CN102835954A - Method for generating heart beating waveform template and treating ventricular premature beat detection and device - Google Patents
Method for generating heart beating waveform template and treating ventricular premature beat detection and device Download PDFInfo
- Publication number
- CN102835954A CN102835954A CN2012103285032A CN201210328503A CN102835954A CN 102835954 A CN102835954 A CN 102835954A CN 2012103285032 A CN2012103285032 A CN 2012103285032A CN 201210328503 A CN201210328503 A CN 201210328503A CN 102835954 A CN102835954 A CN 102835954A
- Authority
- CN
- China
- Prior art keywords
- template
- waveform
- correlation coefficient
- thought
- read
- 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
Images
Abstract
The invention discloses a method for generating a template and detecting a premature beat, and a device. The method comprises the following steps: sequentially and respectively putting M waveforms for measuring a heart beating in N templates relative to the waveforms by sequentially performing a relativity comparison between the waveforms for measuring the heart beating and the N templates, wherein N is less than M; and taking the template which obtains most heart beating times from the first template to the N template as a normal template. The method for detecting the premature beat comprises the following steps: pretreating an inputted electrocardiogram signal to obtain a pretreated signal; extracting the feather parameters of the heart beating for measuring from the pretreated signal, wherein the feather parameters include the width of a QRS wave, an existing RR interphase and a related average RR interphase; obtaining the waveform of the heart beating for measuring from the pretreated signal, and calculating the association coefficient between the waveform of the heart beating for measuring and the waveform of the template; and according to judging conditions that whether the association coefficient between the waveform for measuring the heart beating and the waveform of the template is less than a set threshold and whether the feather parameters are deviated from normal values, judging whether a ventricular premature beat exists.
Description
Technical field
The present invention relates to the medical electronics technical field, be specifically related to a kind of heart and clap the generation of waveform template, ventricular premature contraction detection processing method and device.
Background technology
Arrhythmia is the instable important indicator of reflection cardiac electrical activity.Arrhythmia can influence heart synchronous sequential, reduces the efficient of cardiac pumping.(Premature Ventricular Contraction is the most common a kind of in the abnormal heart rhythm PVC) to ventricular premature contraction, have the important clinical meaning, and most arrhythmia is all relevant with its existence.Therefore, the correct and fast detecting of PVC plays a crucial role to the performance that improves arrhythmia monitoring and dynamic cardiograph analysis system.
PVC detection method of the prior art generally has specialist system, feature extraction, template matching, neutral net and fuzzy technology etc.Wherein, the physical significance of neutral net method is difficult for understanding, and the time of training study is longer; The fuzzy technology method is in order to reach the purpose of fast detecting, and Rulemaking is simple relatively, is difficult to adapt to complicated electrocardiographic recording; And the method for feature extraction and template matching is comparatively commonly used, generally is used for the quick identification of PVC, and still, this method rule is too simple, and accuracy rate has much room for improvement.
Summary of the invention
The present invention provides a kind of heart to clap the generation of waveform template, ventricular premature contraction detects processing method and device, and it is more reasonable to make that heart bat waveform template generates, more accurate to the detection of ventricular premature contraction, and operand still less.
Technical scheme provided by the invention is following:
An object of the present invention is to provide a kind of heart and clap the waveform template generation method, may further comprise the steps:
Earlier first waveform of treating that thought-read is clapped is put in first template; Treat that with second the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare, calculate correlation coefficient, judge that whether said correlation coefficient is greater than first thresholding of setting; If; Treat that with said second it is first template class that the thought-read bat gathers, if not, then gathering is second template class; Treat that with the 3rd the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare again, calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Treat that with said the 3rd thought-read claps that to gather be first template class, if not, then again with said second template in the waveform clapped of the heart compare; Calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Then gathering is second template class, and if not, then gathering is the 3rd template class; By that analogy, successively M the waveform of treating that thought-read is clapped put into the N relevant with it template class, wherein N < M respectively;
One types that acquisition heart umber of beats in said first template class to the said N template class is maximum as normal template.
Preferably, when the heart umber of beats order of input during greater than M, the heart bat waveform that will import successively in waveform that the heart claps and first to N the template compares; Calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Treat that thought-read is clapped to gather and be this template class said; If not, then with next template relatively, gather and be the corresponding template class.
Preferably, when the quantity of template is completely set number N,, comprising if the next waveform correlation coefficient of treating thought-read bat and N template all smaller or equal to the thresholding of setting, then merges template or deletes processing:
Calculate the correlation coefficient that obtains between outer other N-1 template of the maximum template of heart umber of beats, find out maximum correlation coefficient; If maximum correlation coefficient is more than or equal to second thresholding of setting, two then that this maximum correlation coefficient is corresponding templates merge, otherwise the template of finding out the minimum number of N-1 template center's bat is deleted;
Classify the new thought-read bat of treating as template.
Preferably, clap waveform clustering after corresponding template when the new thought-read of treating, also comprise: 7/8 of waveform that will original template adds 1/8 of the waveform of treating the thought-read bat, forms the waveform of new template.
Another object of the present invention provides a kind of heart and claps waveform template generation module, comprising:
Modular unit, total N template is used to store N the dissimilar heart and claps waveform;
The template cluster cell is used for earlier first waveform of treating that thought-read is clapped being put into first template, treats that with second the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare; Calculate correlation coefficient; Whether judge said correlation coefficient greater than first thresholding of setting, if treat that with said second it is first template class that the thought-read bat gathers; If not, then gathering is second template class; Treat that with the 3rd the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare again, calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Treat that with said the 3rd thought-read claps that to gather be first template class, if not, then again with said second template in the waveform clapped of the heart compare; Calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Then gathering is second template class, and if not, then gathering is the 3rd template class; By that analogy, successively M the waveform of treating that thought-read is clapped put into the N relevant with it template class, wherein N < M respectively;
Judging unit, one types that acquisition heart umber of beats in said first template class to the said N template class is maximum as normal template.
