CN116350199A - Dynamic electrocardiogram and heart beat template generation method and system - Google Patents
Dynamic electrocardiogram and heart beat template generation method and system Download PDFInfo
- Publication number
- CN116350199A CN116350199A CN202310630528.6A CN202310630528A CN116350199A CN 116350199 A CN116350199 A CN 116350199A CN 202310630528 A CN202310630528 A CN 202310630528A CN 116350199 A CN116350199 A CN 116350199A
- Authority
- CN
- China
- Prior art keywords
- heart beat
- heart
- global
- beats
- divided
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 206010015856 Extrasystoles Diseases 0.000 claims description 12
- 208000000418 Premature Cardiac Complexes Diseases 0.000 claims description 12
- 238000011282 treatment Methods 0.000 claims description 11
- 230000006698 induction Effects 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 230000001746 atrial effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002861 ventricular Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000011419 induction treatment Methods 0.000 claims description 2
- 230000000747 cardiac effect Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 description 3
- 206010003119 arrhythmia Diseases 0.000 description 2
- 230000006793 arrhythmia Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002565 electrocardiography Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004660 morphological change Effects 0.000 description 1
- 208000031225 myocardial ischemia Diseases 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/0245—Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—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
-
- 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
- A61B5/35—Detecting specific parameters of the electrocardiograph cycle by template matching
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention belongs to the technical field of electrocardiosignal processing, and relates to a method for acquiring heart beat data; dividing the acquired heart beat according to the detected heart beat type to generate divided heart beat; calculating the median heart beat of the divided heart beats and extracting the local features and the global features of the median heart beat and the divided heart beats; performing hard rule division on the global features; performing soft rule division on the global features and the local features to generate a heart beat template; the heart beat template comprises N heart beats, and the heart beats with N less than 5 are divided into other heart beat templates. Therefore, the difference of global features can be reduced, heartbeats with larger waveform forms can be finely divided, and the accuracy of dividing the heart beat templates is improved.
Description
Technical Field
The invention belongs to the technical field of electrocardiosignals, and particularly relates to a method and a system for generating a dynamic electrocardiogram and heart beat template.
Background
Dynamic electrocardiography is a method that can continuously record and analyze electrocardiographic changes of the human heart in active and quiet states for a long period of time. Compared with the common electrocardiogram, the dynamic electrocardiogram can continuously record about 10 ten thousand times of electrocardiosignals within 24 hours, so that the detection rate of non-sustained arrhythmia, particularly transient arrhythmia and transient myocardial ischemia attack can be improved, and the clinical application range of the electrocardiogram is widened. However, the amplification of data volume further increases the difficulty of data analysis, which makes automatic electrocardiographic detection and analysis techniques necessary. In computer-aided diagnostic analysis of dynamic electrocardiography, physicians often focus on morphological changes in a single heartbeat (i.e., heart beat). However, in a dynamic electrocardiogram, the number of thousands of beats makes it necessary for a doctor to consume a great deal of effort to complete analysis of the dynamic electrocardiogram. Thus, accurate partitioning of the heart beat in rapid batches by matching to the heart beat template becomes extremely important.
At present, the heart beat dividing mode is generally further edited after pretreatment by adopting a template classifying method. However, the following two key issues prevent accurate generation of dynamic electrocardiographic heart beat templates.
1. Existing methods tend to focus on local features in the heart beat, ignoring the integrity. This results in a partitioned template that, although highly similar locally, still has a large difference globally.
2. The existing calculation mode carries out template similarity calculation by extracting a plurality of features, the comparison mode is single, so that the similarity is smaller, the features are close to templates, but heartbeats with larger waveform morphology differences can be divided into the same class, and the accuracy of heart beat division is seriously affected.
Disclosure of Invention
In view of the above problems, the invention provides a method and a system for generating a dynamic electrocardiogram heart beat template, which can reduce the difference of global features, finely divide heart beats with larger waveform forms and improve the accuracy of heart beat template division.
