CN109691994A - A kind of rhythm of the heart analysis method based on electrocardiogram - Google Patents
A kind of rhythm of the heart analysis method based on electrocardiogram Download PDFInfo
- Publication number
- CN109691994A CN109691994A CN201910099538.5A CN201910099538A CN109691994A CN 109691994 A CN109691994 A CN 109691994A CN 201910099538 A CN201910099538 A CN 201910099538A CN 109691994 A CN109691994 A CN 109691994A
- Authority
- CN
- China
- Prior art keywords
- heart
- electrocardiogram
- electrocardiosignal
- noise
- rhythm
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/0245—Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02405—Determining heart rate variability
-
- 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
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- 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
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- 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
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
-
- 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)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Cardiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The rhythm of the heart analysis method based on electrocardiogram that the invention proposes a kind of, comprising: step S1 using the electrocardiosignal of patch type electrocardioelectrode acquisition measured, and the electrocardiosignal is sent on the electrocardiogram equipment connecting with the electrocardioelectrode;Step S2, the electrocardiogram equipment pre-process collected electrocardiosignal, generate the block-shaped signal generated including noise and QRS wave;Step S3 identifies the block-shaped signal, identifies noise and QRS wave from the signal peak of detection;Step S4 respectively forwardly and backward takes multiple points using datum marks algorithm on the basis of the position of QRS wave, this number of segment strong point that interception is come out is as cardiac cycle;Step S5 designs the characteristic feature that each heart is clapped, and takes each cardiac cycle as a sample, all samples input classifier classify and output attribute marks.The present invention has rational design, Stability and veracity with higher, can be extensively with fields such as health risk assessments.
Description
Technical field
The present invention relates to bio-medical technology field, in particular to a kind of rhythm of the heart analysis method based on electrocardiogram.
Background technique
Today's society, cardiovascular disease are to endanger one of the principal disease of human health in the world, and arrhythmia cordis is one
Kind and its common and very important electrocardio-activity abnormality, can cause blood circulation not normal, it might even be possible to lead when serious
Cause sudden death.Electrocardiogram (Electrocardiogram, ECG) accurately automatically analyzes the diagnosis with diagnosis for cardiovascular disease
Play key effect.With the improvement of living condition, the development of hygiene industry, relative to other diseases, cardiovascular disease by
Walking becomes high morbidity, and people's health consciousness is also gradually reinforced at the same time, pays close attention to increasingly the physical condition of oneself
More, how the health and fitness information of convenient and efficient detection human body is just at very important topic instantly.Domestic portable cardiac monitoring
Equipment is just come into being in this background.
Summary of the invention
The purpose of the present invention aims to solve at least one of described technological deficiency.
For this purpose, it is an object of the invention to propose a kind of rhythm of the heart analysis method based on electrocardiogram.
To achieve the goals above, the embodiment of the present invention provides a kind of rhythm of the heart analysis method based on electrocardiogram,
Include the following steps:
Step S1, using patch type electrocardioelectrode acquisition measured electrocardiosignal, and by the electrocardiosignal be sent to
On the electrocardiogram equipment of the electrocardioelectrode connection;
Step S2, the electrocardiogram equipment pre-process collected electrocardiosignal, and generating includes that noise and QRS wave generate
Block-shaped signal;
Step S3 identifies the block-shaped signal, identifies noise and QRS wave from the signal peak of detection;
Step S4 respectively forwardly and backward takes multiple points using datum marks algorithm on the basis of the position of QRS wave,
This number of segment strong point that interception is come out is as cardiac cycle;
Step S5 designs the characteristic feature that each heart is clapped, takes each cardiac cycle as a sample, and all samples is defeated
Enter classifier classify and output attribute label.
Further, in the step S2, the pretreatment includes the following steps:
1) sampling frequency is set, electrocardiosignal is sampled with the sampling frequency;
2) it obtains data to sampling using bandpass filter to be filtered, to filter out because the dry determination of myoelectricity is disturbed and Hz noise
Caused noise only retains signal relevant to electrocardio-activity;
3) filtered electrocardiosignal value is calculated using difference method change maximum section;
4) square operation then is carried out to the maximum electrocardiosignal variation of acquisition;
5) to square after electrocardiosignal carry out sliding window integral operation to increase absolute amplitude, and keep waveform further
Smooth, sliding window width is set as 17 sampled points, is empirical parameter;
6) block-shaped signal generated including noise and QRS is generated using signal peak detection algorithm.
Further, in the step S3, noise is identified from the signal peak of detection using dynamic threshold set algorithm
And QRS wave.
Further, the threshold value in dynamic threshold set algorithm is adjusted in real time according to the noise and QRS wave that recognize, packet
It includes:
Two peak values in real time and a threshold value are set, for detecting QRS wave and noise waves;
If current wave crest is higher than threshold value, it is intended that thinking, judge that threshold value is relatively low at this time, at this time QRS dynamic peak
Value will will increase so that threshold value increases with it;Conversely, noise dynamic peak value increases so that threshold value reduces therewith.
Further, in the step S4, forward include 100 points on the basis of the position of QRS wave, backward include 150
A, it is 250 points that each heart thus intercepted, which claps length,.
Further, in the step S5, the characteristic of Analysis On Multi-scale Features can be extracted using wavelet transform function, obtained effectively
Wavelet coefficient, clapped to characterize the heart, after obtaining the characteristic feature that each heart is clapped, utilize SVM classifier to divide data set and carry out mould
The training and test of type.
Further, in the step S5, the wavelet transform function uses db6 wavelet function.
Rhythm of the heart analysis method according to an embodiment of the present invention based on electrocardiogram is summarizing ECG automatic analysis field
On the working foundation of forefathers, be domestic portable cardiac monitoring equipment (patch type dynamic electrocardiogram recording instrument) from Signal Pretreatment,
Signature waveform identification, proposes a whole set of algorithm solution, the outstanding feature of algorithm be it is anti-interference it is strong, real-time is good, effectively
Realize the cardiac monitoring of user.The present invention has rational design, and Stability and veracity with higher can be commented with health risk extensively
Estimate equal fields.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 is the flow chart according to the rhythm of the heart analysis method based on electrocardiogram of the embodiment of the present invention;
Fig. 2 is the general frame figure according to the rhythm of the heart analysis method based on electrocardiogram of the embodiment of the present invention;
Fig. 3 is the ECG signal preprocess method flow chart according to the embodiment of the present invention;
Fig. 4 is the Signal Pretreatment result figure according to the embodiment of the present invention;
Fig. 5 is according to the detection of the QRS wave of the embodiment of the present invention and positioning result figure;
Fig. 6 is to be defined according to the bat of the heart of the embodiment of the present invention and interception result figure;
Fig. 7 is the normal cardiac rhythm and abnormal heart rhythm heart bat figure according to the type mark of the embodiment of the present invention used;
Fig. 8 is the schematic diagram according to the classification results of the embodiment of the present invention;
Fig. 9 is the schematic diagram according to the user report of the embodiment of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, the example of embodiment is shown in the accompanying drawings, wherein identical from beginning to end
Or similar label indicates same or similar element or element with the same or similar functions.It is retouched below with reference to attached drawing
The embodiment stated is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
The analysis of dynamic electrocardiogram diagram data is to react a kind of important method of human body electrocardio health and fitness information.Dynamic ECG is logical
Spending dynamic cardiograph continuous 24 hours or longer time under patient's daily life state records the overall process of its electrocardio-activity,
And be analyzed and processed by computer, important objective basis is provided for the health data of measured.
As shown in Figure 1, the rhythm of the heart analysis method based on electrocardiogram of the embodiment of the present invention, includes the following steps:
Step S1, using patch type electrocardioelectrode acquisition measured electrocardiosignal, and by the electrocardiosignal be sent to
On the electrocardiogram equipment of electrocardioelectrode connection.