Another object of the present invention provides a kind of ventricular premature contraction and detects processing method, comprising:
ECG signal to input carries out pretreatment, obtains pretreated signal;
From said pretreated signal, extract the characteristic parameter treat that thought-read is clapped, said characteristic parameter comprises the width of QRS ripple, current RR interval and related average RR interval;
From said pretreated signal, obtain the waveform of treating that thought-read is clapped, calculate the correlation coefficient of the waveform of treating waveform that thought-read is clapped and template;
According to the correlation coefficient of treating waveform that thought-read is clapped and the waveform of said template whether less than setting thresholding, and the average RR interval of the width of QRS ripple, current RR interval and association whether depart from first Rule of judgment of normal value, determine whether to be ventricular premature contraction.
Preferably, first Rule of judgment comprises:
Judge treat waveform that thought-read claps and the normal waveform of template correlation coefficient whether greater than 0.99 and current RR interval be in average RR interval 90%～120% between;
If the result is for being; To treat that thought-read is clapped to gather is normal template class, and it is normal to confirm as chamber property, if the result is not for; Judge that successively whether the correlation coefficient treat waveform that thought-read claps and waveform beyond the normal template is greater than 0.99; If then treat that thought-read is clapped to gather and be this template class, and calculate said by the correlation coefficient of the template class of cluster and said normal template class with said; Further, determine whether to be ventricular premature contraction according to being accounted for the ratio of average interval and second Rule of judgment of QRS wave width by the correlation coefficient of the template class of cluster and said normal template class, current RR interval.
Preferably; Second Rule of judgment comprises: further judge said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.96, perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and current RR interval be average interval 90%～120% between; Perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.5 and current RR interval be average interval 90%～120% between and the QRS wave width less than 120 milliseconds; If it is normal to confirm as chamber property,, further, determine whether to be ventricular premature contraction according to the ratio and the QRS wave width Rule of judgment that are accounted for average interval by the correlation coefficient of the template class of cluster and said normal template class, current RR interval if the result is not for.
Preferably, the 3rd Rule of judgment comprises: said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and the QRS width greater than 120 milliseconds; Perhaps by the correlation coefficient of the template class of cluster and said normal template class greater than 0.5 and current RR interval greater than average interval 120% or less than average interval 90%, if then confirm as ventricular premature contraction, otherwise be uncertain.
Another object of the present invention provides a kind of ventricular premature contraction and detects blood processor, comprising:
Pretreatment unit is used for the ECG signal of input is carried out pretreatment, obtains pretreated signal;
Feature extraction unit is used for extracting the characteristic parameter of treating that thought-read is clapped from said pretreated signal, and said characteristic parameter comprises the width of QRS ripple, current RR interval and related average RR interval;
The correlation coefficient computing unit is used for obtaining the waveform of treating that thought-read is clapped from said pretreated signal, calculates the correlation coefficient of the waveform of treating waveform that thought-read is clapped and template;
Judging unit, according to said correlation coefficient whether less than certain thresholding, and the width of QRS ripple, current RR interval and related average RR interval whether depart from the normal value Rule of judgment, determine whether to be ventricular premature contraction
Preferably, said judging unit specifically comprises following determination methods:
Judge treat waveform that thought-read claps and the normal waveform of template correlation coefficient whether greater than 0.99 and current RR interval be in average RR interval 90%～120% between; If the result is for being; To treat that thought-read is clapped to gather is normal template class, and it is normal to confirm as chamber property, if the result is not for; Whether the correlation coefficient of judging the waveform treat waveform that thought-read is clapped and other template successively is greater than 0.99; If then treat that thought-read is clapped to gather and be this template class, and calculate said by the correlation coefficient of the template class of cluster and said normal template class with said; If do not match with normal template; Further judge said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.96, perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and current RR interval be average interval 90%～120% between; Perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.5 and current RR interval be average interval 90%～120% between and the QRS wave width less than 120 milliseconds; If it is normal to confirm as chamber property, if the result confirms as and treats further judgement for not; Treat further judgement if confirm as, then further comprise: said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and the QRS width greater than 120 milliseconds; Perhaps by the correlation coefficient of the template class of cluster and said normal template class greater than 0.5 and current RR interval greater than average interval 120% or less than average interval 90%, if then confirm as ventricular premature contraction, otherwise be uncertain.
Technique scheme can find out, the embodiment of the invention is taked a plurality of templates in that template is set up in the process, makes the accurately situation of the normal waveform of reflection of template; After electrocardiosignal carried out pretreatment; Extracted parameters such as the width that comprises the QRS ripple of treating that thought-read is clapped, current RR interval and related average RR interval, and calculated the correlation coefficient of treating waveform that thought-read claps and the waveform of normal template, comprehensive then these parameters judge meet set require after; The result of ventricular premature contraction is confirmed as in output; Thereby can more accurately detect ventricular premature contraction PVC with respect to art methods, improve accuracy rate, and operand still less.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art; To do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below; Obviously, the accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills; Under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is that the embodiment of the invention one ventricular premature contraction detects process flow figure.
Fig. 2 is the framework flow chart that the embodiment of the invention two ventricular premature contractions detect processing method.
Fig. 3 is the particular flow sheet that the embodiment of the invention two ventricular premature contractions detect processing method.
Fig. 4 is the template matching flow chart in the embodiment of the invention two methods.
Fig. 5 is the template product process figure in the embodiment of the invention two methods.
Fig. 6 is R wave height, the QRS wave width marked graph in the embodiment of the invention two methods.
Fig. 7 is that the heart in the embodiment of the invention two methods is clapped and interval relation figure.
Fig. 8 is a template matching procedure chart in the embodiment of the invention two methods.
Fig. 9 is that embodiment of the invention ventricular premature contraction detects the blood processor structural representation.
The specific embodiment
To combine the accompanying drawing in the embodiment of the invention below, the technical scheme in the embodiment of the invention is carried out clear, intactly description, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills are not making all other embodiment that obtained under the creative work prerequisite, all belong to the scope of the present invention's protection.
The present invention provides a kind of heart to clap that the waveform template generates, ventricular premature contraction detects processing method and device, generates more fast, template easily, and it is more accurate to the detection of ventricular premature contraction to make, and operand still less.
Be elaborated respectively below in conjunction with accompanying drawing.
