythmia electrocardiographic signal and the waveforms of the plurality of electrical stimulation electrocardiographic signals;

a position difference matrix establishing module 830, configured to establish a position difference matrix of each pacing position according to the pacing position corresponding to each of the plurality of electrical stimulation electrocardiographic signals;

an origin position prediction module 840, configured to determine an origin position of the first arrhythmia cardiac signal through at least one of the difference prediction models according to the position difference matrix of each pacing position.

In one embodiment, the prediction model establishing module 820 is further configured to establish a waveform difference matrix for each pacing position according to a plurality of waveforms of the electrical stimulation electrocardiographic signals; establishing a waveform difference matrix of the origin position according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals; and establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

In an embodiment, the apparatus further includes a waveform reconstruction module, configured to perform waveform reconstruction on the obtained plurality of body surface electrocardiographic signals, respectively, to obtain reconstructed waveform vectors of the plurality of body surface electrocardiographic signals.

The prediction model establishing module 820 is further configured to determine a waveform difference vector of each pacing position according to the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals; determining a waveform difference vector of an origin position according to the reconstructed waveform vector of the first arrhythmia electrocardiosignal and the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals; at least one difference prediction model is established based on the waveform difference vector for each pacing site and the waveform difference vector for the originating site.

In one embodiment, the waveform reconstruction module is further configured to detect a peak position of each body surface electrocardiosignal, and perform alignment interception on each body surface electrocardiosignal through the peak position; down-sampling each intercepted electrocardiosignal, and normalizing each electrocardiosignal obtained by down-sampling; and respectively carrying out end-to-end connection on each electrocardiosignal obtained by the normalization processing to obtain a reconstructed waveform vector of each body surface electrocardiosignal.

In one embodiment, the prediction model establishing module 820 is further configured to establish a waveform difference matrix for each pacing location and a waveform difference matrix for the originating location according to the waveform difference vector for each pacing location and the waveform difference vector for the originating location; and establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

In one embodiment, the predictive model building module 820 is further configured to calculate a transformation matrix between the waveform difference matrix for each pacing site and the waveform difference matrix for the originating site using a least squares method; and establishing at least one difference prediction model through each conversion matrix obtained by calculation.

In one embodiment, the apparatus further comprises a screening module for predicting a number of pacing locations using the respective difference prediction models; and determining a prediction error according to the pacing position and a prediction result corresponding to the pacing position, and performing optimization screening on each difference prediction model according to the prediction error.

In one embodiment, the origination location prediction module 840 is further configured to determine a location difference matrix for the origination location from the location difference matrix for each pacing location via at least one difference prediction model; and determining the origin position of the first arrhythmia electrocardiosignal according to the position information of each pacing position and the position difference matrix of the origin position.

In one embodiment, the origin position prediction module 840 is further configured to select a difference prediction model satisfying a preset condition according to the prediction error; and determining the origin position of the first arrhythmia electrocardiosignal through the selected difference prediction model according to the position difference matrix of each pacing position.

In one embodiment, the apparatus further comprises a display module for displaying the originating location of the first arrhythmic cardiac signal and the originating location of the second arrhythmic cardiac signal.

For specific limitations of the processing device of the electrocardiographic signal, reference may be made to the above limitations on the processing method of the electrocardiographic signal, and details are not described here. All or part of the modules in the electrocardiosignal processing device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, the present application provides a three-dimensional mapping system, as shown in fig. 9, comprising:

an electrical stimulation generation module 910, configured to perform periodic electrical stimulation on the heart through an intracardiac interventional device;

the signal acquisition module 920 is used for acquiring body surface electrocardiosignals and intracardiac electrocardiosignals; the intracardiac cardiac electrical signals comprise intracardiac electrical stimulation signals;

a positioning module 930 for acquiring the position of the intracardiac interventional device;

the data processing module 940 is connected to the signal acquisition module and the positioning module, respectively, and is configured to implement the steps of the method for processing an electrocardiographic signal according to any one of the foregoing embodiments.

