WO2019015017A1

WO2019015017A1 - Quantitative analysis method for electrocardio dynamics data

Info

Publication number: WO2019015017A1
Application number: PCT/CN2017/098901
Authority: WO
Inventors: 王聪; 吴伟明; 邓木清; 徐赤坤
Original assignee: 上海图灵医疗科技有限公司
Priority date: 2017-07-18
Filing date: 2017-08-24
Publication date: 2019-01-24
Also published as: CN107260161A; CN107260161B

Abstract

A quantitative analysis method for electrocardio dynamics data, belonging to the technical field of electrocardiogram detection. The method comprises: step S1, collecting a vectorcardiogram to obtain electrocardiogram data; step S2, according to the collected electrocardiogram data, acquiring corresponding electrocardio dynamics data; step S3, extracting space discrete quantization characteristics of the electrocardio dynamics data, and extracting time discrete quantization characteristics of the electrocardio dynamics data; and step S4, forming quantization information about the electrocardio dynamics data according to the space discrete quantization characteristics and the time discrete quantization characteristics, and carrying out quantitative analysis on the vectorcardiogram according to the quantization information. The beneficial effects of the method are that electrocardio dynamics data can be quantitatively described, an effective quantization index is provided, and convenience is provided for a doctor in carrying out disease diagnosis by using the electrocardio dynamics data.

Description

A method for quantitative analysis of electrocardiographic data

Technical field

The invention relates to the technical field of electrocardiogram detection, in particular to a method for quantitative analysis of electrocardiographic data.

Background technique

For a long time, cardiovascular disease has been recognized as one of the most serious diseases that endanger human health. Among them, the incidence and mortality of myocardial infarction due to myocardial ischemia is the highest among all diseases. Because some patients with myocardial ischemia have no obvious clinical symptoms or mild symptoms in the early stage of the disease, the condition is easily overlooked.

In the prior art, for myocardial ischemia, there is a certain detection means in theory, that is, the electrocardiogram (ECG) is used to continuously observe and diagnose the heart features clinically. However, in the prior art, the electrocardiogram data in the electrocardiogram is usually only subjected to relatively rough image detection, and there is no means for quantitative description and detection, so the accuracy of the electrocardiographic detection result is not high, and thus it is difficult to grasp the ECG data. Subtle changes, it is possible to miss some of the patient's cardiac abnormalities such as myocardial ischemic conditions during the test. In the process of observing ECG data such as electrocardiogram, doctors usually only make subjective qualitative judgments, which affects the accuracy of the final result to some extent.

Summary of the invention

According to the above problems existing in the prior art, a technical solution for quantitative analysis of electrocardiographic data is provided, which aims to quantitatively describe electrocardiographic data, provide an effective quantitative index, and adopt an electrocardiogram vector for doctors. It is convenient to diagnose the disease.

The above technical solutions specifically include:

A method for quantitatively analyzing electrocardiographic data, comprising:

Step S1, collecting ECG data;

Step S2: Acquire corresponding electrocardiographic data according to the collected ECG data;

Step S3, extracting spatial discrete quantization features of the electrocardiographic data, and extracting time-discrete quantization features of the electrocardiographic data;

Step S4, forming quantization information of the electrocardiographic data according to the spatial discrete quantization feature and the temporal discrete quantization feature, and performing quantitative analysis on the ECG vector map according to the quantization information.

Preferably, the method for quantitatively analyzing the electrocardiographic data is characterized in that, in the step S2, the step of acquiring the electrocardiographic data specifically includes:

Step S21: Perform dynamic modeling on the ECG data by using a determining learning method to form a dynamic model associated with the ECG data;

Step S22, obtaining the electrocardiographic data associated with the electrocardiographic data according to the electrocardiogram data and the dynamic model.

Preferably, the electrocardiographic data quantitative analysis method is characterized in that the electrocardiographic data includes a plurality of data points arranged in a three-dimensional space;

In the step S3, the step of acquiring the spatial discrete quantization feature of the electrocardiographic data specifically includes:

Step S31a, processing the electrocardiographic data in chronological order to obtain an exponential change rate of each of the data points;

Step S32a, integrating the exponential change rate of all the data points into the spatial discrete quantization feature.

Preferably, the method for quantitatively analyzing the electrocardiographic data is characterized in that the step S31a specifically includes:

Step S311a, processing to obtain an initial distance set of the data points in the electrocardiographic data;

Step S312a, processing to obtain a corresponding end distance set of the data points;

Step S313a, respectively, obtaining the exponential change rate of each of the data points according to the initial distance set and the end distance set.

Preferably, the electrocardiographic data quantitative analysis method is characterized in that the step S311a

among them,

i=1, 2,..., I _k ;

x _{k is} used to represent the current kth data point;

a set of neighboring points of x _k , used to represent a set of points of a ₁ point closest to x _k in spatial distance;

I _{k is} used to represent the total number of elements of the set of neighboring points described in step k, and I _k ≤ a ₁ ;

For the initial distance set, used to represent

A set of distances between x _k and .

Preferably, the electrocardiographic data quantitative analysis method is characterized in that, in the step S312a, the end distance set is obtained according to the following formula:

among them,

i=1,2,...,I _k ,Δ∈N;

x _{k is} used to represent the current kth data point;

x _{k+Δ is} used to represent the data point obtained by increasing the time of x _k by Δ step;

Used to indicate

Time to increase the set of points obtained by the Δ step;

For the end distance set, used to represent

Increase the distance set after Δ step with x _k respectively.

Preferably, the electrocardiographic data quantitative analysis method is characterized in that, in the step S313a, each of the initial distance set and the end distance set is logarithmically calculated to obtain each The exponential rate of change of the data points.

Preferably, the electrocardiographic data quantitative analysis method is characterized in that, in the step S32a, the exponential change rate of all the data points is integrated into the spatial discrete quantization feature by a non-negative averaging method.

Preferably, the electrocardiographic data quantitative analysis method is characterized in that the electrocardiographic data is multi-dimensional data;

In the step S3, the step of acquiring the time-discrete quantization feature of the electrocardiographic data specifically includes:

Step S31b, respectively converting the electrocardiographic data of each dimension into a corresponding frequency domain number according to;

Step S32b, using a preset feature function group to respectively fit the frequency domain data of each dimension to obtain a time dispersion feature component of each dimension;

Step S33b, synthesizing the time dispersion feature components of all dimensions to form the time-discrete quantization feature of the electrocardiographic data.

Preferably, the electrocardiographic data quantitative analysis method is characterized in that, in the step S31b, the electrocardiographic data of each dimension is respectively converted into corresponding frequency domain data by using a fast Fourier transform method.

Preferably, the electrocardiographic data quantitative analysis method is characterized in that, in the step S33b, the time dispersion feature component of all dimensions is integrated by a geometric mean method to form the time dispersion of the electrocardiographic data. Quantify features.

Preferably, the method for quantitatively analyzing the electrocardiographic data is characterized in that, in the step S4,

And using one of the time-discrete quantized feature and the spatial discrete quantized feature as an X-axis coordinate of the corresponding electrocardiographic data, and using the time-discrete quantized feature and the space in an XOY coordinate plane Another one of the discrete quantized features as the corresponding Y-axis coordinate of the electrocardiographic data to form coordinate information of the electrocardiographic data;

The coordinate information is used as the quantization information of the electrocardiographic data.

Preferably, the electrocardiographic data quantitative analysis method is characterized in that the XOY coordinate plane is divided into a first region, a second region, and a third region in advance;

When the quantized information indicates that the electrocardiographic data falls into the first region, indicating that the corresponding cardiac sign represented by the electrocardiogram vector is normal;

When the quantized information indicates that the electrocardiographic data falls into the second region, indicating that the corresponding cardiac energy map represented by the electrocardiogram is abnormal;

When the quantized information indicates that the electrocardiographic data falls into the third region, it indicates that the corresponding cardiac sign represented by the electrocardiogram vector is suspected to be abnormal.

The beneficial effects of the above technical solution are: providing a quantitative analysis method of electrocardiographic data, capable of quantitatively describing the electrocardiogram data, providing an effective quantitative index, and providing convenience for the doctor to use the electrocardiogram vector diagram for disease diagnosis.

DRAWINGS

1 is a schematic overall flow chart of a method for quantitatively analyzing electrocardiographic data in a preferred embodiment of the present invention;

2 is a flow chart showing the acquisition of electrocardiographic data in a preferred embodiment of the present invention;

3-4 are schematic flow diagrams of obtaining spatial discrete quantization features in electrocardiographic data in a preferred embodiment of the present invention;

5 is a flow chart showing the acquisition of time-discrete quantization features in electrocardiographic data in a preferred embodiment of the present invention;

Figure 6 is a schematic diagram of electrocardiographic data of myocardial infarction data in a specific embodiment of the present invention;

Figure 7 is a schematic illustration of the analysis of electrocardiographic data for myocardial infarction in a specific embodiment of the invention.

Detailed ways

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

It should be noted that the embodiments in the present invention and the features in the embodiments may be combined with each other without conflict.

The invention is further illustrated by the following figures and specific examples, but is not to be construed as limiting.

According to the above problems existing in the prior art, a method for quantitative analysis of electrocardiographic data is provided. The method is specifically shown in FIG. 1 and includes:

Step S1, collecting ECG data;

Step S2, acquiring corresponding electrocardiographic data according to the collected ECG data;

Step S3, extracting spatial discrete quantization features of electrocardiographic data, and extracting time-discrete quantization features of electrocardiographic data;

Step S4, forming quantitative information of the electrocardiographic data according to the spatial discrete quantization feature and the time discrete quantization feature, and performing quantitative analysis on the ECG vector map according to the quantization information.

Specifically, the above ECG data can be obtained from a Vector Cardiogram (VCG). The so-called electrocardiogram vector diagram refers to a stereoscopic image in which the direction and size of the cardiac electrical excitation are different at each instant, and the electrical excitation generated in each moment of the heart is recorded in a stereoscopic direction and size. The ECG vector map can accurately record the cardiac action current, which can be used to clarify the principle of ECG generation and explain the ECG waveform, thus improving the clinical diagnosis. ECG vector diagrams and ECGs are reflections of ECG activity, and only the methods of recording are different. In the above step S1, the process of collecting the ECG data is a prior art, and details are not described herein again.

In this embodiment, the learning dynamics modeling is then determined based on the electrocardiographic data to obtain electrocardiographic (CDVG) data.

In this embodiment, in step S3, the time-discrete quantization feature and the spatial discrete quantization feature are respectively extracted according to the electrocardiographic data, and then the quantitative information of the electrocardiographic data is formed according to the time-discrete quantization feature and the spatial discrete quantization feature. The quantitative information can be used to quantitatively describe the electrocardiographic data, so the ECG vector map can be quantitatively analyzed according to the quantitative information to determine whether the patient has abnormal cardiac signs according to the analysis result.

In a preferred embodiment of the present invention, in the step S2, the step of acquiring electrocardiographic data is as shown in FIG. 2, and specifically includes:

Step S21, using a determining learning method, performing dynamic modeling on the ECG data to form a dynamic model associated with the ECG data;

Step S22, obtaining electrocardiographic data associated with the electrocardiogram data according to the electrocardiogram data and the kinetic model.

Specifically, in this embodiment, firstly, the collected electrocardiogram data is subjected to determining learning dynamics modeling, thereby obtaining corresponding electrocardiographic data. Specifically, the original electrocardiographic data e(t), e∈R, t=1, 2, . . . , T is converted into electrocardiographic data x(t), x∈R ³ , t=1, 2 ,...,T.

In a preferred embodiment of the present invention, the electrocardiographic data includes a plurality of data points arranged in a three-dimensional space;

Then, in the above step S3, the step of acquiring the spatial discrete quantization feature of the electrocardiographic data is specifically as shown in FIG. 3, and includes:

Step S31a, processing the electrocardiographic data in chronological order to obtain an exponential change rate of each data point;

In step S32a, the exponential rate of change of all data points is integrated into a spatial discrete quantization feature.

Specifically, in the embodiment, the electrocardiographic data includes a plurality of data points arranged in a three-dimensional space, and firstly, the three-dimensional spatial data of the electrocardiographic data is obtained in time order to obtain an exponential change rate of each data point, and the processing is performed. The manner of changing the rate of the index (that is, the above step S31a) is specifically as shown in FIG. 4, and includes:

Step S311a, processing to obtain an initial distance set of data points in the electrocardiographic data;

Step S312a, processing obtains a corresponding end distance set of data points;

Step S313a, respectively, processing the index change rate of each data point according to the initial distance set and the end distance set.

Specifically, in a preferred embodiment of the present invention, in the above step S311a, according to the following formula

among them,

i=1, 2,..., I _k ;

x _{k is} used to represent the current kth data point;

I _{k is} used to represent the total number of elements of the point set near the kth step, and I _k ≤ a ₁ ;

Is the initial distance set, used to represent

A set of distances between x _k and .

That is, in the above step S311a, first, the a ₁ point closest to the current k-th data point x _k in the electrocardiographic data is marked, and the point set of the a ₁ point is counted as the adjacent point set.

i = 1, 2, ..., I _k , where I _k is the total number of elements of the set of points adjacent to the kth step, and I _k ≤ a ₁ . Then, the distance between the set of neighboring points and the current track point (ie, the current data point x _k ) is set as the initial distance set, as shown in the above formula (1).

In a preferred embodiment of the present invention, in the above step S312a, the end distance set is obtained according to the following formula:

among them,

i=1,2,...,I _k ,Δ∈N;

x _{k is} used to represent the current kth data point;

Used to indicate

Time to increase the set of points obtained by the Δ step;

For the end distance set, used to represent

Increase the distance set after Δ step with x _k respectively.

That is, in the above step S312a, the current track point x _k and the time of the adjacent point set are respectively increased by Δ steps, thereby calculating the end distance set according to the above formula (2).

In a preferred embodiment of the present invention, in step S313a, each corresponding item in the initial distance set and the end distance set is logarithmically calculated to obtain an exponential change rate of each data point. The exponential change rate obtained by the above logarithmic operation is

i=1, 2,..., I _k . Exponential rate of change obtained through the above process

It is the set of exponential growth factors.

In a preferred embodiment of the present invention, in the above step S32a, the exponential change rate of all data points may be integrated into a spatial discrete quantization feature by a non-negative averaging method.

Specifically, first, take out the non-negative exponential rate of change of the current kth step and record it as

among them,

Also, the maximum value of j is denoted as J _k .

Then, calculate the current spatial dispersion coefficient according to the following formula:

Where φ _{k is} used to represent the above spatial dispersion coefficient.

Finally, the averaging operation of all the steps is performed as the spatial discrete quantization feature described above. This feature is calculated according to the following formula:

In a preferred embodiment of the present invention, the electrocardiographic data is multi-dimensional data;

Then, in step S3, the step of acquiring the time-discrete quantization feature of the electrocardiographic data is specifically as shown in FIG. 5, and includes:

Step S31b, converting each dimension of electrocardiographic data into corresponding frequency domain data;

Step S32b, using a preset exponential feature function group to respectively fit the frequency domain data of each dimension to obtain a time dispersion feature component of each dimension;

In step S33b, the time dispersion feature components of all dimensions are integrated to form a time-discrete quantization feature of the electrocardiographic data.

Specifically, in a preferred embodiment of the present invention, in the above step S31b, the CDVG data of each dimension is converted into frequency domain data by using a fast Fourier transform method.

Specifically, the CDVG data for each dimension can be expressed as:

x _i (t), x _i ∈R ¹ , t=1, 2,..., T, i=1, 2, 3;

Converting the above CDVG data into frequency domain information by fast Fourier transform can be expressed as:

f _i (n), f _∈ R ³ , n = 1, 2, ..., N, i = 1, 2, 3.

The above N is the sampling frequency.

In the above process, the zeroing operation of the zero frequency point is also included, that is, f _i (1)=0, i=1, 2, 3.

After the frequency domain data is converted, a preset exponential feature function group is used to fit the frequency domain data of each dimension to obtain time-discrete feature components of each dimension.

Specifically, the preset exponential feature function group is a class of exponential functions with specific features, and may be an exponential function with λ as an index, which may be specifically expressed as f _{i, λ} (n), i=1, 2 , 3. The exponential feature function set f _{i, λ} (n) is fitted to the frequency domain data f _i (n), and the optimal feature λ _i parameter used for the fitting is taken as the time-discrete feature component of each dimension.

Finally, by means of geometric averaging, the time-discrete feature components λ _i , i=1, 2 of each dimension form a time-discrete quantitative feature of CDVG data, which is calculated by the following formula:

In a preferred embodiment of the present invention, in the above step S4,

In a XOY coordinate plane, using time-discrete quantization features and spatial discrete quantization features One of the X-axis coordinates as the corresponding electrocardiographic data, and the other of the time-discrete quantized features and the spatial discrete quantized features as the corresponding Y-axis coordinates of the electrocardiographic data to form the coordinate information of the electrocardiographic data ;

And, the coordinate information is used as the quantitative information of the electrocardiographic data.

Specifically, in one embodiment of the present invention, in an XOY coordinate plane, on the xy coordinate system, the x coordinate is defined as the time-discrete quantization feature (ie, the TD index), and the y coordinate is defined as the spatial discrete quantization feature. (ie SD indicator), so a CDVG data has a coordinate information with the TD index as the x coordinate and the SD index as the y coordinate (ie, the quantitative information of the CDVG data), then the CDVG data corresponds to a two-dimensional space distribution. Point to represent the temporal and spatial characteristics of electrocardiography.

In this case, the larger the TD index (x coordinate), the stronger the time periodicity of the CDVG data, that is, the temporal characteristics of the electrocardiographic data tend to be more regular. The larger the SD index (y coordinate), the stronger the spatial chaos of CDVG data, that is, the spatial characteristics of ECG data tend to divergence.

In order to make the doctor more intuitive in making judgments, the electrocardiographic spatiotemporal feature distribution map represented by the XOY coordinate plane can be divided into three regions (the first region, the second region, and the third region) by dividing lines. specifically:

When the quantized information indicates that the electrocardiographic data falls into the first region, it indicates that the cardiac sign represented by the corresponding electrocardiogram vector is normal, that is, the first region is a negative region.

When the quantized information indicates that the electrocardiographic data falls into the second region, it indicates that the cardiac sign of the corresponding electrocardiogram vector is abnormal, that is, the second region is a positive region.

When the quantized information indicates that the electrocardiographic data falls into the third region, it indicates that the corresponding cardiac electrocardiogram represents a suspected abnormality in the cardiac sign, that is, the third region is a suspected positive region.

According to the characteristics of the above TD index and SD index, if the dynamic characteristics of the CDVG data are better (that is, it is a regular ring structure), then the TD index is larger and the SD index is smaller; if the dynamic characteristics of the CDVG data are worse (that is, a scattered spatial structure), then the smaller the TD indicator and the larger the SD index. Therefore, the second region may be distributed on the upper left of the XOY coordinate plane, and the first region may be distributed on the lower right side of the XOY coordinate plane with the third region distributed therebetween.

In another embodiment of the present invention, in an XOY coordinate plane, on the xy coordinate system, the x coordinate is defined as the spatial discrete quantization feature (ie, the SD index), and the y coordinate is defined. For the time discrete quantization feature (ie TD indicator), therefore, a CDVG data has a coordinate information with the SD index as the x coordinate and the TD index as the y coordinate (ie, the quantitative information of the CDVG data), then the CDVG data corresponds to one The distribution points of the two-dimensional space are used to represent the temporal and spatial characteristics of electrocardiography. The analysis of the quantized information of the CDVG data and the division of the corresponding judgment area may be processed as described above, and will not be described herein.

The following describes a specific process for verifying the technical solution of the present invention by performing quantitative analysis on CDVG data in a preferred embodiment of the present invention:

In the present embodiment, the myocardial infarction data P065 provided in the PTB data is taken as an example.

In this embodiment, CDVG data x _t (as shown in FIG. 6) is first generated by determining learning dynamics modeling according to the electrocardiographic data of P065 myocardial infarction, and then time-discrete quantitative features and spatial discrete quantization features are extracted from the CDVG data. .

In extracting the spatial discrete quantization feature, the step of finding a set of adjacent points of the current track point is first performed at the first point x _k , k=1. In this embodiment, the above a ₁ may take a value of 30, that is, the adjacent point set includes 30 data points, and then the initial distance set is calculated according to the above formula (1). Then, the end distance set is calculated according to the above formula (2). In the present embodiment, when the above formula (2) is applied, the value Δ=10 can be taken. In this embodiment, a non-negative exponential growth coefficient set (i.e., an exponential rate of change) is then found using a base 2 logarithmic function and the spatial dispersion coefficient is calculated according to the method described above. Finally, a cyclic operation of CDVG data length T is performed to obtain spatial dispersion coefficients at all time points, and the average operation is used as a spatial discrete quantization feature (ie, SD index) of CDVG data. For example, after the above-mentioned myocardial infarction data P065 is calculated, the SD index SD=3.0691 can be obtained.

Before the time-discrete quantization feature is extracted, the data pre-processing operation is required, that is, the CDVG data of each dimension is separately converted into the frequency domain data by the fast Fourier transform method. Since the zero frequency point of some data will be greatly shifted during the conversion process, the zeroing operation of the zero frequency point is performed to solve the offset problem. Then, the preset feature function group is used to fit the frequency domain data, and the optimal feature parameters used for the fitting are used as time-discrete feature components corresponding to the data of each dimension respectively. Finally, the time-discrete feature components of each dimension are integrated by geometric averaging to form time-discrete quantized features (ie, TD indicators) of CDVG data. For example, the above myocardial infarction data P065, which is calculated, can obtain a TD index TD=42.4774.

After getting the SD indicator and TD indicator of CDVG data, you can use XOY coordinate information. The way to form quantitative information of the CDVG data. For example, if the SD index is taken as the x-axis coordinate and the TD index is taken as the y-axis coordinate, the above-described quantization information can be expressed as (3.0691, 42.4774), that is, the distribution point position of the CDVG data in the two-dimensional plane indicated by the XOY coordinate plane. For example, if the SD index is used as the y-axis coordinate and the TD index is taken as the x-axis coordinate, the above-described quantization information can be expressed as (42.4774, 3.0691).

Finally, the CDVG data can be judged based on the quantized information. Specifically, as shown in FIG. 7, the TD index is taken as the x-axis coordinate, and the SD index is taken as the y-axis coordinate. The first area A, the second area B, and the third area C are divided in the XOY coordinate plane. The first region A is a negative region, the second region B is a positive region, and the third region C is a suspected positive region. The quantitative information (point a) of the above myocardial infarction data P065 indicates that it falls within the second region B and is far from the boundary line, and therefore the CDVG data is considered to indicate that the patient has a risk of myocardial ischemia.

Finally, according to the medical record information of the myocardial infarction data P065 in the PTB database, the patient died of myocardial infarction, and its CDVG map is shown in Fig. 6, which is shown as a slightly scattered ring. This is consistent with the analysis results of the final quantitative information, thus completing the verification of the technical solution of the present invention.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the embodiments and the scope of the present invention, and those skilled in the art should be able to Alternatives and obvious variations are intended to be included within the scope of the invention.

Claims

A method for quantitatively analyzing electrocardiographic data, comprising:

Step S1, collecting ECG data;

Step S2: Acquire corresponding electrocardiographic data according to the collected ECG data;

Step S3, extracting spatial discrete quantization features of the electrocardiographic data, and extracting time-discrete quantization features of the electrocardiographic data;

Step S4, forming quantization information of the electrocardiographic data according to the spatial discrete quantization feature and the temporal discrete quantization feature, and performing quantitative analysis on the ECG vector map according to the quantization information.
The method for quantitatively analyzing the electrocardiographic data according to claim 1, wherein the step of acquiring the electrocardiographic data in the step S2 comprises:

Step S21: Perform dynamic modeling on the ECG data by using a determining learning method to form a dynamic model associated with the ECG data;

Step S22, obtaining the electrocardiographic data associated with the electrocardiographic data according to the electrocardiogram data and the dynamic model.
The electrocardiographic data quantitative analysis method according to claim 1, wherein the electrocardiographic data comprises a plurality of data points arranged in a three-dimensional space;

In the step S3, the step of acquiring the spatial discrete quantization feature of the electrocardiographic data specifically includes:

Step S31a, processing the electrocardiographic data in chronological order to obtain an exponential change rate of each of the data points;

Step S32a, integrating the exponential change rate of all the data points into the spatial discrete quantization feature.
The electrocardiographic data quantification analysis method according to claim 3, wherein the step S31a specifically comprises:

Step S311a, processing to obtain an initial distance set of the data points in the electrocardiographic data;

Step S312a, processing to obtain a corresponding end distance set of the data points;

Step S313a, respectively, according to the initial distance set and the end distance set respectively processed The exponential rate of change to each of the data points.
The electrocardiographic data quantitative analysis method according to claim 4, wherein in the step S311a, the initial distance set is obtained according to the following formula:

among them,

i=1, 2,..., I k ;

x k is used to represent the current kth data point;

a set of neighboring points of x k , used to represent a set of points of a 1 point closest to x k in spatial distance;

I k is used to represent the total number of elements of the set of neighboring points described in step k, and I k ≤ a 1 ;

For the initial distance set, used to represent
A set of distances between x k and .
The electrocardiographic data quantitative analysis method according to claim 4, wherein in the step S312a, the end distance set is obtained according to the following formula:

among them,

i=1,2,...,I k ,Δ∈N;

x k is used to represent the current kth data point;

x k+Δ is used to represent the data point obtained by increasing the time of x k by Δ step;

a set of neighboring points of x k , used to represent a set of points of a 1 point closest to x k in spatial distance;

Used to indicate
Time to increase the set of points obtained by the Δ step;

I k is used to represent the total number of elements of the set of neighboring points described in step k, and I k ≤ a 1 ;

For the end distance set, used to represent
Increase the distance set after Δ step with x k respectively.
The electrocardiographic data quantitative analysis method according to claim 4, wherein in step S313a, each of the initial distance set and the end distance set is logarithmically calculated to obtain The rate of change of the index for each of the data points.
The electrocardiographic data quantitative analysis method according to claim 3, wherein in the step S32a, the exponential change rate of all the data points is integrated into the spatial discrete quantization by a non-negative averaging method feature.
The electrocardiographic data quantitative analysis method according to claim 1, wherein the electrocardiographic data is multi-dimensional data;

In the step S3, the step of acquiring the time-discrete quantization feature of the electrocardiographic data specifically includes:

Step S31b, respectively converting the electrocardiographic data of each dimension into corresponding frequency domain data;

Step S32b, using a preset exponential feature function group to respectively fit the frequency domain data of each dimension to obtain a time dispersion feature component of each dimension;

Step S33b, synthesizing the time dispersion feature components of all dimensions to form the time-discrete quantization feature of the electrocardiographic data.
The electrocardiographic data quantitative analysis method according to claim 9, wherein in the step S31b, the electrocardiographic data of each dimension is converted into a corresponding frequency domain by using a fast Fourier transform method, respectively. data.
The electrocardiographic data quantitative analysis method according to claim 9, wherein in the step S33b, the geometric dispersion method is used to synthesize the time dispersion feature components of all dimensions to form the electrocardiographic data. Time discrete quantized features.
The electrocardiographic data quantitative analysis method according to claim 1, wherein in the step S4,

And using one of the time-discrete quantized feature and the spatial discrete quantized feature as an X-axis coordinate of the corresponding electrocardiographic data, and using the time-discrete quantized feature and the space in an XOY coordinate plane Another one of the discrete quantized features as the corresponding Y-axis coordinate of the electrocardiographic data to form coordinate information of the electrocardiographic data;

The coordinate information is used as the quantization information of the electrocardiographic data.
The electrocardiographic data quantitative analysis method according to claim 12, wherein the XOY coordinate plane is divided into a first region, a second region, and a third region in advance;

When the quantized information indicates that the electrocardiographic data falls into the first region, indicating that the corresponding cardiac sign represented by the electrocardiogram vector is normal;

When the quantized information indicates that the electrocardiographic data falls into the second region, indicating that the corresponding cardiac energy map represented by the electrocardiogram is abnormal;

When the quantized information indicates that the electrocardiographic data falls within the third region, indicating Corresponding said ECG vector diagram represents a suspected abnormality in the cardiac sign.