CN111493856B - Correction method and device for heart beat classification, electrocardiogram checking system and storage medium - Google Patents
Correction method and device for heart beat classification, electrocardiogram checking system and storage medium Download PDFInfo
- Publication number
- CN111493856B CN111493856B CN201910097616.8A CN201910097616A CN111493856B CN 111493856 B CN111493856 B CN 111493856B CN 201910097616 A CN201910097616 A CN 201910097616A CN 111493856 B CN111493856 B CN 111493856B
- Authority
- CN
- China
- Prior art keywords
- heart beat
- heart
- classification
- difference degree
- beats
- 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.)
- Active
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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Cardiology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a correction method of heart beat classification, which comprises the following steps: when a correction instruction is received, acquiring a target heart beat in the correction instruction; calculating the difference degree of the heart beat characteristics between each heart beat characteristic of the target heart beat and other heart beats in the heart beat type template; and reclassifying the other heart beats according to the difference degree of the heart beat characteristics to obtain a classification result so as to correct the heart beat classification. The invention also discloses a heart beat classification device, an electrocardiogram detection system and a computer readable storage medium. The effect of improving the working efficiency of the heart beat classification and correction work is achieved.
Description
Technical Field
The present invention relates to the field of medical technology, and more particularly, to a correction method for cardiac classification, a cardiac classification apparatus, an electrocardiogram inspection system, and a computer-readable storage medium.
Background
Dynamic electrocardiographic examination is an examination in which continuous monitoring of electrocardiographic activity is recorded for 24 hours, or more, in the patient's daily life. Compared with a common electrocardiogram, the dynamic electrocardiogram can continuously record about 10 ten thousand cardiac cycles within 24 hours, so that symptoms such as arrhythmia and myocardial ischemia which are not easy to find in the conventional body surface electrocardiographic examination can be found through dynamic electrocardiographic detection. Can improve the detection rate of non-sustained arrhythmia, especially transient arrhythmia and transient myocardial ischemia, and expand the range of clinical application of electrocardiogram.
Because the dynamic electrocardiogram is a signal acquired by a subject in daily life, the acquired signal inevitably has larger interference and artifact, and the heart beat analysis algorithm of the dynamic electrocardiogram cannot accurately classify all heart beats due to the influence of various factors, so that the analysis result is incorrect, and misdiagnosis and/or delay treatment are easy to cause particularly when the arrhythmia is judged to have errors.
In the prior art, correction of the heart beat type is required after automatic analysis due to limitations of the dynamic electrocardiogram automatic analysis technique. However, the classification rule of the existing heart beat type correction technology has the problem that the classification condition is too harsh or too loose, so that the accuracy of data classification needs to be manually judged in the automatic classification process, and the working efficiency is low.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The main object of the present invention is to provide a correction method for heart beat classification, a heart beat classification device, an electrocardiogram inspection system and a computer readable storage medium, which aim to improve the working efficiency.
In order to achieve the above object, the present invention provides a method for correcting a heart beat classification, the method comprising the steps of:
when a correction instruction is received, acquiring a target heart beat in the correction instruction;
calculating the difference degree of the heart beat characteristics between each heart beat characteristic of the target heart beat and other heart beats in the heart beat type template;
and reclassifying the other heart beats according to the difference degree of the heart beat characteristics to obtain a classification result so as to correct the heart beat classification.
Optionally, the step of reclassifying the other heart beats according to the degree of difference of the heart beat characteristics to obtain a classification result includes:
according to the difference degree of the heart beat characteristics, classifying the other heart beats step by step according to the determined classification sequence of the heart beat characteristics to obtain a plurality of heart beat subsets; when classifying the heart beats at the previous time, classifying the heart beats in the heart beat subset of the previous classification result again according to the difference degree of the heart beat characteristics of the current classification;
and screening the plurality of heart beat subsets to obtain a classification result.
Optionally, the step of screening the plurality of heart beat subsets to obtain a classification result comprises:
obtaining heart beats with the difference degree of the heart beat characteristics being greater than or equal to a first difference degree threshold corresponding to the heart beat characteristics according to the difference degree of the heart beat characteristics;
and removing the obtained heart beat to obtain a classification result.
Optionally, the step of reclassifying the other heart beats according to the degree of difference of the heart beat characteristics to obtain a classification result includes:
according to the difference degree of the heart beat characteristics, the other heart beats are screened step by step according to the determined classification sequence of the heart beat characteristics, and a classification result is obtained;
and when screening is performed for the previous time, screening is performed for the heart beats after the previous time according to the difference degree of the heart beat characteristics screened for the current time, so that the heart beats with the difference degree of the heart beat characteristics being larger than or equal to a first difference degree threshold corresponding to the heart beat characteristics are removed.