A method for generating a dynamic electrocardiogram and heart beat template, comprising: the method comprises the steps of obtaining heart beat data, wherein S1, the obtained heart beats are divided according to detected heart beat types to generate different types of divided heart beats, wherein the heart beat types comprise normal heart beats, atrial premature beats, ventricular premature beats, pacing, artifacts and unknown heart beats;
s2, calculating the median heart beat of one type of divided heart beat and extracting the characteristic point positions of the median heart beat and the divided heart beat, wherein the characteristic point positions of the median heart beat and the divided heart beat are obtained by extracting the characteristic points of the median heart beat and the divided heart beat through wavelet transformation; the characteristic points comprise Q wave positions, R wave positions and S wave positions;
s3, extracting local features and global features of the central heart beat and the divided heart beat according to the obtained feature points;
s4, carrying out hard rule division on a certain class of divided heart beats by the global features, and dividing the heart beats one by using the global features and set hard conditions from the first heart beat of the divided heart beats; repeatedly dividing the heart beat one by using the global features and the set hard conditions from the first heart beat of dividing the heart beat until all the global features are used to obtain a series of global feature heart beat templates and heart beats corresponding to the global feature heart beat templates;
s5, carrying out soft rule division on heartbeats corresponding to each global characteristic heartbeat template by the global characteristic and the local characteristic to generate a final heartbeat template; specifically, the local similarity P of heart beat is calculated by heart beat and median heart beat corresponding to each type of global characteristic heart beat template l And a global similarity Pg; carrying out induction processing according to the local similarity and the global similarity to obtain a heart beat template;
s6, counting the number of heart beats of the heart beat template obtained in the step S5, wherein the heart beat template comprises N heart beats, and dividing the heart beats with N less than 5 into other heart beat templates corresponding to each global feature;
s7, repeating the steps S1-S6 to obtain template generation of heart beats corresponding to the global characteristic heart beat template;
and S8, repeating the steps S1-S7 to obtain template generation for completing different types of divided heart beats.
Further, comparing the median heart beat and the divided heart beat feature points to determine feature point positions;
wherein the position of the feature point is further refined by comparing the magnitude within 0.05 seconds each to the left and right of the center beat and the divided heart beat feature point.
Further, the global features include: number of heart beat R waves, global height of heart beat, offset before and after heart beat; the local features include: the R/S amplitude ratio in the center QRS wave, the center QRS wave area, the center QRS wave width, the center QRS wave height, and the center QRS wave QR/RS offset.
Further, the method further comprises: calculating characteristics according to the Q wave position, the R wave position and the S wave position; the R/S amplitude ratio and the central QRS wave height in the QRS wave are calculated according to the R wave position and the S wave position;
calculating to obtain the characteristic center QRS wave area according to the Q wave position, the R wave position and the S wave position and the amplitude;
calculating to obtain the characteristic center QRS wave width according to the Q wave position and the R wave position;
and calculating according to the ratio of the sum of the absolute values of the amplitude values from the Q wave to the R wave to the sum of the absolute values of the amplitude values from the R wave to the S wave to obtain the QRS wave QR/RS offset of the characteristic center.
Further, extracting global features of the median heart beat and the divided heart beat includes: calculating the sum of the R wave amplitudes in the median heart beat and the divided heart beat through a wave crest detection algorithm; and calculating by extracting the sum of the maximum value and the minimum value absolute value of the amplitude in the heart beat to obtain the global heart beat height.
Further, the extracting global features of the median heart beat and the divided heart beat further includes: and calculating the pre-and post-heartbeat offset according to the ratio of the sum of the absolute values of the amplitudes from the heart beat starting point to the central R wave to the sum of the absolute values of the amplitudes from the heart beat starting point to the heart beat ending point.
Further, the method also comprises feature similarity calculation; comprises calculating global similarity P according to global features of heart beat and median heart beat corresponding to each type of global feature heart beat template g The method comprises the steps of carrying out a first treatment on the surface of the Calculating global similarity P according to the local features of heart beat and median heart beat corresponding to each type of global feature heart beat template l The method comprises the steps of carrying out a first treatment on the surface of the According to the local similarity P l And the global similarity P g And carrying out induction treatment to obtain the heart beat template.
