CN110192853A - A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart - Google Patents
A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart Download PDFInfo
- Publication number
- CN110192853A CN110192853A CN201910364522.2A CN201910364522A CN110192853A CN 110192853 A CN110192853 A CN 110192853A CN 201910364522 A CN201910364522 A CN 201910364522A CN 110192853 A CN110192853 A CN 110192853A
- Authority
- CN
- China
- Prior art keywords
- entropy
- electrocardio
- sequence
- time parameter
- electrocardiographic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000002547 anomalous effect Effects 0.000 title abstract 4
- 239000013598 vector Substances 0.000 claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000012706 support-vector machine Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000010586 diagram Methods 0.000 claims description 18
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 230000000747 cardiac effect Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 210000003205 muscle Anatomy 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims 1
- 238000003745 diagnosis Methods 0.000 abstract 1
- 230000004069 differentiation Effects 0.000 abstract 1
- 238000007689 inspection Methods 0.000 abstract 1
- 238000000926 separation method Methods 0.000 abstract 1
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 108010076504 Protein Sorting Signals Proteins 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 208000010125 myocardial infarction Diseases 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Cardiology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of anomalous ecg appraisal procedures based on electrocardio entropy chart.The present invention passes through the entropy feature-approximate entropy for extracting conventional twelve-lead electrocardiogram signal, Sample Entropy, fuzzy entropy, using the training of support vector cassification algorithm and seek cut off value corresponding to each feature, support vector machines, entropy feature and graphic software platform method are combined, it proposes electrocardio entropy chart, provides powerful measure for the diagnosis and assessment of anomalous ecg.The three entropy features mentioned in the method for the present invention characterize the internal characteristics of electrocardiosignal well, calculate simple and convenient.In tested crowd, if multiple indexs of electrocardio entropy chart all exceed the separation of differentiation figure, illustrate that the probability of its anomalous ecg or heart electrical disorder will greatly increase, needs to cause the close attention of individual itself and the further inspection of doctor.
Description
Technical Field
The invention belongs to the technical field of electrocardiogram detection, and particularly relates to an electrocardiogram abnormity evaluation method based on an electrocardiogram entropy diagram.
Background
The twelve-lead electrocardiogram is a routine examination in hospitals, basically, the electrocardiogram examination is configured from the basic level to the third hospital, the electrodes are placed on the chest cavity and the limb surfaces of a human body, the electrocardiogram waveform at a specific position is recorded, and a doctor can roughly deduce whether the beating state of the heart is abnormal or not according to the amplitude and the time sequence of the electrocardiogram waveform. Because the body surface potential recorded by the electrocardiogram is only a rough projection of the electrophysiological activity of the heart on the body surface, the doctor can make an inference from the subjective nature of experience to diagnose the physiological state of the heart according to the body surface potential, and the requirement on the doctor is high.
Most of the existing electrocardiogram signal-based electrocardiogram intelligent analysis methods extract time frequency characteristics of a signal superficial layer, often ignore intrinsic dynamic characteristics of the complex non-stationary signal, namely the electrocardiogram signal, and obviously do not sufficiently depict intrinsic dynamic essential characteristics of the electrocardiogram signal only by adopting time-frequency characteristics.
Disclosure of Invention
According to the problems in the prior art, the invention provides an electrocardio abnormality evaluation method based on an electrocardio entropy diagram, which aims to evaluate electrocardiosignals simply and intuitively and make reference for doctors to diagnose illness states.
The specific technical scheme of the invention is realized by the following steps:
step 1, acquiring electrocardiogram data:
the method comprises the steps of obtaining human body electrocardio time parameter data by utilizing a standard twelve-lead system, and particularly obtaining twelve-dimensional electrocardiosignals x ═ x1,x2,...,x12]T。
Step 2, data preprocessing:
and (3) removing the noise such as baseline drift, muscle interference, power supply interference and the like in the electrocardio data extracted in the step (1) by utilizing a median filtering algorithm. The median filtering algorithm is to input an electrocardio time sequence xk＝{xk(n)|n＝1,2,...,N}
Wherein k is 1, 2.., 12; defining a window range M for the time series xk(n-M),...,xk(n),...,xk(n+M)
Taking the median value to replace xk(n), i.e. yk(n)＝med[xk(n-M),...,xk(n),...,xk(n+M)]. The electrocardio dimension reduction process converts 12 dimensions through linear transformation without losing any electrocardio informationElectrocardiosignal x ═ x1,x2,...,x12]TReduced to 3-dimensional electrocardiosignal v ═ v1,v2,v3]TThe concrete formula is as follows:
step 3, entropy characteristic extraction:
extracting entropy characteristic of the 3-dimensional electrocardiosignals processed in the step 2, extracting approximate entropy, sample entropy and fuzzy entropy corresponding to each electrocardiosignal sequence, and normalizing each characteristic;
3-1. the extraction method of approximate entropy is as follows:
3-1-1. inputting the electrocardiosignal sequence x after dimensionality reductionk＝{xk(N) | N ═ 1,2,.., N }, and k ═ 1,2, 3. Reconstructing an m-dimensional vector:
Xk(1)，Xk(2),....,Xk(N-m+1)
3-1-2. arbitrary vector X in the coring electrical time seriesk，Calculating Xk，Distance d [ X ] betweenk,X* k]：
Wherein u isk(a) Is a vector XkThe elements of (a) and (b),is a vectorOf (2) is used.
3-1-3, setting a threshold r, and counting that d [ X ] is satisfied in the reconstructed electrocardiosignal sequencek(i),Xk(j)]X under the condition of not more than rk(j) The number of vectors S.
Definition ofWherein j has a value in the range of [1, N-m +1 ]]And j is included as i.
4. Note the bookThe approximate entropy (ApEn) of the kth dimension of the cardiac signal sequence is defined as:
3-2. the extraction method of the sample entropy is as follows:
3-2-1, inputting the electrocardiosignal sequence x after dimensionality reductionk＝{xk(N) | N ═ 1,2,.., N }, and k ═ 1,2, 3. Reconstructing an m-dimensional vector:
Xk(1)，Xk(2),....,Xk(N-m+1)
3-2-2, calculating any vector X in the electrocardio time sequencek，Distance d [ X ] betweenk,X* k]：
Wherein u isk(a) Is a vector XkOf (2) is used.
3-2-3, setting a threshold r, and counting that d [ X ] is satisfied in the reconstructed electrocardiosignal sequencek(i),Xk(j)]X under the condition of not more than rk(j) The number of vectors S.
Definition ofWherein j has a value in the range of [1, N-m +1 ]]But j ≠ i.
3-2-4, average value of all i values of the electrocardiosignal sequence is recorded
3-2-5, repeating the steps 3-2-3 and 3-2-4, setting a threshold r, and counting the satisfied d [ X ] in the reconstructed electrocardiosignal sequencek(i),Xk(j)]X under the condition of not more than rk(j) The number of vectors S.
Note the book
3-2-6, sample entropy of k-dimension of the electrocardiosignal sequence:
3-3. the extraction method of the fuzzy entropy is as follows:
3-3-1, inputting the electrocardiosignal sequence x after dimensionality reductionk＝{xk(N) | N ═ 1,2,.., N }, and k ═ 1,2, 3. For reconstructing m-dimensional cardiac electrical signal sequencesPhase space:
Xk(i)＝[uk(i),uk(i+1),...,uk(i+m-1)]-uk0(i),i＝1,2,...,N-m+1
wherein,
3-3-2, introducing fuzzy membership function
For i 1,2,.., N-m +1, calculate:
whereinIs a vector Xk(i) And Xk(j) The maximum absolute distance between the two is specifically:
3-3-3, average value of all i values of electrocardiosignal sequence
3-3-4, definitionThe fuzzy entropy estimation of the k dimension of the electrocardiosignal sequence is as follows:
the feature normalization method is as follows:
and (4) carrying out normalization processing on the three entropy characteristics of the approximate entropy, the sample entropy and the fuzzy entropy by adopting a min-max method. The calculation method is as follows: suppose for sequence x1,x2,···,xnAnd (3) carrying out transformation:
then the new sequence y1,y2,···,yn∈[0,1]。
And 4, step 4: drawing an electrocardiogram entropy value graph:
respectively training the normalized features in the step 3 by using a support vector machine classification algorithm and solving a boundary corresponding to each feature; and (4) according to the trained boundary, calculating a boundary point according to a boundary equation omega x + b which is 0. And (3) making coordinate axes concentric with the circle and equally dividing the circle, respectively taking the attribute values or the demarcation points of the characteristics on the corresponding coordinate axes, and connecting the points to form the electrocardiogram entropy diagram. And drawing an interface of the electrocardiogram entropy diagram according to the demarcation points of the characteristics, wherein the interface is used as a standard for checking diseases.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. according to the method, three entropy characteristics of approximate entropy, sample entropy and fuzzy entropy are combined with a support vector machine, the electrocardio classification and abnormal evaluation are realized by utilizing the difference of the entropy characteristics between the abnormal electrocardio individual and the normal electrocardio individual in an electrocardio mode, and the classification result is good;
2. the invention visually presents the critical ranges of the normal control group and the abnormal electrocardio patient in the form of an entropy characteristic distribution diagram, and a clinician can visually observe the specific size of the characteristic value through the electrocardio entropy diagram to approximately estimate the electrocardio condition of the patient. If the multiple indexes of the ECG entropy map exceed the given critical range, the risk or degree of the disease is higher in the subject, and the individual needs to pay close attention and further examination by a doctor.
Drawings
FIG. 1 is a flow chart of an ECG entropy diagram for the evaluation of ECG anomalies according to an embodiment of the present invention.
FIG. 2a is a twelve-lead electrocardiogram of a patient with an abnormal cardiac electrical activity in accordance with an embodiment.
FIG. 2b is a twelve-lead electrocardiogram of a normal control group of individuals according to the example.
FIG. 3 is an interface of an ECG entropy diagram in an embodiment of the invention.
FIG. 4 is a chart of the entropy values of the electrocardiograms of normal individuals and abnormal individuals in the embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited thereto.
Examples
As shown in fig. one, a flowchart of an ecg entropy chart for evaluating ecg abnormalities according to an embodiment of the present invention includes the following steps:
acquiring a body surface electrocardio time parameter:
in order to ensure the research result to be true and reliable and verify the better effect of the research result, the data set is a PTB Diagnostic ECG Database provided by (https:// www.physionet.org/cgi-bin/ATM/ATM). Fig. 2a is a twelve-lead electrocardiogram of a patient with an abnormal electrocardiogram, and fig. 2b is a twelve-lead electrocardiogram of a normal control group of individuals.
Step two, data preprocessing: and (4) removing the noise such as baseline drift, muscle interference, power supply interference and the like in the original electrocardiosignal from the data in the step one by using a median filtering algorithm. The median filtering algorithm is to input an electrocardio time sequence xk＝{xk(N) | N ═ 1, 2., N } where k ═ 1, 2.., 12. Defining a window range M for the action time sequence Xk(n-M),...,Xk(n),...,Xk(n+M)
Taking the median value to replace Xk(n), i.e. Yk(n)＝med[Xk(n-M),...,Xk(n),...,Xk(n+M)]. Performing electrocardio dimensionality reduction treatment: changing 12D electrocardiosignal x into [ x ] without losing any electrocardio information by linear transformation1,x2,...,x12]TReduced to 3-dimensional electrocardiosignal v ═ v1,v2,v3]TThe concrete formula is as follows:
extracting entropy value characteristics and normalizing: extracting features of entropy values of the data processed in the step two, extracting approximate entropy, sample entropy and fuzzy entropy corresponding to each electrocardio sequence, and normalizing each feature;
1. the algorithm for approximating entropy is as follows:
(1) inputting the electrocardiosignal sequence x after dimensionality reductionk＝{xk(N) | N ═ 1,2,.., N }, and k ═ 1,2, 3. Reconstructing an m-dimensional vector:
Xk(1)，Xk(2),....,Xk(N-m+1)
(2) calculating any vector X in electrocardio time sequencek，Distance d [ X ] betweenk,X* k]：
Wherein u isk(a) Is a vector XkOf (2) is used.
(3) Setting a threshold r, and counting the satisfied d [ X ] in the reconstructed electrocardiosignal sequencek(i),Xk(j)]X under the condition of not more than rk(j) The number of vectors S.
Definition ofWherein j has a value in the range of [1, N-m +1 ]]And j is included as i.
(4) Note the bookThe approximate entropy (ApEn) of the kth dimension of the cardiac signal sequence is defined as:
2. the algorithm for sample entropy is as follows:
(1) inputting the electrocardiosignal sequence x after dimensionality reductionk＝{xk(N) | N ═ 1,2,.., N }, and k ═ 1,2, 3. Reconstructing an m-dimensional vector:
Xk(1)，Xk(2),....,Xk(N-m+1)
(2) calculating any vector X in electrocardio time sequencek，Distance d [ X ] betweenk,X* k]：
Wherein u isk(a) Is a vector XkOf (2) is used.
(3) Setting a threshold r, and counting the satisfied d [ X ] in the reconstructed electrocardiosignal sequencek(i),Xk(j)]X under the condition of not more than rk(j) The number of vectors S.
Definition ofWherein j has a value in the range of [1, N-m +1 ]]Including j ≠ i.
(4) Average values of all i values in the electrocardiosignal sequence are recorded
(5) Repeating the steps 3 and 4, setting a threshold r, and counting the electrocardiosignal sequence which satisfies d [ X ] in the reconstructed electrocardiosignal sequencek(i),Xk(j)]X under the condition of not more than rk(j) The number of vectors S.
Note the book
(6) Sample entropy of kth dimension of the electrocardiosignal sequence:
3. the algorithm of fuzzy entropy is as follows:
(1) inputting the electrocardiosignal sequence x after dimensionality reductionk＝{xk(N) | N ═ 1,2,.., N }, and k ═ 1,2, 3. Reconstructing the phase space of the m-dimensional electrocardiosignal sequence:
Xk(i)＝[uk(i),uk(i+1),...,uk(i+m-1)]-uk0(i),i＝1,2,...,N-m+1
wherein,
(2) introducing fuzzy membership functionFor i ═ 1, 2.., N-m +1, calculations were madeWhereinIs a window vector Xk(i) And Xk(j) The maximum absolute distance between.
(3) Average value of all i values of electrocardiosignal sequence
(4) Definition ofThe fuzzy entropy estimation of the kth dimension of the electrocardiosignal sequence is as follows:
the feature normalization method is as follows:
and (4) carrying out normalization processing on the three entropy characteristics of the approximate entropy, the sample entropy and the fuzzy entropy by adopting a min-max method. The calculation method is as follows: suppose for sequence x1,x2,···,xnAnd (3) carrying out transformation:then the new sequence y1,y2,···,yn∈[0,1]。
Step four, drawing an electrocardiogram entropy diagram:
and the support vector machine calculates the final classification hyperplane omega x + b to be 0. The algorithm process is as follows:
(1) constructing a constraint optimization problem:
(2) using SMO algorithm to obtain the value α of α vector corresponding to the minimum of the above formula*And (5) vector quantity.
(3) Computing
(4) Find all S support vectors, i.e. satisfy αSSample for > 0 correspondence (x)S,yS) By passingCalculate each support vector (x)S,yS) Corresponding toCalculate theseAll ofThe corresponding average value is the final oneSo that the final classification hyperplane is ω*·x+b*The final classification decision function is 0: (x) sign (ω)*·x+b*)。
And (4) according to the boundary line trained in the step, obtaining a boundary point according to a boundary line equation omega x + b which is 0. Here, 80 cases of data (40 cases of myocardial infarction and 40 cases of normal) are used as training data, and the boundary equation and the boundary point corresponding to each feature are shown in table 1 below:
TABLE 1 boundary equation and boundary Point for each feature
| Feature(s) | Equation of boundary | Demarcation point |
| Approximate entropy | 1.8287x-0.8824＝0 | 0.4825 |
| Sample entropy | 4.1906x-1.5591＝0 | 0.378 |
| Fuzzy entropy | 2.1244x-0.8682＝0 | 0.4087 |
And (3) making coordinate axes concentric with the circle and equally dividing the circle, respectively taking the attribute values or the demarcation points of the characteristics on the corresponding coordinate axes, and connecting the points to form the electrocardiogram entropy diagram. Drawing an interface of the electrocardio-entropy diagram according to the dividing points of the characteristics, wherein the interface is used as a standard for checking diseases, such as the interface of the electrocardio-entropy diagram in figure 3. FIG. 4 is a diagram of the entropy values of the electrocardio of normal individuals and abnormal individuals, the outermost circle is the characteristic plane of the abnormal individuals, the middle is the interface, and the inside is the interface of the normal individuals. Whether the subject has heart diseases can be visually seen from the electrocardiogram entropy diagram, and the classification result after the three entropies are fused is 95.8%.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. An electrocardio abnormality evaluation method based on an electrocardio entropy diagram is characterized by comprising the following steps:
step 1, obtaining a body surface electrocardio time parameter;
extracting a twelve-dimensional surface electrocardiosignal, representing as 12-dimensional electrocardio time parameters, and forming a group of electrocardio time parameter sequence;
step 2, preprocessing data;
removing baseline drift, muscle interference and power supply interference in the electrocardio time parameters in the step 1 by using a median filtering algorithm; carrying out dimension reduction processing on the 12-dimensional electrocardio time parameter sequence to obtain a three-dimensional electrocardio data sequence;
step 3, extracting entropy characteristics and carrying out normalization processing;
and 2, solving three entropy characteristics of the 3-dimensional electrocardio time parameter sequence processed in the step 2: approximate entropy, sample entropy and fuzzy entropy, and carrying out normalization processing on each entropy value characteristic;
and 4, step 4: drawing an electrocardiogram entropy value graph;
solving the optimal hyperplane wx + b of each entropy characteristic in the optimal characteristic combination as 0 by a support vector machine model obtained by a support vector machine training set; and (4) combining the demarcation point and the entropy characteristic parameter of the optimal hyperplane to draw an electrocardiogram entropy diagram.
2. The method for evaluating abnormal electrocardio-based on the electrocardio-entropy chart according to claim 1, wherein the electrocardio-time parameters in the step 1 are obtained by using a standard body surface 12 lead system, and comprise 12-dimensional electrocardiosignals as an electrocardio-time parameter sequence x ═ x1,x2,...,x12]T。
3. The method for evaluating abnormal electrocardio-based on the electrocardio-entropy diagram according to claim 1, wherein the median filtering algorithm in the step 2 is used for preprocessing, and the median filtering algorithm is an input electrocardio time parameter sequence xk＝{xk(N) | N ═ 1,2,.., N }; wherein k is 1, 2.., 12; defining a window range M for the time series xk(n-M),...,xk(n),...,xk(n+M)
Taking the median value to replace xk(n), i.e. yk(n)＝med[xk(n-M),...,xk(n),...,xk(n+M)]。
4. The method for evaluating abnormal electrocardio-based on the electrocardio-entropy chart according to claim 2 or 3, wherein the electrocardio-dimensionality reduction processing in the step 2 refers to the step of converting the electrocardio-time in 12 dimensions by linear transformationParameter sequence x ═ x1,x2,...,x12]TReducing to 3-dimensional electrocardio time parameter sequence v ═ v1,v2,v3]TThe dimension reduction processing does not lose any information, and the specific formula is as follows:
5. the method for evaluating electrocardiographic abnormality based on an electrocardiographic entropy chart according to claim 4, wherein the approximate entropy extraction in step 3 is specifically as follows:
5-1, inputting the electrocardio time parameter sequence x after dimension reductionk＝{xk(N) | N ═ 1,2,.., N }, k ═ 1,2, 3; reconstructing an m-dimensional vector:
Xk(1)，Xk(2),....,Xk(N-m+1)
5-2. taking any vector X in the sequence of electrical time parameters of the heartk,X* kCalculating Xk,X* kDistance d [ X ] betweenk,X* k]: calculating any vector X in the electrocardio time parameter sequencek，Distance d [ X ] betweenk,X* k]：
Wherein u isk(a) Is a vector XkAn element of (1);
5-3, setting a threshold r, and counting that d [ X ] is satisfied in the reconstructed electrocardio time parameter sequencek(i),Xk(j)]X under the condition of not more than rk(j) The number of vectors S;
definition ofWherein j has a value in the range of [1, N-m +1 ]]J ═ i, inclusive;
5-4. noteThe approximate entropy (ApEn) of the kth dimension of the cardiac electrical time parameter series of the cardiac electrical signal series is defined as:
6. the method for evaluating electrocardiographic abnormality based on an electrocardiographic entropy chart according to claim 5, wherein the sample entropy extraction in step 3 is specifically as follows: :
6-1, according to the steps 5-1 and 5-2, setting a threshold r, and counting that d [ X ] is satisfied in the reconstructed electrocardio time parameter sequencek(i),Xk(j)]X under the condition of not more than rk(j) The number of vectors S;
definition ofWherein j has a value in the range of [1, N-m +1 ]]But j ≠ i;
6-2, the average value of all the i values in the electrocardio time parameter sequence is recorded as
6-3 repeating 6-1 and 6-2, setting a threshold r, and counting the satisfied d [ X ] in the reconstructed electrocardiosignal sequencek(i),Xk(j)]X under the condition of not more than rk(j) The number of vectors S;
note the book
6-4 sample entropy of kth dimension of the electrocardiosignal sequence:
7. the method for evaluating electrocardiographic abnormality based on an electrocardiographic entropy chart according to claim 6, wherein the fuzzy entropy extraction in step 3 is specifically as follows:
7-1, inputting the electrocardio time parameter sequence x after dimension reductionk＝{xk(N) | N ═ 1,2,.., N }, k ═ 1,2, 3; reconstructing the phase space of the m-dimensional electrocardio time parameter sequence:
Xk(i)＝[uk(i),uk(i+1),...,uk(i+m-1)]-uk0(i),i＝1,2,...,N-m+1
wherein,
7-2, introducing fuzzy membership function Ak(x) For i 1, 2.., N-m +1, the following is calculated:
and j ≠ i;
whereinIs a vector Xk(i) And Xk(j) The maximum absolute distance therebetween;
7-3, obtaining the average value of all the i values in the electrocardio time parameter sequence
7-4. fuzzy entropy FuzzyEn of kth dimension of electrocardio time parameter sequencek(m,r,N)：
8. The method for evaluating electrocardiographic abnormality based on an electrocardiographic entropy chart according to claim 7, wherein the feature normalization processing in step 3 is to normalize the 3 features by a min-max method; the calculation method is as follows:
suppose for sequence a1,a2,···,anAnd (3) carrying out transformation:
then the new sequence b1,b2,···,bn∈[0,1]。
9. The method as claimed in claim 8, wherein the step 4 of obtaining the optimal hyperplane demarcation point is performed by using a support vector machine, a support vector, a lagrange multiplier and a bias term b can be obtained from a training model obtained by using the support vector machine, and a weight ω can be obtained from the support vector and the lagrange multiplier, so that a boundary ω x + b can be trained to be 0, and thus a demarcation point of each single feature can be obtained.
10. The method for evaluating the electrocardiographic abnormality based on the electrocardiographic entropy map according to claim 9, wherein the step 4 of drawing the electrocardiographic entropy map means performing support vector machine classification calculation on a single entropy feature, mapping an obtained boundary line to each attribute coordinate axis in a two-dimensional map as a boundary point, connecting each boundary point to form a triangular interface, and using the interface as the interface of a triangle of entropy values of normal electrocardiographic individuals and abnormal electrocardiographic individuals to prompt whether there is an electrocardiographic abnormality risk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910364522.2A CN110192853A (en) | 2019-04-30 | 2019-04-30 | A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910364522.2A CN110192853A (en) | 2019-04-30 | 2019-04-30 | A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110192853A true CN110192853A (en) | 2019-09-03 |
Family
ID=67752311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910364522.2A Pending CN110192853A (en) | 2019-04-30 | 2019-04-30 | A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110192853A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232253A (en) * | 2020-10-26 | 2021-01-15 | 南通大学 | Fetal electrocardiogram abnormity detection method driven by rough and reasonable granularity |
| CN112401903A (en) * | 2020-11-03 | 2021-02-26 | 沈阳东软智能医疗科技研究院有限公司 | Electrocardio data identification method and device, storage medium and electronic equipment |
| CN115662629A (en) * | 2022-10-11 | 2023-01-31 | 珠海弘昕医疗科技有限公司 | Heart failure monitoring system and prediction evaluation method thereof |
| CN115844415A (en) * | 2022-11-23 | 2023-03-28 | 广东工业大学 | Method and system for evaluating motion stability based on electrocardiogram data |
| CN117970858A (en) * | 2024-04-02 | 2024-05-03 | 山西久远爱思普软件股份有限公司 | Medical equipment monitoring method and system based on Internet of things |
| CN118245974A (en) * | 2024-05-28 | 2024-06-25 | 广东技术师范大学 | Method, device, system and storage medium for quantitatively evaluating stability of welding electric signal |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104586387A (en) * | 2015-01-19 | 2015-05-06 | 秦皇岛市惠斯安普医学系统有限公司 | Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters |
| CN104840186A (en) * | 2015-05-07 | 2015-08-19 | 中山大学 | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) |
| CN105411565A (en) * | 2015-11-20 | 2016-03-23 | 北京理工大学 | Heart rate variability feature classification method based on generalized scale wavelet entropy |
| CN105686801A (en) * | 2015-12-25 | 2016-06-22 | 四川大学 | An atrial fibrillation spontaneous termination predication method based on inherent time scale decomposing |
| CN105852807A (en) * | 2016-03-25 | 2016-08-17 | 中山大学 | Unsupervised autonomic nervous function quantitative evaluation method |
| CN106529478A (en) * | 2016-11-08 | 2017-03-22 | 中国人民解放军空军工程大学 | Radar radiation source signal identification method according to three-dimensional entropy characteristic |
| WO2018002541A1 (en) * | 2016-06-30 | 2018-01-04 | Université D'aix-Marseille | Device for detecting at least one cardiac rhythm disturbance |
| US20180296105A1 (en) * | 2015-06-19 | 2018-10-18 | Michael Blake | Wearable physiological monitoring and notification system based on real-time heart rate variability analysis |
| CN108968915A (en) * | 2018-06-12 | 2018-12-11 | 山东大学 | Sleep state classification method and system based on entropy feature and support vector machines |
| CN109044348A (en) * | 2018-08-08 | 2018-12-21 | 广州视源电子科技股份有限公司 | Atrial fibrillation detection apparatus and storage medium |
| CN109199362A (en) * | 2018-08-15 | 2019-01-15 | 哈尔滨理工大学 | The ECG auto-check system and device of cardiac extra systole |
-
2019
- 2019-04-30 CN CN201910364522.2A patent/CN110192853A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104586387A (en) * | 2015-01-19 | 2015-05-06 | 秦皇岛市惠斯安普医学系统有限公司 | Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters |
| CN104840186A (en) * | 2015-05-07 | 2015-08-19 | 中山大学 | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) |
| US20180296105A1 (en) * | 2015-06-19 | 2018-10-18 | Michael Blake | Wearable physiological monitoring and notification system based on real-time heart rate variability analysis |
| CN105411565A (en) * | 2015-11-20 | 2016-03-23 | 北京理工大学 | Heart rate variability feature classification method based on generalized scale wavelet entropy |
| CN105686801A (en) * | 2015-12-25 | 2016-06-22 | 四川大学 | An atrial fibrillation spontaneous termination predication method based on inherent time scale decomposing |
| CN105852807A (en) * | 2016-03-25 | 2016-08-17 | 中山大学 | Unsupervised autonomic nervous function quantitative evaluation method |
| WO2018002541A1 (en) * | 2016-06-30 | 2018-01-04 | Université D'aix-Marseille | Device for detecting at least one cardiac rhythm disturbance |
| CN106529478A (en) * | 2016-11-08 | 2017-03-22 | 中国人民解放军空军工程大学 | Radar radiation source signal identification method according to three-dimensional entropy characteristic |
| CN108968915A (en) * | 2018-06-12 | 2018-12-11 | 山东大学 | Sleep state classification method and system based on entropy feature and support vector machines |
| CN109044348A (en) * | 2018-08-08 | 2018-12-21 | 广州视源电子科技股份有限公司 | Atrial fibrillation detection apparatus and storage medium |
| CN109199362A (en) * | 2018-08-15 | 2019-01-15 | 哈尔滨理工大学 | The ECG auto-check system and device of cardiac extra systole |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232253A (en) * | 2020-10-26 | 2021-01-15 | 南通大学 | Fetal electrocardiogram abnormity detection method driven by rough and reasonable granularity |
| CN112232253B (en) * | 2020-10-26 | 2021-11-09 | 南通大学 | Fetal electrocardiogram abnormity detection method driven by rough and reasonable granularity |
| CN112401903A (en) * | 2020-11-03 | 2021-02-26 | 沈阳东软智能医疗科技研究院有限公司 | Electrocardio data identification method and device, storage medium and electronic equipment |
| CN112401903B (en) * | 2020-11-03 | 2023-12-22 | 沈阳东软智能医疗科技研究院有限公司 | Electrocardiogram data identification method and device, storage medium and electronic equipment |
| CN115662629A (en) * | 2022-10-11 | 2023-01-31 | 珠海弘昕医疗科技有限公司 | Heart failure monitoring system and prediction evaluation method thereof |
| CN115844415A (en) * | 2022-11-23 | 2023-03-28 | 广东工业大学 | Method and system for evaluating motion stability based on electrocardiogram data |
| CN115844415B (en) * | 2022-11-23 | 2024-08-16 | 广东工业大学 | Exercise stability assessment method and system based on electrocardiographic data |
| CN117970858A (en) * | 2024-04-02 | 2024-05-03 | 山西久远爱思普软件股份有限公司 | Medical equipment monitoring method and system based on Internet of things |
| CN117970858B (en) * | 2024-04-02 | 2024-06-11 | 山西久远爱思普软件股份有限公司 | Medical equipment monitoring method and system based on Internet of things |
| CN118245974A (en) * | 2024-05-28 | 2024-06-25 | 广东技术师范大学 | Method, device, system and storage medium for quantitatively evaluating stability of welding electric signal |
| CN118245974B (en) * | 2024-05-28 | 2024-08-20 | 广东技术师范大学 | Method, device, system and storage medium for quantitatively evaluating stability of welding electric signal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110192853A (en) | A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart | |
| Gupta et al. | QRS complex detection using STFT, chaos analysis, and PCA in standard and real-time ECG databases | |
| Sangaiah et al. | An intelligent learning approach for improving ECG signal classification and arrhythmia analysis | |
| CN109561841B (en) | Non-invasive method and system for measuring myocardial ischemia, stenosis identification, localization and fractional flow reserve estimation | |
| CN106214145B (en) | Electrocardiogram classification method based on deep learning algorithm | |
| CN109117730B (en) | Real-time electrocardiogram atrial fibrillation judgment method, device and system and storage medium | |
| JP7429371B2 (en) | Method and system for quantifying and removing asynchronous noise in biophysical signals | |
| Wang et al. | A robust signal preprocessing framework for wrist pulse analysis | |
| Zeng et al. | Classification of myocardial infarction based on hybrid feature extraction and artificial intelligence tools by adopting tunable-Q wavelet transform (TQWT), variational mode decomposition (VMD) and neural networks | |
| Mandal et al. | Detection of Ventricular Arrhythmia by using Heart rate variability signal and ECG beat image | |
| CN104840186A (en) | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) | |
| KR20220150901A (en) | Fusion signal processing for detection of maternal uterine activity | |
| Ganguly et al. | A non-invasive approach for fetal arrhythmia detection and classification from ecg signals | |
| Krishnan et al. | ANovel severity index of heart disease from beat-wise analysis of ECG using fuzzy logic for smart-health | |
| Allam et al. | Patient-specific ECG beat classification using EMD and deep learning-based technique | |
| CN117338309B (en) | Identity recognition method and storage medium | |
| CN113180684A (en) | II-lead electrocardiosignal classification method | |
| Dessai et al. | Emotion detection using physiological signals | |
| Hegde et al. | A review on ECG signal processing and HRV analysis | |
| CN114569116A (en) | Three-channel image and transfer learning-based ballistocardiogram ventricular fibrillation auxiliary diagnosis system | |
| Oktivasari et al. | A simple real-time system for detection of normal and myocardial ischemia in the ST segment and t wave ECG signal | |
| Sun et al. | Multi-scale Joint Recurrence Quantification Analysis Integrating ECG Spatiotemporal and Dynamic Information for Cardiopathy Detection | |
| Dembrani et al. | Accurate detection of ECG signals in ECG monitoring systems by eliminating the motion artifacts and improving the signal quality using SSG filter with DBE | |
| Yang et al. | A Classification Method for ECG Signals Based on Convolutional Neural Network | |
| Lin et al. | Nonlinear interpolation fractal classifier for multiple cardiac arrhythmias recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190903 |