CN115778402A - Method and system for identifying artifact of dynamic electrocardiosignal - Google Patents
Method and system for identifying artifact of dynamic electrocardiosignal Download PDFInfo
- Publication number
- CN115778402A CN115778402A CN202211540499.6A CN202211540499A CN115778402A CN 115778402 A CN115778402 A CN 115778402A CN 202211540499 A CN202211540499 A CN 202211540499A CN 115778402 A CN115778402 A CN 115778402A
- Authority
- CN
- China
- Prior art keywords
- data
- heart beat
- pseudo
- dynamic
- marked
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 239000013598 vector Substances 0.000 claims abstract description 43
- 238000007781 pre-processing Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000012706 support-vector machine Methods 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 27
- 238000001914 filtration Methods 0.000 claims description 26
- 238000010606 normalization Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 12
- 239000007787 solid Substances 0.000 claims description 8
- 230000000747 cardiac effect Effects 0.000 claims description 5
- 239000000284 extract Substances 0.000 abstract description 3
- 238000009412 basement excavation Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 230000002861 ventricular Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 208000000418 Premature Cardiac Complexes Diseases 0.000 description 6
- 230000001746 atrial effect Effects 0.000 description 6
- 238000000354 decomposition reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000003183 myoelectrical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 206010015856 Extrasystoles Diseases 0.000 description 2
- 241001325280 Tricardia watsonii Species 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012880 independent component analysis Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000001685 thyroid gland Anatomy 0.000 description 1
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a method and a system for identifying pseudo-errors of dynamic electrocardiosignals, wherein the method comprises the following steps: acquiring marked dynamic electrocardiogram data, wherein the marked dynamic electrocardiogram data comprise heart beat data, performing first preprocessing operation on the marked heart beat data, extracting a characteristic value of each preprocessed heart beat and normalizing the characteristic values to obtain a sample characteristic vector; inputting the sample feature vector into a pre-constructed support vector machine for training to generate a pseudo-error recognition model; carrying out second preprocessing operation on the acquired dynamic electrocardiogram data, extracting a characteristic value of each preprocessed heart beat and normalizing the characteristic value to obtain a heart beat characteristic vector; and inputting the heart beat feature vector into a pseudo-error recognition model, and taking an output result as a pseudo-error recognition result. The embodiment of the invention extracts the characteristics of the data to be analyzed by deep excavation, and the identification model is obtained by training by adopting a support vector machine and is used for pseudo-difference identification of dynamic electrocardiosignals, so that the identification accuracy and the algorithm robustness are improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for identifying artifact of dynamic electrocardiosignals.
Background
The dynamic electrocardiogram is a whole process of continuously recording the electrocardio activity of a patient for 24 hours or more in a daily life state through a dynamic electrocardiograph, the electrocardio information obtained by the recorder is input into a computer for processing, and a dynamic electrocardio report is printed out through manual editing, thereby providing a basis for diagnosing and treating diseases for clinic.
The dynamic electrocardiogram is collected in the daily life state of a patient, so that the dynamic electrocardiogram is inevitably interfered by different degrees in the recording process, including noise such as baseline drift, power frequency interference, electromyographic interference and the like. Although part of interference can be filtered by designing a related filter, the filter cannot completely eliminate interference introduced by motion and other reasons due to the similarity with the shape of a real heart beat, the interference is called as "pseudo-error", and the ventricular premature beat or the atrial premature beat is easily misjudged during program automatic analysis, so that the analysis and the diagnosis of doctors are influenced.
In the prior art, methods such as template matching clustering, high-order statistics, wavelet analysis and independent component analysis are mainly adopted for artifact identification, but the methods mainly utilize the characteristics of data to be analyzed, so that the identification accuracy is low, the stability is poor, and the effect is not ideal in practical clinical application.
The prior art therefore remains to be developed further.
Disclosure of Invention
Aiming at the technical problems, the embodiment of the invention provides a method and a system for identifying artifacts of dynamic electrocardiosignals, which can solve the technical problems that in the prior art, artifacts are identified by mainly adopting methods such as template matching clustering, high-order statistics, wavelet analysis, independent component analysis and the like, but the methods mainly utilize the characteristics of data to be analyzed, so that the identification accuracy is low and the stability is poor.
The first aspect of the embodiments of the present invention provides a method for identifying artifacts of a dynamic electrocardiographic signal, including:
acquiring marked dynamic electrocardiogram data, wherein the marked dynamic electrocardiogram data comprise heart beat data, and the types of the heart beat data comprise real solid beats and pseudo errors;
carrying out first preprocessing operation on the marked heart beat data, extracting a characteristic value of each preprocessed heart beat and carrying out normalization processing to obtain a sample characteristic vector;
inputting the sample feature vector into a pre-constructed support vector machine for training to generate a pseudo-error recognition model;
acquiring collected dynamic electrocardiogram data, performing second preprocessing operation on the collected dynamic electrocardiogram data, extracting a characteristic value of each preprocessed heartbeat, and performing normalization processing to obtain a heartbeat characteristic vector;
and inputting the heart beat feature vector into a pseudo-error recognition model, acquiring an output result of the pseudo-error recognition model, and taking the output result as a pseudo-error recognition result.
Optionally, the first preprocessing operation is performed on the marked heart beat data, and includes:
and sequentially carrying out template matching on the real heart beats and the pseudo-errors in the marked heart beat data according to positions, and counting the number of the heart beats in each template after the matching of all the marked data is finished.
Optionally, extracting a feature value of each preprocessed heartbeat and performing normalization processing to obtain a sample feature vector, where the method includes:
extracting a characteristic value of each preprocessed heart beat, wherein the characteristic value comprises a wavelet coefficient of the heart beat, the total number of the heart beats of the template, interval ratios of three intervals before and after the current heart beat, matching degree of the current heart beat and the previous and following heart beats, heart beat differential data information and low-frequency and high-frequency noise interference information;
and carrying out normalization processing on the extracted characteristic values to obtain sample characteristic vectors.
Optionally, the acquiring the acquired dynamic electrocardiographic data, and performing a second preprocessing operation on the acquired dynamic electrocardiographic data includes:
acquiring collected dynamic electrocardiogram data, and filtering the collected dynamic electrocardiogram data to generate filtered data;
performing heartbeat detection on the filtered data based on a differential threshold algorithm, and recording the position information of each heartbeat;
and performing cluster statistics on each heart beat, and counting the number of the heart beats of each template.
Optionally, the sequentially performing template matching on the real heart beat and the artifact in the marked heart beat data according to the position includes:
carrying out similarity calculation on the marked heart beat data and the existing template according to the position in sequence;
if the similarity is larger than or equal to the threshold value, judging that the heartbeat data belongs to the template, and updating the data in the template;
if the similarity is smaller than the threshold value, performing matching calculation with the next template;
and if the marked heartbeat data are not matched with all the templates, establishing a corresponding template based on the heartbeat data.
A second aspect of the embodiments of the present invention provides a system for identifying artifacts of a dynamic electrocardiographic signal, where the system includes: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of:
acquiring marked dynamic electrocardiogram data, wherein the marked dynamic electrocardiogram data comprise heart beat data, and the types of the heart beat data comprise real solid beats and pseudo errors;
carrying out first preprocessing operation on the marked heart beat data, extracting a characteristic value of each preprocessed heart beat, and carrying out normalization processing to obtain a sample characteristic vector;
inputting the sample feature vector into a pre-constructed support vector machine for training to generate a pseudo-error recognition model;
acquiring collected dynamic electrocardiogram data, performing second preprocessing operation on the collected dynamic electrocardiogram data, extracting a characteristic value of each preprocessed heartbeat, and performing normalization processing to obtain a heartbeat characteristic vector;
and inputting the heartbeat feature vector into a pseudo-error recognition model, acquiring an output result of the pseudo-error recognition model, and taking the output result as a pseudo-error recognition result.
Optionally, the computer program when executed by the processor implements the steps of:
and sequentially carrying out template matching on the real heart beats and the pseudo-errors in the marked heart beat data according to positions, and counting the number of the heart beats in each template after the matching of all the marked data is finished.
Optionally, the computer program when executed by the processor further implements the steps of:
extracting a characteristic value of each preprocessed heart beat, wherein the characteristic value comprises a wavelet coefficient of the heart beat, the total number of the heart beats of the template, the interval ratio of three intervals before and after the current heart beat, the matching degree of the current heart beat and the previous and subsequent heart beats, heart beat differential data information and low-frequency and high-frequency noise interference information;
and carrying out normalization processing on the extracted characteristic values to obtain sample characteristic vectors.
Optionally, the computer program when executed by the processor further implements the steps of:
acquiring collected dynamic electrocardiogram data, and filtering the collected dynamic electrocardiogram data to generate filtered data;
performing heartbeat detection on the filtered data based on a differential threshold algorithm, and recording the position information of each heartbeat;
and performing cluster statistics on each heart beat, and counting the number of the heart beats of each template.
A third aspect of the embodiments of the present invention provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by one or more processors, the computer-executable instructions may cause the one or more processors to perform the above-mentioned artifact identification method for dynamic electrocardiographic signals.
In the technical scheme provided by the embodiment of the invention, marked dynamic electrocardiogram data are obtained, the marked dynamic electrocardiogram data comprise heart beat data, first preprocessing operation is carried out on the marked heart beat data, and a characteristic value is extracted and normalized for each preprocessed heart beat to obtain a sample characteristic vector; inputting the sample feature vector into a pre-constructed support vector machine for training to generate a pseudo-error recognition model; carrying out second preprocessing operation on the acquired dynamic electrocardiogram data, extracting a characteristic value of each preprocessed heartbeat, and normalizing to obtain a heartbeat characteristic vector; and inputting the heart beat feature vector into a pseudo-error recognition model, and taking an output result as a pseudo-error recognition result. The embodiment of the invention extracts the characteristics of the data to be analyzed by deep excavation, adopts a support vector machine to train to obtain the recognition model, is used for pseudo-error recognition of dynamic electrocardiosignals, and improves the recognition accuracy and the algorithm robustness.
Drawings
Fig. 1 is a schematic flowchart of an embodiment of a method for identifying artifacts of a dynamic electrocardiographic signal according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a true heartbeat and a pseudo-difference of an embodiment of a method for identifying pseudo-difference of a dynamic electrocardiographic signal according to the present invention;
FIG. 3a is a schematic interval diagram illustrating an embodiment of a method for artifact identification of a dynamic electrocardiographic signal according to the present invention;
FIG. 3b is a schematic diagram illustrating the interval mapping of FIG. 3a according to an embodiment of the present invention;
FIG. 4a is a schematic diagram of an electrocardiographic waveform of an embodiment of a method for identifying artifacts of dynamic electrocardiographic signals according to the present invention;
FIG. 4b is a schematic diagram of a difference signal of an embodiment of a method for artifact identification of a dynamic electrocardiographic signal according to the present invention;
FIG. 5 is a schematic diagram of a high-frequency noise calculation range according to an embodiment of the method for identifying artifacts of dynamic electrocardiographic signals according to the present invention;
FIG. 6 is a flowchart illustrating an identification preprocessing according to an embodiment of a method for identifying artifacts of a dynamic electrocardiographic signal according to the present invention;
fig. 7 is a flow chart of QRS wave detection in an embodiment of a method for identifying artifacts of dynamic electrocardiographic signals according to the present invention;
fig. 8 is a schematic diagram of a hardware structure of another embodiment of the system for identifying artifact of dynamic electrocardiographic signals according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The following detailed description of embodiments of the invention refers to the accompanying drawings.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an embodiment of a method for identifying artifacts of a dynamic electrocardiographic signal according to the present invention. As shown in fig. 1, includes:
s100, obtaining marked dynamic electrocardiogram data, wherein the marked dynamic electrocardiogram data comprise heart beat data, and the types of the heart beat data comprise real solid beats and pseudo errors;
step S200, carrying out first preprocessing operation on the marked heart beat data, extracting a characteristic value of each preprocessed heart beat and carrying out normalization processing to obtain a sample characteristic vector;
s300, inputting the sample feature vector into a pre-constructed support vector machine for training to generate a pseudo-error recognition model;
s400, acquiring acquired dynamic electrocardiogram data, performing second preprocessing operation on the acquired dynamic electrocardiogram data, extracting a characteristic value of each preprocessed heartbeat, and performing normalization processing on each preprocessed heartbeat to obtain a heartbeat characteristic vector;
and S500, inputting the heartbeat feature vector into a pseudo-error recognition model, acquiring an output result of the pseudo-error recognition model, and taking the output result as a pseudo-error recognition result.
In specific implementation, the technical scheme of the invention is used for obtaining a training module of a recognition model and a recognition module applied to dynamic electrocardiosignal artifact recognition. The training module extracts characteristic values after preprocessing the marked electrocardiogram data, takes a plurality of characteristic values as input and carries out model training by using a support vector machine to finally obtain a pseudo-error recognition model. And in the identification module, preprocessing the acquired dynamic electrocardiogram data, extracting features by adopting a method consistent with that of the training module, finally performing artifact identification by using the model acquired by the training module, and outputting an artifact identification result.
Marking the real heart beat and the artifact mark in the dynamic electrocardiogram data; the method comprises the steps that a professional electrocardiograph marks real heartbeats (including normal heartbeats, ventricular heartbeats, atrial heartbeats and the like) and pseudo-errors in dynamic electrocardiographic data by means of software, and the obtained results are used as training samples, as shown in fig. 2, wherein the real solid heartbeats are marked as N (sinus heartbeats) and V (ventricular premature beats), and the pseudo-errors are marked as X (noise interference).
The real heart beat is a name relative to the artifact, and includes a normal heart beat, a ventricular heart beat, an atrial heart beat and the like. Wherein the normal heart beat includes sinus heart beat, left bundle branch and right bundle; atrial heartbeat includes atrial premature beat, atrial escape, etc.; ventricular beats include ventricular premature beat, ventricular escape, etc. N (sinus beats) and V (ventricular premature beats) described above are specific descriptions for fig. 2.
Performing cluster statistics on the marked real heart beats and the marked artifact, sequentially performing template matching on the real heart beats and the artifact of the dynamic electrocardiogram data according to positions, and counting the number of each template center beat after all data are matched;
extracting the characteristics of each heart beat to generate a training sample, wherein the extracted characteristic values comprise wavelet coefficients of the heart beats, the total number of the heart beats of the template, interval ratios of three intervals before and after the current heart beat, matching degree of the current heart beat and the previous and following heart beats, information of heart beat differential data and low-frequency and high-frequency noise interference information;
normalizing the extracted features to obtain feature vectors; and after the feature extraction is finished, training the obtained features by using a support vector machine as a classifier, taking the normalized feature vectors as input, and taking a radial basis function kernel as a kernel function to obtain a pseudo-error recognition model for the subsequent pseudo-error recognition.
Filtering the acquired dynamic electrocardiogram data, performing heartbeat detection on the filtered data by adopting a differential threshold method, recording the position information of each heartbeat, performing cluster statistics on each heartbeat, and counting the number of each template heartbeat;
after the preprocessing is finished, feature extraction is carried out on each heart beat (real heart beat and artifact), extracted features and methods are consistent with those of the training module, and extracted feature values are also subjected to normalization processing.
And inputting the normalized characteristic value into the recognition model obtained by the training module to obtain a final recognition result (real heart beat or pseudo error), and outputting the result to a user.
Further, performing a first preprocessing operation on the marked heartbeat data, including:
and sequentially carrying out template matching on the real heart beats and the pseudo-errors in the marked heart beat data according to positions, and counting the number of the heart beats in each template after the matching of all the marked data is finished.
In specific implementation, because the positions of the real heart beat and the artifact in the electrocardiogram data are marked, the training preprocessing is mainly used for carrying out cluster statistics on the real heart beat and the artifact. The method comprises the steps of sequentially carrying out template matching on the real heart beats and the pseudo-errors of the dynamic electrocardiogram data according to positions, and counting the number of the heart beats (the real heart beats and the pseudo-errors) of each template after all data are matched.
Further, the real heart beat and the artifact in the marked heart beat data are sequentially subjected to template matching according to positions, and the method comprises the following steps:
carrying out similarity calculation on the marked heart beat data and the existing template in sequence according to positions;
if the similarity is larger than or equal to the threshold value, judging that the heart beat data belongs to the template, and updating the data in the template;
if the similarity is smaller than the threshold value, performing matching calculation with the next template;
and if the marked heartbeat data are not matched with all the templates, establishing a corresponding template based on the heartbeat data.
When the method is specifically implemented, inputting a true solid beat or artifact data, sequentially carrying out similarity calculation with the existing template, if the result is greater than or equal to a threshold value, determining that the data belongs to the template, updating the data in the template, and otherwise, continuously carrying out matching calculation with the next template; and if the data is not matched with all the templates, establishing a new template based on the data.
Further, extracting a characteristic value of each preprocessed heart beat, wherein the characteristic value comprises a wavelet coefficient of the heart beat, the total number of the heart beats of the template, the interval ratio of three intervals before and after the current heart beat, the matching degree of the current heart beat and the previous and subsequent heart beats, heart beat difference data information and low-frequency and high-frequency noise interference information;
and carrying out normalization processing on the extracted characteristic values to obtain sample characteristic vectors.
In specific implementation, after pretreatment, feature extraction is performed on each heart beat (real heart beat and artifact), and the following feature values are mainly extracted:
1) Wavelet coefficient of heart beat
Selecting data of 1 second in total of 400ms before and 600ms after the position of the heartbeat to carry out 5-order wavelet decomposition, and taking an obtained wavelet coefficient as a characteristic value;
the wavelet transform is a signal analysis method, which can simultaneously perform time domain and frequency domain analysis and has the characteristics of time-frequency localization and multi-resolution. The multi-resolution analysis characteristic of wavelet transform is used to decompose the signal at different scales. The fundamental theory of wavelet transform is rather complex, involving a large number of difficult mathematical concepts and operations. From an application point of view, however, we can see the wavelet transform as a cascade of low-pass and high-pass filters, one after the other, followed by a down-sampling operation. Wavelet transform is also the signal obtained after a series of filtering and down-sampling operations, and these signals are also called wavelet coefficients. In this example, db6 of the parent wavelet Daubechies basis is used for wavelet decomposition, and after 5-scale wavelet decomposition, the obtained signal (wavelet coefficient) is used as a characteristic value.
2) Total number of heartbeats of the template
Taking the total number of heartbeats under the template where each heart beat is positioned as a characteristic value;
3) Interval ratio of 3 intervals before and after current heartbeat
As shown in fig. 3a and fig. 3b, R3 is the current heart beat, R0 to R2 are the first three heart beats, R4 to R6 are the last three heart beats, RR1 is the interval between the two heart beats of R0 and R1, the value is the position of R1 minus the position of R0, and other RR interval algorithms are similar. Acquiring 5 interval ratios as characteristic values by calculating the ratio between two adjacent intervals in the 6 intervals;
4) Matching degree of current heart beat and front and back heart beats
Respectively calculating the similarity of the current heartbeat and the previous heartbeat and the next heartbeat by adopting a similarity calculation method, and taking two calculated results as characteristic values;
5) Information of cardiac beat differential data
As shown in fig. 4a and 4b, difference data is obtained by difference operation of the electrocardiographic signals, a maximum difference position (point P1 in the figure) and a minimum difference position (point P0 in the figure) are searched on the difference data, and three values are calculated as feature values: the time interval between P0 and P1, and the magnitudes of points P0 and P1;
in this example, a backward difference operation is used, and the formula is as follows. Where D (n) is the difference result of the current point, X (n) is the signal value of the current point, and X (n-10 ms) is the signal value before 10 ms.
D(n)＝X(n)–X(n-10ms)
6) Low and high frequency noise interference information
And selecting data of 1 second in total of 400ms before and 600ms after the heart beat position to perform median filtering to extract low-frequency interference information, specifically searching the maximum value and the minimum value of the signal in a filtering signal obtained after the median filtering, and taking the result of subtracting the minimum value from the maximum value as the interference value of the low-frequency noise. As shown in fig. 5, the interference value calculation range of the high-frequency noise is such that, with the current heartbeat as a reference position, signal noise values having a length of 100ms are calculated, excluding 150ms before and after the reference position. The calculation method is to carry out second-order difference on the signals within 100ms, sum absolute values of difference results in sequence, and take the final sum result as a noise value. The interference value of the high-frequency noise is the maximum value of the two preceding and following noise values. And taking the low-frequency noise interference value and the high-frequency noise interference value as characteristic values.
The time in this embodiment is a time length for obtaining a more ideal result according to the current experiment, and other time lengths can be selected, but generally, it is not suitable to be too short or too long.
In this example, a second order backward difference is used, and the specific formula is as follows. Wherein, D2 (n) is the second order difference result of the current point, X (n) is the signal value of the current point, and X (n-5 ms) and X (n-10 ms) are the signal values before 5ms and 10ms, respectively.
D2(n)＝X(n)–2*X(n-5ms)+X(n-10ms)
And normalizing the characteristic values, mapping all the characteristic values to [0,1] to obtain a final characteristic vector, wherein the normalization can effectively improve the convergence speed of the algorithm. The method is to traverse all the characteristic values of the current heartbeat and search the maximum characteristic value FMax and the minimum characteristic value FMin. Then, the following formula is used to transform each eigenvalue, where FIn and FOut are the input eigenvalue and the transformed eigenvalue, respectively.
FOut＝(FIn-FMin)/(FMax-FMin)。
Further, acquiring the collected dynamic electrocardiographic data, and performing a second preprocessing operation on the collected dynamic electrocardiographic data, wherein the second preprocessing operation comprises:
acquiring collected dynamic electrocardiogram data, and filtering the collected dynamic electrocardiogram data to generate filtered data;
performing heartbeat detection on the filtering data based on a differential threshold algorithm, and recording the position information of each heartbeat;
and performing cluster statistics on each heart beat, and counting the number of the heart beats of each template.
In specific implementation, as shown in fig. 6, first, filtering is performed on the acquired electrocardiographic data to filter out noise interferences such as baseline drift, power frequency interference, electromyographic interference, and the like. Secondly, the filtered data is subjected to heartbeat detection by adopting a differential threshold method, and the position information of each heartbeat (real heartbeat and artifact) is recorded. And finally, performing cluster statistics by adopting a method consistent with training pretreatment, and counting the number of central beats (real heart beats and artifacts) of each template.
And filtering the baseline drift, the power frequency interference and the myoelectric interference by adopting different filtering methods.
A baseline drift. Baseline wander is generally due to respiration of the subject, electrode wander, etc. during a cardiac measurement. Features low frequency (generally below 0.7 Hz), smooth change and large change amplitude. In this example, median filtering is used to filter the baseline wander interference, a window with a length of 800ms is used to obtain the median of the signal in the window, and the original signal minus the median signal is used as the final filtering result. Specifically, each sampling point in the electrocardiosignal is processed as follows in turn: and calculating the median of signals in a window of 800ms in total before 400ms and after 400ms of the current point, and subtracting the median from the value of the current point to obtain the median filtering result of the current point.
And (4) power frequency interference. The power frequency interference is mainly caused by the electromagnetic field action generated by an alternating current power supply, a loop circuit between the electrocardio acquisition instrument and a human body and other factors, and the frequency is 50Hz or 60Hz. The power frequency interference mainly consists of sinusoidal signals and is represented as regularly distributed raised grains on an electrocardiogram. In this example, the trap filter is used to eliminate the power frequency interference noise, and the filtering formula is as follows. Wherein Y (n) is the filtering result, Y (n-20 ms) is the filtering result of the previous 20ms, X (n) is the signal value of the current point, and X (n-20 ms) is the signal value of the previous 20 ms.
Y(n)＝0.86*Y(n-20ms)+0.93*(X(n)–X(n-20ms))
Myoelectric interference. The electromyographic interference is caused by diseases such as thyroid gland, muscle excitation and contraction, stress cold stimulation of human body and other factors, and the frequency is between 5 and 2000 Hz. Myoelectric interference belongs to a high-frequency interference signal relative to an electrocardiosignal. In this example, a low-pass filter is used to eliminate the electromyographic interference noise, and the filtering formula is as follows. Wherein Y (n) is the filtering result, Y (n-1) and Y (n-2) are the filtering results of the previous two points, X (n) is the signal value of the current point, and X (n-10 ms) and X (n-20 ms) are the signal values before 10ms and 20ms, respectively.
Y(n)＝2*Y(n-1)–Y(n-2)+X(n)–2*X(n-10ms)+X(n-20ms)
A differential threshold method. As shown in fig. 7, a QRS wave (i.e., heart beat) detection is performed by using a differential threshold method. Specifically, after filtering the electrocardiographic data, sequentially performing difference, square and moving average processing, then searching for a peak value, after obtaining the peak value, comparing the peak value with a threshold value, if the peak value is greater than the threshold value, considering that a QRS wave is detected, otherwise, treating the detected QRS wave as noise, finally updating the threshold value, for example, making the updated threshold value half of the previous threshold value, then pointing to the difference, square and moving average processing again, searching for a new peak value, and comparing again. It should be noted that the QRS wave detection in this embodiment belongs to the prior art, and specifically, reference may be made to the related description of the processes of difference, square, moving average processing, peak searching, threshold comparison, and the like in "a method and system for detecting a heart rate in real time by an electrocardiographic signal" (CN 104586384B) in the invention patent of china, of course, the invention may also adopt other manners to perform QRS wave detection on electrocardiographic data, and details are not repeated herein.
The embodiment of the invention provides a method for identifying pseudo-errors of dynamic electrocardiosignals, wherein in the aspect of selecting characteristic values, characteristic parameters comprise self information (wavelet coefficients and difference information) of heart beat data, related information (the number of matched heart beats, interval ratio and the matching degree of the front heart beat and the back heart beat) of other data and information (low-frequency and high-frequency noise interference values) interfered by noise. Features of data to be analyzed are extracted through deep mining, and a support vector machine is adopted for training to obtain a recognition model for pseudo-difference recognition of dynamic electrocardiosignals. The characteristics used for artifact identification not only comprise the data to be analyzed, but also comprise the similarity between the data to be analyzed and the previous and subsequent data, the interval ratio of the data sequence, the noise of the data to be analyzed and other information, so that the influence of factors such as individual difference on the identification result is avoided, and the identification accuracy and the algorithm robustness are improved.
It should be noted that, a certain order does not necessarily exist between the above steps, and those skilled in the art can understand, according to the description of the embodiments of the present invention, that in different embodiments, the above steps may have different execution orders, that is, may be executed in parallel, may also be executed interchangeably, and the like.
With reference to fig. 8, fig. 8 is a schematic diagram of a hardware structure of another embodiment of the system for identifying artifacts of dynamic electrocardiographic signals according to the embodiment of the present invention, and as shown in fig. 8, the system 10 includes: a memory 101, a processor 102 and a computer program stored on the memory and executable on the processor, the computer program realizing the following steps when executed by the processor 101:
acquiring marked dynamic electrocardiogram data, wherein the marked dynamic electrocardiogram data comprise heart beat data, and the types of the heart beat data comprise real solid beats and pseudo errors;
carrying out first preprocessing operation on the marked heart beat data, extracting a characteristic value of each preprocessed heart beat and carrying out normalization processing to obtain a sample characteristic vector;
inputting the sample feature vector into a pre-constructed support vector machine for training to generate a pseudo-error recognition model;
acquiring collected dynamic electrocardiogram data, performing second preprocessing operation on the collected dynamic electrocardiogram data, extracting a characteristic value of each preprocessed heartbeat, and performing normalization processing to obtain a heartbeat characteristic vector;
and inputting the heart beat feature vector into a pseudo-error recognition model, acquiring an output result of the pseudo-error recognition model, and taking the output result as a pseudo-error recognition result.
The specific implementation steps are the same as those of the method embodiments, and are not described herein again.
Optionally, the computer program when executed by the processor 101 further implements the steps of:
and sequentially carrying out template matching on the real heart beats and the pseudo-errors in the marked heart beat data according to positions, and counting the number of the heart beats in each template after the matching of all the marked data is finished.
The specific implementation steps are the same as those of the method embodiments, and are not described herein again.
Optionally, the computer program when executed by the processor 101 further realizes the steps of:
extracting a characteristic value of each preprocessed heart beat, wherein the characteristic value comprises a wavelet coefficient of the heart beat, the total number of the heart beats of the template, interval ratios of three intervals before and after the current heart beat, matching degree of the current heart beat and the previous and following heart beats, heart beat differential data information and low-frequency and high-frequency noise interference information;
and carrying out normalization processing on the extracted characteristic values to obtain sample characteristic vectors.
The specific implementation steps are the same as those of the method embodiments, and are not described herein again.
Optionally, the computer program when executed by the processor 101 further realizes the steps of:
acquiring collected dynamic electrocardiogram data, and filtering the collected dynamic electrocardiogram data to generate filtered data;
performing heartbeat detection on the filtered data based on a differential threshold algorithm, and recording the position information of each heartbeat;
and performing cluster statistics on each heart beat, and counting the number of the heart beats of each template.
The specific implementation steps are the same as those of the method embodiments, and are not described herein again.
Optionally, the computer program when executed by the processor 101 further realizes the steps of:
carrying out similarity calculation on the marked heart beat data and the existing template in sequence according to positions;
if the similarity is larger than or equal to the threshold value, judging that the heart beat data belongs to the template, and updating the data in the template;
if the similarity is smaller than the threshold value, matching calculation is carried out with the next template;
and if the marked heartbeat data are not matched with all the templates, establishing a corresponding template based on the heartbeat data.
The specific implementation steps are the same as those of the method embodiments, and are not described herein again.
Embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer-executable instructions for execution by one or more processors, for example, to perform method steps S100-S500 of fig. 1 described above.
By way of example, nonvolatile storage media can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically erasable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The disclosed memory components or memory of the operating environment described in the embodiments of the invention are intended to comprise one or more of these and/or any other suitable types of memory.
The above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for identifying artifact of dynamic electrocardiosignals is characterized by comprising the following steps:
acquiring marked dynamic electrocardiogram data, wherein the marked dynamic electrocardiogram data comprise heart beat data, and the types of the heart beat data comprise real solid beats and pseudo errors;
carrying out first preprocessing operation on the marked heart beat data, extracting a characteristic value of each preprocessed heart beat, and carrying out normalization processing to obtain a sample characteristic vector;
inputting the sample feature vector into a pre-constructed support vector machine for training to generate a pseudo-error recognition model;
acquiring collected dynamic electrocardiogram data, performing second preprocessing operation on the collected dynamic electrocardiogram data, extracting a characteristic value of each preprocessed heartbeat, and performing normalization processing to obtain a heartbeat characteristic vector;
and inputting the heartbeat feature vector into a pseudo-error recognition model, acquiring an output result of the pseudo-error recognition model, and taking the output result as a pseudo-error recognition result.
2. The method for identifying artifacts of dynamic electrocardiographic signals according to claim 1, wherein said first preprocessing operation on the marked heart beat data comprises:
and sequentially carrying out template matching on the real heart beats and the pseudo-errors in the marked heart beat data according to positions, and counting the number of the heart beats in each template after the matching of all the marked data is finished.
3. The method for identifying artifacts of dynamic electrocardiographic signals according to claim 2, wherein said extracting a feature value for each preprocessed cardiac beat and performing normalization processing to obtain a sample feature vector comprises:
extracting a characteristic value of each preprocessed heart beat, wherein the characteristic value comprises a wavelet coefficient of the heart beat, the total number of the heart beats of the template, interval ratios of three intervals before and after the current heart beat, matching degree of the current heart beat and the previous and following heart beats, heart beat differential data information and low-frequency and high-frequency noise interference information;
and carrying out normalization processing on the extracted characteristic values to obtain sample characteristic vectors.
4. The method for artifact identification of dynamic electrocardiographic signals according to claim 3, wherein said acquiring the collected dynamic electrocardiographic data and performing a second preprocessing operation on the collected dynamic electrocardiographic data comprises:
acquiring collected dynamic electrocardiogram data, and filtering the collected dynamic electrocardiogram data to generate filtered data;
performing heartbeat detection on the filtered data based on a differential threshold algorithm, and recording the position information of each heartbeat;
and performing cluster statistics on each heart beat, and counting the number of the heart beats of each template.
5. The method for identifying artifacts of dynamic electrocardiographic signals according to claim 4, wherein said sequentially performing template matching on the true heart beats and the artifacts in the marked heart beat data according to positions comprises:
carrying out similarity calculation on the marked heart beat data and the existing template according to the position in sequence;
if the similarity is larger than or equal to the threshold value, judging that the heart beat data belongs to the template, and updating the data in the template;
if the similarity is smaller than the threshold value, matching calculation is carried out with the next template;
and if the marked heartbeat data are not matched with all the templates, establishing a corresponding template based on the heartbeat data.
6. An artifact identification system of a dynamic cardiac signal, said system comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of:
acquiring marked dynamic electrocardiogram data, wherein the marked dynamic electrocardiogram data comprise heart beat data, and the types of the heart beat data comprise real solid beats and pseudo errors;
carrying out first preprocessing operation on the marked heart beat data, extracting a characteristic value of each preprocessed heart beat and carrying out normalization processing to obtain a sample characteristic vector;
inputting the sample feature vector into a pre-constructed support vector machine for training to generate a pseudo-error recognition model;
acquiring collected dynamic electrocardiogram data, performing second preprocessing operation on the collected dynamic electrocardiogram data, extracting a characteristic value of each preprocessed heartbeat, and performing normalization processing to obtain a heartbeat characteristic vector;
and inputting the heart beat feature vector into a pseudo-error recognition model, acquiring an output result of the pseudo-error recognition model, and taking the output result as a pseudo-error recognition result.
7. System for artifact recognition of dynamic electrocardiographic signals according to claim 6 wherein said computer program when executed by said processor implements the steps of:
and sequentially carrying out template matching on the real heart beats and the pseudo-errors in the marked heart beat data according to positions, and counting the number of the heart beats of each template after the matching of all the marked data is finished.
8. System for artifact identification of dynamic electrocardiographic signals according to claim 7 wherein said computer program when executed by said processor further implements the steps of:
extracting a characteristic value of each preprocessed heart beat, wherein the characteristic value comprises a wavelet coefficient of the heart beat, the total number of the heart beats of the template, the interval ratio of three intervals before and after the current heart beat, the matching degree of the current heart beat and the previous and subsequent heart beats, heart beat differential data information and low-frequency and high-frequency noise interference information;
and carrying out normalization processing on the extracted characteristic values to obtain sample characteristic vectors.
9. The system for artifact identification of dynamic electrocardiographic signals according to claim 8 wherein said computer program when executed by said processor further performs the steps of:
acquiring collected dynamic electrocardiogram data, and performing filtering processing on the collected dynamic electrocardiogram data to generate filtering data;
performing heartbeat detection on the filtered data based on a differential threshold algorithm, and recording the position information of each heartbeat;
and performing cluster statistics on each heart beat, and counting the number of the heart beats of each template.
10. A non-transitory computer-readable storage medium storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform the method for artifact identification of dynamic cardiac electrical signals as recited in any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211540499.6A CN115778402A (en) | 2022-12-02 | 2022-12-02 | Method and system for identifying artifact of dynamic electrocardiosignal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211540499.6A CN115778402A (en) | 2022-12-02 | 2022-12-02 | Method and system for identifying artifact of dynamic electrocardiosignal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115778402A true CN115778402A (en) | 2023-03-14 |
Family
ID=85445081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211540499.6A Pending CN115778402A (en) | 2022-12-02 | 2022-12-02 | Method and system for identifying artifact of dynamic electrocardiosignal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115778402A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108937915A (en) * | 2018-07-24 | 2018-12-07 | 杭州质子科技有限公司 | The recognition methods of premature beat in a kind of dynamic ECG |
| CN109303561A (en) * | 2018-11-01 | 2019-02-05 | 杭州质子科技有限公司 | It is a kind of to clap the recognition methods clapped with the abnormal heart based on the artifact heart of misclassification and supervised learning |
| CN109645979A (en) * | 2017-10-10 | 2019-04-19 | 深圳市理邦精密仪器股份有限公司 | Ambulatory ecg signal artifact identification method and device |
| CN111281378A (en) * | 2020-02-13 | 2020-06-16 | 苏州百慧华业精密仪器有限公司 | Method and device for screening suspected T-wave electricity alternate sections in dynamic electrocardiogram |
| CN111297351A (en) * | 2020-02-13 | 2020-06-19 | 苏州百慧华业精密仪器有限公司 | Motion artifact identification method and device in dynamic electrocardiogram |
| WO2021169296A1 (en) * | 2020-02-27 | 2021-09-02 | 平安科技（深圳）有限公司 | Method and apparatus for processing electrocardiogram data, computer device, 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 |
| CN113995420A (en) * | 2020-07-14 | 2022-02-01 | 深圳华清心仪医疗电子有限公司 | Dynamic electrocardiogram data processing method and processing device based on RR interval ratio scatter diagram |
| CN114494798A (en) * | 2022-01-28 | 2022-05-13 | 厦门纳龙健康科技股份有限公司 | Electrocardiogram artifact confirmation method, terminal equipment and storage medium |
| WO2022110524A1 (en) * | 2020-11-30 | 2022-06-02 | 深圳邦健生物医疗设备股份有限公司 | Method and device for electrocardiogram heartbeat data clustering, electronic device, and medium |
| CN114795235A (en) * | 2022-04-14 | 2022-07-29 | 中国人民解放军陆军第八十二集团军医院 | Single-lead electrocardiogram monitoring method and system based on morphological contour algorithm |
-
2022
- 2022-12-02 CN CN202211540499.6A patent/CN115778402A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109645979A (en) * | 2017-10-10 | 2019-04-19 | 深圳市理邦精密仪器股份有限公司 | Ambulatory ecg signal artifact identification method and device |
| CN108937915A (en) * | 2018-07-24 | 2018-12-07 | 杭州质子科技有限公司 | The recognition methods of premature beat in a kind of dynamic ECG |
| CN109303561A (en) * | 2018-11-01 | 2019-02-05 | 杭州质子科技有限公司 | It is a kind of to clap the recognition methods clapped with the abnormal heart based on the artifact heart of misclassification and supervised learning |
| CN111281378A (en) * | 2020-02-13 | 2020-06-16 | 苏州百慧华业精密仪器有限公司 | Method and device for screening suspected T-wave electricity alternate sections in dynamic electrocardiogram |
| CN111297351A (en) * | 2020-02-13 | 2020-06-19 | 苏州百慧华业精密仪器有限公司 | Motion artifact identification method and device in dynamic electrocardiogram |
| WO2021169296A1 (en) * | 2020-02-27 | 2021-09-02 | 平安科技（深圳）有限公司 | Method and apparatus for processing electrocardiogram data, computer device, 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 |
| CN113995420A (en) * | 2020-07-14 | 2022-02-01 | 深圳华清心仪医疗电子有限公司 | Dynamic electrocardiogram data processing method and processing device based on RR interval ratio scatter diagram |
| WO2022110524A1 (en) * | 2020-11-30 | 2022-06-02 | 深圳邦健生物医疗设备股份有限公司 | Method and device for electrocardiogram heartbeat data clustering, electronic device, and medium |
| CN114494798A (en) * | 2022-01-28 | 2022-05-13 | 厦门纳龙健康科技股份有限公司 | Electrocardiogram artifact confirmation method, terminal equipment and storage medium |
| CN114795235A (en) * | 2022-04-14 | 2022-07-29 | 中国人民解放军陆军第八十二集团军医院 | Single-lead electrocardiogram monitoring method and system based on morphological contour algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 涂岳文等: ""基于心搏聚类的Holter运动伪差段快速识别算法"", 《浙江大学学报(工学版)》, vol. 46, no. 06, 30 June 2012 (2012-06-30), pages 1148 - 1156 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6367442B2 (en) | Method and system for disease analysis based on conversion of diagnostic signals | |
| Yang | Multiscale recurrence quantification analysis of spatial cardiac vectorcardiogram signals | |
| Saini et al. | QRS detection using K-Nearest Neighbor algorithm (KNN) and evaluation on standard ECG databases | |
| EP1802230B1 (en) | Monitoring physiological activity using partial state space reconstruction | |
| Rakshit et al. | An efficient wavelet-based automated R-peaks detection method using Hilbert transform | |
| US20160256063A1 (en) | Analyte assessment and arrhythmia risk prediction using physiological electrical data | |
| CN107233093B (en) | R wave detection method and device and electronic equipment | |
| Malek et al. | Automated detection of premature ventricular contraction in ECG signals using enhanced template matching algorithm | |
| CN111481192A (en) | Electrocardiosignal R wave detection method based on improved U-Net | |
| Prabhakararao et al. | A weighted SVM based approach for automatic detection of posterior myocardial infarction using VCG signals | |
| Kaur et al. | On the detection of cardiac arrhythmia with principal component analysis | |
| KR20220150901A (en) | Fusion signal processing for detection of maternal uterine activity | |
| CN111956203A (en) | Electrocardiosignal parameterization method, model training method, device, equipment and medium | |
| CN111832537A (en) | Abnormal electrocardiosignal identification method and abnormal electrocardiosignal identification device | |
| CN113180685B (en) | Electrocardio abnormity discrimination system and method based on morphological filtering and wavelet threshold | |
| Liu et al. | A novel P-QRS-T wave localization method in ECG signals based on hybrid neural networks | |
| Boucheham et al. | Piecewise linear correction of ECG baseline wander: a curve simplification approach | |
| CN115778402A (en) | Method and system for identifying artifact of dynamic electrocardiosignal | |
| Rodrigues et al. | The issue of automatic classification of heartbeats | |
| Gómez-Herrero et al. | Relative estimation of the Karhunen-Loève transform basis functions for detection of ventricular ectopic beats | |
| Banerjee et al. | A classification approach for myocardial infarction using voltage features extracted from four standard ECG leads | |
| Khandait et al. | ECG signal processing using classifier to analyses cardiovascular disease | |
| Davydov et al. | Myocardial infarction detection using wavelet analysis of ECG signal | |
| Soe et al. | ECG Signal Classification using Discrete Wavelet Transform and Pan Tompkins Algorithm | |
| Pander et al. | Fuzzy-based algorithm for QRS detection |
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 |