Specifically, contacting patient skin by patch type electrocardioelectrode, long-time continuous acquisition patient electrocardiosignal is simultaneously remembered
It records in the reservoir built in electrocardiogram equipment, recordable 72 hours electrocardiographic recordings of longest.
Step S2, electrocardiogram equipment pre-process collected electrocardiosignal, generate the block generated including noise and QRS wave
Shape signal.That is, by the electrocardiosignal collected in step S1 through over-sampling, filtering, square and sliding window integral obtain
Rolling average signal.Then, in rolling average signal, being generated using signal peak detection algorithm includes that noise and QRS are generated
Block-shaped signal, ECG signal processing result are as shown in Figure 4.
Specifically, in this step, pretreatment includes the following steps:
1) sampling frequency is set, electrocardiosignal is sampled with the sampling frequency.Wherein, sampling frequency is, for example, 250.
2) it obtains data to sampling using bandpass filter to be filtered, to filter out because the dry determination of myoelectricity is disturbed and Hz noise
Caused noise only retains signal relevant to electrocardio-activity.For example, the data of sampling use the bandpass filtering of 0.1~15Hz
Device filtering.P wave after filtering, T wave are significantly attenuated, and QRS wave becomes apparent from.
3) filtered electrocardiosignal value is calculated using difference method and change maximum section, that is, define and change the most fast heart
Electrical change value;
4) then maximum electrocardiosignal is changed and carries out square operation, and carrying out integral operation becomes apparent from its variation,
That is amplitude variation is bigger;
5) to square after electrocardiosignal carry out sliding window integral operation to increase absolute amplitude, and keep waveform further
Smooth, sliding window width is set as 17 sampled points, is empirical parameter;
6) QRS wave detects: in rolling average signal, being generated using signal peak detection algorithm includes that noise and QRS are generated
Block-shaped signal.
Step S3, identifies block-shaped signal, identifies noise and QRS wave from the signal peak of detection.
In this step, noise and QRS wave are identified from the signal peak of detection using dynamic threshold set algorithm, such as schemed
Shown in 5.
Specifically, the threshold value in dynamic threshold set algorithm is adjusted in real time according to the noise and QRS wave that recognize, packet
It includes:
Set 2 peak values in real time and threshold value for detect QRS wave and noise waves (qrs_peak, noise_peak,
), threshold_value update method is as follows:
if detected_peaks>threshold_value:
Qrs_peak=0.125*detected_peaks+0.875*qrs_peak
else:
Noise_peak=0.125*detected_peaks+0.875*noise_peak
Threshold_value=noise_peak+0.25* (qrs_peak-noise_peak)
Specifically, if current wave crest is higher than threshold value, judge that threshold value is relatively low at this time, at this time QRS wave dynamic peak value
It will will increase so that threshold value increases with it;Conversely, noise dynamic peak value increases so that threshold value reduces therewith.
Step S4 respectively forwardly and backward takes multiple points using datum marks algorithm on the basis of the position of QRS wave,
This number of segment strong point that interception is come out is as cardiac cycle.
Specifically, the R wave detected using datum marks algorithm tag, as center 100 150 data backward forward
Point is used as a cardiac cycle.
In this step, forward include 100 points on the basis of the position of QRS wave, include backward 150 points, thus cut
It is 250 points that each heart taken, which claps length,.
Specifically, on the basis of the position of QRS wave, if respectively forwardly backward including doing, then by this one piece of data point
Interception comes out claps as the heart.Here we include 100 points to the left, to the right include 150 points, that is, each heart intercepted claps length
For 250 points (about 0.7s).
Heart bat is defined, the R wave detected using datum marks algorithm tag, 150 100 is counted backward forward as center
Strong point is as a cardiac cycle, as shown in Figure 6.
Step S5 designs the characteristic feature that each heart is clapped, takes each cardiac cycle as a sample, and all samples is defeated
Enter classifier classify and output attribute label, as shown in Figure 7.
Specifically, the characteristic of Analysis On Multi-scale Features can be extracted using wavelet transform function, effective wavelet coefficient is obtained, table is carried out
It levies the heart to clap, after obtaining the characteristic feature that each heart is clapped, divides the training and test that data set carries out model using SVM classifier.
In an embodiment of the present invention, above-mentioned wavelet transform function can use db6 wavelet function.
In this step, this algorithm using some mathematic(al) manipulations handle ECG, obtain less coefficient, with these coefficients come
The heart is characterized to clap.This step uses wavelet transformation, and the characteristic of Analysis On Multi-scale Features can be extracted using wavelet transformation, obtains effective small echo
Coefficient is clapped to characterize the heart.Specifically, the wavelet decomposition that carries out 5 ranks is clapped each heart, and wavelet function utilizes db6 small echo, uses
Wavedec function in Matlab:
[C, L]=wavedec (sig, 5, ' db6') (1)
Wherein, C contains the coefficient after each rank wavelet transformation, and sig indicates that we clap extracted 250 dessert herein.
After 5 rank wavelet decompositions and 2 times of down-samplings, after taking " approximation " coefficient of original signal in wavelet conversion coefficient, i.e. 5 ranks to decompose
A coefficient takes preceding 25 points here.
After obtaining the characteristic feature that each heart is clapped, training and test that data set carries out model are divided.Used here as SVM points
Class device is trained and tests.
Model=libsvmtrain (train_y, train_x, '-c 2-g 1');% model training;
[ptest ,~,~]=libsvmpredict (test_y, test_x, model);% model prediction;
Libsvm training default kernel function be RBF kernel function, need to be manually set two hyper parameters c and g. here we
It is set as 2 and 1.
Training result is as shown in Figure 8.In this experiment, our SVM model macro-forecast accuracy rate is 96.69%,
Wherein the accuracy rate of four class target types is respectively normal (N): 99.68%, ventricular premature beat (V): and 90.90%, right bundle branch block
(R): 97.58%, left bundle branch block (L): a kind of common polytypic method of measurement is given in 98.49%. figure: being obscured
Matrix.Classification 1,2,3,4 respectively indicates N, V, R, L.From confusion matrix, it can be seen that the distribution situation of prediction result.Diagonally
It is correctly predicted number of all categories on line, remaining is error prediction number.For example, the 2nd row the 4th arranges, there are 128 premature beat hearts
Clapping mispredicted is left bundle branch block, is most during institute is wrong.It can guess, the premature beat heart is clapped to be clapped with the left bundle branch block heart
It may be phenomenologically more more like;And the 3rd column error prediction number of the 4th row is 0, i.e., no left bundle branch block heart is clapped by wrong pre-
Surveying is right bundle branch block, illustrates that both possible difference is larger.
1, ECG diagnostic model under big data:
(1) universal model: using the ECG large-scale data composing training collection in multiple sources, the data of new patient are done pre-
It surveys;
(2) special purpose model: individual fine tuning training is constituted using a part of historical data (case or diagnosis records) of patient
Collection, is finely adjusted universal model, constructs special purpose model, then gives a forecast to the new data of patient.
Here training set is divided into global training set and individual training set, and global training set and test set are from different diseases
People.
For universal diagnostic model, we analyze the intension of separate sources patient's large-scale data, with overall situation training training
Practice a classifier and new patient is tested;For separate diagnostic model, we are not predicted not instead of directly, will new disease
The sub-fraction data of people are tagged, come to make classifier fine tuning training as individual training set, then predict remaining number
According to.
2, ECG x AI: efficient ECG diagnostic mode
The expectation of algorithm: the training in old complaint personal data is tested in new patient's data
The advantage of algorithm:
(1) historical data and real time data of each patient big data source: are made full use of
(2) artificial intelligence learning algorithm: diagnostic model is constructed using LSTM deep neural network and machine learning algorithm
(3) personalized customization model: using active learning strategies, constructs on-line study model, establishes exclusive diagnostic model
The function of algorithm:
(1) diagnosis of a variety of electrocardio diseases is provided, provides support for the health control of patient;
(2) historical diagnostic data of patient is efficiently utilized, learns different diagnostic models, optimization health for different patients
Management;
(3) combination of cloud big data and on-line study, so that diagnosing patient is quickly and accurate.
Then, by the relationship analysis cardiac rhythm between analysis R -- R interval and the bat of the classified heart, and the rhythm of the heart is diagnosed
Arrhythmic event, experimental result are as shown in Figure 9.Arrhythmic events show as following some situations:
(1) atrial arrhythmia, including Premature atrial contraction, atrial tachycardia, paroxysmal auricular flutter, auricular fibrillation
(2) pulsus alternans are not normal
(3) ventricular arrhythmia: Premature Ventricular Beats, Ventricular Tachycardia, room property ease are rich
(4) other arrhythmia cordis
In addition, this step also carries out heart-rate variability analysis of HRV, following index result is provided:
The standard deviation of whole normal cardiac cycle NN in SDNN:24h (<50ms is abnormal, and>100ms is normal);
RMSSD: the root-mean-square value of the difference of whole adjacent NN interphase;
PNN50: percentage shared by the number of adjacent NN difference > 50ms.
The present invention uses the electrocardiosignal of portable cardiac custodial care facility acquisition user first, is then based on signal processing side
Method pre-processes the electrocardiosignal of acquisition, and pretreated electrocardiosignal is extracted the spy that the characterization heart is clapped by computerized algorithm
Sign.It is also possible to identify arrhythmic events by clapping feature by the analysis heart, it is simple to be finally provided to measured
Clear user report.By the electrocardiogram (ECG) data of mobile cardiac monitoring equipment dynamic acquisition user, Bluetooth transmission to meter is utilized
Cardiac electrical in-situ analysis is done at calculation machine center, then sends the application of Client handset end for the user report for analyzing result.This
Sample user can receive cardiac monitoring and health and fitness information risk management at any time.
Rhythm of the heart analysis method according to an embodiment of the present invention based on electrocardiogram is summarizing ECG automatic analysis field
On the working foundation of forefathers, be domestic portable cardiac monitoring equipment (patch type dynamic electrocardiogram recording instrument) from Signal Pretreatment,
Signature waveform identification, proposes a whole set of algorithm solution, the outstanding feature of algorithm be it is anti-interference it is strong, real-time is good, effectively
Realize the cardiac monitoring of user.The present invention has rational design, and Stability and veracity with higher can be commented with health risk extensively
Estimate equal fields.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art are not departing from the principle of the present invention and objective
In the case where can make changes, modifications, alterations, and variations to the above described embodiments within the scope of the invention.The scope of the present invention
By appended claims and its equivalent limit.
Claims (7)
1. a kind of rhythm of the heart analysis method based on electrocardiogram, which comprises the steps of:
Step S1, using patch type electrocardioelectrode acquisition measured electrocardiosignal, and by the electrocardiosignal be sent to it is described
On the electrocardiogram equipment of electrocardioelectrode connection;
Step S2, the electrocardiogram equipment pre-process collected electrocardiosignal, generate the block generated including noise and QRS wave
Shape signal;
Step S3 identifies the block-shaped signal, identifies noise and QRS wave from the signal peak of detection;
Step S4 respectively forwardly and backward takes multiple points using datum marks algorithm on the basis of the position of QRS wave, will cut
This number of segment strong point taken out is as cardiac cycle;
Step S5 designs the characteristic feature that each heart is clapped, and takes each cardiac cycle as a sample, by the input point of all samples
Class device classify and output attribute label.
2. the rhythm of the heart analysis method based on electrocardiogram as described in claim 1, which is characterized in that in the step S2
In, the pretreatment includes the following steps:
1) sampling frequency is set, electrocardiosignal is sampled with the sampling frequency;
2) it obtains data to sampling using bandpass filter to be filtered, to filter out because the dry determination of myoelectricity is disturbed and Hz noise causes
Noise, only retain relevant to electrocardio-activity signal;
3) filtered electrocardiosignal value is calculated using difference method change maximum section;
4) square operation then is carried out to the maximum electrocardiosignal variation of acquisition;
5) to square after electrocardiosignal carry out sliding window integral operation to increase absolute amplitude, and make the further light of waveform
Sliding, sliding window width is set as 17 sampled points, is empirical parameter;
6) block-shaped signal generated including noise and QRS is generated using signal peak detection algorithm.
3. the rhythm of the heart analysis method based on electrocardiogram as described in claim 1, which is characterized in that in the step S3
In, noise and QRS wave are identified from the signal peak of detection using dynamic threshold set algorithm.
4. the rhythm of the heart analysis method based on electrocardiogram as claimed in claim 3, which is characterized in that dynamic threshold setting is calculated
Threshold value in method is adjusted in real time according to the noise and QRS wave that recognize, comprising:
Two peak values in real time and a threshold value are set, for detecting QRS wave and noise waves;
If current wave crest is higher than threshold value, it is intended that thinking, judge that threshold value is relatively low at this time, QRS dynamic peak value will at this time
It will increase so that threshold value increases with it;Conversely, noise dynamic peak value increases so that threshold value reduces therewith.
5. the rhythm of the heart analysis method based on electrocardiogram as described in claim 1, which is characterized in that in the step S4
In, forward include 100 points on the basis of the position of QRS wave, backward include 150 points, each heart thus intercepted claps length
For 250 points.
6. the rhythm of the heart analysis method based on electrocardiogram as described in claim 1, which is characterized in that in the step S5
In, the characteristic of Analysis On Multi-scale Features can be extracted using wavelet transform function, obtains effective wavelet coefficient, clapped, obtained to characterize the heart
After the characteristic feature that each heart is clapped, the training and test that data set carries out model are divided using SVM classifier.
7. the rhythm of the heart analysis method based on electrocardiogram as claimed in claim 6, which is characterized in that in the step S5
In, the wavelet transform function uses db6 wavelet function.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910099538.5A CN109691994A (en) | 2019-01-31 | 2019-01-31 | A kind of rhythm of the heart analysis method based on electrocardiogram |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910099538.5A CN109691994A (en) | 2019-01-31 | 2019-01-31 | A kind of rhythm of the heart analysis method based on electrocardiogram |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109691994A true CN109691994A (en) | 2019-04-30 |
Family
ID=66234712
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910099538.5A Pending CN109691994A (en) | 2019-01-31 | 2019-01-31 | A kind of rhythm of the heart analysis method based on electrocardiogram |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109691994A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110742599A (en) * | 2019-11-01 | 2020-02-04 | 广东工业大学 | Electrocardiosignal feature extraction and classification method and system |
CN111345815A (en) * | 2020-02-11 | 2020-06-30 | 广州视源电子科技股份有限公司 | Method, device, equipment and storage medium for detecting QRS wave in electrocardiosignal |
CN111449645A (en) * | 2020-03-07 | 2020-07-28 | 河南大学 | Intelligent classification and identification method for electrocardiogram and heartbeat |
CN111528832A (en) * | 2020-05-28 | 2020-08-14 | 四川大学华西医院 | Arrhythmia classification method and validity verification method thereof |
CN111657918A (en) * | 2020-06-12 | 2020-09-15 | 电子科技大学 | Falling detection method and system combining electrocardio and inertial sensing data |
CN112450942A (en) * | 2020-11-26 | 2021-03-09 | 中国人民解放军南部战区总医院 | Electrocardiosignal monitoring method, system, device and medium |
CN112545501A (en) * | 2020-12-10 | 2021-03-26 | 徐岩 | Blood component concentration detection method and device |
CN112545526A (en) * | 2020-12-10 | 2021-03-26 | 青岛大爱慈康智能医疗科技有限公司 | Electrocardiosignal detection method and device |
CN113288169A (en) * | 2021-05-26 | 2021-08-24 | 东软集团股份有限公司 | Method, device and equipment for identifying waveform of electrocardiographic waveform signal |
CN113647959A (en) * | 2021-07-27 | 2021-11-16 | 东软集团股份有限公司 | Method, device and equipment for identifying waveform of electrocardiographic waveform signal |
CN113795195A (en) * | 2019-05-06 | 2021-12-14 | 美敦力公司 | Personalization of artificial intelligence models for analyzing heart rhythms |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1951320A (en) * | 2006-11-16 | 2007-04-25 | 上海交通大学 | Abnormal electrocardiogram recognition method based on ultra-complete characteristics |
WO2008007236A2 (en) * | 2006-06-07 | 2008-01-17 | Koninklijke Philips Electronics N.V. | Atrial fibrillation detection |
CN102085095A (en) * | 2009-12-07 | 2011-06-08 | 深圳市新元素医疗技术开发有限公司 | Method, system and electrocardioscanner for detecting ST segment in electrocardiogram |
CN105534505A (en) * | 2016-02-04 | 2016-05-04 | 湖南信息职业技术学院 | Health management equipment, monitoring method and health monitoring system |
CN107582046A (en) * | 2017-09-18 | 2018-01-16 | 山东正心医疗科技有限公司 | ECG real-time monitor method |
CN109044347A (en) * | 2018-07-11 | 2018-12-21 | 上海夏先机电科技发展有限公司 | Identify electrocardio wave image junctional escape beat method, apparatus, system and electronic equipment |
CN109077715A (en) * | 2018-09-03 | 2018-12-25 | 北京工业大学 | A kind of electrocardiosignal automatic classification method based on single lead |
-
2019
- 2019-01-31 CN CN201910099538.5A patent/CN109691994A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008007236A2 (en) * | 2006-06-07 | 2008-01-17 | Koninklijke Philips Electronics N.V. | Atrial fibrillation detection |
CN1951320A (en) * | 2006-11-16 | 2007-04-25 | 上海交通大学 | Abnormal electrocardiogram recognition method based on ultra-complete characteristics |
CN102085095A (en) * | 2009-12-07 | 2011-06-08 | 深圳市新元素医疗技术开发有限公司 | Method, system and electrocardioscanner for detecting ST segment in electrocardiogram |
CN105534505A (en) * | 2016-02-04 | 2016-05-04 | 湖南信息职业技术学院 | Health management equipment, monitoring method and health monitoring system |
CN107582046A (en) * | 2017-09-18 | 2018-01-16 | 山东正心医疗科技有限公司 | ECG real-time monitor method |
CN109044347A (en) * | 2018-07-11 | 2018-12-21 | 上海夏先机电科技发展有限公司 | Identify electrocardio wave image junctional escape beat method, apparatus, system and electronic equipment |
CN109077715A (en) * | 2018-09-03 | 2018-12-25 | 北京工业大学 | A kind of electrocardiosignal automatic classification method based on single lead |
Non-Patent Citations (1)
Title |
---|
高振东: "小波变换在远程心电仪系统中的应用", 《中国优秀硕士学位论文全文数据库(电子期刊)信息科技辑》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113795195A (en) * | 2019-05-06 | 2021-12-14 | 美敦力公司 | Personalization of artificial intelligence models for analyzing heart rhythms |
CN110742599A (en) * | 2019-11-01 | 2020-02-04 | 广东工业大学 | Electrocardiosignal feature extraction and classification method and system |
CN110742599B (en) * | 2019-11-01 | 2022-05-10 | 广东工业大学 | Electrocardiosignal feature extraction and classification method and system |
CN111345815A (en) * | 2020-02-11 | 2020-06-30 | 广州视源电子科技股份有限公司 | Method, device, equipment and storage medium for detecting QRS wave in electrocardiosignal |
CN111449645A (en) * | 2020-03-07 | 2020-07-28 | 河南大学 | Intelligent classification and identification method for electrocardiogram and heartbeat |
CN111528832A (en) * | 2020-05-28 | 2020-08-14 | 四川大学华西医院 | Arrhythmia classification method and validity verification method thereof |
CN111528832B (en) * | 2020-05-28 | 2023-04-18 | 四川大学华西医院 | Arrhythmia classification method and validity verification method thereof |
CN111657918A (en) * | 2020-06-12 | 2020-09-15 | 电子科技大学 | Falling detection method and system combining electrocardio and inertial sensing data |
CN111657918B (en) * | 2020-06-12 | 2021-09-24 | 电子科技大学 | Falling detection method and system combining electrocardio and inertial sensing data |
CN112450942A (en) * | 2020-11-26 | 2021-03-09 | 中国人民解放军南部战区总医院 | Electrocardiosignal monitoring method, system, device and medium |
CN112545526A (en) * | 2020-12-10 | 2021-03-26 | 青岛大爱慈康智能医疗科技有限公司 | Electrocardiosignal detection method and device |
CN112545501A (en) * | 2020-12-10 | 2021-03-26 | 徐岩 | Blood component concentration detection method and device |
CN113288169A (en) * | 2021-05-26 | 2021-08-24 | 东软集团股份有限公司 | Method, device and equipment for identifying waveform of electrocardiographic waveform signal |
CN113288169B (en) * | 2021-05-26 | 2024-05-17 | 东软集团股份有限公司 | Waveform identification method, device and equipment for electrocardiographic waveform signals |
CN113647959A (en) * | 2021-07-27 | 2021-11-16 | 东软集团股份有限公司 | Method, device and equipment for identifying waveform of electrocardiographic waveform signal |
CN113647959B (en) * | 2021-07-27 | 2024-01-12 | 东软集团股份有限公司 | Waveform identification method, device and equipment for electrocardiographic waveform signals |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109691994A (en) | A kind of rhythm of the heart analysis method based on electrocardiogram | |
CN107714023B (en) | Static electrocardiogram analysis method and device based on artificial intelligence self-learning | |
CN107951485B (en) | Ambulatory ECG analysis method and apparatus based on artificial intelligence self study | |
CN108478209B (en) | Electrocardio information dynamic monitoring method and dynamic monitoring system | |
CN107358196B (en) | Heart beat type classification method and device and electrocardiograph | |
Ge et al. | Cardiac arrhythmia classification using autoregressive modeling | |
Kannathal et al. | Cardiac state diagnosis using adaptive neuro-fuzzy technique | |
WO2019161609A1 (en) | Method for analyzing multi-parameter monitoring data and multi-parameter monitor | |
KR20070087787A (en) | Emotion classification system of real time bio signals and emotion classification method | |
Ranjan et al. | A unified approach of ECG signal analysis | |
CN107582040B (en) | Method and device for monitoring heart rhythm | |
Zhang et al. | Deep learning-based signal quality assessment for wearable ECGs | |
Al-Masri | Detecting ECG heartbeat abnormalities using artificial neural networks | |
Pang et al. | Real time heart ischemia detection in the smart home care system | |
CN115607167A (en) | Lightweight model training method, atrial fibrillation detection method, device and system | |
Ahmed et al. | Heart rate and inter-beat interval computation to diagnose stress using ECG sensor signal | |
Kalpana et al. | ECG feature extraction using principal component analysis for studying the effect of diabetes | |
Kelwade et al. | Comparative study of neural networks for prediction of cardiac arrhythmias | |
Gnanavel et al. | GUI Base Prediction of Heart Stroke Stages by Finding the Accuracy using Machine Learning Algorithm | |
Nanarkar et al. | A Survey on Classification and identification of Arrhythmia using Machine Learning techniques | |
Yasmeen et al. | Detection of real time QRS complex using wavelet transform | |
Chen et al. | Beat-to-beat heart rate detection based on seismocardiogram using BiLSTM network | |
Ghaffari et al. | Finding events of electrocardiogram and arterial blood pressure signals via discrete wavelet transform with modified scales | |
Revanth et al. | Detection of QRS Complexes in ECG Signal | |
Gu et al. | A Novel Diagnostic Algorithm for Heart Disease in ECG Monitoring System |
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 |
Application publication date: 20190430 |
|
RJ01 | Rejection of invention patent application after publication |