Based on the above inventive concept, the present invention further provides a dynamic electrocardiogram and heart beat template generating system, comprising: the acquisition module is used for acquiring heart beat data, dividing the acquired heart beats according to the detected heart beat types, and generating different types of divided heart beats, wherein the heart beat types comprise normal heart beats, atrial premature beats, ventricular premature beats, paces, artifacts and unknown heart beats;
the calculating module is used for calculating the median heart beat of one type of divided heart beat and extracting the characteristic point positions of the median heart beat and the divided heart beat, wherein the characteristic point positions of the median heart beat and the divided heart beat are obtained by extracting the characteristic points of the median heart beat and the divided heart beat through wavelet transformation; the characteristic points comprise Q wave positions, R wave positions and S wave positions;
the extraction module is used for extracting local features and global features of the central heart beat and the divided heart beat according to the acquired feature points;
dividing the module byPerforming hard rule division on a certain type of divided heart beat by using the global features, and dividing the heart beat one by using the global features and the set hard conditions from the first heart beat of the divided heart beat; repeatedly dividing the heart beat one by using the global features and the set hard conditions from the first heart beat of dividing the heart beat until all the global features are used to obtain a series of global feature heart beat templates and heart beats corresponding to the global feature heart beat templates; s4, carrying out soft rule division on the heart beats corresponding to each global feature heart beat template by the global features and the local features to generate a final heart beat template; specifically, the local similarity P of heart beat is calculated by heart beat and median heart beat corresponding to each type of global characteristic heart beat template l And global similarity P g The method comprises the steps of carrying out a first treatment on the surface of the Carrying out induction processing according to the local similarity and the global similarity to obtain a heart beat template;
the statistics module is used for counting the number of heart beats, the heart beat templates comprise N heart beats, and the heart beats with N less than 5 are divided into other heart beat templates corresponding to each global feature; repeating the steps S1-S6 to obtain template generation of the heart beat corresponding to the global characteristic heart beat template; and repeating the steps S1 to S7 to obtain the template generation for completing the different types of divided heart beats.
Based on the same inventive concept, the invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any one of the methods for generating a dynamic electrocardiogram and heart beat template when executing the program.
Based on the same inventive concept, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements the steps of any one of the methods of generating a dynamic electrocardiogram and heart beat template.
The above-mentioned one or at least one technical solution in the embodiments of the present application has at least the following technical effects:
the invention acquires heart beat data; dividing the acquired heart beat according to the detected heart beat type to generate divided heart beat; calculating the median heart beat of the divided heart beats and extracting the local features and the global features of the median heart beat and the divided heart beats; performing hard rule division on the global features; performing soft rule division on the local features to generate a heart beat template; the heart beat templates comprise N heart beats, and the heart beat templates with N less than 5 are divided into other heart beat templates. Therefore, the difference of global features can be reduced, heartbeats with larger waveform forms can be finely divided, and the accuracy of dividing the heart beat templates is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for generating a heart beat template according to the present invention;
FIG. 2 is a schematic diagram of a heart beat template generation system of the present invention;
fig. 3 is a schematic diagram of a heart beat template dividing process according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "first," "second," and the like herein are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. In the present application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate an azimuth or a positional relationship based on that shown in the drawings.
The invention provides a method for generating a dynamic electrocardiogram and heart beat template, which comprises the following steps: s1, acquiring heart beat data, dividing the acquired heart beats according to detected heart beat types, and generating different types of divided heart beats, wherein the heart beat types comprise normal heart beats, atrial premature beats, ventricular premature beats, paces, artifacts and unknown heart beats;
s2, calculating the median heart beat of one type of divided heart beat and extracting the characteristic point positions of the median heart beat and the divided heart beat, wherein the characteristic point positions of the median heart beat and the divided heart beat are obtained by extracting the characteristic points of the median heart beat and the divided heart beat through wavelet transformation; the characteristic points comprise Q wave positions, R wave positions and S wave positions;
s3, extracting local features and global features of the central heart beat and the divided heart beat according to the obtained feature points;
s4, carrying out hard rule division on a certain class of divided heart beats by the global features, and dividing the heart beats one by using the global features and set hard conditions from the first heart beat of the divided heart beats; repeatedly dividing the heart beat one by using the global features and the set hard conditions from the first heart beat of dividing the heart beat until all the global features are used to obtain a series of global feature heart beat templates and heart beats corresponding to the global feature heart beat templates;
s5, carrying out soft rule division on heartbeats corresponding to each global characteristic heartbeat template by the global characteristic and the local characteristic to generate a final heartbeat template; specifically, each ofHeart beat local similarity P calculated by heart beat corresponding to global feature heart beat template and median heart beat l And global similarity P g The method comprises the steps of carrying out a first treatment on the surface of the Carrying out induction processing according to the local similarity and the global similarity to obtain a heart beat template;
s6, counting the number of heart beats of the heart beat template obtained in the step S5, wherein the heart beat template comprises N heart beats, and dividing the heart beats with N less than 5 into other heart beat templates corresponding to each global feature;
s7, repeating the steps S1-S6 to obtain template generation of heart beats corresponding to the global characteristic heart beat template;
and S8, repeating the steps S1-S7 to obtain template generation for completing different types of divided heart beats.