A kind of heart is clapped the waveform template generation method, may further comprise the steps:
Earlier first waveform of treating that thought-read is clapped is put in first template; Treat that with second the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare, calculate correlation coefficient, judge that whether said correlation coefficient is greater than first thresholding of setting; If; Treat that with said second it is first template class that the thought-read bat gathers, if not, then gathering is second template class; Treat that with the 3rd the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare again, calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Treat that with said the 3rd thought-read claps that to gather be first template class, if not, then again with said second template in the waveform clapped of the heart compare; Calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Then gathering is second template class, and if not, then gathering is the 3rd template class; By that analogy, successively M the waveform of treating that thought-read is clapped put into the N relevant with it template class, wherein N < M respectively;
One types that acquisition heart umber of beats in said first template class to the said N template class is maximum as normal template.
As embodiment, first thresholding>0.8, preferred 0.95.
As an embodiment M=10, N=8.
Template is along with the new arrival that thought-read is clapped of treating, constantly real-time update.When the heart umber of beats order of input during, will import waveform that the heart claps successively and compare the calculating correlation coefficient with heart bat waveform in first to N template greater than M; Judge that whether said correlation coefficient is greater than first thresholding of setting; If treat that thought-read is clapped to gather and be this template class said, if not; Then with next template relatively, gather and be the corresponding template class.
When the quantity of template is completely set number N,, comprising if the new waveform correlation coefficient of treating thought-read bat and N template all smaller or equal to the thresholding of setting, then merges template or deletes processing:
Calculate the correlation coefficient that obtains between outer other N-1 template of the maximum template of heart umber of beats, find out maximum correlation coefficient; If maximum correlation coefficient is more than or equal to second thresholding of setting, two then that this maximum correlation coefficient is corresponding templates merge, otherwise the template of finding out the minimum number of N-1 template center's bat is deleted;
Classify the new thought-read bat of treating as template.
As embodiment, second thresholding>0.7, be preferably 0.95.
Clap waveform clustering after corresponding template when the new thought-read of treating, also comprise: 7/8 of waveform that will original template adds 1/8 of the waveform of treating the thought-read bat, forms the waveform of new template.
A kind of heart is clapped waveform template generation module, comprising:
Modular unit, total N template is used to store N the dissimilar heart and claps waveform;
The template cluster cell is used for earlier first waveform of treating that thought-read is clapped being put into first template, treats that with second the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare; Calculate correlation coefficient; Whether judge said correlation coefficient greater than first thresholding of setting, if treat that with said second it is first template class that the thought-read bat gathers; If not, then gathering is second template class; Treat that with the 3rd the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare again, calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Treat that with said the 3rd thought-read claps that to gather be first template class, if not, then again with said second template in the waveform clapped of the heart compare; Calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Then gathering is second template class, and if not, then gathering is the 3rd template class; By that analogy, successively M the waveform of treating that thought-read is clapped put into the N relevant with it template class, wherein N < M respectively;
Judging unit, one types that acquisition heart umber of beats in said first template class to the said N template class is maximum as normal template.
Fig. 1 is that the embodiment of the invention one ventricular premature contraction detects process flow figure.As shown in Figure 1, comprising:
Here the average RR interval of saying, be meant the average of setting number (for example 8) the RR interval that current RR interval is nearest.
What need explanation is that step 102 and 103 does not have inevitable ordering relation.Treat that thought-read is clapped premature beat detection processing and template renewal does not have sequencing to limit yet.
Can find, the embodiment of the invention after electrocardiosignal is carried out pretreatment, parameters such as the average RR interval of extracted the width that comprises the QRS ripple of treating that thought-read is clapped, treating that thought-read claps; And calculate the correlation coefficient of the waveform treat waveform that thought-read is clapped and template; After comprehensive then these parameters were judged and met the setting requirement, the result of ventricular premature contraction was confirmed as in output, thereby can more accurately detect ventricular premature contraction PVC with respect to art methods; Improved accuracy rate, and operand still less.
Fig. 2 is the framework flow chart that the embodiment of the invention two ventricular premature contractions detect processing method.
As shown in Figure 2, the entire process flow process comprises: behind the input signal, carry out Signal Pretreatment, again signal is carried out feature extraction, the input template matching system carries out template matching and logical judgment then, last output category result.Concrete:
Digitized electrocardiogram ECG signal carries out pretreatment, promptly carries out pretreatment through high and low pass filter, can be through pretreatment so that baseline drift obtain proofreading and correct, and suppressed high-frequency noise basically, disturb thereby reduce.Carry out feature extraction on this basis, promptly extract QRS wave characteristic parameter, can guarantee veracity of parameters.Because the main morphological characteristic of PVC is the roomy lopsided QRS wave group that occurs ahead of time, therefore the characteristic so RR interval (RR representes two intervals between the QRS ripple), QRS wave width are absolutely necessary extracts these as characteristic parameter.
In addition, when carrying out template matching, also further obtain it and treat that thought-read claps the correlation coefficient of waveform and template waveforms, judge, draw classification results through parametric synthesis such as RR interval, QRS wave width and correlation coefficient CC.
The inventive method is after data of every input, and the carry out PVC real-time by flow process shown in Figure 2 detects.When a heartbeat arrives, detect the QRS ripple, and measure its a stack features parameter, send into the template matching system then, draw the heart and clap classification results.When detecting, the inventive method postpones a heart claps, and when front center is clapped, returns the classification results that a last heart is clapped when detecting so.
Fig. 3 is the particular flow sheet that the embodiment of the invention two ventricular premature contractions detect processing method.As shown in Figure 3, comprise step:
Can comprise noises such as power frequency, myoelectricity, baseline drift in the electrocardiogram ECG signal of general input.Baseline drift is by kinetic low-frequency disturbance between breathing or electrode and human body, generally below 0.5Hz, can change the form of ST section among the ECG, influence the accuracy of parameter extraction, so the filtering baseline drift is very important.The inventive method is carried out Filtering Processing in order to reduce noise to input signal in advance, for example carries out high and low pass filter.
The present invention extracts treats that characteristic parameter that thought-read is clapped mainly comprises the QRS wave width treating thought-read and clap, current RR interval, related average RR interval.