Optionally, the classification order of the heart beat features is determined by sorting from low to high according to the difference degree of the heart beat features; or determining the comprehensive difference degree of the heart beat characteristics according to the difference degree of the heart beat characteristics and the heart beat number corresponding to the difference degree, and sequencing and determining according to the comprehensive difference degree of the heart beat characteristics from low to high.
Optionally, the first difference threshold corresponding to the heart beat feature is correspondingly adjusted according to the heart beat feature value of the target heart beat.
Optionally, the step of reclassifying the other heart beats according to the degree of difference of the heart beat characteristics to obtain a classification result, so as to correct the heart beat classification further includes:
determining the comprehensive difference degree of the heart beat characteristics according to the difference degree of the heart beat characteristics and the heart beat number corresponding to the difference degree;
and removing the heart beat characteristics with the comprehensive difference degree being greater than or equal to a second difference degree threshold value.
Optionally, the correction instructions include a plurality of target heart beats to concurrently categorize other heart beats in a heart beat type template in which the plurality of target heart beats are located.
In addition, to achieve the above object, the present invention also provides a heart beat classification device, including: the heart beat classification correction device comprises a memory, a processor and a correction program stored in the memory and capable of running on the processor, wherein the correction program realizes the steps of the heart beat classification correction method when being executed by the processor.
In addition, in order to achieve the above object, the present invention also provides an electrocardiographic examination system, comprising an electrocardiographic examination device and an electrocardiographic data processing device, wherein the electrocardiographic examination device is used for continuously recording electrocardiographic activity data of a user; the electrocardio data processing device comprises the heart beat classification device which is used for analyzing and processing the electrocardio activity data and outputting an electrocardio analysis result of a user.
In addition, to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a correction program which, when executed by a processor, implements the steps of the correction method of heart beat classification as described above.
According to the correction method, the heart beat classification device, the electrocardiogram detection system and the computer readable storage medium for heart beat classification, when a correction instruction is received, target heart beats in the correction instruction are acquired, then the difference degree of heart beat characteristics between each heart beat characteristic of the target heart beats and other heart beats in a heart beat type template where the heart beat characteristics are located is calculated, and then the other heart beats are reclassified according to the difference degree of the heart beat characteristics, so that classification results are obtained, and the heart beat classification is corrected. The classification result can be automatically corrected according to the target heart beat selected by the user, so that the working efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of a terminal structure of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of an embodiment of a method for correcting a heart beat classification according to the present invention;
FIG. 3 is a schematic diagram of a refinement flow for obtaining a classification result according to the present invention;
FIG. 4 is a schematic diagram of a refinement flow for screening a subset of heartbeats to obtain a classification result;
FIG. 5 is a flow chart of another embodiment of a method for correcting a heart beat classification according to the present invention;
fig. 6 is a flow chart of a method for correcting a heart beat classification according to another embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The main solutions of the embodiments of the present invention are:
when a correction instruction is received, acquiring a target heart beat in the correction instruction;
calculating the difference degree of the heart beat characteristics between each heart beat characteristic of the target heart beat and other heart beats in the heart beat type template;
and reclassifying the other heart beats according to the difference degree of the heart beat characteristics to obtain a classification result so as to correct the heart beat classification.
In the prior art, the classification rule of the heart beat type correction technology has the problem that the classification condition is too harsh or too loose, so that the accuracy of data classification needs to be manually judged in the automatic classification process, and the working efficiency is low.
According to the correction method, the heart beat classification device, the electrocardiogram detection system and the computer readable storage medium for heart beat classification, when a correction instruction is received, target heart beats in the correction instruction are acquired, then the difference degree of heart beat characteristics between each heart beat characteristic of the target heart beats and other heart beats in a heart beat type template where the heart beat characteristics are located is calculated, and then the other heart beats are reclassified according to the difference degree of the heart beat characteristics, so that classification results are obtained, and the heart beat classification is corrected. The classification result can be automatically corrected according to the target heart beat selected by the user, so that the working efficiency is improved.
As shown in fig. 1, fig. 1 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present invention.
The terminal of the embodiment of the invention can be a PC and/or an intelligent mobile terminal and the like.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a communication bus 1002, a display, a network interface 1004, and a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the terminal structure shown in fig. 1 is not limiting of the terminal and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a correction program may be included in the memory 1005, which is a computer-readable storage medium.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user end) and performing data communication with the client, so as to achieve the purpose of outputting data through the client; and the processor 1001 may be configured to call the correction program stored in the memory 1005 and perform the following operations:
when a correction instruction is received, acquiring a target heart beat in the correction instruction;
calculating the difference degree of the heart beat characteristics between each heart beat characteristic of the target heart beat and other heart beats in the heart beat type template;
and reclassifying the other heart beats according to the difference degree of the heart beat characteristics to obtain a classification result so as to correct the heart beat classification.