The invention is applied to the medical instrument technology, and mainly generates a heart beat template based on tree-shaped classified dynamic electrocardiogram; the dynamic electrocardiogram heart beat template generation method provided by the embodiment of the specification can be applied to terminal equipment or a server, wherein the terminal equipment comprises equipment such as a smart watch, a notebook computer, a desktop computer, a smart phone, a tablet computer and the like; the server comprises a notebook computer, a desktop computer, an integrated machine, a tablet computer and other devices.
In some alternative embodiments, the median heart beat and the divided heart beat feature points are compared to determine feature point locations;
wherein the position of the feature point is further refined by comparing the magnitude within 0.05 seconds each to the left and right of the center beat and the divided heart beat feature point.
In some alternative embodiments, the global features include: number of heart beat R waves, global height of heart beat, offset before and after heart beat; the local features include: the R/S amplitude ratio in the center QRS wave, the center QRS wave area, the center QRS wave width, the center QRS wave height, and the center QRS wave QR/RS offset. Wherein the QRS wave specifically refers to the following, and the Q wave is the first downward waveform; the R wave is the first upward wave form; the S wave is a waveform that follows downward; the QRS wave reflects the overall condition of the electrocardiogram.
Specifically, referring to fig. 3, hard rule partitioning the global features includes: and acquiring the number of R wave peaks, and acquiring the heights of a plurality of heart beat global features according to the acquired R wave peaks.
In some alternative embodiments, the extracting the local features of the median heart beat and the divided heart beat includes: extracting the positions of the central heart beat and the heart beat dividing feature points through wavelet transformation; the feature points include a Q wave position, an R wave position, and an S wave position.
In some alternative embodiments, the method further comprises: calculating characteristics according to the Q wave position, the R wave position and the S wave position; the R/S amplitude ratio and the central QRS wave height in the QRS wave are calculated according to the R wave position and the S wave position;
calculating to obtain the characteristic center QRS wave area according to the Q wave position, the R wave position and the S wave position and the amplitude;
calculating to obtain the characteristic center QRS wave width according to the Q wave position and the R wave position;
and calculating according to the ratio of the sum of the absolute values of the amplitude values from the Q wave to the R wave to the sum of the absolute values of the amplitude values from the R wave to the S wave to obtain the QRS wave QR/RS offset of the characteristic center.
In some alternative embodiments, extracting global features of the median and divided heart beats includes: calculating the sum of the R wave amplitudes in the median heart beat and the divided heart beat through a wave crest detection algorithm; and calculating by extracting the sum of the maximum value and the minimum value absolute value of the amplitude in the heart beat to obtain the global heart beat height.
In some alternative embodiments, the extracting global features of the median heart beat and the divided heart beat further comprises: and calculating the pre-and post-heartbeat offset according to the ratio of the sum of the absolute values of the amplitudes from the heart beat starting point to the central R wave to the sum of the absolute values of the amplitudes from the heart beat starting point to the heart beat ending point.
Specifically, referring to fig. 3, a plurality of R-wave peaks are acquired, a global heart beat height of the R-wave peaks is calculated, and a global heart beat height is calculated at the same time; the heart beat is divided according to its global height.
Specifically, heart beats with a heart beat global height of more than or equal to one hundred and five percent of a median heart beat global height are divided into first heart beats, heart beats with a heart beat global height of less than one hundred and five percent of the median heart beat global height and more than or equal to ninety five percent of the median heart beat global height are divided into second heart beats, and heart beats with a heart beat global height of less than ninety five percent of the median heart beat global height are divided into third heart beats;
calculating the front-back offset of the first class of heart beat, calculating the front-back offset of the middle heart beat, and comparing and dividing the front-back offset of the middle heart beat with the front-back offset of the first class of heart beat;
specifically, heart beats with a pre-and-post offset greater than or equal to one hundred and five percent of a pre-and-post offset of a median heart beat are divided into fourth heart beats, heart beats with a pre-and-post offset less than one hundred and five percent of a pre-and-post offset of a median heart beat and greater than or equal to ninety five percent of a pre-and-post offset of a median heart beat are divided into fifth heart beats, and heart beats with a pre-and-post offset less than ninety five percent of a pre-and-post offset of a median heart beat are divided into sixth heart beats;
calculating the sum of the heart beat R wave amplitudes of the fourth type of heart beat, calculating the sum of the heart beat R wave amplitudes of the middle position, and comparing and dividing the sum of the heart beat R wave amplitudes of the middle position with the sum of the heart beat R wave amplitudes of the fourth type of heart beat;
specifically, heart beats with the central-position heart beat R wave amplitude and more than or equal to the central-position heart beat R wave amplitude and one hundred and five percent are divided into a seventh heart beat, heart beats with the central-position heart beat R wave amplitude and less than one hundred and five percent and more than or equal to the central-position heart beat R wave amplitude and ninety five percent are divided into an eighth heart beat, and heart beats with the heart beat R wave amplitude and less than the central-position heart beat R wave amplitude and ninety five percent are divided into a ninth heart beat; feature similarity calculation is performed for the seventh, eighth, and ninth classes of heart beats, respectively.