Wherein, as shown in Figure 6, the width between Q ripple and the S ripple is the QRS wave width.Fig. 6 is R wave height in the embodiment of the invention two methods, QRS wave width marked graph.The RR interval, need last interval RR, current interval RR and back one interval RR, and it is as shown in Figure 7 with the relation that the heart is clapped, and Fig. 7 is that the heart in the embodiment of the invention two methods is clapped and interval relation figure.
Fig. 4 is the template matching flow chart in the embodiment of the invention two methods, and Fig. 8 has then shown the signal process of template matching.
Before introducing this flow chart, earlier relational language is defined.
Average RR interval, be meant the average of setting number (for example 8) the RR interval that current RR interval is nearest.
What need explanation is; Here the threshold value that compares that sets of correlation coefficient CC is as 0.95,0.99 etc.; The threshold values 90%～120% that compare with average RR interval etc. with 120 milliseconds of QRS width threshold values relatively etc., all are gained rule of thumb; Be not to immobilize, can be provided with according to result of the test.
As shown in Figure 4, to preceding M bat carrying out the earlier training study of signal, after study is accomplished the new-comer is treated the thought-read bat; Mate with normal template earlier; If satisfy correlation coefficient CC greater than 0.99, current RR interval be average RR interval 90%～120% between, mate successfully; Then gather and be normal template class, return normal; If coupling is unsuccessful, then successively with other template matching, if mate successfully, then gather and be this class template, if satisfy correlation coefficient CC more than or equal to 0.96 at this moment; Perhaps correlation coefficient greater than 0.78 and current RR interval be average RR interval 90%～120% between; Perhaps correlation coefficient CC greater than 0.5 and current RR interval be average RR interval 90%～120% between and the QRS wave width less than 120 milliseconds, then export normal result; If do not satisfy, but satisfy correlation coefficient CC greater than 0.78 and the QRS width greater than 120 milliseconds; Perhaps correlation coefficient CC greater than 0.5 and current RR interval greater than average interval 120%, perhaps correlation coefficient whether greater than 0.5 and current RR interval less than average interval 90%, then return the result who confirms PVC, if do not satisfy again, then return uncertain result.
Concrete, Fig. 4 comprises step:
The thought-read bat is treated in step 401, input.
Treat that the thought-read bat can be R wavefront 600ms, one section waveform of back 400ms.
The correlation coefficient CC parameter of waveform with the waveform of normal template of thought-read bat is treated in step 403, calculating.
The inventive method is learnt through preceding 10 waveforms to every segment signal data, obtains the waveform of normal template, each is treated that thought-read is clapped carry out cluster, obtains itself and the correlation coefficient CC of the waveform of normal template.What need explanation is, is with 10 waveforms for example but be not limited to this here.
The correlation coefficient computing formula of extraction of the present invention is following:
Wherein, N is the length of the number of winning the confidence, and refers to promptly that also with the QRS ripple be the signal number of gathering in the front and back, center a period of time (for example 320ms), and for example sample rate is 600, then N=320*600/1000=192; X (n); Y (n) is respectively the waveshape signal and the waveshape signal of treating that thought-read is clapped of template;
is respectively x (n), the meansigma methods of y (n).
Average RR interval, extracted acquisition in step 302.
Upgrade normal template according to the result of step 405 in this step.
After the cluster, template is upgraded, then adopted 7/8 of normal template waveforms to add to treat now 1/8 of waveform that thought-read is clapped, form the waveform of new normal template if satisfy condition.In addition; The maximum quantity of template can be made as M (for example being 8); When template number is expired, newly clap if having with the unmatched heart of waveform template, then template is merged or delete processing; Handling process is following: 1) calculate the correlation coefficient between other 7 templates except that normal template, find out maximum correlation coefficient; 2) if maximum correlation coefficient more than or equal to 0.80, two then that this maximum correlation coefficient is corresponding templates merge, and delete if maximum correlation coefficient, is then found out the template of the minimum number that 7 template center clap less than 0.80.
The result of PVC is confirmed as in step 412, output.
Through above-mentioned judgement flow process, finally determine PVC.
Above template renewal and premature beat detect judges that not having sequencing concerns, should not be limited to the foregoing description.
Fig. 5 is the template product process figure in the embodiment of the invention two methods.
Template generative process of the present invention adopts altogether and sets number (for example 8) template, and a QRS ripple is placed in each template the inside, and each template has a template waveforms.Learn preceding ten hearts and clap, QRS ripple cluster forms template set, and the templates that cluster is maximum are as the advantage template, as later ECG signal optimum object relatively, also promptly as the normal template that is used for comparison.
Concrete, as shown in Figure 5, the template generative process comprises step:
The thought-read bat is treated in step 501, input.
Step 502, first waveform of treating that thought-read is clapped is put in first template, second waveform of treating that the waveform that thought-read claps and the heart in first template are clapped compared the calculating correlation coefficient.
Step 503, according to the parameter comparative result, judge whether to satisfy correlation coefficient CC greater than 0.95, if, get into step 504, if not, get into step 505.
Step 504, because satisfy correlation coefficient CC greater than 0.95, therefore treat that with second thought-read claps that to gather be first template class.Get into step 506.
Step 505, because do not satisfy correlation coefficient CC greater than 0.95, therefore treat that with second waveform that thought-read claps carries out correlation ratio with the waveform of other templates successively, if relevant, then gather and be this template class, also be other types.Get into step 507.
Step 506, new template more.Get into step 507.
More the description in the mode of new template and the earlier figures 4 is similar, repeats no more here.
Step 507, judgement treat whether the thought-read bat has been imported N and clapped, if, get into step 508, if not, return step 501 input bat newly.
N in this step claps as required and sets.
Step 508, will obtain the maximum template of heart umber of beats, promptly as being used for and the template of treating that waveform that thought-read is clapped compares as normal template.
This step is that first template class is obtained maximum one type of heart umber of beats to the said N template class as normal template.
Can find from the said method flow process; The inventive method has following beneficial effect: the embodiment of the invention is after carrying out pretreatment to electrocardiosignal; Extracted parameters such as the width that comprises the QRS ripple of treating that thought-read is clapped, current RR interval and related average RR interval, and calculated the correlation coefficient of treating waveform that thought-read claps and the waveform of normal template, comprehensive then these parameters judge meet set require after; The result of ventricular premature contraction is confirmed as in output; Thereby can more accurately detect ventricular premature contraction PVC with respect to art methods, improve accuracy rate, and operand still less.
The present invention is corresponding also to provide a kind of ventricular premature contraction to detect blood processor.
Fig. 9 is embodiment of the invention apparatus structure sketch map, and is as shown in Figure 9, and this device comprises:
Pretreatment unit 91 is used for the ECG signal of input is carried out pretreatment, obtains pretreated signal;
Feature extraction unit 92 is used for extracting the characteristic parameter of treating that thought-read is clapped from said pretreated signal, and said characteristic parameter comprises the width of QRS ripple, current RR interval and related average RR interval;
Correlation coefficient computing unit 93 is used for obtaining the waveform of treating that thought-read is clapped from said pretreated signal, and the waveform of thought-read bat and the correlation coefficient of the waveform of normal template are treated in calculating;
Judging unit 93, according to said correlation coefficient whether less than certain thresholding, and the width of QRS ripple, current RR interval and related average RR interval whether depart from the normal value Rule of judgment, determine whether to be ventricular premature contraction.
Further, judging unit comprises:
Judge treat waveform that thought-read claps and the normal waveform of template correlation coefficient whether greater than 0.99 and current RR interval be in average RR interval 90%～120% between; If the result is for being; To treat that thought-read is clapped to gather is normal template class, and it is normal to confirm as chamber property, if the result is not for; Whether the correlation coefficient of judging the waveform treat waveform that thought-read is clapped and other template successively is greater than 0.99; If then treat that thought-read is clapped to gather and be this template class, and calculate said by the correlation coefficient of the template class of cluster and said normal template class with said; If do not match with normal template; Further judge said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.96, perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and current RR interval be average interval 90%～120% between; Perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.5 and current RR interval be average interval 90%～120% between and the QRS wave width less than 120 milliseconds; If it is normal to confirm as chamber property, if the result confirms as and treats further judgement for not; Treat further judgement if confirm as, then further comprise: said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and the QRS width greater than 120 milliseconds; Perhaps by the correlation coefficient of the template class of cluster and said normal template class greater than 0.5 and current RR interval greater than average interval 120% or less than average interval 90%, if then confirm as ventricular premature contraction, otherwise be uncertain.
More than to the scheme that the embodiment of the invention provided, carried out detailed introduction, used concrete example among this paper principle of the present invention and embodiment set forth, the explanation of above embodiment just is used for helping to understand method of the present invention and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, the part that on the specific embodiment and range of application, all can change, in sum, this description should not be construed as limitation of the present invention.
Claims (10)
1. a heart is clapped the waveform template generation method, it is characterized in that, may further comprise the steps:
Earlier first waveform of treating that thought-read is clapped is put in first template; Treat that with second the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare, calculate correlation coefficient, judge that whether said correlation coefficient is greater than first thresholding of setting; If; Treat that with said second it is first template class that the thought-read bat gathers, if not, then gathering is second template class; Treat that with the 3rd the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare again, calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Treat that with said the 3rd thought-read claps that to gather be first template class, if not, then again with said second template in the waveform clapped of the heart compare; Calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Then gathering is second template class, and if not, then gathering is the 3rd template class; By that analogy, successively M the waveform of treating that thought-read is clapped put into the N relevant with it template class, wherein N < M respectively;
One types that acquisition heart umber of beats in said first template class to the said N template class is maximum as normal template.
2. the heart according to claim 1 is clapped the waveform template generation method, it is characterized in that, may further comprise the steps:
When the heart umber of beats order of input during, will import waveform that the heart claps successively and compare the calculating correlation coefficient with heart bat waveform in first to N template greater than M; Judge that whether said correlation coefficient is greater than first thresholding of setting; If treat that thought-read is clapped to gather and be this template class said, if not; Then with next template relatively, gather and be the corresponding template class.
3. the heart according to claim 1 and 2 is clapped the waveform template generation method, and it is characterized in that: said method also comprises
When the quantity of template is completely set number N,, comprising if the next waveform correlation coefficient of treating thought-read bat and N template all smaller or equal to the thresholding of setting, then merges template or deletes processing:
Calculate the correlation coefficient that obtains between outer other N-1 template of the maximum template of heart umber of beats, find out maximum correlation coefficient; If maximum correlation coefficient is more than or equal to second thresholding of setting, two then that this maximum correlation coefficient is corresponding templates merge, otherwise the template of finding out the minimum number of N-1 template center's bat is deleted;
Classify the new thought-read bat of treating as template.
4. the heart according to claim 1 and 2 is clapped the waveform template generation method, and it is characterized in that: said method also comprises:
Clap waveform clustering after corresponding template when the new thought-read of treating, also comprise: 7/8 of waveform that will original template adds 1/8 of the waveform of treating the thought-read bat, forms the waveform of new template.
5. a heart is clapped waveform template generation module, it is characterized in that, comprising:
Modular unit, total N template is used to store N the dissimilar heart and claps waveform;
The template cluster cell is used for earlier first waveform of treating that thought-read is clapped being put into first template, treats that with second the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare; Calculate correlation coefficient; Whether judge said correlation coefficient greater than first thresholding of setting, if treat that with said second it is first template class that the thought-read bat gathers; If not, then gathering is second template class; Treat that with the 3rd the waveform of thought-read bat and the waveform that the heart in said first template is clapped compare again, calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Treat that with said the 3rd thought-read claps that to gather be first template class, if not, then again with said second template in the waveform clapped of the heart compare; Calculate correlation coefficient, whether judge said correlation coefficient greater than first thresholding of setting, if; Then gathering is second template class, and if not, then gathering is the 3rd template class; By that analogy, successively M the waveform of treating that thought-read is clapped put into the N relevant with it template class, wherein N < M respectively;
Judging unit, one types that acquisition heart umber of beats in said first template class to the said N template class is maximum as normal template.
6. a ventricular premature contraction detects processing method, it is characterized in that, comprising:
ECG signal to input carries out pretreatment, obtains pretreated signal;
From said pretreated signal, extract the characteristic parameter treat that thought-read is clapped, said characteristic parameter comprises the width of QRS ripple, current RR interval and related average RR interval;
From said pretreated signal, obtain the waveform of treating that thought-read is clapped, the correlation coefficient of the waveform of the waveform of thought-read bat and the template that any described heart of claim 1 to 4 is clapped the acquisition of waveform template generation method is treated in calculating;
According to the correlation coefficient of treating waveform that thought-read is clapped and the waveform of said template whether less than setting thresholding, and the average RR interval of the width of QRS ripple, current RR interval and association whether depart from first Rule of judgment of normal value, determine whether to be ventricular premature contraction.
7. method according to claim 6 is characterized in that:
Said first Rule of judgment comprises:
Judge treat waveform that thought-read claps and the normal waveform of template correlation coefficient whether greater than 0.99 and current RR interval be in average RR interval 90%～120% between;
If the result is for being; To treat that thought-read is clapped to gather is normal template class, and it is normal to confirm as chamber property, if the result is not for; Judge that successively whether the correlation coefficient treat waveform that thought-read claps and waveform beyond the normal template is greater than 0.99; If then treat that thought-read is clapped to gather and be this template class, and calculate said by the correlation coefficient of the template class of cluster and said normal template class with said; Further, determine whether to be ventricular premature contraction according to being accounted for the ratio of average interval and second Rule of judgment of QRS wave width by the correlation coefficient of the template class of cluster and said normal template class, current RR interval.
8. method according to claim 7 is characterized in that:
Said second Rule of judgment comprises: further judge said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.96; Perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and current RR interval be average interval 90%～120% between; Perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.5 and current RR interval be average interval 90%～120% between and the QRS wave width less than 120 milliseconds; If it is normal to confirm as chamber property,, further, determine whether to be ventricular premature contraction according to being accounted for the ratio of average interval and the 3rd Rule of judgment of QRS wave width by the correlation coefficient of the template class of cluster and said normal template class, current RR interval if the result is not for.
9. method according to claim 8 is characterized in that:
Said the 3rd Rule of judgment comprises: said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and the QRS width greater than 120 milliseconds; Perhaps by the correlation coefficient of the template class of cluster and said normal template class greater than 0.5 and current RR interval greater than average interval 120% or less than average interval 90%, if then confirm as ventricular premature contraction, otherwise be uncertain.
10. a ventricular premature contraction detects blood processor, it is characterized in that, comprising:
Pretreatment unit is used for the ECG signal of input is carried out pretreatment, obtains pretreated signal;
Feature extraction unit is used for extracting the characteristic parameter of treating that thought-read is clapped from said pretreated signal, and said characteristic parameter comprises the width of QRS ripple, current RR interval and related average RR interval;
The correlation coefficient computing unit is used for obtaining the waveform of treating that thought-read is clapped from said pretreated signal, and the correlation coefficient of the waveform of the waveform of thought-read bat and the template that any described heart of claim 1 to 4 is clapped the acquisition of waveform template generation method is treated in calculating;
Judging unit, judge treat waveform that thought-read claps and the normal waveform of template correlation coefficient whether greater than 0.99 and current RR interval be in average RR interval 90%～120% between; If the result is for being; To treat that thought-read is clapped to gather is normal template class, and it is normal to confirm as chamber property, if the result is not for; Whether the correlation coefficient of judging the waveform treat waveform that thought-read is clapped and other template successively is greater than 0.99; If then treat that thought-read is clapped to gather and be this template class, and calculate said by the correlation coefficient of the template class of cluster and said normal template class with said; If do not match with normal template; Further judge said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.96, perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and current RR interval be average interval 90%～120% between; Perhaps said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.5 and current RR interval be average interval 90%～120% between and the QRS wave width less than 120 milliseconds; If it is normal to confirm as chamber property, if the result confirms as and treats further judgement for not; Treat further judgement if confirm as, then further comprise: said by the correlation coefficient of the template class of cluster and said normal template class whether greater than 0.78 and the QRS width greater than 120 milliseconds; Perhaps by the correlation coefficient of the template class of cluster and said normal template class greater than 0.5 and current RR interval greater than average interval 120% or less than average interval 90%, if then confirm as ventricular premature contraction, otherwise be uncertain.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210328503.2A CN102835954B (en) | 2012-09-07 | 2012-09-07 | Method for generating heart beating waveform template and treating ventricular premature beat detection and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210328503.2A CN102835954B (en) | 2012-09-07 | 2012-09-07 | Method for generating heart beating waveform template and treating ventricular premature beat detection and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102835954A true CN102835954A (en) | 2012-12-26 |
| CN102835954B CN102835954B (en) | 2015-03-11 |
Family
ID=47363880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210328503.2A Active CN102835954B (en) | 2012-09-07 | 2012-09-07 | Method for generating heart beating waveform template and treating ventricular premature beat detection and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102835954B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104398256A (en) * | 2014-11-13 | 2015-03-11 | 北京海思敏医疗技术有限公司 | Method and device for detecting electrocardio waveforms through computer |
| CN106108880A (en) * | 2016-06-28 | 2016-11-16 | 吉林大学 | A kind of heart claps automatic identifying method and system |
| CN107397547A (en) * | 2017-08-01 | 2017-11-28 | 深圳大学 | A kind of ECG typical case's heart beat template generation method and system |
| CN107456227A (en) * | 2017-08-16 | 2017-12-12 | 北京蓬阳丰业医疗设备有限公司 | Full lead electrocardiogram cluster template system and method |
| CN107495960A (en) * | 2017-01-19 | 2017-12-22 | 山东医联万家健康科技有限公司 | A kind of heart real time signal monitoring processing method |
| CN107529998A (en) * | 2015-04-23 | 2018-01-02 | 美敦力公司 | For determining the method and device of VPB in medical monitoring equipment |
| CN107714033A (en) * | 2016-08-10 | 2018-02-23 | 韦伯斯特生物官能(以色列)有限公司 | ECG signal of the identification with same modality |
| CN109288515A (en) * | 2018-11-14 | 2019-02-01 | 东南大学 | Periodical monitoring method and device based on premature beat signal in wearable ECG signal |
| CN109394206A (en) * | 2018-11-14 | 2019-03-01 | 东南大学 | Method of real-time and its device based on premature beat signal in wearable ECG signal |
| CN109948396A (en) * | 2017-12-20 | 2019-06-28 | 深圳市理邦精密仪器股份有限公司 | A kind of beat classification method, beat classification device and electronic equipment |
| WO2019140604A1 (en) * | 2018-01-18 | 2019-07-25 | 深圳迈瑞生物医疗电子股份有限公司 | Method for analyzing arrhythmia in real time, electrocardiograph monitoring device and storage medium |
| CN110327031A (en) * | 2018-11-29 | 2019-10-15 | 武汉中旗生物医疗电子有限公司 | A method of removal electrocardiosignal motion artifacts |
| CN111053551A (en) * | 2019-12-27 | 2020-04-24 | 深圳邦健生物医疗设备股份有限公司 | RR interval electrocardio data distribution display method, device, computer equipment and medium |
| CN112528783A (en) * | 2020-11-30 | 2021-03-19 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram heartbeat data clustering method and device, electronic equipment and medium |
| CN112842349A (en) * | 2021-02-20 | 2021-05-28 | 无锡市中健科仪有限公司 | Intelligent analysis method for supraventricular premature beat based on attention transfer mechanism |
| CN112971800A (en) * | 2021-01-27 | 2021-06-18 | 东南大学 | Deep learning-based electrocardio premature beat signal processing method, module and device |
| CN113180687A (en) * | 2021-04-29 | 2021-07-30 | 深圳邦健生物医疗设备股份有限公司 | Multi-lead dynamic heartbeat real-time classification method, device, equipment and storage medium |
| CN113712525A (en) * | 2020-05-21 | 2021-11-30 | 深圳市理邦精密仪器股份有限公司 | Physiological parameter processing method and device and medical equipment |
| WO2021253709A1 (en) * | 2020-06-17 | 2021-12-23 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram heartbeat classification method and apparatus, and electronic device and medium |
| CN114027853A (en) * | 2021-12-16 | 2022-02-11 | 安徽心之声医疗科技有限公司 | QRS complex detection method, device, medium and equipment based on feature template matching |
| CN114224353A (en) * | 2022-02-21 | 2022-03-25 | 深圳泰和智能医疗科技有限公司 | Electrocardio detection classification method based on body temperature monitor |
| CN116350199A (en) * | 2023-05-31 | 2023-06-30 | 合肥心之声健康科技有限公司 | Dynamic electrocardiogram and heart beat template generation method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2103253A1 (en) * | 2008-03-18 | 2009-09-23 | BIOTRONIK CRM Patent AG | Device, method and computer-readable storage medium for SVT and VT Classification |
| CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
| CN101953682A (en) * | 2010-10-15 | 2011-01-26 | 张辉 | Heartbeat detection method based on cuff device |
-
2012
- 2012-09-07 CN CN201210328503.2A patent/CN102835954B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2103253A1 (en) * | 2008-03-18 | 2009-09-23 | BIOTRONIK CRM Patent AG | Device, method and computer-readable storage medium for SVT and VT Classification |
| CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
| CN101953682A (en) * | 2010-10-15 | 2011-01-26 | 张辉 | Heartbeat detection method based on cuff device |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104398256B (en) * | 2014-11-13 | 2017-01-11 | 北京海思敏医疗技术有限公司 | Method and device for detecting electrocardio waveforms through computer |
| CN104398256A (en) * | 2014-11-13 | 2015-03-11 | 北京海思敏医疗技术有限公司 | Method and device for detecting electrocardio waveforms through computer |
| CN107529998A (en) * | 2015-04-23 | 2018-01-02 | 美敦力公司 | For determining the method and device of VPB in medical monitoring equipment |
| CN107529998B (en) * | 2015-04-23 | 2021-03-09 | 美敦力公司 | Method and apparatus for determining ventricular premature beats in a medical monitoring device |
| CN106108880A (en) * | 2016-06-28 | 2016-11-16 | 吉林大学 | A kind of heart claps automatic identifying method and system |
| CN107714033A (en) * | 2016-08-10 | 2018-02-23 | 韦伯斯特生物官能(以色列)有限公司 | ECG signal of the identification with same modality |
| CN107495960A (en) * | 2017-01-19 | 2017-12-22 | 山东医联万家健康科技有限公司 | A kind of heart real time signal monitoring processing method |
| CN107397547A (en) * | 2017-08-01 | 2017-11-28 | 深圳大学 | A kind of ECG typical case's heart beat template generation method and system |
| CN107456227A (en) * | 2017-08-16 | 2017-12-12 | 北京蓬阳丰业医疗设备有限公司 | Full lead electrocardiogram cluster template system and method |
| CN107456227B (en) * | 2017-08-16 | 2021-03-30 | 北京蓬阳丰业医疗设备有限公司 | Full-lead electrocardiogram clustering template system and method |
| CN109948396B (en) * | 2017-12-20 | 2021-07-23 | 深圳市理邦精密仪器股份有限公司 | Heart beat classification method, heart beat classification device and electronic equipment |
| CN109948396A (en) * | 2017-12-20 | 2019-06-28 | 深圳市理邦精密仪器股份有限公司 | A kind of beat classification method, beat classification device and electronic equipment |
| WO2019140604A1 (en) * | 2018-01-18 | 2019-07-25 | 深圳迈瑞生物医疗电子股份有限公司 | Method for analyzing arrhythmia in real time, electrocardiograph monitoring device and storage medium |
| US11596343B2 (en) | 2018-01-18 | 2023-03-07 | Shenzhen Mindray Biomedical Electronics Co., Ltd. | Method for analyzing arrhythmia in real time, electrocardiogram monitoring device and storage medium |
| CN109288515A (en) * | 2018-11-14 | 2019-02-01 | 东南大学 | Periodical monitoring method and device based on premature beat signal in wearable ECG signal |
| CN109394206A (en) * | 2018-11-14 | 2019-03-01 | 东南大学 | Method of real-time and its device based on premature beat signal in wearable ECG signal |
| CN109288515B (en) * | 2018-11-14 | 2021-06-22 | 东南大学 | Periodicity monitoring method and device based on premature beat signal in wearable electrocardiosignal |
| CN110327031A (en) * | 2018-11-29 | 2019-10-15 | 武汉中旗生物医疗电子有限公司 | A method of removal electrocardiosignal motion artifacts |
| CN111053551A (en) * | 2019-12-27 | 2020-04-24 | 深圳邦健生物医疗设备股份有限公司 | RR interval electrocardio data distribution display method, device, computer equipment and medium |
| CN113712525A (en) * | 2020-05-21 | 2021-11-30 | 深圳市理邦精密仪器股份有限公司 | Physiological parameter processing method and device and medical equipment |
| CN113876335A (en) * | 2020-06-17 | 2022-01-04 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram heart beat classification method, electrocardiogram heart beat classification device, electronic equipment and medium |
| CN113876335B (en) * | 2020-06-17 | 2023-05-02 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram and heart beat classification method, device, electronic equipment and medium |
| WO2021253709A1 (en) * | 2020-06-17 | 2021-12-23 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram heartbeat classification method and apparatus, and electronic device and medium |
| CN112528783A (en) * | 2020-11-30 | 2021-03-19 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram heartbeat data clustering method and device, electronic equipment and medium |
| CN112528783B (en) * | 2020-11-30 | 2024-04-16 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram and heart beat data clustering method, device, electronic equipment and medium |
| CN112971800A (en) * | 2021-01-27 | 2021-06-18 | 东南大学 | Deep learning-based electrocardio premature beat signal processing method, module and device |
| CN112971800B (en) * | 2021-01-27 | 2023-01-03 | 东南大学 | Deep learning-based electrocardio premature beat signal processing method, module and device |
| CN112842349B (en) * | 2021-02-20 | 2022-03-11 | 无锡市中健科仪有限公司 | Intelligent analysis method for supraventricular premature beat based on attention transfer mechanism |
| CN112842349A (en) * | 2021-02-20 | 2021-05-28 | 无锡市中健科仪有限公司 | Intelligent analysis method for supraventricular premature beat based on attention transfer mechanism |
| CN113180687A (en) * | 2021-04-29 | 2021-07-30 | 深圳邦健生物医疗设备股份有限公司 | Multi-lead dynamic heartbeat real-time classification method, device, equipment and storage medium |
| CN113180687B (en) * | 2021-04-29 | 2024-02-09 | 深圳邦健生物医疗设备股份有限公司 | Multi-guide dynamic heartbeat real-time classification method, device, equipment and storage medium |
| CN114027853B (en) * | 2021-12-16 | 2022-09-27 | 安徽心之声医疗科技有限公司 | QRS complex detection method, device, medium and equipment based on feature template matching |
| CN114027853A (en) * | 2021-12-16 | 2022-02-11 | 安徽心之声医疗科技有限公司 | QRS complex detection method, device, medium and equipment based on feature template matching |
| CN114224353A (en) * | 2022-02-21 | 2022-03-25 | 深圳泰和智能医疗科技有限公司 | Electrocardio detection classification method based on body temperature monitor |
| CN116350199A (en) * | 2023-05-31 | 2023-06-30 | 合肥心之声健康科技有限公司 | Dynamic electrocardiogram and heart beat template generation method and system |
| CN116350199B (en) * | 2023-05-31 | 2023-08-18 | 合肥心之声健康科技有限公司 | Dynamic electrocardiogram and heart beat template generation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102835954B (en) | 2015-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102835954B (en) | Method for generating heart beating waveform template and treating ventricular premature beat detection and device | |
| CN101766484B (en) | Method and equipment for identification and classification of electrocardiogram | |
| CN104887220B (en) | A kind of method and system that Fetal ECG signal is extracted by stomach wall electrocardiosignal | |
| Sepehri et al. | A novel method for pediatric heart sound segmentation without using the ECG | |
| Sadhukhan et al. | R-peak detection algorithm for ECG using double difference and RR interval processing | |
| Sayadi et al. | A model-based Bayesian framework for ECG beat segmentation | |
| CN101828918B (en) | Electrocardiosignal R peak detection method based on waveform characteristic matching | |
| CN101856225B (en) | Method for detecting R wave crest of electrocardiosignal | |
| CN108647565A (en) | A kind of data preprocessing method classified to electrocardiosignal based on deep learning model | |
| Panigrahy et al. | Extraction of fetal ECG signal by an improved method using extended Kalman smoother framework from single channel abdominal ECG signal | |
| CN104840186A (en) | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) | |
| CN104473631B (en) | A kind of based on non-negative blind separation Fetal ECG instantaneous heart rate recognition methods and system | |
| US9451901B2 (en) | Method and device for evaluation of myocardial damages based on the current density variations | |
| CN102579039B (en) | Method for detecting TWA (T wave alternans) in electrocardiogram | |
| CN102258368B (en) | Time-domain sparsity linear aliasing blind separation model discrimination method in fetal electrocardiogram detection | |
| CN106691402A (en) | Fatigue level analysis method and device based on pulse characteristics | |
| Hasan et al. | Fetal electrocardiogram extraction and R-peak detection for fetal heart rate monitoring using artificial neural network and Correlation | |
| CN105877739A (en) | Clinical examination method of electrocardio intelligent analyzing system | |
| WO2012173583A1 (en) | Method and device for evaluation of myocardial ischemia based on current density maps | |
| CN110192853A (en) | A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart | |
| CN106108850A (en) | The recognition methods of the interference data of ecg database and device | |
| CN105310688A (en) | Fetal ECG characteristic signal extraction method based on nonnegative blind separation | |
| CN114052681B (en) | Blood pressure monitoring method and system based on electrocardiograph interpretation system | |
| CN106725487A (en) | A kind of respiratory rate extracting method and device | |
| Kamath et al. | Modeling QRS complex in dECG |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 518102, Shenzhen, Guangdong Province, Baoan District, Xixiang Bao Road 168, Shenzhen famous industrial products display procurement center, block A, building seven Applicant after: Shenzhen Biocare Bio-Medical Equipment Co., Ltd. Address before: 518102, Shenzhen, Guangdong Province, Baoan District, Xixiang Bao Road 168, Shenzhen famous industrial products display procurement center, block A, building seven Applicant before: Shenzhen Biocare Electronics Co., Ltd. |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: APPLICANT; FROM: SHENZHEN BIOCARE ELECTRONICS CO., LTD. TO: SHENZHEN BIOCARE BIO-MEDICAL EQUIPMENT CO., LTD. |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |