CN111419212A - Method and device for processing electrocardiogram data, storage medium and computer equipment - Google Patents
Method and device for processing electrocardiogram data, storage medium and computer equipment Download PDFInfo
- Publication number
- CN111419212A CN111419212A CN202010123259.0A CN202010123259A CN111419212A CN 111419212 A CN111419212 A CN 111419212A CN 202010123259 A CN202010123259 A CN 202010123259A CN 111419212 A CN111419212 A CN 111419212A
- Authority
- CN
- China
- Prior art keywords
- wave
- waveform
- mean
- processing
- data information
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/366—Detecting abnormal QRS complex, e.g. widening
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Cardiology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Power Engineering (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a method, a device, a storage medium and computer equipment for processing electrocardiogram data, relates to the field of data processing, and mainly aims to synthesize a mean value waveform through clustering so as to smooth filtering, effectively weaken the influence of baseline drift noise, myoelectric noise, power frequency interference and sudden noise, and greatly improve the accuracy of marking the starting and stopping points of P waves, QRS waves and T waves. The method comprises the following steps: acquiring all heart beat data information of a sample electrocardiogram; carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram; and carrying out information annotation on the P wave, the QRS wave, the T wave and the ST segment on the mean value waveform, and outputting the annotated waveform information of the P wave, the QRS wave, the T wave and the ST segment. The invention is suitable for processing electrocardiogram data.
Description
Technical Field
The present invention relates to the field of data processing, and in particular, to a method, an apparatus, a storage medium, and a computer device for processing electrocardiogram data.
Background
With the continuous development of medical information technology, the automatic electrocardiogram diagnosis technology has been applied clinically to a certain extent, and although the current automatic electrocardiogram diagnosis technology cannot be compared with the diagnosis level of professional doctors, the automatic electrocardiogram diagnosis technology has been accepted to a certain extent in some aspects, so that the burden of the professional doctors is greatly reduced.
Currently, the existing automatic electrocardiogram diagnosis technology is to label and extract the information of P wave, QRS wave and T wave of each heart beat of the electrocardiogram. However, in the process of labeling the start and stop points of P wave, QRS wave and T wave, the accuracy of the detection result is greatly reduced compared with the top point of the R wave due to the influence of baseline drift noise, myoelectric noise, power frequency interference and other sudden noises.
Disclosure of Invention
In view of this, the present invention provides a method, an apparatus, a storage medium and a computer device for processing electrocardiographic data, and mainly aims to synthesize a mean waveform by clustering, so as to smooth filtering, effectively weaken the influence of baseline drift noise, myoelectric noise, power frequency interference and sudden noise, and greatly improve the accuracy of labeling the start and stop points of P waves, QRS waves and T waves.
According to an aspect of the present invention, there is provided a method of electrocardiographic data processing, comprising:
acquiring all heart beat data information of a sample electrocardiogram;
carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram;
carrying out information annotation on a P wave, a QRS wave, a T wave and an ST segment on the mean waveform;
and outputting the labeled waveform information of the P wave, the QRS wave, the T wave and the ST segment.
Optionally, the performing mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram includes:
carrying out noise processing on the heartbeat data information, and carrying out R wave detection on the processed heartbeat data information to obtain R wave data information;
screening the heartbeat data information according to the R wave data information and a preset screening algorithm;
and clustering and merging the screening results, and determining the result obtained by clustering and merging as the mean waveform of the sample electrocardiogram.
Further, the denoising the heartbeat data information comprises:
the sample electrocardiogram data is subjected to noise processing using band-pass filtering.
The screening of the heartbeat data information according to the R wave data information and a preset screening algorithm comprises the following steps:
calculating average RR interval data information according to the acquired RR interval data information of all heartbeats;
and configuring a screening interval according to the average RR interval data information, and screening the heart beat data information of the RR interval data information in the screening interval.
The clustering and merging the screening results and determining the result obtained by clustering and merging as the mean waveform of the sample electrocardiogram comprise:
configuring sampling points for the screened heartbeat data information, and carrying out superposition averaging processing on all the sampling points;
and determining the processed result as a mean waveform of the sample electrocardiogram.
Optionally, after the information labeling of the P wave, QRS wave, T wave and ST segment is performed on the mean waveform, the method further includes:
and carrying out wave band analysis on the mean waveform to obtain R wave notch, QRS wave form and QRS wave voltage change information of the mean waveform.
Further, the performing of the wave band analysis on the mean waveform to obtain the R wave notch, the QRS wave form, and the QRS wave voltage change information of the mean waveform includes:
according to the mean value waveform, inflection point position information on two sides of the R wave vertex is detected, and whether the R wave has a notch or not is judged according to the inflection point position information;
calculating the number of QRS wave zero-crossing points in the mean waveform, and determining the form of QRS waves according to the number;
and respectively recording the voltage change processes of the waveforms on two sides of the central point by taking the peak of the R wave in the mean waveform as the central point.
Further, the detecting inflection point position information on two sides of an R wave vertex according to the mean value waveform, and determining whether the R wave has a notch according to the inflection point position information includes:
performing first-order difference processing on the mean value waveform, and detecting inflection point position information on two sides of the top point of the R wave;
comparing the inflection point position information with the position information of the starting and ending points of the P wave, the QRS wave, the T wave and the ST segment;
and judging whether the R wave has the notch or not according to the comparison result.
Optionally, after performing a wave band analysis on the mean waveform to obtain an R wave notch, a QRS wave morphology, and QRS wave voltage change information of the mean waveform, the method further includes:
when an electrocardiogram analysis processing request is received, prediction analysis is carried out according to electrocardiogram data information carried in the request and a pre-trained target state recognition model, an analysis result is output to determine target state information, and training sample data of the pre-trained target state recognition model is obtained through mean wave processing and band analysis.
According to a second aspect of the present invention, there is provided an apparatus for electrocardiographic data processing, comprising:
the acquisition unit is used for acquiring all heartbeat data information of the sample electrocardiogram;
the processing unit is used for carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm and determining the processing result as a mean waveform of the sample electrocardiogram;
the marking unit is used for marking the information of the P wave, the QRS wave, the T wave and the ST segment of the mean value waveform;
and the output unit is used for outputting the labeled waveform information of the P wave, the QRS wave, the T wave and the ST segment.
Optionally, the processing unit comprises: a processing module, a detection module and a screening module,
the processing module is used for carrying out noise processing on the heartbeat data information;
the detection module is used for carrying out R wave detection on the processed heartbeat data information to acquire R wave data information;
the screening module is used for screening the heartbeat data information according to the R wave data information and a preset screening algorithm;
and the clustering and merging module is used for clustering and merging the screening results and determining the result obtained by clustering and merging as the mean waveform of the sample electrocardiogram.
Further, the processing module is specifically configured to perform noise processing on the sample electrocardiogram data by using band-pass filtering.
Further, the screening module is specifically configured to calculate average RR interval data information according to the acquired RR interval data information of all heart beats, configure a screening interval according to the average RR interval data information, and screen the heart beat data information of which the RR interval data information is located in the screening interval.
Further, the cluster merging module is specifically configured to configure sampling points for the screened heartbeat data information, perform superposition averaging processing on all the sampling points, and determine a result obtained by the processing as a mean waveform of the sample electrocardiogram.
Optionally, the apparatus further comprises: a first analysis unit for analyzing the first sample,
the first analysis unit is used for carrying out wave band analysis on the mean value waveform to obtain R wave notch, QRS wave form and QRS wave voltage change information of the mean value waveform.
Further, the first analysis unit includes: a judging module, a determining module and a recording module,
the judging module is used for detecting inflection point position information on two sides of the top point of the R wave according to the mean value waveform and judging whether the R wave has a notch or not according to the inflection point position information;
the determining module is used for calculating the number of QRS wave zero-crossing points in the mean waveform and determining the form of QRS waves according to the number;
and the recording module is used for respectively recording voltage change processes of waveforms on two sides of the central point by taking the peak of the R wave in the mean waveform as the central point.
Further, the determining module is specifically configured to perform first-order difference processing on the mean waveform, detect inflection point position information on two sides of a vertex of the R wave, compare the inflection point position information with position information of start and stop points of the P wave, the QRS wave, the T wave, and the ST segment, and determine whether the R wave has a notch according to the comparison result.
Optionally, the apparatus further comprises: second analysis unit
The second analysis unit is used for performing predictive analysis according to electrocardiogram data information carried in an electrocardiogram analysis processing request and a pre-trained target state recognition model when the electrocardiogram analysis processing request is received, and outputting an analysis result to determine target state information, wherein training sample data of the pre-trained target state recognition model is obtained by performing band analysis through mean wave processing.
Optionally, the apparatus further comprises: acquisition unit and training unit
The acquisition unit is used for acquiring sample data information of the sample electrocardiogram, wherein the sample data information comprises P waves, QRS waves, T waves, ST segments, R wave notches, QRS wave forms, QRS wave voltage change information and RR interval data information of all heartbeats;
and the training unit is used for training a preset machine learning algorithm according to the sample data information and a target state identification label corresponding to the sample electrocardiogram, and determining a target state identification model.
According to a third aspect of the present invention, there is provided a storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform the steps of: acquiring all heart beat data information of a sample electrocardiogram; carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram; and carrying out information annotation on the P wave, the QRS wave, the T wave and the ST segment on the mean value waveform, and outputting the annotated waveform information of the P wave, the QRS wave, the T wave and the ST segment.
According to a fourth aspect of the present invention, there is provided a computer device comprising a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus, and the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to perform the following steps: acquiring all heart beat data information of a sample electrocardiogram; carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram; and carrying out information annotation on the P wave, the QRS wave, the T wave and the ST segment on the mean value waveform, and outputting the annotated waveform information of the P wave, the QRS wave, the T wave and the ST segment.
Compared with the prior art for carrying out information annotation and characteristic extraction on the P wave, the QRS wave and the T wave of each heart beat of an electrocardiogram, the method, the device, the storage medium and the computer equipment for processing electrocardiogram data acquire all heart beat data information of a sample electrocardiogram; carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram; and carrying out information annotation on the P wave, the QRS wave, the T wave and the ST segment on the mean value waveform, and outputting the annotated waveform information of the P wave, the QRS wave, the T wave and the ST segment. Therefore, the influence of baseline drift noise, myoelectric noise, power frequency interference and sudden noise can be effectively weakened through clustering synthesis of mean waveform and smooth filtering, the accuracy of marking the starting and stopping points of P waves, QRS waves and T waves is greatly improved, the accuracy of electrocardiogram data processing is improved, and the efficiency of analyzing the data obtained by utilizing electrocardiogram is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a method for processing ECG data according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an electrocardiogram data processing apparatus according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of another electrocardiogram data processing apparatus provided by the embodiment of the invention;
FIG. 4 is a block diagram illustrating an embodiment of a computer device according to the present invention;
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As described in the background, the conventional automatic electrocardiographic diagnosis technology is to label information and extract features of P wave, QRS wave and T wave of each heart beat of an electrocardiograph. However, in the process of labeling the start and stop points of P wave, QRS wave and T wave, the accuracy of the detection result is greatly reduced compared with the top point of the R wave due to the influence of baseline drift noise, myoelectric noise, power frequency interference and other sudden noises.
In order to solve the above problem, an embodiment of the present invention provides a method for processing electrocardiographic data, as shown in fig. 1, the method including:
101. all heartbeat data information of the sample electrocardiogram is acquired.
Wherein the heartbeat data information may include waveform data information in the sample electrocardiogram.
102. And carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram.
In order to reduce noise such as power frequency interference, baseline drift and the like during waveform data information acquisition, the preset clustering and merging algorithm can be used for clustering and merging the waveform data information in the sample electrocardiogram to obtain a mean waveform of the lead electrocardiogram, and the mean waveform can embody common characteristics of most waveforms, so that the accuracy of labeling the starting and stopping points of P waves, QRS waves and T waves is improved. The specific process of performing mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm may include: and sequentially carrying out R wave detection, screening treatment and clustering combination on all heart beat data information of the obtained sample electrocardiogram, wherein the obtained waveform can be determined as a mean waveform of the sample electrocardiogram.
In the prior art, R wave detection and analysis of P wave, QRS wave, T wave, and ST segment are performed for all heartbeats, and feature values are extracted. The invention only needs to analyze and extract the characteristics of the P wave, QRS wave, T wave and ST segment of the synthesized mean waveform, thereby greatly reducing the calculation amount and improving the efficiency of electrocardiogram data analysis and characteristic extraction.
103. And carrying out information annotation on P waves, QRS waves, T waves and ST segments on the mean waveform.
Specifically, the identification can be directly performed according to the mean waveform and the shape features corresponding to the P wave, the QRS wave, the T wave and the ST segment, and the information labeling can be performed on the P wave, the QRS wave, the T wave and the ST segment according to the identification result. It should be noted that the mean waveform obtained by aggregating heart beats can embody common features of most waveforms, in addition, because the electrocardiosignal is weak, it is easy to be interfered by power frequency interference, baseline drift and the like during acquisition, which may affect the accuracy of marking P wave, QRS wave and T wave start and stop points, and the marked position may fluctuate with the interference, and the mean waveform obtained by aggregating heart beats may reduce the interference, thereby improving the accuracy of marking P wave, QRS wave and T wave start and stop points.
104. And outputting the labeled waveform information of the P wave, the QRS wave, the T wave and the ST segment.
Specifically, after information of a P wave, a QRS wave, a T wave and an ST segment is labeled on the mean waveform, the labeled waveform information is output.
Further, in order to better explain the process of the above-mentioned electrocardiogram data processing method, as a refinement and an extension of the above-mentioned embodiment, several alternative embodiments are provided in the embodiments of the present invention, but are not limited thereto, and specifically, the following embodiments are shown:
in an optional embodiment of the present invention, the step 102 may specifically include: carrying out noise processing on the heartbeat data information, and carrying out R wave detection on the processed heartbeat data information to obtain R wave data information; screening the heartbeat data information according to the R wave data information and a preset screening algorithm; and clustering and merging the screening results, and determining the result obtained by clustering and merging as the mean waveform of the sample electrocardiogram. The specific process of R-wave detection may include: band-pass filtering: filtering the input electrocardiogram signal by using a forward filter of 5-18Hz and performing phase delay compensation; difference: carrying out differential processing on the signals output by the forward filter to form differential signals d (n); data arrangement: converting the differential signal: output d' (n) — absolute value of input/G1; performing shannon energy conversion on the data-processed signal by using a formula-d ' (n) × log (d ' (n) × d ' (n)); average filtering: filtering the processed signal by using a forward filter with a filter width M of 55-75 points (153-208 ms) and performing phase delay compensation; detection of maximum/small points: the maximum point is a selected point with a value larger than points positioned at the left side and the right side of the maximum point, and the minimum point is a selected point with a value smaller than points positioned at the left side and the right side of the minimum point; eliminating false R points; correcting the error elimination points; the true R position is found within ± 25 points around the approximate R wave position.
For the embodiment of the present invention, the performing noise processing on the heartbeat data information specifically may include: the sample electrocardiogram data is subjected to noise processing using band-pass filtering.
The base line drift noise, the myoelectric noise, the power frequency interference, the sudden noise and the like can be filtered through band-pass filtering, and the accuracy of marking the starting and stopping points of the P wave, the QRS wave and the T wave is improved. Specifically, bandpass filtering with a low-frequency cutoff frequency of 14Hz and a high-frequency cutoff frequency of 20Hz may be employed for filtering at the time of R-wave detection. A second-order median filter can be adopted for baseline drift, baseline drift can be effectively inhibited after filtering, and no obvious change is caused to an ST segment after filtering. And a self-adaptive filter can be used for filtering 50Hz power frequency interference in the electrocardiosignals.
For the embodiment of the present invention, the screening the heartbeat data information according to the R-wave data information and a preset screening algorithm specifically may include: calculating average RR interval data information according to the acquired RR interval data information of all heartbeats; and configuring a screening interval according to the average RR interval data information, and screening the heart beat data information of the RR interval data information in the screening interval.
The RR interval may be a position difference value between a current R wave and a previous R wave vertex, the heart rate and the RR interval have an inverse relationship, and a specific conversion formula may be:
for the embodiment of the present invention, the average RR interval may be an average value of RR intervals of all heart beats, and a screening interval of the average RR interval is configured, for example, 0.8 times to 1.2 times of the average RR interval may be selected as the screening interval.
It should be noted that the aggregation of heartbeats to obtain a mean waveform is to merge most heartbeats with the same attribute, but for accidental premature beats, especially ventricular premature beats, since the pacing point is different from other heartbeats, that is, the attribute of a heartbeat is different, some differences in the shape of the heartbeat may be brought, and if the accidental premature beats participate in superposition aggregation, the accuracy of the aggregated heartbeat waveform is affected, so the accidental premature beats do not participate in superposition aggregation.
For the embodiment of the present invention, the clustering and merging the screening results, and determining the result obtained by clustering and merging as the mean waveform of the sample electrocardiogram may specifically include: configuring sampling points for the screened heartbeat data information, and carrying out superposition averaging processing on all the sampling points; and determining the processed result as a mean waveform of the sample electrocardiogram.
Sampling points can be configured on the screened heartbeat data information, and the sampling points are subjected to superposition averaging processing; and determining the processed result as a mean waveform of the sample electrocardiogram. It should be noted that the overlapping range of both sides of the R-wave can be determined according to the average RR interval. Such as: and if the average RR interval is 1000ms, the sampling points in the range of R-500ms to R +500ms can be determined to be superposed and averaged by taking the peak of the R wave as a central point.
In an optional embodiment of the present invention, in order to obtain information on R wave notch, QRS wave morphology, and QRS wave voltage variation of the mean waveform, the method may further include: and carrying out wave band analysis on the mean waveform to obtain R wave notch, QRS wave form and QRS wave voltage change information of the mean waveform.
It should be noted that, in terms of feature labeling and extraction, the prior art usually only focuses on information such as Q wave of QRS wave, wave voltage of R wave and S wave, and QRS wave time, and often ignores the collection and analysis of information on the time of each wave of Q wave, R wave and S wave, and the change in the depolarization process of left and right ventricles. For example: the half part of the QRS wave front of the left bundle branch conduction block is normal in shape and time, the time of the half part is prolonged, and the shape of the QRS wave is a wide, flat or incisional R wave; in addition, the prior art is not concerned with the morphology of the QRS wave, such as the "M" morphology exhibited by the QRS wave in the right bundle branch block, which is not reflected in the features labeled and extracted by the prior art. The invention judges the incisure and the shape of the QRS wave and records the voltage change process, so that the electrocardiogram characteristics play a certain role in AI prediction.
For the embodiment of the present invention, the performing the band analysis on the mean waveform to obtain the R wave notch, the QRS wave form, and the QRS wave voltage change information of the mean waveform may specifically include: according to the mean value waveform, inflection point position information on two sides of the R wave vertex is detected, and whether the R wave has a notch or not is judged according to the inflection point position information; calculating the number of QRS wave zero-crossing points in the mean waveform, and determining the form of QRS waves according to the number; and respectively recording the voltage change processes of the waveforms on two sides of the central point by taking the peak of the R wave in the mean waveform as the central point.
The calculating of the number of QRS wave zero-crossing points in the mean waveform, and the determining of the QRS wave morphology according to the number may specifically include: calculating the number of QRS wave zero crossings in said mean waveform and determining the morphology of QRS waves from said number, said QRS waves may exhibit rsR ', RSR ' or rR ' morphology. Specifically, the number of zero-crossing points on the left and right sides of the R wave may be determined by taking the R wave vertex as a center. For example, if there is one zero-crossing point on the left side of the top point of the R wave and there are three zero-crossing points on the right side of the top point of the R wave, the QRS wave form can be determined to be RSR'.
The recording mode of the QRS wave voltage change process may include: and respectively recording voltage change processes of waveforms on two sides of the mean waveform by taking the peak of the R wave in the mean waveform as a central point, wherein the voltage change processes can embody the characteristics of wide pause and pause in the rear half part of the QRS wave. Specifically, a point may be taken every Nms (e.g., 10ms) centered on the R-wave vertex. For example, the sampling rate is 500Hz, the peak of the R wave in the mean waveform is at point x, and the voltage of the mean wave is yxRecording voltage values y every 10ms to the left and right sides of the mean waveform with the R wave vertex as the centerx+5、yx-5、yx+10、yx-10… …, the range of the abscissa can be x-0.1s to x +0.1 s.
Further, the detecting inflection point position information on two sides of an apex of the R wave according to the mean waveform, and determining whether the R wave has a notch according to the inflection point position information may specifically include: performing first-order difference processing on the mean value waveform, and detecting inflection point position information on two sides of the top point of the R wave; comparing the inflection point position information with the position information of the starting and ending points of the P wave, the QRS wave, the T wave and the ST segment; and judging whether the R wave has the notch or not according to the comparison result.
The specific process of judging whether the notch exists in the R wave may include: performing first-order difference processing on the mean waveform, detecting inflection points on two sides of the top point of the R wave, wherein the first-order difference is the voltage difference between the point x and the point x +1 of the mean waveform, and if the positive and negative of the first-order difference on the left side and the right side of a certain point of the mean waveform are opposite, judging that the point is the inflection point in the QRS wave; according to the comparison result of the position of the inflection point and the positions of the starting and stopping points of the P wave, the QRS wave and the T wave, whether the R wave has the notch or not can be judged. For example, if there are two inflection points between the R wave apex and the QRS wave apex, it is said that the R wave has a notch.
In an alternative embodiment of the present invention, in order to determine the target state information using the data-processed electrocardiogram data, the method may further include: when an electrocardiogram analysis processing request is received, prediction analysis is carried out according to electrocardiogram data information carried in the request and a pre-trained target state recognition model, an analysis result is output to determine target state information, and training sample data of the pre-trained target state recognition model is obtained through mean wave processing and band analysis.
Specifically, an electrocardiogram analysis processing request is received, wherein the request may carry data information of the electrocardiogram; the prediction analysis can be performed according to a pre-trained target state recognition model, and an analysis result is output, so that target state information can be correspondingly determined according to the analysis result.
The method can synthesize the mean waveform through clustering, thereby smoothing filtering, effectively weakening the influence of baseline drift noise, myoelectric noise, power frequency interference and sudden noise, and greatly improving the accuracy of marking the starting and stopping points of P waves, QRS waves and T waves.
In an optional embodiment of the invention, to determine the target state recognition model, the method may further comprise: acquiring sample data information of the sample electrocardiogram, wherein the sample data information comprises P waves, QRS waves, T waves, ST segments, R wave notches, QRS wave forms, QRS wave voltage change information and RR interval data information of all heartbeats; and training a preset machine learning algorithm according to the sample data information and a target state identification label corresponding to the sample electrocardiogram, and determining a target state identification model.
Specifically, sample data information such as P-wave, QRS-wave, T-wave, and ST-wave, R-wave notch, QRS-wave morphology, RR interval information of all heartbeats in the QRS voltage variation process of the sample electrocardiogram may be acquired, and a preset machine learning algorithm may be trained by using a target state identification tag corresponding to the sample electrocardiogram to determine the target state identification model, where the target state identification tag corresponding to the sample electrocardiogram may be a correspondence between an identification result of the sample electrocardiogram and the target state, for example: after the characteristics of the sample data information are extracted, the corresponding target state information may be identified according to the corresponding target state identification tag, for example, the target state information may be heart state information, and specifically may include abnormal beats from an atrium or a ventricle, atrioventricular, bundle branch block, arrhythmia, and the like. The recognition target state recognition model may be used to determine target state information, and the machine learning algorithm may include a deep learning algorithm, an SVM algorithm, and the like.
Further, as a specific implementation of fig. 1, an embodiment of the present invention provides an electrocardiogram data processing apparatus, as shown in fig. 2, the apparatus including: an acquisition unit 21, a processing unit 22, a labeling unit 23, and an output unit 24.
The acquisition unit 21 can be used for acquiring all heart beat data information of a sample electrocardiogram;
the processing unit 22 may be configured to perform mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determine the processing result as a mean waveform of the sample electrocardiogram;
the labeling unit 23 may be configured to label information of a P wave, a QRS wave, a T wave, and an ST segment of the mean waveform.
The output unit 24 may be configured to output the labeled waveform information of the P wave, the QRS wave, the T wave, and the ST segment.
The processing unit 22 may include: a processing module 221, a detection module 222, a screening module 223, and a cluster merging module 224, as shown in fig. 3.
A processing module 221, which may be configured to perform noise processing on the heartbeat data information;
the detection module 222 may be configured to perform R-wave detection on the processed heartbeat data information to obtain R-wave data information;
the screening module 223 may be configured to screen the heartbeat data information according to the R-wave data information and a preset screening algorithm;
the cluster merging module 224 may be configured to perform cluster merging on the screening results, and determine a result of the cluster merging as a mean waveform of the sample electrocardiogram.
Further, the processing module 221 may be specifically configured to perform noise processing on the sample electrocardiogram data by using band-pass filtering.
Further, the screening module 223 may be specifically configured to calculate average RR interval data information according to the obtained RR interval data information of all heart beats, configure a screening interval according to the average RR interval data information, and screen the heart beat data information of which the RR interval data information is located in the screening interval.
Further, the cluster merging module 224 may be specifically configured to configure sampling points for the screened cardiac data information, perform an overlap averaging process on all the sampling points, and determine a result obtained by the process as a mean waveform of the sample electrocardiogram.
For the embodiment of the present invention, in order to obtain the R wave notch, the QRS wave form, and the QRS wave voltage variation information of the mean waveform, the apparatus may further include: a first analysis unit 25.
The first analyzing unit 25 may be configured to perform a wave band analysis on the mean waveform to obtain an R wave notch, a QRS wave form, and QRS wave voltage change information of the mean waveform.
The first analysis unit 25 may include: a judgment module 251, a determination module 252, and a recording module 253.
The determining module 251 may be configured to detect inflection point position information on two sides of a vertex of the R wave according to the mean waveform, and determine whether the R wave has a notch according to the inflection point position information;
a determining module 252, configured to calculate the number of QRS wave zero-crossing points in the mean waveform, and determine the morphology of QRS waves according to the number;
the recording module 253 may be configured to record voltage variation processes of waveforms on two sides of the central point by using a peak of the R wave in the mean waveform as the central point.
Further, the determining module 251 may be specifically configured to perform first-order difference processing on the mean waveform, detect inflection point position information on two sides of a vertex of the R wave, compare the inflection point position information with position information of start and stop points of the P wave, the QRS wave, the T wave, and the ST segment, and determine whether the R wave has a notch according to the comparison result.
For the embodiment of the present invention, in order to determine the target state information, the apparatus may further include: a second analysis unit 26.
The second analysis unit 26 may be configured to, when an electrocardiogram analysis processing request is received, perform predictive analysis according to electrocardiogram data information carried in the request and a pre-trained target state recognition model, and output an analysis result to determine target state information, where training sample data of the pre-trained target state recognition model is obtained by performing band analysis through mean wave processing.
For the embodiment of the present invention, in order to determine the target state recognition model, the apparatus may further include: an acquisition unit 27 and a training unit 28.
The obtaining unit 26 may be configured to obtain sample data information of the sample electrocardiogram, where the sample data information includes P-wave, QRS-wave, T-wave, ST-segment, R-wave notch, QRS-wave morphology, QRS-wave voltage variation information, and RR interval data information of all heartbeats;
the training unit 28 may be configured to train a preset machine learning algorithm according to the sample data information and the target state identification tag corresponding to the sample electrocardiogram, and determine a target state identification model.
Based on the method shown in fig. 1, correspondingly, an embodiment of the present invention further provides a storage medium, where the storage medium may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory, where the storage medium has at least one executable instruction stored therein, where the executable instruction causes a processor to perform the following steps: acquiring all heart beat data information of a sample electrocardiogram; carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram; and carrying out information annotation on the P wave, the QRS wave, the T wave and the ST segment on the mean value waveform, and outputting the annotated waveform information of the P wave, the QRS wave, the T wave and the ST segment.
Based on the above-mentioned embodiments of the method shown in fig. 1 and the apparatus shown in fig. 2, the embodiment of the present invention further provides a computer device, as shown in fig. 4, including a processor (processor)31, a communication Interface (communication Interface)32, a memory (memory)33, and a communication bus 34. Wherein: the processor 31, the communication interface 32, and the memory 33 communicate with each other via a communication bus 34. A communication interface 34 for communicating with network elements of other devices, such as clients or other servers. The processor 31 is configured to execute a program, and may specifically execute relevant steps in the above-described method embodiment of processing electrocardiogram data. In particular, the program may include program code comprising computer operating instructions. The processor 31 may be a central processing unit CPU or a Specific integrated circuit asic (application Specific integrated circuit) or one or more integrated circuits configured to implement an embodiment of the present invention.
The terminal comprises one or more processors, which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs. And a memory 33 for storing a program. The memory 33 may comprise a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory. The program may specifically be adapted to cause the processor 31 to perform the following operations: acquiring all heart beat data information of a sample electrocardiogram; carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram; and carrying out information annotation on the P wave, the QRS wave, the T wave and the ST segment on the mean value waveform, and outputting the annotated waveform information of the P wave, the QRS wave, the T wave and the ST segment.
According to the technical scheme, all heartbeat data information of the sample electrocardiogram are obtained; carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram; and carrying out information annotation on the P wave, the QRS wave, the T wave and the ST segment on the mean value waveform, and outputting the annotated waveform information of the P wave, the QRS wave, the T wave and the ST segment. Therefore, the mean waveform can be synthesized through clustering, so that smooth filtering is realized, the influence of baseline drift noise, myoelectric noise, power frequency interference and sudden noise is effectively weakened, and the accuracy of marking the starting and stopping points of P waves, QRS waves and T waves is greatly improved.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It will be appreciated that the relevant features of the method and apparatus described above are referred to one another. In addition, "first", "second", and the like in the above embodiments are for distinguishing the embodiments, and do not represent merits of the embodiments.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in accordance with embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. An electrocardiogram data processing method, characterized by comprising:
acquiring all heart beat data information of a sample electrocardiogram;
carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm, and determining the processing result as a mean waveform of the sample electrocardiogram;
carrying out information annotation on P waves, QRS waves, T waves and ST segments of the mean waveform;
and outputting the labeled waveform information of the P wave, the QRS wave, the T wave and the ST segment.
2. The method of claim 1, wherein the performing mean wave processing on the heartbeat data information according to a preset cluster merging algorithm and determining the processing result as a mean waveform of the sample electrocardiogram comprises:
carrying out noise processing on the heartbeat data information, and carrying out R wave detection on the processed heartbeat data information to obtain R wave data information;
screening the heartbeat data information according to the R wave data information and a preset screening algorithm;
and clustering and merging the screening results, and determining the result obtained by clustering and merging as the mean waveform of the sample electrocardiogram.
3. The method of claim 2, wherein said noise processing said heartbeat data information comprises:
carrying out noise processing on the sample electrocardiogram data by using band-pass filtering;
the screening of the heartbeat data information according to the R wave data information and a preset screening algorithm comprises the following steps:
calculating average RR interval data information according to the acquired RR interval data information of all heartbeats;
configuring a screening interval according to the average RR interval data information, and screening heart beat data information of the RR interval data information in the screening interval;
the clustering and merging the screening results and determining the result obtained by clustering and merging as the mean waveform of the sample electrocardiogram comprise:
configuring sampling points for the screened heartbeat data information, and carrying out superposition averaging processing on all the sampling points;
and determining the processed result as a mean waveform of the sample electrocardiogram.
4. The method of claim 1, wherein after said information labeling of P-wave, QRS-wave, T-wave and ST-segment of said mean waveform, said method further comprises:
and carrying out wave band analysis on the mean waveform to obtain R wave notch, QRS wave form and QRS wave voltage change information of the mean waveform.
5. The method of claim 4, wherein said performing a band analysis on said mean waveform to obtain information about R wave notch, QRS wave morphology, and QRS wave voltage variation of said mean waveform comprises:
according to the mean value waveform, inflection point position information on two sides of the R wave vertex is detected, and whether the R wave has a notch or not is judged according to the inflection point position information;
calculating the number of QRS wave zero-crossing points in the mean waveform, and determining the form of QRS waves according to the number;
and respectively recording the voltage change processes of the waveforms on two sides of the central point by taking the peak of the R wave in the mean waveform as the central point.
6. The method of claim 5, wherein the detecting inflection point position information on both sides of an R wave vertex according to the mean value waveform and determining whether the R wave has a notch according to the inflection point position information comprises:
performing first-order difference processing on the mean value waveform, and detecting inflection point position information on two sides of the top point of the R wave;
comparing the inflection point position information with the position information of the starting and ending points of the P wave, the QRS wave, the T wave and the ST segment;
and judging whether the R wave has the notch or not according to the comparison result.
7. The method of claim 4, wherein after performing a band analysis on the mean waveform to obtain information about R wave notch, QRS wave morphology, and QRS wave voltage variation of the mean waveform, the method further comprises:
when an electrocardiogram analysis processing request is received, prediction analysis is carried out according to electrocardiogram data information carried in the request and a pre-trained target state recognition model, an analysis result is output to determine target state information, and training sample data of the pre-trained target state recognition model is obtained through mean wave processing and band analysis.
8. An electrocardiogram data processing apparatus, comprising:
the acquisition unit is used for acquiring all heartbeat data information of the sample electrocardiogram;
the processing unit is used for carrying out mean wave processing on the heartbeat data information according to a preset clustering and merging algorithm and determining the processing result as a mean waveform of the sample electrocardiogram;
the marking unit is used for marking the information of the P wave, the QRS wave, the T wave and the ST segment of the mean value waveform;
and the output unit is used for outputting the labeled waveform information of the P wave, the QRS wave, the T wave and the ST segment.
9. A storage medium having a computer program stored thereon, the storage medium having stored therein at least one executable instruction that causes a processor to perform operations corresponding to the method of electrocardiographic data processing according to any one of claims 1-7.
10. A computer device comprising a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus, and the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the electrocardiogram data processing according to any one of claims 1-7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010123259.0A CN111419212A (en) | 2020-02-27 | 2020-02-27 | Method and device for processing electrocardiogram data, storage medium and computer equipment |
| PCT/CN2020/119053 WO2021169296A1 (en) | 2020-02-27 | 2020-09-29 | Method and apparatus for processing electrocardiogram data, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010123259.0A CN111419212A (en) | 2020-02-27 | 2020-02-27 | Method and device for processing electrocardiogram data, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111419212A true CN111419212A (en) | 2020-07-17 |
Family
ID=71547239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010123259.0A Pending CN111419212A (en) | 2020-02-27 | 2020-02-27 | Method and device for processing electrocardiogram data, storage medium and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111419212A (en) |
| WO (1) | WO2021169296A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111959132A (en) * | 2020-08-17 | 2020-11-20 | 厦门纳龙科技有限公司 | Electrocardiogram chest lead halving report printing method, terminal equipment and storage medium |
| CN111956205A (en) * | 2020-10-21 | 2020-11-20 | 平安科技（深圳）有限公司 | Electrocardiogram data processing equipment, method and device and storage medium |
| CN112799556A (en) * | 2021-01-26 | 2021-05-14 | 浙江吉利控股集团有限公司 | Vehicle data display control method and waveform display device |
| 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 |
| WO2023071268A1 (en) * | 2021-11-01 | 2023-05-04 | 毕胜普生物科技有限公司 | Method and apparatus for analyzing high-frequency qrs-complex data |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114073534B (en) * | 2021-11-25 | 2023-05-26 | 成都泰盟软件有限公司 | Heart function analysis algorithm |
| CN115486855B (en) * | 2022-09-15 | 2024-05-03 | 浙江好络维医疗技术有限公司 | Electrocardiogram and heart beat classification method based on QRS complex indefinite cycle superposition |
| CN115778402B (en) * | 2022-12-02 | 2024-08-30 | 深圳华清心仪医疗电子有限公司 | Artifact identification method and system for dynamic electrocardiosignal |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1084044A (en) * | 1992-09-11 | 1994-03-23 | 中日友好医院 | Three-D high frequency electrocardio signal analytical system and method |
| CN1915166A (en) * | 2006-08-15 | 2007-02-21 | 武汉大学 | Method for examining property of heart recovery based on cardiogram of flat motion |
| CN101103910A (en) * | 2006-07-14 | 2008-01-16 | 深圳迈瑞生物医疗电子股份有限公司 | Electrocardiogram computer-aided diagnosis system and method |
| CN101268938A (en) * | 2008-04-30 | 2008-09-24 | 董军 | Method and apparatus for electrocardiogram recognition and specification |
| CN101766484A (en) * | 2010-01-18 | 2010-07-07 | 董军 | Method and equipment for identification and classification of electrocardiogram |
| CN102188240A (en) * | 2010-03-05 | 2011-09-21 | 华东师范大学 | Electrocardiographic data sampling method and device |
| CN102397067A (en) * | 2011-12-07 | 2012-04-04 | 秦皇岛市康泰医学系统有限公司 | Method and system for performing superposition analysis on exercise load electrocardio waveforms |
| CN102834050A (en) * | 2011-07-25 | 2012-12-19 | 深圳市理邦精密仪器股份有限公司 | Method and system for automated detection and analysis in pediatric electrocardiography |
| CN103083013A (en) * | 2013-01-18 | 2013-05-08 | 哈尔滨工业大学深圳研究生院 | Electrocardio signal QRS complex wave detection method based on morphology and wavelet transform |
| CN104398257A (en) * | 2014-12-08 | 2015-03-11 | 蚌埠医学院 | Electrocardio waveform periodicity statistic analysis method |
| CN104586383A (en) * | 2015-01-12 | 2015-05-06 | 北京世纪今科医疗器械有限公司 | Electrocardiogram waveform classification method and device |
| CN105640545A (en) * | 2015-12-31 | 2016-06-08 | 深圳先进技术研究院 | Fetal electrocardiosignal extraction method and device |
| CN110226919A (en) * | 2019-06-26 | 2019-09-13 | 广州视源电子科技股份有限公司 | Electrocardiosignal type detection method and device, computer equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10779744B2 (en) * | 2015-10-27 | 2020-09-22 | Cardiologs Technologies Sas | Automatic method to delineate or categorize an electrocardiogram |
| US9706938B2 (en) * | 2015-10-29 | 2017-07-18 | Medtronic Monitoring, Inc. | System and method to determine premature ventricular contraction (PVC) type and burden |
| CN106108889B (en) * | 2016-07-20 | 2019-11-08 | 杨一平 | Electrocardiogram classification method based on deep learning algorithm |
| CN110367969A (en) * | 2019-07-05 | 2019-10-25 | 复旦大学 | A kind of improved electrocardiosignal K-Means Cluster |
| CN111419212A (en) * | 2020-02-27 | 2020-07-17 | 平安科技（深圳）有限公司 | Method and device for processing electrocardiogram data, storage medium and computer equipment |
-
2020
- 2020-02-27 CN CN202010123259.0A patent/CN111419212A/en active Pending
- 2020-09-29 WO PCT/CN2020/119053 patent/WO2021169296A1/en active Application Filing
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1084044A (en) * | 1992-09-11 | 1994-03-23 | 中日友好医院 | Three-D high frequency electrocardio signal analytical system and method |
| CN101103910A (en) * | 2006-07-14 | 2008-01-16 | 深圳迈瑞生物医疗电子股份有限公司 | Electrocardiogram computer-aided diagnosis system and method |
| CN1915166A (en) * | 2006-08-15 | 2007-02-21 | 武汉大学 | Method for examining property of heart recovery based on cardiogram of flat motion |
| CN101268938A (en) * | 2008-04-30 | 2008-09-24 | 董军 | Method and apparatus for electrocardiogram recognition and specification |
| CN101766484A (en) * | 2010-01-18 | 2010-07-07 | 董军 | Method and equipment for identification and classification of electrocardiogram |
| CN102188240A (en) * | 2010-03-05 | 2011-09-21 | 华东师范大学 | Electrocardiographic data sampling method and device |
| CN102834050A (en) * | 2011-07-25 | 2012-12-19 | 深圳市理邦精密仪器股份有限公司 | Method and system for automated detection and analysis in pediatric electrocardiography |
| CN102397067A (en) * | 2011-12-07 | 2012-04-04 | 秦皇岛市康泰医学系统有限公司 | Method and system for performing superposition analysis on exercise load electrocardio waveforms |
| CN103083013A (en) * | 2013-01-18 | 2013-05-08 | 哈尔滨工业大学深圳研究生院 | Electrocardio signal QRS complex wave detection method based on morphology and wavelet transform |
| CN104398257A (en) * | 2014-12-08 | 2015-03-11 | 蚌埠医学院 | Electrocardio waveform periodicity statistic analysis method |
| CN104586383A (en) * | 2015-01-12 | 2015-05-06 | 北京世纪今科医疗器械有限公司 | Electrocardiogram waveform classification method and device |
| CN105640545A (en) * | 2015-12-31 | 2016-06-08 | 深圳先进技术研究院 | Fetal electrocardiosignal extraction method and device |
| CN110226919A (en) * | 2019-06-26 | 2019-09-13 | 广州视源电子科技股份有限公司 | Electrocardiosignal type detection method and device, computer equipment and storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111959132A (en) * | 2020-08-17 | 2020-11-20 | 厦门纳龙科技有限公司 | Electrocardiogram chest lead halving report printing method, terminal equipment and storage medium |
| CN111959132B (en) * | 2020-08-17 | 2021-11-16 | 厦门纳龙科技有限公司 | Electrocardiogram chest lead halving report printing method, terminal equipment and storage medium |
| CN111956205A (en) * | 2020-10-21 | 2020-11-20 | 平安科技（深圳）有限公司 | Electrocardiogram data processing equipment, method and device and storage medium |
| CN111956205B (en) * | 2020-10-21 | 2021-01-08 | 平安科技（深圳）有限公司 | Electrocardiogram data processing equipment, method and device and storage medium |
| CN112799556A (en) * | 2021-01-26 | 2021-05-14 | 浙江吉利控股集团有限公司 | Vehicle data display control method and waveform display device |
| WO2023071268A1 (en) * | 2021-11-01 | 2023-05-04 | 毕胜普生物科技有限公司 | Method and apparatus for analyzing high-frequency qrs-complex data |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021169296A1 (en) | 2021-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111419212A (en) | Method and device for processing electrocardiogram data, storage medium and computer equipment | |
| Kathirvel et al. | An efficient R-peak detection based on new nonlinear transformation and first-order Gaussian differentiator | |
| Arzeno et al. | Analysis of first-derivative based QRS detection algorithms | |
| Mazomenos et al. | A time-domain morphology and gradient based algorithm for ECG feature extraction | |
| CN111134659B (en) | Method and device for detecting P wave and T wave in electrocardiosignal | |
| US20070197926A1 (en) | Method for analysing an intracardiac electrocardiogram and an electrophysiological system as well as a computer program product | |
| US20060167364A1 (en) | Algorithms for detecting cardiac arrhythmia and methods and apparatuses utilizing the algorithms | |
| JP2000333922A (en) | System and method for quantifying alternation of electrocardiogram signal | |
| EP2713866B1 (en) | Classification of atrial fibrillation by determining an af complexity value | |
| US8684942B2 (en) | System for cardiac impairment detection based on signal regularity | |
| US10856756B2 (en) | Time-frequency analysis of electrocardiograms | |
| WO2015171804A1 (en) | Detecting artifacts in a signal | |
| Umer et al. | Electrocardiogram feature extraction and pattern recognition using a novel windowing algorithm | |
| CN113499082B (en) | QRS complex detection method, electrocardiograph detection device and readable storage medium | |
| Gupta et al. | R-peak based arrhythmia detection using hilbert transform and principal component analysis | |
| JPH10211180A (en) | Method for automatically diagnosing heart function | |
| KR20140097039A (en) | Method and apparatus for classifying cardiac arrhythmia using an auto associative neural network | |
| CN109009071A (en) | A kind of method and apparatus identifying electrocardio wave image characteristic point | |
| Burte et al. | Advances in QRS detection: Modified Wavelet energy gradient method | |
| CN114668401B (en) | AI (artificial intelligence) electrocardiogram training data labeling method and device, electronic equipment and medium | |
| CN116135147B (en) | Electrocardiosignal processing method and device, electronic equipment and storage medium | |
| CN113288169B (en) | Waveform identification method, device and equipment for electrocardiographic waveform signals | |
| CN112438735B (en) | Electrocardiogram P wave detection method, analysis device and storage medium | |
| Kužílek et al. | Processing holter ECG signal corrupted with noise: Using ICA for QRS complex detection | |
| Sbrollini et al. | Athria: a new adaptive threshold identification algorithm for electrocardiographic p waves |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200717 |
|
| RJ01 | Rejection of invention patent application after publication |