In some alternative embodiments, the method further comprises feature similarity calculation; calculating global similarity Pg according to global features of heart beats and median heart beats corresponding to each type of global feature heart beat template; calculating global similarity P according to the local features of heart beat and median heart beat corresponding to each type of global feature heart beat template l The method comprises the steps of carrying out a first treatment on the surface of the According to the local similarity P l And carrying out induction processing on the global similarity Pg to obtain a heart beat template.
Specifically, the specific process of calculating the feature similarity is as follows: acquiring a first heart beat in a heart beat set screened based on a global characteristic hard rule, and calculating a local correlation coefficient and a global correlation coefficient between the first heart beat and other heart beats; the similarity is represented by a correlation coefficient, wherein the local correlation coefficient represents the local similarity P of heart beat l The method comprises the steps of carrying out a first treatment on the surface of the The global correlation coefficient represents the global similarity P of heart beat g 。
Specifically, the calculated local similarity P of heart beat l Global similarity to heart beat P g Multiplying to obtain final similarity P f Screening the final similarity, wherein the final similarity P is selected f Combining heart beats with the diameter of more than or equal to 0.96 into a template; calculating the final similarity P of the first heart beat in the non-combined heart beats f Will finally be similar to P f Combining the heart beats with the frequency of more than or equal to 0.96 into another template; according to the method, all heartbeats are combined, a series of heart beat templates are obtained, and accuracy of heart beat division can be improved through the method.
Based on the above inventive concept, the present invention further provides a dynamic electrocardiogram and heart beat template generating system, referring to fig. 2, including: the acquisition module is used for acquiring heart beat data, dividing the acquired heart beats according to the detected heart beat types, and generating different types of divided heart beats, wherein the heart beat types comprise normal heart beats, atrial premature beats, ventricular premature beats, paces, artifacts and unknown heart beats;
the calculating module is used for calculating the median heart beat of one type of divided heart beat and extracting the characteristic point positions of the median heart beat and the divided heart beat, wherein the characteristic point positions of the median heart beat and the divided heart beat are obtained by extracting the characteristic points of the median heart beat and the divided heart beat through wavelet transformation; the characteristic points comprise Q wave positions, R wave positions and S wave positions;
the extraction module is used for extracting local features and global features of the central heart beat and the divided heart beat according to the acquired feature points;
the dividing module is used for dividing the global feature into hard rules for a certain class of divided heart beats, and dividing the heart beats one by using the global feature and the set hard condition from the first heart beat of the divided heart beats; repeatedly dividing the heart beat one by using the global features and the set hard conditions from the first heart beat of dividing the heart beat until all the global features are used to obtain a series of global feature heart beat templates and heart beats corresponding to the global feature heart beat templates; s4, carrying out soft rule division on the heart beats corresponding to each global feature heart beat template by the global features and the local features to generate a final heart beat template; specifically, the local similarity P of heart beat is calculated by heart beat and median heart beat corresponding to each type of global characteristic heart beat template l And global similarity P g The method comprises the steps of carrying out a first treatment on the surface of the Carrying out induction processing according to the local similarity and the global similarity to obtain a heart beat template;
the statistics module is used for counting the number of heart beats, the heart beat templates comprise N heart beats, and the heart beats with N less than 5 are divided into other heart beat templates corresponding to each global feature; repeating the steps S1-S6 to obtain template generation of the heart beat corresponding to the global characteristic heart beat template; and repeating the steps S1 to S7 to obtain the template generation for completing the different types of divided heart beats.
Based on the same inventive concept, the invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any one of the methods for generating a dynamic electrocardiogram and heart beat template when executing the program.
Based on the same inventive concept, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements the steps of any one of the methods of generating a dynamic electrocardiogram and heart beat template.
The computer-readable storage medium may be embodied in the apparatus/means described in the above embodiments; or may exist alone without being assembled into the apparatus/device. The computer-readable storage medium carries one or more programs which, when executed, implement the steps of any one of the methods of generating a dynamic electrocardiogram and heart beat template according to embodiments of the present disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Based on the technical scheme, the heart beat data are acquired; dividing the acquired heart beat according to the detected heart beat type to generate divided heart beat; calculating the median heart beat of the divided heart beats and extracting the local features and the global features of the median heart beat and the divided heart beats; performing hard rule division on the global features; performing soft rule division on the local features to generate a heart beat template; the heart beat templates comprise N heart beats, and the heart beat templates with N less than 5 are divided into other heart beat templates. Therefore, the difference of global features can be reduced, heartbeats with larger waveform forms can be finely divided, and the accuracy of dividing the heart beat templates is improved.
Although the 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 scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for generating a dynamic electrocardiogram heart beat template, comprising: s1, acquiring heart beat data, dividing the acquired heart beats according to detected heart beat types, and generating different types of divided heart beats, wherein the heart beat types comprise normal heart beats, atrial premature beats, ventricular premature beats, paces, artifacts and unknown heart beats;
s2, calculating the median heart beat of one type of divided heart beat and extracting the characteristic point positions of the median heart beat and the divided heart beat, wherein the characteristic point positions of the median heart beat and the divided heart beat are obtained by extracting the characteristic points of the median heart beat and the divided heart beat through wavelet transformation; the characteristic points comprise Q wave positions, R wave positions and S wave positions;
s3, extracting global features and local features of the central heart beat and the divided heart beat according to the obtained feature points;
s4, carrying out hard rule division on a certain class of divided heart beats by the global features, and dividing the heart beats one by using the global features and set hard conditions from the first heart beat of the divided heart beats; repeating the steps of dividing the heart beats one by using the global features and the set hard conditions from the first heart beat of dividing the heart beats until all the global features are used to obtain a series of global feature heart beat templates and heart beats corresponding to the global feature heart beat templates;
s5, carrying out soft rule division on heartbeats corresponding to each global characteristic heartbeat template by the global characteristic and the local characteristic to generate a final heartbeat template; specifically, the local similarity P of heart beat is calculated by heart beat and median heart beat corresponding to each type of global characteristic heart beat template l And global similarity P g The method comprises the steps of carrying out a first treatment on the surface of the Carrying out induction processing according to the local similarity and the global similarity to obtain a heart beat template;
s6, counting the number of heart beats of the heart beat template obtained in the step S5, wherein the heart beat template comprises N heart beats, and dividing the heart beats with N less than 5 into other heart beat templates corresponding to each global feature;
s7, repeating the steps S1-S6 to obtain template generation of heart beats corresponding to the global characteristic heart beat template;
and S8, repeating the steps S1-S7 to obtain template generation for completing different types of divided heart beats.
2. The method of claim 1, wherein the median heart beat and the divided heart beat feature points are compared to determine feature point locations;
wherein the position of the feature point is further refined by comparing the magnitude within 0.05 seconds each to the left and right of the center beat and the divided heart beat feature point.
3. The method of claim 1, wherein the global features comprise: number of heart beat R waves, global height of heart beat, offset before and after heart beat; the local features include: the R/S amplitude ratio in the center QRS wave, the center QRS wave area, the center QRS wave width, the center QRS wave height, and the center QRS wave QR/RS offset.
4. The method according to claim 1, wherein the method further comprises: calculating characteristics according to the Q wave position, the R wave position and the S wave position; the R/S amplitude ratio and the central QRS wave height in the QRS wave are calculated according to the R wave position and the S wave position;
calculating to obtain the characteristic center QRS wave area according to the Q wave position, the R wave position and the S wave position and the amplitude;
calculating to obtain the characteristic center QRS wave width according to the Q wave position and the R wave position;
and calculating according to the ratio of the sum of the absolute values of the amplitude values from the Q wave to the R wave to the sum of the absolute values of the amplitude values from the R wave to the S wave to obtain the QRS wave QR/RS offset of the characteristic center.
5. The method of claim 1, wherein extracting global features of the median heart beat and the divided heart beat comprises: calculating the sum of the R wave amplitudes in the median heart beat and the divided heart beat through a wave crest detection algorithm; and calculating by extracting the sum of the maximum value and the minimum value absolute value of the amplitude in the heart beat to obtain the global heart beat height.