Further, the processor 1001 may call a correction program stored in the memory 1005, and further perform the following operations:
according to the difference degree of the heart beat characteristics, classifying the other heart beats step by step according to the determined classification sequence of the heart beat characteristics to obtain a plurality of heart beat subsets; when classifying the heart beats at the previous time, classifying the heart beats in the heart beat subset of the previous classification result again according to the difference degree of the heart beat characteristics of the current classification;
and screening the plurality of heart beat subsets to obtain a classification result.
Further, the processor 1001 may call a correction program stored in the memory 1005, and further perform the following operations:
obtaining heart beats with the difference degree of the heart beat characteristics being greater than or equal to a first difference degree threshold corresponding to the heart beat characteristics according to the difference degree of the heart beat characteristics;
and removing the obtained heart beat to obtain a classification result.
Further, the processor 1001 may call a correction program stored in the memory 1005, and further perform the following operations:
according to the difference degree of the heart beat characteristics, the other heart beats are screened step by step according to the determined classification sequence of the heart beat characteristics, and a classification result is obtained;
and when screening is performed for the previous time, screening is performed for the heart beats after the previous time according to the difference degree of the heart beat characteristics screened for the current time, so that the heart beats with the difference degree of the heart beat characteristics being larger than or equal to a first difference degree threshold corresponding to the heart beat characteristics are removed.
Further, the processor 1001 may call a correction program stored in the memory 1005, and further perform the following operations:
determining the comprehensive difference degree of the heart beat characteristics according to the difference degree of the heart beat characteristics and the heart beat number corresponding to the difference degree;
and removing the heart beat characteristics with the comprehensive difference degree being greater than or equal to a second difference degree threshold value.
Referring to fig. 2, a first embodiment of a method for correcting a heart beat classification according to the present invention includes:
step S100, when a correction instruction is received, acquiring a target heart beat in the correction instruction;
in one embodiment, upon receiving the to-be-processed electrocardiographic data, heart beat characteristics in the to-be-processed electrocardiographic data are first acquired. And classifying the heart beat according to the heart beat characteristics, and generating a type template. The electrocardiographic data to be processed can be raw data which are acquired during dynamic electrocardiographic examination. The dynamic electrocardiographic examination is an electrocardiographic activity examination which is continuously carried out for 24 hours or longer in daily life of a patient, and the dynamic electrocardiographic examination can continuously record about 10 ten thousand cardiac cycles within 24 hours, so that diseases such as arrhythmia, myocardial ischemia and the like which are not easy to find in the conventional body surface electrocardiographic examination can be found.
Specifically, when classifying the data to be processed, any heart beat in the data to be processed can be acquired, a first type template is generated, and the heart beat is used as the template heart beat of the first type template. Further, acquiring the next heartbeat in the data to be processed, namely a second heartbeat, calculating the heartbeat characteristic difference degree of the second heartbeat and the template heartbeat in the first type template, and judging whether the heartbeat characteristic difference degree is smaller than or equal to a preset threshold value (wherein the heartbeat characteristic can comprise a plurality of heartbeat characteristics such as QRS wave amplitude, RR (radio frequency) advance and the like, and the heartbeat characteristic difference degree refers to the overall difference degree of the plurality of heartbeat characteristics; and when the heart beat characteristic difference degree is larger than a preset threshold value, creating a second type template, classifying the second heart beat into the second type template, and taking the second heart beat as a template heart beat of the second type template. And then acquiring the next heart beat, namely a third heart beat, and calculating the heart beat characteristic difference degree of the third heart beat and the template heart beat in the first type template. Classifying the third heart beat into the first type template when the heart beat feature difference degree of the template heart beat of the third heart beat and the first type template is smaller than or equal to the preset threshold value; calculating the heart beat characteristic difference degree of the template heart beat in the third heart beat and the second template heart beat when the heart beat characteristic difference degree of the template heart beat of the third heart beat and the first template is larger than a preset threshold value, and classifying the third heart beat into the second template when the heart beat characteristic difference degree is smaller than or equal to the preset threshold value; otherwise, a third type template is created using the third heartbeat as a template heartbeat. And so on, all heartbeats in the data to be processed are processed in turn.
After classifying the electrocardiographic data to be processed, a heart beat that does not belong to the current class may be selected in each class (i.e., type template) and determined as the target heart beat. After the target heart beat is determined, a corresponding correction instruction may be generated according to the target heart beat.
Specifically, after selecting a target heart beat, the user may send a correction instruction containing the target heart beat to a heart beat classification device through an external input device (such as a keyboard or a mouse). When the heart beat correction device receives the correction instruction, the target heart beat is acquired.
Step 200, calculating the difference degree of the heart beat characteristics between each heart beat characteristic of the target heart beat and other heart beats in the heart beat type template;
in an embodiment, when a target heart beat is acquired, a degree of difference in heart beat characteristics between the target heart beat and other heart beats in the template of the type in which it is located may be calculated. Wherein the degree of difference may be the degree of difference of individual cardiac beats. For example, the degree of difference between target heart beat a and other heart beat B may include QRS amplitude difference, RR lead difference, RR interval difference, etc. between target heart beat a and other heart beat B.
And step S300, reclassifying the other heart beats according to the difference degree of the heart beat characteristics to obtain a classification result so as to correct the heart beat classification.
In one embodiment, when the degree of variability of the heart beat characteristics is calculated, the heart beat may be reclassified based on the portion of other heart beats in the template of the type in which the target heart beat is located. Specifically, referring to fig. 3 of the specification, the step of reclassifying other heartbeats includes:
step S310, classifying the other heartbeats step by step according to the degree of difference of the heart beat characteristics and the determined classification sequence of the heart beat characteristics to obtain a plurality of heart beat subsets; when classifying the heart beats at the previous time, classifying the heart beats in the heart beat subset of the previous classification result again according to the difference degree of the heart beat characteristics of the current classification;
step 320, screening the plurality of heart beat subsets to obtain a classification result.
In one embodiment, a sort order may be acquired first, where the sort order may be preset and stored in a storage medium. The heart beat characteristics can also be determined by sorting from low to high according to the difference degree of the heart beat characteristics; or, the comprehensive difference degree of the heart beat characteristics can be determined according to the difference degree of the heart beat characteristics and the heart beat number corresponding to the difference degree, and the comprehensive difference degree of the heart beat characteristics is determined in a sequence from low to high.
Specifically, when the classification order is determined according to the sorting of the differences of the heart beat features from low to high, in an embodiment, an average value of the differences of each heart beat feature between each other heart beat and the target heart beat in the current template is obtained, and then sorting can be performed according to the average value of the differences. For example, the mean value of the QRS wave amplitude difference and the RR advance difference between the target heart beat and the other heart beats is then sorted according to the order of the mean value from small to large. Of course, other embodiments, for example, perform weighted calculation of the degree of difference according to the degree of difference of one or several heart beat features between each other heart beat and the target heart beat in the current template, and then rank according to the calculated degree of difference from low to high.
When determining the comprehensive difference degree of the heart beat characteristics according to the difference degree of the heart beat characteristics and the heart beat number corresponding to the difference degree, and sorting the heart beat characteristics according to the comprehensive difference degree of the heart beat characteristics from low to high, in an embodiment, the heart beat characteristics may be sorted according to the average value of the difference degrees corresponding to the heart beat characteristics, and then sorted according to the number of other heart beats corresponding to the heart beat characteristics when the average value is equal. In another embodiment, the other heart beat numbers corresponding to the heart beat features are ranked first, and when the numbers are equal, the heart beat features with equal numbers are ranked according to the difference mean value corresponding to the heart beat features. In yet another embodiment, according to the weight given to the difference mean value and the number, further according to the weight, the difference mean value and the number, the comprehensive difference of each heart beat is determined through weighted calculation, the heart beat features are ranked according to the comprehensive difference, and further the classification sequence is determined according to the ranking result.
The above number refers to the number of other heartbeats included in the screening result when other heartbeats are screened with the degree of difference corresponding to the heart beat characteristics. For example, when QRS wave amplitude is used as a screening condition, the number of other heartbeats included in the screening condition is p, and the average difference degree of the other heartbeats is q; when RR lead is taken as screening condition, the other heart beat quantity contained in the screening condition is p 1 The average difference degree of the other heart beats is q 1 . Thus, the above-described ordering includes the following three:
1. firstly judging the magnitude relation between q and q1, and if q is greater than q1, arranging the QRS wave amplitude before the RR advance in the sorting process; if q is equal to q1, judging the magnitude relation between p and p1, and when p is greater than p1, arranging the QRS wave amplitude before the RR advance in the sorting process; if q is less than q1, the QRS wave amplitude is ranked after the RR lead at ranking.
2. First judge p and p 1 The magnitude relationship between if p is greater than p 1 The QRS wave amplitude is ranked before the RR advance when ranked; if p is equal to p 1 Then judge q and q 1 The magnitude relation between the two is that when q is larger than q 1 The QRS wave amplitude is ranked before the RR advance when ranked; if p is smaller than p 1 The QRS wave amplitude is ranked after the RR advance in ranking.
3. The number of the weights m and n which are different from the average value, the comprehensive difference degree h=mq+np corresponding to the QRS wave amplitude value, and the comprehensive difference degree f=mq corresponding to the RR advance 1 +np 1 And comparing the magnitude relation of h and f, and determining the ordering relation between the QRS wave amplitude value and the RR advance according to the magnitude relation.
After the classification sequence is determined, the difference degree of a plurality of heart beat characteristics between the target heart beat and each other heart beat can be obtained, and then according to the classification sequence of the heart beat characteristics, other heart beats in the current type template can be screened according to the difference degree of the first heart beat characteristic a, namely, in the current type template, other heart beats with the difference degree of the heart beat characteristic a between the target heart beat and the target heart beat smaller than a preset threshold value are screened. And classifying the other screened heartbeats according to the difference degree of the second heart beat characteristic b. Dividing the variation range of the difference degree of the heart beat characteristic b between the other heart beats and the target heart beat into a plurality of sections, determining the section to which the difference degree of the heart beat characteristic b between the other heart beats and the target heart beat belongs, and dividing the other heart beats with the difference degree belonging to the same section into the same category. Other heartbeats in the same category are classified according to the degree of difference of the third heart beat feature c. And then reclassifying each classification obtained when classifying according to the third heart beat feature according to the fourth heart beat feature until all heart beat features are finished when all the heart beat features are used up.
For example: and when the heart beat g is acquired, other heart beats with the QRS waveform state difference degree lower than a preset threshold value with the heart beat g are screened out from other heart beats of the type template N to form a screening set V. Then continuously comparing the QRS amplitude difference between the target heart beat and other heart beats in the screening set V to obtain a corresponding difference interval of the QRS amplitude difference, and classifying other heart beats in different difference intervals into the same category; and then comparing RR lead difference degrees between other heartbeats in each category and the target heart beat again, and classifying the other heartbeats in each category again according to the RR lead difference degrees.
It should be noted that, the other heartbeats are classified only once according to the degree of difference corresponding to each heart beat feature.
When the step-by-step classification is completed, a plurality of classification categories can be obtained, each category being a subset of heartbeats. Thus, upon completion of the progressive classification, multiple subsets of heartbeats may be obtained.
When multiple subsets of heartbeats are obtained, subsets of heartbeats that are not satisfactory may be screened out of the subsets of heartbeats. The screened subset of heartbeats is then removed. Further, other heartbeats in the remaining heart beat subset are acquired to form a heart beat correction set, namely a classification result.
In an embodiment, referring to fig. 4, the step S320 includes:
step S321, obtaining a heart beat of which the heart beat characteristic difference is greater than or equal to a first difference threshold corresponding to the heart beat characteristic according to the heart beat characteristic difference;
and step S322, removing the obtained heart beat to obtain a classification result.
In one embodiment, after the progressive classification is completed, a plurality of subsets of heartbeats are determined. And then a first difference threshold corresponding to each heart beat characteristic of the target heart beat can be obtained, and further a heart beat subset with the difference greater than or equal to the threshold is screened out according to the first difference threshold, and the screened heart beat subset is removed. And forming the heart beats in the rest heart beat subsets into a heart beat correction set as the classification result.
The first difference threshold may be pre-stored in a storage medium, and the first difference threshold corresponding to each heart beat feature may be obtained in the implementation process, and then the first difference threshold is adjusted according to the variation range of the difference. For example, when the variation range of QRS waveform morphology is 0% -20%, the preset variation of the corresponding QRS waveform morphology is 5%, and when the variation range is 0% -40%, the preset variation of the corresponding QRS waveform morphology can be adjusted to 10%. The rule that the preset difference degree is adjusted according to the variation range can be set by a developer in a self-defined mode.
In this embodiment, when a correction instruction is received, a target heart beat in the correction instruction is acquired, then the difference degree of the heart beat characteristics between each heart beat characteristic of the target heart beat and other heart beats in the heart beat type template where the heart beat characteristic is located is calculated, and then the other heart beats are reclassified according to the difference degree of the heart beat characteristics, so as to obtain a classification result, and correct the heart beat classification. The classification result can be automatically corrected according to the target heart beat selected by the user, so that the working efficiency is improved.
Further, in another embodiment, the step S300 specifically includes:
according to the difference degree of the heart beat characteristics, the other heart beats are screened step by step according to the determined classification sequence of the heart beat characteristics, and a classification result is obtained; and when screening is performed for the previous time, screening is performed for the heart beats after the previous time according to the difference degree of the heart beat characteristics screened for the current time, so that the heart beats with the difference degree of the heart beat characteristics being larger than or equal to a first difference degree threshold corresponding to the heart beat characteristics are removed.
In this embodiment, the classification sequence may be first obtained, then the first heart beat feature is selected according to the classification sequence, the difference degree of the first heart beat feature between the target heart beat and other heart beats in the current type template is calculated, other heart beats in the current type template, which are greater than or equal to a threshold value corresponding to the preset first heart beat feature difference degree, are screened out, the other heart beats screened out from the current type template are removed, the rest other heart beats form a heart beat subset, and the classification sequence determines the second heart beat feature. And then screening and removing other heartbeats in the current heart beat subset, wherein the difference degree of the second heart beat characteristic between other heart beats in the current heart beat subset and the target heart beat is larger than or equal to the second heart beat characteristic difference degree threshold value. The rest heart beats of the current heart beat subset are combined into the heart beat subset of the next level. And according to the classification sequence, sequentially screening and removing other heart beats in the current heart beat subset until the heart beat subset determined after the last heart beat feature in the classification sequence is screened and removed is determined, and taking the heart beat subset as a heart beat correction set, namely the classification result.
For example, the other heart beats having a QRS waveform morphology difference of greater than or equal to 5% from the target heart beat are first screened out in the current template, and the remaining other heart beats are formed into a first heart beat subset. Further, screening the first heart beat subset to remove heart beats with the difference degree of the QRS wave amplitude value being more than or equal to 5%, and forming the rest other heart beats into a second heart beat subset. And finally, screening and removing the heart beats with the RR lead difference degree more than or equal to 3% in the second heart beat subset, and forming the rest other heart beats into a heart beat correction set.
In the embodiment, the classification result is determined through step-by-step screening, so that the system overhead is saved, and the operation speed is improved.
Further, referring to fig. 5, according to another embodiment of the correction method for cardiac classification of the present invention, before step S300, the method further includes:
step S400, determining the comprehensive difference degree of the heart beat characteristics according to the difference degree of the heart beat characteristics and the heart beat number corresponding to the difference degree;
step S500, removing the heart beat characteristics with the comprehensive difference degree larger than or equal to a second difference degree threshold value.
In an embodiment, the variation range of the difference degree of each heart beat characteristic of other heart beats in the current type template and the heart beat number corresponding to the difference degree can be counted. And then, according to the heart beat number corresponding to the difference degree of the variation range of the difference degree of each heart beat characteristic of other heart beats, determining the comprehensive difference degree corresponding to the heart beat characteristic through weighted calculation. The heart beat features having an integrated degree of difference greater than or equal to the second degree of difference threshold are then removed. And gradually classifying or gradually screening other heartbeats in the current type template according to the residual heart beat characteristics to determine a classification result.
For example, taking the P-wave form as an example, if the comprehensive difference degree of the P-wave forms is high, it may indicate that there is a large difference in the P-wave form of the asystole, and it may not be necessary to classify according to the P-wave form. If the P waveform state difference degree is low, the P waveform state of the heart beat set is not obviously identifiable, classification is carried out according to the P waveform state, heart beats similar to the P waveform state of the target heart beat are found, and classification is corrected.
In this embodiment, according to the difference degree of the heart beat features and the heart beat number corresponding to the difference degree, the comprehensive difference degree of the heart beat features is determined, and then the heart beat features with the comprehensive difference degree greater than or equal to the second difference degree threshold are removed, so that the number of classification and/or screening in the step-by-step classification and/or step-by-step screening process is reduced, and the purpose of saving the system overhead is achieved.
Further, referring to fig. 6, in still another embodiment of the method for correcting a heart beat classification according to the present invention, based on the above embodiment, the method for correcting a heart beat classification further includes:
and step S600, when a correction instruction is received, acquiring a plurality of target heartbeats according to the correction instruction so as to classify other heartbeats in the heart beat type template where the plurality of target heartbeats are located in parallel.
In an embodiment, the correction instructions may include a plurality of target heart beats, which may belong to the same type of template or may belong to different types of templates. When each target heart beat is acquired, the steps S100 to S300 are sequentially performed according to each target heart beat, respectively. To categorize each target heart beat into the other heart beats in the template of the type in which the target heart beat is located.
In this embodiment, when a correction instruction is received, a plurality of target heart beats are acquired according to the correction instruction, so that other heart beats in a heart beat type template where the plurality of target heart beats are located are classified in parallel, and because a plurality of processes can be processed at the same time, the efficiency of heart beat correction is improved.
In addition, an embodiment of the present invention further provides a heartbeat classifying device, including: the heart beat classification correction device comprises a memory, a processor and a correction program stored in the memory and capable of running on the processor, wherein the correction program realizes the steps of the heart beat classification correction method when being executed by the processor.
In addition, the embodiment of the invention also provides an electrocardiographic examination system, which comprises an electrocardiographic examination device and an electrocardiographic data processing device, wherein the electrocardiographic examination device is used for continuously recording electrocardiographic activity data of a user; the electrocardio data processing device comprises the heart beat classification device which is used for analyzing and processing the electrocardio activity data and outputting an electrocardio analysis result of a user.
Furthermore, an embodiment of the present invention also proposes a computer-readable storage medium, on which a correction program is stored, which when executed by a processor implements the steps of the correction method for cardiac classification as described in the above embodiment.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a computer readable storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. A method of modifying a heart beat classification, the method comprising:
when a correction instruction is received, acquiring target heart beats in the correction instruction, wherein the target heart beats are heart beat data which do not accord with the current classification in each heart beat classification;
calculating the difference degree of the heart beat characteristics between each heart beat characteristic of the target heart beat and other heart beats in the heart beat type template;
reclassifying the other heart beats according to the difference degree of the heart beat characteristics to obtain a classification result so as to correct heart beat classification;
the step of reclassifying the other heart beats according to the degree of difference of the heart beat characteristics to obtain a classification result comprises the following steps:
according to the difference degree of the heart beat characteristics, classifying the other heart beats step by step according to the determined classification sequence of the heart beat characteristics to obtain a plurality of heart beat subsets; and when classifying the heart beats at the previous time, reclassifying the heart beats in the heart beat subset of the previous classification result according to the difference degree of the heart beat characteristics of the current classification, wherein the difference degree of the heart beat characteristics refers to the overall difference degree of a plurality of heart beat characteristics.
2. The method for modifying a heart beat classification of claim 1, wherein the step of screening the plurality of subsets of heart beats to obtain a classification result comprises:
obtaining heart beats with the difference degree of the heart beat characteristics being greater than or equal to a first difference degree threshold corresponding to the heart beat characteristics according to the difference degree of the heart beat characteristics;
and removing the obtained heart beat to obtain a classification result.
3. The method for modifying a heart beat classification according to claim 1, wherein the step of reclassifying the other heart beats based on the degree of difference in the heart beat characteristics to obtain a classification result comprises:
according to the difference degree of the heart beat characteristics, the other heart beats are screened step by step according to the determined classification sequence of the heart beat characteristics, and a classification result is obtained;
and when screening is performed for the previous time, screening is performed for the heart beats after the previous time according to the difference degree of the heart beat characteristics screened for the current time, so that the heart beats with the difference degree of the heart beat characteristics being larger than or equal to a first difference degree threshold corresponding to the heart beat characteristics are removed.
4. The method for modifying a heart beat classification as defined in claim 1, wherein the classification order of the heart beat features is determined by sorting from low to high according to the degree of difference of the heart beat features; or determining the comprehensive difference degree of the heart beat characteristics according to the difference degree of the heart beat characteristics and the heart beat number corresponding to the difference degree, and sequencing and determining according to the comprehensive difference degree of the heart beat characteristics from low to high.
5. The method for modifying a heart beat classification as defined in any one of claims 2 to 4, wherein the first degree of variance threshold corresponding to the heart beat feature is adjusted correspondingly to the heart beat feature value of the target heart beat.
6. The method for correcting a heart beat classification according to claim 1, wherein the step of reclassifying the other heart beats based on the degree of difference in the heart beat characteristics to obtain a classification result further comprises, prior to the step of correcting the heart beat classification:
determining the comprehensive difference degree of the heart beat characteristics according to the difference degree of the heart beat characteristics and the heart beat number corresponding to the difference degree;
and removing the heart beat characteristics with the comprehensive difference degree being greater than or equal to a second difference degree threshold value.
7. The method of claim 1, wherein the correction instructions include a plurality of target heart beats to concurrently classify other heart beats in a heart beat type template in which the plurality of target heart beats are located.
8. A heart beat classification device, comprising: memory, a processor and a correction program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the method for correcting a heart beat classification as defined in any one of claims 1 to 7.
9. An electrocardiographic examination system is characterized by comprising an electrocardiographic examination device and an electrocardiographic data processing device, wherein the electrocardiographic examination device is used for continuously recording electrocardiographic activity data of a user; the electrocardio data processing device comprises the heart beat classification device of claim 8, and is used for analyzing and processing the electrocardio activity data and outputting an electrocardio analysis result of a user.
10. A computer-readable storage medium, wherein a correction program is stored on the computer-readable storage medium, which when executed by a processor, implements the steps of the method for correcting a heart beat classification as defined in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910097616.8A CN111493856B (en) | 2019-01-31 | 2019-01-31 | Correction method and device for heart beat classification, electrocardiogram checking system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910097616.8A CN111493856B (en) | 2019-01-31 | 2019-01-31 | Correction method and device for heart beat classification, electrocardiogram checking system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111493856A CN111493856A (en) | 2020-08-07 |
| CN111493856B true CN111493856B (en) | 2023-05-09 |
Family
ID=71848152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910097616.8A Active CN111493856B (en) | 2019-01-31 | 2019-01-31 | Correction method and device for heart beat classification, electrocardiogram checking system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111493856B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114271829B (en) * | 2020-09-18 | 2023-07-25 | 深圳邦健生物医疗设备股份有限公司 | Method, device, equipment and medium for analyzing heart beat double marks |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006116207A (en) * | 2004-10-25 | 2006-05-11 | Fukuda Denshi Co Ltd | Device for classifying electrocardiogram |
| CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
| CN107358196A (en) * | 2017-07-12 | 2017-11-17 | 北京卫嘉高科信息技术有限公司 | A kind of sorting technique of heart beat type, device and electrocardiogram equipment |
| CN107785066A (en) * | 2016-08-26 | 2018-03-09 | 深圳市理邦精密仪器股份有限公司 | Change the method, apparatus and system of heart beat type |
-
2019
- 2019-01-31 CN CN201910097616.8A patent/CN111493856B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006116207A (en) * | 2004-10-25 | 2006-05-11 | Fukuda Denshi Co Ltd | Device for classifying electrocardiogram |
| CN101810476A (en) * | 2009-12-22 | 2010-08-25 | 李顶立 | Classification method of heart beat template of dynamic electrocardiogram |
| CN107785066A (en) * | 2016-08-26 | 2018-03-09 | 深圳市理邦精密仪器股份有限公司 | Change the method, apparatus and system of heart beat type |
| CN107358196A (en) * | 2017-07-12 | 2017-11-17 | 北京卫嘉高科信息技术有限公司 | A kind of sorting technique of heart beat type, device and electrocardiogram equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111493856A (en) | 2020-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108186011B (en) | Atrial fibrillation detection method, atrial fibrillation detection device and readable storage medium | |
| AU2009243424B2 (en) | ECG signal analysis tool | |
| CN110464333B (en) | Method and device for storing electrocardiogram data | |
| US20200074281A1 (en) | Computer-readable recording medium, abnormality determination method, and abnormality determination device | |
| CN112528783B (en) | Electrocardiogram and heart beat data clustering method, device, electronic equipment and medium | |
| CN106923820B (en) | Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device | |
| WO2022202943A1 (en) | Electrocardiogram analysis assistance device, program, electrocardiogram analysis assistance method, and electrocardiogram analysis assistance system | |
| CN117651523A (en) | Electrocardiogram analysis support device, program, electrocardiogram analysis support method, electrocardiogram analysis support system, peak estimation model generation method, and interval estimation model generation method | |
| CN111493856B (en) | Correction method and device for heart beat classification, electrocardiogram checking system and storage medium | |
| CN114742113B (en) | High-frequency QRS waveform curve analysis method and device, computer equipment and storage medium | |
| JP5207172B2 (en) | Waveform analysis apparatus and waveform analysis program | |
| JP6706996B2 (en) | Biological signal processing device, abnormality determination method and program | |
| CN112120689A (en) | Method and device for quickly marking long-range electrocardiogram data | |
| CN114680901A (en) | Electronic device and method for selecting features of an electrocardiogram | |
| CN111685754B (en) | Heart rate calculation method and system for wearable ECG acquisition equipment | |
| CN117814809B (en) | Atrial tachycardia event batch identification method, terminal equipment and medium | |
| CN111297348A (en) | Method for generating electrocardiogram analysis result, electrocardiograph and storage medium | |
| CN113712568A (en) | Electrocardiosignal data classification method and device | |
| US20230335278A1 (en) | Diagnosis assistance apparatus, diagnosis assistance method, and computer readable recording medium | |
| CN111317463B (en) | Heart beat insertion method, heart beat automatic insertion device and storage medium | |
| CN114403889A (en) | NN interval signal acquisition device, system and storage medium | |
| CN113935381A (en) | Electrocardiogram analysis method based on contrast learning, terminal device and storage medium | |
| CN114219028A (en) | Training of electrocardio ST-segment elevation recognition model, ST-segment elevation recognition method and device | |
| CN112353400A (en) | Heart beat classification method and device, computer equipment and storage medium | |
| CN118021315A (en) | Dynamic electrocardiographic data processing method and device, electronic equipment and storage medium |
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 |