In one embodiment, with continued reference to fig. 9, the three-dimensional mapping system further includes: and the display module 950 is connected with the data processing module and is used for displaying the origin position of the arrhythmia electrocardiosignal.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of processing an electrocardiographic signal. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:

obtaining a plurality of body surface electrocardiosignals, wherein the body surface electrocardiosignals comprise a first arrhythmia electrocardiosignal with unknown origin position and a plurality of electric stimulation electrocardiosignals generated by the intracardiac intervention device during pacing at each pacing position; establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals; establishing a position difference matrix of each pacing position according to the respective corresponding pacing positions of the plurality of electrical stimulation electrocardiosignals; and determining the origin position of the first arrhythmia electrocardiosignal through at least one difference prediction model according to the position difference matrix of each pacing position.

In one embodiment, the processor, when executing the computer program, further performs the steps of: establishing a waveform difference matrix of each pacing position according to the waveforms of the plurality of electrical stimulation electrocardiosignals; establishing a waveform difference matrix of an origin position according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals; and establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

In one embodiment, the processor, when executing the computer program, further performs the steps of: respectively carrying out waveform reconstruction on the obtained plurality of body surface electrocardiosignals to obtain reconstructed waveform vectors of the plurality of body surface electrocardiosignals; determining a waveform difference vector of each pacing position according to the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals; determining a waveform difference vector of an origin position according to the reconstructed waveform vector of the first arrhythmia electrocardiosignal and the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals; at least one difference prediction model is established based on the waveform difference vector for each pacing site and the waveform difference vector for the originating site.

In one embodiment, the processor, when executing the computer program, further performs the steps of: detecting the peak position of each body surface electrocardiosignal, and aligning and intercepting each body surface electrocardiosignal through the peak position; down-sampling each intercepted electrocardiosignal, and normalizing each electrocardiosignal obtained by down-sampling; and respectively carrying out end-to-end connection on each electrocardiosignal obtained by the normalization processing to obtain a reconstructed waveform vector of each body surface electrocardiosignal.

In one embodiment, the processor, when executing the computer program, further performs the steps of: establishing a waveform difference matrix of each pacing position and a waveform difference matrix of an origin position according to the waveform difference vector of each pacing position and the waveform difference vector of the origin position; and establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

In one embodiment, the processor, when executing the computer program, further performs the steps of: calculating a conversion matrix between the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position by using a least square method; and establishing at least one difference prediction model through each conversion matrix obtained by calculation.

In one embodiment, the processor, when executing the computer program, further performs the steps of: predicting a plurality of pacing positions by utilizing each difference prediction model; and determining a prediction error according to the pacing position and a prediction result corresponding to the pacing position, and performing optimization screening on each difference prediction model.

In one embodiment, the processor, when executing the computer program, further performs the steps of: determining a position difference matrix of the origin position by at least one difference prediction model according to the position difference matrix of each pacing position; and determining the origin position of the first arrhythmia electrocardiosignal according to the position information of each pacing position and the position difference matrix of the origin position.

In one embodiment, the processor, when executing the computer program, further performs the steps of: selecting a difference value prediction model meeting a preset condition through a prediction error; and determining the origin position of the first arrhythmia electrocardiosignal through the selected difference prediction model according to the position difference matrix of each pacing position.

In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring an intracardiac electrical stimulation signal; calculating the triggering lag time of each body surface electrocardiosignal relative to the intracardiac electrical stimulation signal; judging whether the electrocardiosignals of all body surfaces are effective or not according to the triggering lag time; and if the body surface electrocardiosignals are judged to be effective, establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals.

In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a plurality of second arrhythmia electrocardiosignals; averaging a plurality of electrical stimulation electrocardiosignals used for establishing a difference value prediction model to obtain corresponding average waveform difference vectors; comparing the obtained average waveform difference vector with the obtained waveform difference vectors of the plurality of second arrhythmia electrocardiosignals one by one to obtain a plurality of comparison parameters; and determining a second arrhythmia electrocardiosignal matched with the characteristics of the difference prediction model according to the obtained comparison parameters.

In one embodiment, the processor, when executing the computer program, further performs the steps of: and displaying the origin position of the first arrhythmia electrocardiosignal and the origin position of the second arrhythmia electrocardiosignal.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

obtaining a plurality of body surface electrocardiosignals, wherein the body surface electrocardiosignals comprise a first arrhythmia electrocardiosignal with unknown origin position and a plurality of electric stimulation electrocardiosignals generated by the intracardiac intervention device during pacing at each pacing position; establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals; establishing a position difference matrix of each pacing position according to the respective corresponding pacing positions of the plurality of electrical stimulation electrocardiosignals; and determining the origin position of the first arrhythmia electrocardiosignal through at least one difference prediction model according to the position difference matrix of each pacing position.

In one embodiment, the computer program when executed by the processor further performs the steps of: establishing a waveform difference matrix of each pacing position according to the waveforms of the plurality of electrical stimulation electrocardiosignals; establishing a waveform difference matrix of an origin position according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals; and establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

In one embodiment, the computer program when executed by the processor further performs the steps of: respectively carrying out waveform reconstruction on the obtained plurality of body surface electrocardiosignals to obtain reconstructed waveform vectors of the plurality of body surface electrocardiosignals; determining a waveform difference vector of each pacing position according to the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals; determining a waveform difference vector of an origin position according to the reconstructed waveform vector of the first arrhythmia electrocardiosignal and the reconstructed waveform vectors of the plurality of electrical stimulation electrocardiosignals; at least one difference prediction model is established based on the waveform difference vector for each pacing site and the waveform difference vector for the originating site.

In one embodiment, the computer program when executed by the processor further performs the steps of: detecting the peak position of each body surface electrocardiosignal, and aligning and intercepting each body surface electrocardiosignal through the peak position; down-sampling each intercepted electrocardiosignal, and normalizing each electrocardiosignal obtained by down-sampling; and respectively carrying out end-to-end connection on each electrocardiosignal obtained by the normalization processing to obtain a reconstructed waveform vector of each body surface electrocardiosignal.

In one embodiment, the computer program when executed by the processor further performs the steps of: establishing a waveform difference matrix of each pacing position and a waveform difference matrix of an origin position according to the waveform difference vector of each pacing position and the waveform difference vector of the origin position; and establishing at least one difference value prediction model according to the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position.

In one embodiment, the computer program when executed by the processor further performs the steps of: calculating a conversion matrix between the waveform difference matrix of each pacing position and the waveform difference matrix of the origin position by using a least square method; and establishing at least one difference prediction model through each conversion matrix obtained by calculation.

In one embodiment, the computer program when executed by the processor further performs the steps of: predicting a plurality of pacing positions by utilizing each difference prediction model; and determining a prediction error according to the pacing position and a prediction result corresponding to the pacing position, and performing optimization screening on each difference prediction model.

In one embodiment, the computer program when executed by the processor further performs the steps of: determining a position difference matrix of the origin position by at least one difference prediction model according to the position difference matrix of each pacing position; and determining the origin position of the first arrhythmia electrocardiosignal according to the position information of each pacing position and the position difference matrix of the origin position.

In one embodiment, the computer program when executed by the processor further performs the steps of: selecting a difference value prediction model meeting a preset condition through a prediction error; and determining the origin position of the first arrhythmia electrocardiosignal through the selected difference prediction model according to the position difference matrix of each pacing position.

In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring an intracardiac electrical stimulation signal; calculating the triggering lag time of each body surface electrocardiosignal relative to the intracardiac electrical stimulation signal; judging whether the electrocardiosignals of all body surfaces are effective or not according to the triggering lag time; and if the body surface electrocardiosignals are judged to be effective, establishing at least one difference prediction model according to the waveform of the first arrhythmia electrocardiosignal and the waveforms of the plurality of electrical stimulation electrocardiosignals.

In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a plurality of second arrhythmia electrocardiosignals; averaging a plurality of electrical stimulation electrocardiosignals used for establishing a difference value prediction model to obtain corresponding average waveform difference vectors; comparing the obtained average waveform difference vector with the obtained waveform difference vectors of the plurality of second arrhythmia electrocardiosignals one by one to obtain a plurality of comparison parameters; and determining a second arrhythmia electrocardiosignal matched with the characteristics of the difference prediction model according to the obtained comparison parameters.

In one embodiment, the computer program when executed by the processor further performs the steps of: and displaying the origin position of the first arrhythmia electrocardiosignal and the origin position of the second arrhythmia electrocardiosignal.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as StatIc Random Access Memory (SRAM) or DynamIc Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.