6. A method according to claim 1 or 3, wherein the extracting global features of the median and divided heart beats further comprises: and calculating the pre-and post-heartbeat offset according to the ratio of the sum of the absolute values of the amplitudes from the heart beat starting point to the central R wave to the sum of the absolute values of the amplitudes from the heart beat starting point to the heart beat ending point.
7. The method of claim 1, further comprising feature similarity calculation; comprises calculating global similarity P according to global features of heart beat and median heart beat corresponding to each type of global feature heart beat template g The method comprises the steps of carrying out a first treatment on the surface of the Calculating global similarity P according to the local features of heart beat and median heart beat corresponding to each type of global feature heart beat template l The method comprises the steps of carrying out a first treatment on the surface of the According to the local similarity P l And the global similarity P g And carrying out induction treatment to obtain the heart beat template.
8. A dynamic electrocardiogram and heart beat template generation system, comprising: the acquisition module is used for acquiring heart beat data, dividing the acquired heart beats according to the detected heart beat types, and generating different types of divided heart beats, wherein the heart beat types comprise normal heart beats, atrial premature beats, ventricular premature beats, paces, artifacts and unknown heart beats;
the calculating module is used for calculating the median heart beat of one type of divided heart beat and extracting the characteristic point positions of the median heart beat and the divided heart beat, wherein the characteristic point positions of the median heart beat and the divided heart beat are obtained by extracting the characteristic points of the median heart beat and the divided heart beat through wavelet transformation; the characteristic points comprise Q wave positions, R wave positions and S wave positions;
the extraction module is used for extracting local features and global features of the central heart beat and the divided heart beat according to the acquired feature points;
the dividing module is used for dividing the global feature into hard rules for a certain class of divided heart beats, and dividing the heart beats one by using the global feature and the set hard condition from the first heart beat of the divided heart beats; repeating the cardiac beat starting from the first heart beat of the divided heart beats using the global features and the set hard conditions one by oneDividing until all global features are used to obtain a series of global feature heart beat templates and heart beats corresponding to the global feature heart beat templates; s4, carrying out soft rule division on the heart beats corresponding to each global feature heart beat template by the global features and the local features to generate a final heart beat template; specifically, the local similarity P of heart beat is calculated by heart beat and median heart beat corresponding to each type of global characteristic heart beat template l And global similarity P g The method comprises the steps of carrying out a first treatment on the surface of the Carrying out induction processing according to the local similarity and the global similarity to obtain a heart beat template;
the statistics module is used for counting the number of heart beats, the heart beat templates comprise N heart beats, and the heart beats with N less than 5 are divided into other heart beat templates corresponding to each global feature; repeating the steps S1-S6 to obtain template generation of the heart beat corresponding to the global characteristic heart beat template; and repeating the steps S1 to S7 to obtain the template generation for completing the different types of divided heart beats.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1-7 when the program is executed.
10. A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310630528.6A CN116350199B (en) | 2023-05-31 | 2023-05-31 | Dynamic electrocardiogram and heart beat template generation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310630528.6A CN116350199B (en) | 2023-05-31 | 2023-05-31 | Dynamic electrocardiogram and heart beat template generation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116350199A true CN116350199A (en) | 2023-06-30 |
| CN116350199B CN116350199B (en) | 2023-08-18 |
Family
ID=86941927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310630528.6A Active CN116350199B (en) | 2023-05-31 | 2023-05-31 | Dynamic electrocardiogram and heart beat template generation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116350199B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
| CN102835954A (en) * | 2012-09-07 | 2012-12-26 | 深圳市邦健电子有限公司 | Method for generating heart beating waveform template and treating ventricular premature beat detection and device |
| WO2016034203A1 (en) * | 2014-09-01 | 2016-03-10 | Schiller Ag | Method and device for automatically classifying heartbeats, computer program product and ecg device for carrying out the method |
| CN107456227A (en) * | 2017-08-16 | 2017-12-12 | 北京蓬阳丰业医疗设备有限公司 | Full lead electrocardiogram cluster template system and method |
| 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 |
| US20200155029A1 (en) * | 2017-12-21 | 2020-05-21 | Pacesetter, Inc. | Method and device for electrogram based estimation of qrs duration |
| WO2021253709A1 (en) * | 2020-06-17 | 2021-12-23 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram heartbeat classification method and apparatus, and electronic device and medium |
| KR102437350B1 (en) * | 2021-12-21 | 2022-08-29 | (주)씨어스테크놀로지 | Method and Apparatus for Detecting Multiple beat by using Electrocardiogram Global Feature Vector |
| CN115177268A (en) * | 2022-07-13 | 2022-10-14 | 兴化市人民医院 | Atrial fibrillation heart beat detection method, device and storage medium |
-
2023
- 2023-05-31 CN CN202310630528.6A patent/CN116350199B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
| CN102835954A (en) * | 2012-09-07 | 2012-12-26 | 深圳市邦健电子有限公司 | Method for generating heart beating waveform template and treating ventricular premature beat detection and device |
| WO2016034203A1 (en) * | 2014-09-01 | 2016-03-10 | Schiller Ag | Method and device for automatically classifying heartbeats, computer program product and ecg device for carrying out the method |
| CN107456227A (en) * | 2017-08-16 | 2017-12-12 | 北京蓬阳丰业医疗设备有限公司 | Full lead electrocardiogram cluster template system and method |
| US20200155029A1 (en) * | 2017-12-21 | 2020-05-21 | Pacesetter, Inc. | Method and device for electrogram based estimation of qrs duration |
| 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 |
| WO2021253709A1 (en) * | 2020-06-17 | 2021-12-23 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram heartbeat classification method and apparatus, and electronic device and medium |
| CN113876335A (en) * | 2020-06-17 | 2022-01-04 | 深圳邦健生物医疗设备股份有限公司 | Electrocardiogram heart beat classification method, electrocardiogram heart beat classification device, electronic equipment and medium |
| KR102437350B1 (en) * | 2021-12-21 | 2022-08-29 | (주)씨어스테크놀로지 | Method and Apparatus for Detecting Multiple beat by using Electrocardiogram Global Feature Vector |
| CN115177268A (en) * | 2022-07-13 | 2022-10-14 | 兴化市人民医院 | Atrial fibrillation heart beat detection method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116350199B (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Altan et al. | A new approach to early diagnosis of congestive heart failure disease by using Hilbert–Huang transform | |
| US9782092B2 (en) | Patient signal analysis based on vector analysis | |
| Poddar et al. | Automated classification of hypertension and coronary artery disease patients by PNN, KNN, and SVM classifiers using HRV analysis | |
| Velic et al. | Computer aided ECG analysis—State of the art and upcoming challenges | |
| Zhao et al. | Enhancing detection accuracy for clinical heart failure utilizing pulse transit time variability and machine learning | |
| CN103961089A (en) | Sinus heart rate turbulence tendency detecting method based on segmented straight line fitting | |
| Sedighian et al. | Pediatric heart sound segmentation using Hidden Markov Model | |
| US9549681B2 (en) | Matrix-based patient signal analysis | |
| Al-Fahoum et al. | A practical reconstructed phase space approach for ECG arrhythmias classification | |
| Singhal et al. | A systematic review on artificial intelligence-based techniques for diagnosis of cardiovascular arrhythmia diseases: challenges and opportunities | |
| Sun et al. | Early detection of myocardial ischemia in 12‐lead ECG using deterministic learning and ensemble learning | |
| Tseng et al. | Clustering analysis of aging diseases and chronic habits with multivariate time series electrocardiogram and medical records | |
| Krishnan et al. | ANovel severity index of heart disease from beat-wise analysis of ECG using fuzzy logic for smart-health | |
| Hsu et al. | Multi-label arrhythmia classification from 12-lead electrocardiograms | |
| Zhang et al. | Interpretable detection and location of myocardial infarction based on ventricular fusion rule features | |
| CN111528833B (en) | Rapid identification and processing method and system for electrocardiosignals | |
| Spicher et al. | ECG delineation using a piecewise Gaussian derivative model with parameters estimated from scale-dependent algebraic expressions | |
| CN116350199B (en) | Dynamic electrocardiogram and heart beat template generation method and system | |
| US10588577B2 (en) | Patient signal analysis based on affine template matching | |
| Peluffo-Ordóñez et al. | Generalized Bonhoeffer-van der Pol oscillator for modelling cardiac pulse: Preliminary results | |
| CN110688414B (en) | Method and device for processing time series data and computer readable storage medium | |
| Arenas et al. | Morphological and temporal ecg features for myocardial infarction detection using support vector machines | |
| Jokić et al. | An efficient approach for heartbeat classification | |
| Ran et al. | Multi-label classification of abnormalities in 12-lead ECG using deep learning | |
| Zhang et al. | A new test for one-way ANOVA with functional data and application to ischemic heart screening |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |