CN105962926A - Cardiac beat feature analysis method and equipment based on electrocardiogram - Google Patents
Cardiac beat feature analysis method and equipment based on electrocardiogram Download PDFInfo
- Publication number
- CN105962926A CN105962926A CN201610244563.4A CN201610244563A CN105962926A CN 105962926 A CN105962926 A CN 105962926A CN 201610244563 A CN201610244563 A CN 201610244563A CN 105962926 A CN105962926 A CN 105962926A
- Authority
- CN
- China
- Prior art keywords
- heart
- feature
- dimensional
- claps
- waveform
- 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.)
- Granted
Links
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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Cardiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses cardiac beat feature analysis method and equipment based on an electrocardiogram, wherein the method comprises the following steps of respectively extracting N-dimension cardiac beat feature values from each cardiac beat waveform recorded by the electrocardiogram by a specific dimension compression algorithm, wherein the N is an integer greater than or equal to 2; and drawing a scatter diagram of N-dimension cardiac beat features corresponding to the electrocardiogram by using the N-dimension cardiac beat feature value of one cardiac beat waveform as the N-dimension coordinate value of one point. The N-dimension cardiac beat feature values are respectively extracted from each cardiac beat waveform recorded by the electrocardiogram by the specific dimension compression algorithm; compared with the original electrocardiogram, the scatter diagram of the N-dimension cardiac beat features has obvious differences between normal points and abnormal points; and the assistance is easily provided for a doctor to make preliminary judgment on diseases.
Description
Technical field
The present invention relates to ECG Signal Analysis field, particularly relate to one and divide based on Electrocardiographic heart bat feature
Analysis method and equipment.
Background technology
Electrocardiogram is to utilize electrocardiograph from electrical activity produced by the body surface each cardiac cycle of record heart
The technology of change figure.Fig. 1 is the schematic diagram of one section of original electrocardiographicdigital figure, as it is shown in figure 1, issue between RR
According to the data being intended to indicate that heart rate.Wherein between RR, the phase refers in electrocardiogram R in two adjacent QRS complex
X in time span between ripple, i.e. Fig. 1.At present, based on the such as RR of record in original electrocardiographicdigital figure
Interval data etc., can draw out heart rate scatterplot, heart rate panel map etc., assist doctor to carry out such as the heart
Restrain the diagnosis of the diseases such as not normal, myocardial infarction, myocardial ischemia.
But, in electrocardiogram, the heart bat waveform of record is not the most effectively used.
Summary of the invention
Technical problem
In view of this, the technical problem to be solved in the present invention is to provide a kind of based on Electrocardiographic heart bat spy
Levy analysis method and apparatus.
Solution
The present invention provides a kind of and claps characteristic analysis method based on the Electrocardiographic heart, including:
Utilize specific dimension compression algorithm, clap waveform from each heart of electrocardiographic recorder and extract N-dimensional respectively
The heart claps eigenvalue, and wherein N is the integer more than or equal to 2;
The N-dimensional heart that one described heart is clapped waveform claps the eigenvalue N-dimensional coordinate figure as a point, draws
The N-dimensional heart corresponding with described electrocardiogram claps the scatterplot of feature.
In a kind of possible implementation, described dimension compression algorithm is for protecting away from compression algorithm.
In a kind of possible implementation, described guarantor is manifold algorithm away from compression algorithm.
In a kind of possible implementation, described method also includes:
Described scatterplot is noted for clap, with the described N-dimensional heart, the reference heart bat spy that feature carries out contrasting
Levying, wherein said is according to utilizing described dimension compression algorithm from the heart diagnosing mark with reference to heart bat feature
Clap waveform extracting to the N-dimensional heart clap eigenvalue draw.
In a kind of possible implementation, described method also includes:
Calculate the described N-dimensional heart and clap feature with described with reference to heart bat feature distance in described scatterplot, and
The heart bat waveform clapping characteristic present according to the N-dimensional heart described in the distance identification calculated is the most normal.
The present invention also provides for one and claps feature analysis equipment based on the Electrocardiographic heart, including:
The heart claps characteristic extracting module, is used for utilizing specific dimension compression algorithm, each from electrocardiographic recorder
The heart is clapped waveform and is extracted N-dimensional heart bat eigenvalue respectively, and wherein N is the integer more than or equal to 2;
The heart claps feature drafting module, claps eigenvalue as one for a described heart is clapped the N-dimensional heart of waveform
The N-dimensional coordinate figure of individual point, draws the N-dimensional heart corresponding with described electrocardiogram and claps the scatterplot of feature.
In a kind of possible implementation, described dimension compression algorithm is for protecting away from compression algorithm.
In a kind of possible implementation, described guarantor is manifold algorithm away from compression algorithm.
In a kind of possible implementation, described equipment also includes:
Fixed reference feature labeling module, for being noted for and described N-dimensional heart bat feature in described scatterplot
The reference heart carrying out contrasting claps feature, and wherein said is according to utilizing described dimension to compress with reference to heart bat feature
Algorithm from diagnose mark the heart clap waveform extracting to the N-dimensional heart clap eigenvalue draw.
In a kind of possible implementation, described equipment also includes:
Identification module, is used for calculating the described N-dimensional heart and claps feature with described reference heart bat feature in described scatterplot
Distance in figure, and the heart bat waveform of characteristic present is clapped according to the N-dimensional heart described in the distance identification calculated
The most normal.
Beneficial effect
The embodiment of the present invention, it is possible to use specific dimension compression algorithm, claps from each heart of electrocardiographic recorder
Waveform extracts the N-dimensional heart respectively and claps eigenvalue, draws the scatterplot obtaining N-dimensional heart bat feature, with the original heart
Electrograph is compared, and the normal point in the scatterplot of N-dimensional heart bat feature becomes apparent from the difference of abnormity point, it is easy to
Auxiliary doctor carries out the preliminary judgement of disease.
According to below with reference to the accompanying drawings to detailed description of illustrative embodiments, the further feature of the present invention and side
Face will be clear from.
Accompanying drawing explanation
The accompanying drawing of the part comprising in the description and constituting description together illustrates with description
The exemplary embodiment of the present invention, feature and aspect, and for explaining the principle of the present invention.
Fig. 1 is the schematic diagram of one section of original electrocardiographicdigital figure;
Fig. 2 is the flow chart clapping characteristic analysis method based on the Electrocardiographic heart of the embodiment of the present invention one;
Fig. 3 be the embodiment of the present invention one clap the Electrocardiographic heart in characteristic analysis method based on the Electrocardiographic heart
Clap the schematic diagram of waveform;
Fig. 4 a be the embodiment of the present invention one clap non-filtered in characteristic analysis method based on the Electrocardiographic heart
Actual electrocardiogram;
Fig. 4 b is the design sketch using same color depth to represent Fig. 4 a;
Fig. 4 c is the schematic diagram that the heart based on Fig. 4 a claps the two-dimentional heart bat feature that waveform generates;
Fig. 5 is the flow chart clapping characteristic analysis method based on the Electrocardiographic heart of the embodiment of the present invention two;
Fig. 6 is the structural representation of the feature analysis equipment of clapping based on the Electrocardiographic heart of the embodiment of the present invention three
Figure;
Fig. 7 is the structural representation of the feature analysis equipment of clapping based on the Electrocardiographic heart of the embodiment of the present invention four
Figure.
Detailed description of the invention
Various exemplary embodiments, feature and the aspect of the present invention is described in detail below with reference to accompanying drawing.Attached
Reference identical in figure represents the same or analogous element of function.Although enforcement shown in the drawings
The various aspects of example, but unless otherwise indicated, it is not necessary to accompanying drawing drawn to scale.
The most special word " exemplary " means " as example, embodiment or illustrative ".Here as
Any embodiment illustrated by " exemplary " should not necessarily be construed as preferred or advantageous over other embodiments.
It addition, in order to better illustrate the present invention, detailed description of the invention below gives numerous
Detail.It will be appreciated by those skilled in the art that do not have some detail, the present invention is equally
Implement.In some instances, for method well known to those skilled in the art, means, element and circuit
It is not described in detail, in order to highlight the purport of the present invention.
Embodiment 1
Fig. 2 is the flow chart clapping characteristic analysis method based on the Electrocardiographic heart of the embodiment of the present invention one.As
Shown in Fig. 2, characteristic analysis method should be clapped based on the Electrocardiographic heart and mainly may include that
Step 101, utilize specific dimension compression algorithm, clap waveform respectively from each heart of electrocardiographic recorder
Extracting the N-dimensional heart and clap eigenvalue, wherein N is preferably greater than or equal to the integer of 2.
Specifically, all of heart in a certain electrocardiogram can be clapped waveform and all carry out dimension compression, it is also possible to
From electrocardiogram, select part heart bat waveform carry out dimension compression.Such as: as it is shown on figure 3, be the present invention
The clapping the Electrocardiographic heart in characteristic analysis method based on the Electrocardiographic heart and clap the schematic diagram of waveform of embodiment one,
A certain section of waveform before and after R ripple can be chosen from electrocardiogram and clap waveform 301, Ke Yicong as a heart
Electrocardiogram is selected multiple heart bat waveform and carries out dimension compression.
Each heart being clapped waveform and carries out dimension compression, the N-dimensional heart that can obtain correspondence claps eigenvalue.Wherein,
Dimension compression algorithm can include multiple, such as: can use meansigma methods, root-mean-square, summation scheduling algorithm,
The guarantor in similar compression of images can also be used away from compression algorithm such as manifold algorithm etc..
Step 102, the N-dimensional heart that described heart claps waveform clap the eigenvalue N-dimensional coordinate as a point
Value, draws the N-dimensional heart corresponding with described electrocardiogram and claps the scatterplot of feature.
Specifically, the quantity clapping eigenvalue according to the heart after compression is different, can obtain the N-dimensional heart and clap feature.
The N-dimensional heart is clapped the concrete dimension of feature and is not defined, and can be two dimension, the three-dimensional or heart of more various dimensions
Clap feature.
As shown in fig. 4 a, clap in characteristic analysis method not for the embodiment of the present invention one based on the Electrocardiographic heart
Filtered actual electrocardiogram, wherein the curve A in dotted ellipse is normal electrocardiogram curve, bent
Line B is abnormal electrocardiogram curve.Wherein, curve A and B has coincidence, the part intersected, if
Do not made a distinction by the depth of color, the electrocardiogram curve that the more difficult differentiation of doctor is normal with abnormal.As
Shown in Fig. 4 b, for using same color depth to represent the design sketch of Fig. 4 a, wherein cannot be distinguished by which part
Being abnormal electrocardiogram curve, which part is normal electrocardiogram curve.As illustrated in fig. 4 c, for based on
The heart of Fig. 4 a claps the schematic diagram of the two-dimentional heart bat feature that waveform generates, and it can represent the most respectively
Two hearts bat eigenvalues that waveform compression obtains are clapped by each heart of Fig. 4 a.A ' represents by normal electrocardiogram
Curve A extracts the two-dimentional heart obtained and claps feature, and the point of this part compares concentration;B ' represents abnormal electrocardio
The two-dimentional heart of figure curve B claps feature, and the point of this part substantially deviate from A '.
See Fig. 4 a~Fig. 4 c, according to electrocardiogram generate the N-dimensional heart clap feature scatterplot after, doctor or other
User can clap feature according to the N-dimensional heart, tentatively judges heart disease, and auxiliary carries out disease and examines
Disconnected.Concrete determination methods can have multiple, such as: doctor judges according to clinical experience, or, with
The scatterplot having diagnosed the Electrocardiographic N-dimensional heart bat feature marked compares.Wherein, Fig. 4 c
The shown two-dimentional heart claps the scatterplot of feature compared with original electrocardiogram 4a or Fig. 4 b, normal point and exception
The position difference of point is obvious, it is easy to auxiliary doctor carries out the preliminary judgement of disease.
The present embodiment clap characteristic analysis method based on the Electrocardiographic heart, it is possible to use specific dimension compression
Algorithm, claps waveform from each heart of electrocardiographic recorder and extracts N-dimensional heart bat eigenvalue respectively, draw and obtain N-dimensional
The heart claps the scatterplot of feature, and compared with original electrocardiographicdigital figure, the N-dimensional heart claps the normal point in the scatterplot of feature
Become apparent from the difference of abnormity point, it is easy to auxiliary doctor carries out the preliminary judgement of disease.
Embodiment 2
Fig. 5 is the flow chart clapping characteristic analysis method based on the Electrocardiographic heart of the embodiment of the present invention two.As
Shown in Fig. 5, on the basis of a upper embodiment, characteristic analysis method should be clapped based on the Electrocardiographic heart and also might be used
To include:
Step 201, in described scatterplot, it is noted for clapping feature with the described N-dimensional heart carries out the reference that contrasts
The heart claps feature, and wherein said is according to utilizing described dimension compression algorithm from diagnosing mark with reference to heart bat feature
Note the heart clap waveform extracting to the N-dimensional heart clap eigenvalue draw.
Wherein, doctor diagnosed mark the heart clap waveform can include the normal heart clap waveform, it is also possible to bag
Include and represent that the heart that disease such as " arrhythmia ", " premature beat " etc. is abnormal claps waveform.Characterize N being used for
The dimension heart is clapped in the scatterplot of feature, both can mark the normal heart and clap the reference heart bat feature that waveform represents,
The abnormal heart can also be marked and clap the reference heart bat feature that waveform represents, or both of which marks out.
Further, in scatterplot, mark is clapped feature with reference to the heart and marks certain Electrocardiographic N-dimensional heart to be detected
Clap feature, it is also possible to there is no timing requirements, with specific reference to application scenarios, can select flexibly, first mark
Any realization not affecting the present invention.Generally, clap, with reference to the heart, the N-dimensional heart that feature is corresponding with electrocardiogram
The dimension clapping feature is identical, such as, is all two dimension, is labelled with after clapping feature with reference to the heart in scatterplot,
Judgement can be compared with more convenient user.For example, it is possible to the electrocardiogram of user that first will detect
The N-dimensional heart generated is clapped feature and is labeled in scatterplot, and then in scatterplot, mark claps feature with reference to the heart.
For another example, it is also possible to first in scatterplot, mark claps feature with reference to the heart, then marks according to detection in scatterplot
The N-dimensional heart that the electrocardiogram of the user arrived generates claps feature.
Wherein, the method for concrete comparison reference heart bat feature and certain Electrocardiographic N-dimensional heart bat feature can be wrapped
Include multiple, such as:
Step 202, calculate the described N-dimensional heart clap feature with described with reference to the heart clap feature in described scatterplot
Distance, and the most just clapping the heart bat waveform of characteristic present according to the N-dimensional heart described in the distance identification calculated
Often.
Such as, the Electrocardiographic N-dimensional heart calculating certain user respectively claps feature with multiple with reference to heart bat feature
Distance in described scatterplot, obtains and a certain distance minimum clapping feature with reference to the heart, then can be auxiliary
It is closest that the heart helping the electrocardiogram judging this user and this reference heart bat feature to be characterized claps waveform.If
It is normal that the heart that this reference heart bat feature is characterized claps waveform, then can be with the electrocardio of this user of auxiliary judgment
Figure is normal.If it is abnormal (such as premature beat) that the heart that this reference heart bat feature is characterized claps waveform, the most permissible
The electrocardiogram of this user of auxiliary judgment belongs to the heart and claps abnormal, and tends to premature beat.
Further, it is also possible to gather substantial amounts of electrocardiogram for various heart diseases, pre-build and clap with reference to the heart
The data base of feature.Such as, the method that above-mentioned steps 101 arrives step 103 is used, to certain heart disease
Choose multiple electrocardiograms, after each Electrocardiographic heart chosen bat waveform is carried out dimension compression, the most right
The two-dimentional heart answered claps eigenvalue, by statistical analysis, may finally generate for representing this heart disease
The reference heart of corresponding two dimension claps the scatterplot of feature.So, during doctor carries out medical diagnosis on disease,
Directly can clap, from the reference heart, the reference that the Exception Type selecting to need to compare the data base of feature is corresponding
The heart claps the scatterplot of feature.The N-dimensional heart obtained by the electrocardiogram needing diagnosis claps scatterplot and the choosing of feature
The reference heart taken is clapped the scatterplot of feature and is compared, at the beginning of can more easily assisting doctor to carry out disease
Step judges.It is of course also possible to the Electrocardiographic N-dimensional heart needing diagnosis to be clapped the ginseng of feature and a certain disease
Examining heart bat feature to be plotted in a scatterplot compare, user may appear to convenient, directly perceived.
Concrete grammar can select according to the scene of reality application, is not defined in the embodiment of the present invention.
The present embodiment clap characteristic analysis method based on the Electrocardiographic heart, it is possible to use specific dimension compression
Algorithm, claps waveform from each heart of electrocardiographic recorder and extracts N-dimensional heart bat eigenvalue respectively, draw and obtain N-dimensional
The heart claps the scatterplot of feature, and compared with original electrocardiographicdigital figure, the N-dimensional heart claps the normal point in the scatterplot of feature
Become apparent from the difference of abnormity point, it is easy to auxiliary doctor carries out the preliminary judgement of disease.Wherein, by soft
After part automatically extracts heart bat feature, it is also possible to the heart extracted is clapped feature and classifies, thus highlight electrocardio
The abnormal heart in figure is clapped, and therefore, doctor claps the scatterplot of feature by the N-dimensional heart, can be more convenient and more
Determine whether the electrocardiogram of user abnormal and abnormal kind occurs intuitively.Additionally, even for
Unidentified illness, it is also possible to characterized in the N-dimensional heart drawn claps the scatterplot of feature.
Embodiment 3
Fig. 6 is the structural representation of the feature analysis equipment of clapping based on the Electrocardiographic heart of the embodiment of the present invention three
Figure.As shown in Figure 6, feature analysis equipment should be clapped based on the Electrocardiographic heart can also include:
The heart claps characteristic extracting module 61, is used for utilizing specific dimension compression algorithm, from electrocardiographic recorder
Each heart is clapped waveform and is extracted N-dimensional heart bat eigenvalue respectively, and wherein N is the integer more than or equal to 2;
The heart claps feature drafting module 63, for described heart is clapped the N-dimensional heart of waveform clap eigenvalue as
The N-dimensional coordinate figure of one point, draws the N-dimensional heart corresponding with described electrocardiogram and claps feature.
Specifically, all of heart in a certain electrocardiogram can be clapped waveform and all carry out dimension compression, it is also possible to
Selecting part heart bat waveform from electrocardiogram and carry out dimension compression, the N-dimensional heart obtaining correspondence claps eigenvalue.
Wherein, dimension compression algorithm can include multiple, such as: can use meansigma methods, root-mean-square, summation
Scheduling algorithm, it would however also be possible to employ the guarantor in similar compression of images is away from compression algorithm such as manifold algorithm etc..
Seeing Fig. 3, the heart claps each section before and after characteristic extracting module 61 can choose R ripple from electrocardiogram
Waveform claps waveform 301 as a heart.Seeing Fig. 4 a~Fig. 4 c, the heart claps feature drafting module 63 can be by not
The filtered actual Electrocardiographic N-dimensional heart claps character representation in the drawings.Wherein, the two dimension shown in Fig. 4 c
Heart bat feature is compared with original electrocardiogram 4a or Fig. 4 b, and normal point is obvious with the position difference of abnormity point,
It is prone to the preliminary judgement assisting doctor to carry out disease.
The present embodiment clap feature analysis equipment based on the Electrocardiographic heart, the heart claps characteristic extracting module can be in order to
By specific dimension compression algorithm, clap waveform from each heart of electrocardiographic recorder and extract N-dimensional heart bat feature respectively
Value, is clapped feature drafting module by the heart and draws N-dimensional heart bat feature, and compared with original electrocardiographicdigital figure, the N-dimensional heart is clapped
Normal point in feature becomes apparent from the difference of abnormity point, it is easy to auxiliary doctor carries out tentatively sentencing of disease
Disconnected.
Embodiment 4
Fig. 7 is the structural representation of the feature analysis equipment of clapping based on the Electrocardiographic heart of the embodiment of the present invention four
Figure.As it is shown in fig. 7, on the basis of above-described embodiment, feature analysis should be clapped based on the Electrocardiographic heart and set
For including:
Fixed reference feature labeling module 71, is used for being noted for clapping, with the described N-dimensional heart, the ginseng that feature carries out contrasting
Examining the heart and clap feature, wherein said is according to utilizing described dimension compression algorithm from diagnosing with reference to heart bat feature
Mark the heart clap waveform extracting to the N-dimensional heart clap eigenvalue draw.
Specifically, doctor diagnosed mark the heart clap waveform can include the normal heart clap waveform, it is also possible to
Waveform is clapped including the abnormal heart representing disease.In the schematic diagram clapping feature for characterizing the N-dimensional heart, both
The normal heart can be marked and clap the reference heart bat feature that waveform represents, it is also possible to the heart bat waveform that mark is abnormal
The reference heart represented claps feature, or both of which marks out.Further, mark claps feature and mark with reference to the heart
Certain Electrocardiographic N-dimensional heart to be detected claps feature, it is also possible to do not have timing requirements, with specific reference to applied field
Scape, can select flexibly, first marks any realization not affecting the present invention.It is labelled with and claps with reference to the heart
After feature, judgement can be compared with more convenient user.
Further, feature analysis equipment should be clapped based on the Electrocardiographic heart can also include:
Identification module 73, claps feature and the described distance clapping feature with reference to the heart for calculating the described N-dimensional heart,
And it is the most normal to clap waveform according to the heart of N-dimensional heart bat characteristic present described in the distance identification calculated.
Such as, identification module 73 calculates the Electrocardiographic N-dimensional heart bat feature of certain user and multiple ginsengs respectively
Examine the heart and clap the distance of feature, obtain minimum with a certain distance with reference to heart bat feature, then can assist and sentence
It is closest that the heart that the electrocardiogram of this user disconnected and this reference heart bat feature are characterized claps waveform.If this ginseng
It is normal for examining the heart and clap the heart that characterized of feature clapping waveform, then can with the electrocardiogram of this user of auxiliary judgment just
Often.If the heart that this reference heart bat feature is characterized claps waveform for extremely (such as premature beat), then assisting
Judge that the electrocardiogram of this user belongs to the heart and claps abnormal, and tend to premature beat.
The present embodiment clap feature analysis equipment based on the Electrocardiographic heart, the heart claps characteristic extracting module can be in order to
By specific dimension compression algorithm, clap waveform from each heart of electrocardiographic recorder and extract N-dimensional heart bat feature respectively
Value, is clapped feature drafting module by the heart and draws N-dimensional heart bat feature, and compared with original electrocardiographicdigital figure, the N-dimensional heart is clapped
Normal point in feature becomes apparent from the difference of abnormity point, it is easy to auxiliary doctor carries out tentatively sentencing of disease
Disconnected.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited to
In this, any those familiar with the art, can be easily in the technical scope that the invention discloses
Expect change or replace, all should contain within protection scope of the present invention.Therefore, the protection of the present invention
Scope should be as the criterion with described scope of the claims.
Claims (10)
1. clap characteristic analysis method based on the Electrocardiographic heart for one kind, it is characterised in that including:
Utilize specific dimension compression algorithm, clap waveform from each heart of electrocardiographic recorder and extract N-dimensional respectively
The heart claps eigenvalue, and wherein N is the integer more than or equal to 2;
The N-dimensional heart that one described heart is clapped waveform claps the eigenvalue N-dimensional coordinate figure as a point, draws
The N-dimensional heart corresponding with described electrocardiogram claps the scatterplot of feature.
Method the most according to claim 1, it is characterised in that described dimension compression algorithm for protect away from
Compression algorithm.
Method the most according to claim 2, it is characterised in that described guarantor is manifold away from compression algorithm
Algorithm.
4. according to the method according to any one of claims 1 to 3, it is characterised in that also include:
Described scatterplot is noted for clap, with the described N-dimensional heart, the reference heart bat spy that feature carries out contrasting
Levying, wherein said is according to utilizing described dimension compression algorithm from the heart diagnosing mark with reference to heart bat feature
Clap waveform extracting to the N-dimensional heart clap eigenvalue draw.
Method the most according to claim 4, it is characterised in that also include:
Calculate the described N-dimensional heart and clap feature with described with reference to heart bat feature distance in described scatterplot, and
The heart bat waveform clapping characteristic present according to the N-dimensional heart described in the distance identification calculated is the most normal.
6. clap feature analysis equipment based on the Electrocardiographic heart for one kind, it is characterised in that including:
The heart claps characteristic extracting module, is used for utilizing specific dimension compression algorithm, each from electrocardiographic recorder
The heart is clapped waveform and is extracted N-dimensional heart bat eigenvalue respectively, and wherein N is the integer more than or equal to 2;
The heart claps feature drafting module, claps eigenvalue as one for a described heart is clapped the N-dimensional heart of waveform
The N-dimensional coordinate figure of individual point, draws the N-dimensional heart corresponding with described electrocardiogram and claps the scatterplot of feature.
Equipment the most according to claim 6, it is characterised in that described dimension compression algorithm for protect away from
Compression algorithm.
Equipment the most according to claim 7, it is characterised in that described guarantor is manifold away from compression algorithm
Algorithm.
9. according to the equipment according to any one of claim 6~8, it is characterised in that also include:
Fixed reference feature labeling module, for being noted for and described N-dimensional heart bat feature in described scatterplot
The reference heart carrying out contrasting claps feature, and wherein said is according to utilizing described dimension to compress with reference to heart bat feature
Algorithm from diagnose mark the heart clap waveform extracting to the N-dimensional heart clap eigenvalue draw.
Equipment the most according to claim 9, it is characterised in that also include:
Identification module, is used for calculating the described N-dimensional heart and claps feature with described reference heart bat feature in described scatterplot
Distance in figure, and the heart bat waveform of characteristic present is clapped according to the N-dimensional heart described in the distance identification calculated
The most normal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610244563.4A CN105962926B (en) | 2016-04-18 | 2016-04-18 | The heart based on electrocardiogram claps characteristic analysis method and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610244563.4A CN105962926B (en) | 2016-04-18 | 2016-04-18 | The heart based on electrocardiogram claps characteristic analysis method and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105962926A true CN105962926A (en) | 2016-09-28 |
CN105962926B CN105962926B (en) | 2019-01-29 |
Family
ID=56993027
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610244563.4A Expired - Fee Related CN105962926B (en) | 2016-04-18 | 2016-04-18 | The heart based on electrocardiogram claps characteristic analysis method and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105962926B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107157475A (en) * | 2017-05-11 | 2017-09-15 | 陈昕 | The display methods and terminal device of ECG data |
CN107928652A (en) * | 2017-12-15 | 2018-04-20 | 深圳市维亿魄科技有限公司 | A kind of heart disease monitoring method based on pulse frequency variability |
CN109259756A (en) * | 2018-09-04 | 2019-01-25 | 周军 | The ECG signal processing method of Secondary Neural Networks based on non-equilibrium training |
CN109480825A (en) * | 2018-12-13 | 2019-03-19 | 武汉中旗生物医疗电子有限公司 | The processing method and processing device of electrocardiogram (ECG) data |
CN109770893A (en) * | 2019-03-08 | 2019-05-21 | 东南大学 | The method and device of atrial fibrillation position are quickly positioned in a kind of Holter analysis system |
CN111449645A (en) * | 2020-03-07 | 2020-07-28 | 河南大学 | Intelligent classification and identification method for electrocardiogram and heartbeat |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5622178A (en) * | 1994-05-04 | 1997-04-22 | Spacelabs Medical, Inc. | System and method for dynamically displaying cardiac interval data using scatter-plots |
US20100106035A1 (en) * | 2005-10-31 | 2010-04-29 | Medtronic, Inc. | Method of and apparatus for classifying arrhythmias using scatter plot analysis |
CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
CN103271737A (en) * | 2013-05-23 | 2013-09-04 | 山东师范大学 | Heart rate turbulence tendency extraction method based on cloud model and scatter diagram |
CN103815897A (en) * | 2014-02-28 | 2014-05-28 | 吉林大学 | Electrocardiogram characteristic extraction method |
CN104586385A (en) * | 2015-02-12 | 2015-05-06 | 中国人民解放军总医院 | Electrocardiogram-based heart rate analysis method and equipment |
-
2016
- 2016-04-18 CN CN201610244563.4A patent/CN105962926B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5622178A (en) * | 1994-05-04 | 1997-04-22 | Spacelabs Medical, Inc. | System and method for dynamically displaying cardiac interval data using scatter-plots |
US20100106035A1 (en) * | 2005-10-31 | 2010-04-29 | Medtronic, Inc. | Method of and apparatus for classifying arrhythmias using scatter plot analysis |
CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
CN103271737A (en) * | 2013-05-23 | 2013-09-04 | 山东师范大学 | Heart rate turbulence tendency extraction method based on cloud model and scatter diagram |
CN103815897A (en) * | 2014-02-28 | 2014-05-28 | 吉林大学 | Electrocardiogram characteristic extraction method |
CN104586385A (en) * | 2015-02-12 | 2015-05-06 | 中国人民解放军总医院 | Electrocardiogram-based heart rate analysis method and equipment |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107157475A (en) * | 2017-05-11 | 2017-09-15 | 陈昕 | The display methods and terminal device of ECG data |
CN107928652A (en) * | 2017-12-15 | 2018-04-20 | 深圳市维亿魄科技有限公司 | A kind of heart disease monitoring method based on pulse frequency variability |
CN107928652B (en) * | 2017-12-15 | 2021-07-27 | 深圳市维亿魄科技有限公司 | Heart monitoring method based on pulse rate variability |
CN109259756A (en) * | 2018-09-04 | 2019-01-25 | 周军 | The ECG signal processing method of Secondary Neural Networks based on non-equilibrium training |
CN109259756B (en) * | 2018-09-04 | 2020-12-18 | 周军 | ECG signal processing method based on secondary neural network of unbalanced training |
CN109480825A (en) * | 2018-12-13 | 2019-03-19 | 武汉中旗生物医疗电子有限公司 | The processing method and processing device of electrocardiogram (ECG) data |
CN109480825B (en) * | 2018-12-13 | 2021-08-06 | 武汉中旗生物医疗电子有限公司 | Electrocardio data processing method and device |
CN109770893A (en) * | 2019-03-08 | 2019-05-21 | 东南大学 | The method and device of atrial fibrillation position are quickly positioned in a kind of Holter analysis system |
CN109770893B (en) * | 2019-03-08 | 2022-11-18 | 东南大学 | Method and device for rapidly positioning atrial fibrillation position in Holter analysis system |
CN111449645A (en) * | 2020-03-07 | 2020-07-28 | 河南大学 | Intelligent classification and identification method for electrocardiogram and heartbeat |
Also Published As
Publication number | Publication date |
---|---|
CN105962926B (en) | 2019-01-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105962926A (en) | Cardiac beat feature analysis method and equipment based on electrocardiogram | |
Yochum et al. | Automatic detection of P, QRS and T patterns in 12 leads ECG signal based on CWT | |
EP3821807B1 (en) | Method of medical monitoring | |
CN111091116B (en) | Signal processing method and system for judging arrhythmia | |
CN109063552A (en) | A kind of multi-lead electrocardiosignal classification method and system | |
CN103815897B (en) | Electrocardiogram characteristic extraction method | |
CN105025786B (en) | Simplified method and apparatus is carried out to from the obtained information of electrical impedance tomography | |
CN106214145A (en) | A kind of electrocardiogram classification method based on degree of depth learning algorithm | |
CN104271038B (en) | A kind of method and apparatus that myocardial damage is assessed based on current density change | |
WO2019015017A1 (en) | Quantitative analysis method for electrocardio dynamics data | |
CN102869303A (en) | Visualization of myocardial infarct size in diagnostic ECG | |
CN106073760A (en) | 18 Lead ambulatory electrocardiograms based on wilson's lead2s analyze method and system | |
CN106963361B (en) | Detection method, detection device and the electrocardio equipment of limb leads misconnection | |
CN103800004A (en) | Automatic detection method used for wrong placement of electrocardio-electrodes and based on kernel function classification algorithm | |
CN103584852A (en) | Personalized electrocardiogram intelligent auxiliary diagnosis device and method | |
Qi et al. | Non-contact driver cardiac physiological monitoring using video data | |
CN115299956B (en) | Myocardial ischemia detection method and system based on definite learning and electrocardiogram | |
CN112971800A (en) | Deep learning-based electrocardio premature beat signal processing method, module and device | |
JPH10211180A (en) | Method for automatically diagnosing heart function | |
US20240215901A1 (en) | Method and apparatus for correcting electrocardiogram reading | |
Wang et al. | Fetal ECG signal extraction from long-term abdominal recordings based on adaptive QRS removal and joint blind source separation | |
CN108478214B (en) | Anti-confusion superposition method and device for electrocardiogram data analysis | |
Gillette et al. | Medalcare-xl: 16,900 healthy and pathological 12 lead ecgs obtained through electrophysiological simulations | |
CN110141214A (en) | A kind of mask method of electrocardiogram identification and its application | |
CN109589137A (en) | Method, apparatus, terminal and the computer readable storage medium of movement of the foetus identification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190129 Termination date: 20210418 |