CN114343666B - Paroxysmal atrial fibrillation scanning method and system for long-range electrocardiographic monitoring, storage medium and electronic equipment - Google Patents
Paroxysmal atrial fibrillation scanning method and system for long-range electrocardiographic monitoring, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN114343666B CN114343666B CN202210032416.6A CN202210032416A CN114343666B CN 114343666 B CN114343666 B CN 114343666B CN 202210032416 A CN202210032416 A CN 202210032416A CN 114343666 B CN114343666 B CN 114343666B
- Authority
- CN
- China
- Prior art keywords
- atrial fibrillation
- intervals
- suspected
- fragments
- electrocardiographic
- 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
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a paroxysmal atrial fibrillation scanning method aiming at long-range electrocardiographic monitoring, which comprises the following steps of: the first step: acquiring an electrocardio waveform signal, and performing unified dimension processing on the signal; and a second step of: positioning suspected atrial fibrillation, detecting characteristic points of signals, extracting RR intervals, calculating delta RR intervals, screening suspected atrial fibrillation, and removing partial premature beat; and a third step of: rough detection of atrial fibrillation, calculating RR interval characteristics to further determine atrial fibrillation fragments; fourth step: fine detection of atrial fibrillation, namely intercepting 1/2 atrial fibrillation heart beat according to the R peak position, quantifying P wave information, and carefully screening the atrial fibrillation according to the quantified P wave information; fifth step: and finally, outputting typical waveforms of atrial fibrillation, and the occurrence frequency of the atrial fibrillation. The occurrence frequency and the frequency of the atrial fibrillation have important values for the selection of the atrial fibrillation operation, the drug intervention and the diagnosis and the treatment of various clinical complications, and can guide a clinician to carry out personalized treatment schemes.
Description
Technical Field
The invention belongs to the technical field of electrocardiosignal processing, and particularly relates to a paroxysmal atrial fibrillation scanning method, a paroxysmal atrial fibrillation scanning system, a storage medium and electronic equipment aiming at long-range electrocardiosignal monitoring.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Atrial fibrillation (Atrial Fibrillation, AF) refers to rapid and irregular fibrillation emitted by the atria. Paroxysmal atrial fibrillation (Paroxysmal Atrial Fibrillation, PAF) is the initial phase of atrial fibrillation and one of the most common types of arrhythmia. Approximately 18% of PAF evolves into permanent AF within 4 years, and PAF deteriorates over time and negatively affects the quality of life of the patient. Current guidelines recommend AF screening for individuals over 65 years of age or having other characteristics that indicate an increased risk of stroke. Early detection of AF is critical to early onset of AF management. Early rhythm control therapy may reduce the risk of developing adverse cardiovascular events in early stage AF patients over 75 years of age. In addition, for patients with atrial fibrillation with obvious clinical symptoms, the conventional treatment is radio frequency ablation. The study found that the main reason for the high postoperative recurrence rate was the difference in surgical protocol and lesion extent. If clinically, the patients can be continuously monitored before operation, the type and the severity of atrial fibrillation can be accurately quantified, and the recurrence after atrial fibrillation operation can be obviously reduced.
Along with the development of artificial intelligence, portable wearable electronic equipment for electrocardio real-time monitoring is rapidly developed and can be used for home monitoring, so that AF screening and AF real-time monitoring after operation are realized, huge burden is brought to doctors for continuously collecting massive electrocardio data in a state, and a atrial fibrillation scanning algorithm in a long-time acquisition state is needed.
AF detection is a prerequisite to quantifying atrial fibrillation burden. Because the personal electrocardiographic waveform difference and the electrocardiographic signals acquired by the wearable equipment are greatly influenced by noise, and because the R peak is the most obvious characteristic point in the electrocardiographic signals, the current atrial fibrillation detection algorithm used for the wearable electrocardiograph is based on the RR interval atrial fibrillation detection algorithm, but the atrial fibrillation detection algorithm based on the RR interval is easy to misjudge the non-AF patient with irregular RR intervals as AF. Because the P wave is weak and is easily influenced by noise, the atrial fibrillation detection algorithm based on the P wave can be influenced by the detection precision of the P wave detector.
Disclosure of Invention
Aiming at the defects or improvement demands of the prior art, the invention provides a paroxysmal atrial fibrillation scanning method, a paroxysmal atrial fibrillation scanning system, a storage medium and electronic equipment aiming at long-range electrocardio monitoring, wherein the acquired signals are firstly subjected to unified dimension processing, then suspected positioning of atrial fibrillation is carried out, the positioned suspected atrial fibrillation is further determined, and finally the atrial fibrillation is finely detected, so that long-range atrial fibrillation scanning is realized.
To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
a paroxysmal atrial fibrillation scanning method aiming at long-range electrocardiographic monitoring comprises the following steps:
s1: acquiring an electrocardiographic waveform signal, and performing unified dimension processing on the electrocardiographic waveform signal;
s2: positioning suspected atrial fibrillation is carried out on the processed electrocardiosignals, characteristic point R wave detection is carried out on the processed electrocardiosignals, RR intervals are extracted, delta RR intervals are obtained after the RR intervals are differentiated, the electrocardiosignals with irregular RR intervals are screened to be suspected atrial fibrillation through the distribution of the RR intervals and partial premature beat is screened from the suspected atrial fibrillation fragments through the distribution of the delta RR intervals;
s3: further atrial fibrillation determination is carried out on the obtained suspected atrial fibrillation fragments, a plurality of RR interval indexes are calculated, RR interval indexes with atrial fibrillation different from other arrhythmia diseases are selected, and atrial fibrillation diagnosis model construction is carried out to determine atrial fibrillation;
s4: performing fine screening on atrial fibrillation fragments screened by the RR interval model through P-wave information, and finally determining atrial fibrillation fragments;
s5: finally, the atrial fibrillation attack frequency and duration are quantized, and typical atrial fibrillation fragments and quantized results are output.
Further, calculating heartbeat distribution with RR interval more than 10mv as suspected atrial fibrillation; calculating that delta RR intervals have a distribution in a space of more than 700mv and that the space distribution in the range of 100-700mv is less than 40% of premature beats;
further, the RR interval index includes: coefficient sample entropy, atrial fibrillation entropy, normalized fuzzy entropy and sample entropy.
Further, the P-wave information extraction method includes: dynamic template matching (DTW) and automatic coding network (LSTM-AE), wherein the R peak intercepts 1/2 ECG signal forward, and for long-range electrocardiosignals, 1/2 ECG signal is selected from the previous electrocardiosignals for 5 minutes as a template, DTW is performed, and the distance between each signal forward of the P peak and the template is extracted as an index; LSTM-AE is directly carried out on 1/2 ECG signals, 1/2 ECG signals are compressed to 4 points, box graphs are carried out on the distribution of the 4 points, and points with obvious difference distribution on P waves and F waves are selected as characteristics.
One or more embodiments provide an paroxysmal atrial fibrillation scanning system for long-range electrocardiographic monitoring, comprising:
the data acquisition module acquires an electrocardio waveform signal;
the data preprocessing module is used for carrying out unified dimension processing on the obtained electrocardiographic waveform signals;
the atrial fibrillation signal analysis module is used for carrying out characteristic point R wave detection by adopting the processed electrocardiographic waveform, extracting RR intervals, differentiating the RR intervals to obtain delta RR intervals, and screening out irregular electrocardiographic signals of the RR intervals to be suspected atrial fibrillation through the distribution of the RR intervals, namely calculating heartbeat distribution of which the RR intervals are more than 10mv to be suspected atrial fibrillation; partial premature beat is screened from suspected atrial fibrillation fragments through the distribution of delta RR intervals, namely the delta RR intervals are calculated to have the distribution in the space of more than 700mv and the spatial distribution in the space of 100-700mv is less than 40%;
the atrial fibrillation signal scanning module is used for further atrial fibrillation determination of the obtained suspected atrial fibrillation fragments, calculating a plurality of RR interval indexes, selecting RR interval indexes with atrial fibrillation different from other arrhythmia diseases, and establishing an atrial fibrillation diagnosis model for determining atrial fibrillation; performing fine screening on atrial fibrillation fragments screened by the RR interval model through P-wave information, and finally determining atrial fibrillation fragments;
and the atrial fibrillation signal statistics output module is used for quantifying the atrial fibrillation attack frequency and the atrial fibrillation duration and outputting typical atrial fibrillation fragments and quantified results.
One or more embodiments provide a computer readable storage medium having stored thereon a computer program for fingerprint similarity calculation, which when executed by a processor, implements the atrial fibrillation signal scanning method.
One or more embodiments provide an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed implements the atrial fibrillation signal scanning method.
One or more embodiments provide a paroxysmal atrial fibrillation scanning method for long-range electrocardiographic monitoring, which comprises an electrocardiographic signal acquisition device and the electronic equipment.
The one or more of the above technical solutions have the following beneficial effects:
1. the method firstly performs suspected positioning of atrial fibrillation, eliminates sinus rhythm and premature beat signals, and reduces complexity and task amount for the subsequent atrial fibrillation detection;
2. the atrial fibrillation detection algorithm based on the RR interval can erroneously detect a plurality of non-atrial fibrillation fragments as atrial fibrillation, and the method adds P-wave information for further screening, so that the accuracy of atrial fibrillation detection is improved;
3. because the P wave is very weak and is easily influenced by noise, the detection precision of the P wave is not very high, particularly, a long-range monitoring signal is generally monitored by using a wearable device, and the P wave is greatly influenced by the noise in the ECG collected by the wearable device;
4. the algorithm is applied to long-range scanning of atrial fibrillation, the occurrence frequency and the occurrence time of atrial fibrillation are counted, and the method has important value for atrial fibrillation radio frequency ablation patients, and has important value for atrial fibrillation operation selection, medicine intervention and diagnosis and treatment of various clinical complications, and a clinician can be guided to conduct personalized treatment schemes.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a flow chart of the paroxysmal atrial fibrillation scanning method for long-range electrocardiographic monitoring according to the present invention.
Fig. 2 is a map of suspected atrial fibrillation localization.
Fig. 3 is a P-wave metric graph based on a dynamic template.
Fig. 4 is a P-wave metric graph based on LSTM self-encoding network.
Fig. 5 is a box plot of P-wave characteristic distribution.
Fig. 6 is a graph of 60-minute paroxysmal atrial fibrillation scan results.
Fig. 7 is a diagram of a wearable electrocardiograph signal acquisition device and a real-time display.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
The embodiment provides a paroxysmal atrial fibrillation scanning method aiming at long-range electrocardiographic monitoring, which is shown in fig. 1 and comprises the following steps:
step 1: acquiring an electrocardio waveform signal, wherein the long-range electrocardio signal is from wearable electrocardio monitoring equipment and other various forms including non-contact electrocardio monitoring equipment, and then carrying out unified dimension processing on the electrocardio waveform signal;
step 2: positioning suspected atrial fibrillation is carried out on the processed electrocardiosignals, characteristic point R wave detection is carried out on the processed electrocardiosignals, RR intervals are extracted, delta RR intervals are obtained after the RR intervals are differentiated, and the electrocardiosignals with irregular RR intervals are screened out to be the suspected atrial fibrillation through the distribution of the RR intervals, namely, the heartbeat distribution of which is larger than 10mv is calculated to be the suspected atrial fibrillation; screening the suspected atrial fibrillation fragments for partial premature beat by the distribution of delta RR intervals, namely calculating that the delta RR intervals are distributed in a space of more than 700mv and the spatial distribution of 100-700mv is less than 40 percent (figure 2);
step 3: further atrial fibrillation determination is carried out on the obtained suspected atrial fibrillation fragments, a plurality of RR interval indexes are calculated, RR interval indexes with atrial fibrillation different from other arrhythmia diseases are selected, an atrial fibrillation diagnosis model is established for determining atrial fibrillation, and the RR interval indexes comprise: coefficient sample entropy, atrial fibrillation entropy, normalized fuzzy entropy and sample entropy.
Step 4: performing fine screening on atrial fibrillation fragments screened by the RR interval model through P-wave information, and finally determining atrial fibrillation fragments;
the P-wave information extraction method comprises the following steps: dynamic template matching (DTW) and automatic coding network (LSTM-AE), wherein the R peak intercepts 1/2 ECG signal forward, and for long-range electrocardiosignals, 1/2 ECG signal is selected from the previous electrocardiosignals for 5 minutes as a template, DTW is performed, and the distance between each signal forward of P peak and the template is extracted as an index (figure 3); LSTM-AE is directly performed on 1/2 ECG signal (figure 4), 1/2 ECG signal is compressed to 4 points, box graph is performed on distribution of the 4 points (figure 5), and points with obvious difference distribution on P wave and F wave are selected as characteristics.
Step 5: finally, the frequency and duration of atrial fibrillation attacks are quantized, and typical atrial fibrillation fragments and quantized results are output (fig. 6).
Example two
The embodiment provides an paroxysmal atrial fibrillation scanning system for long-range electrocardiographic monitoring, which comprises:
the data acquisition module acquires electrocardiographic waveform signals from wearable electrocardiographic monitoring equipment and other various forms, including non-contact electrocardiographic monitoring equipment, and then performs unified dimension processing on the electrocardiographic waveform signals;
the data preprocessing module is used for carrying out unified dimension processing on the obtained electrocardiographic waveform signals;
the atrial fibrillation signal analysis module is used for carrying out characteristic point R wave detection by adopting the processed electrocardiographic waveform, extracting RR intervals, differentiating the RR intervals to obtain delta RR intervals, and screening out irregular electrocardiographic signals of the RR intervals to be suspected atrial fibrillation through the distribution of the RR intervals, namely calculating heartbeat distribution of which the RR intervals are more than 10mv to be suspected atrial fibrillation; partial premature beat is screened from suspected atrial fibrillation fragments through the distribution of delta RR intervals, namely the delta RR intervals are calculated to have the distribution in the space of more than 700mv and the spatial distribution in the space of 100-700mv is less than 40%;
the atrial fibrillation signal scanning module is used for further atrial fibrillation determination of the obtained suspected atrial fibrillation fragments, calculating a plurality of RR interval indexes, selecting RR interval indexes with atrial fibrillation different from other arrhythmia diseases, and establishing an RR interval atrial fibrillation diagnosis model for determining atrial fibrillation; performing fine screening on the atrial fibrillation fragments subjected to RR interval screening through P-wave information, and finally determining atrial fibrillation fragments;
and the atrial fibrillation signal statistics module is used for quantifying atrial fibrillation attack frequency and atrial fibrillation duration and outputting typical atrial fibrillation fragments and quantified results.
Example III
It is an object of the present embodiment to provide a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program for fingerprint similarity calculation, the program when executed by a processor performing the steps of:
acquiring an electrocardiographic waveform signal, wherein the acquired electrocardiographic waveform signal comes from wearable electrocardiographic monitoring equipment and other various forms, including non-contact electrocardiographic monitoring equipment, and performing unified dimension processing on the electrocardiographic waveform signal;
positioning suspected atrial fibrillation is carried out on the processed electrocardiosignals, characteristic point R wave detection is carried out on the processed electrocardiosignals, RR intervals are extracted, delta RR intervals are obtained after the RR intervals are differentiated, and the electrocardiosignals with irregular RR intervals are screened out to be the suspected atrial fibrillation through the distribution of the RR intervals, namely, the heartbeat distribution of which is larger than 10mv is calculated to be the suspected atrial fibrillation; partial premature beat is screened from suspected atrial fibrillation fragments through the distribution of delta RR intervals, namely the delta RR intervals are calculated to have the distribution in the space of more than 700mv and the spatial distribution in the space of 100-700mv is less than 40%;
further atrial fibrillation determination is carried out on the obtained suspected atrial fibrillation fragments, a plurality of RR interval indexes are calculated, RR interval indexes with atrial fibrillation different from other arrhythmia diseases are selected, and an atrial fibrillation diagnosis model is established to carry out atrial fibrillation determination;
performing fine screening on atrial fibrillation fragments screened by the RR interval model through P-wave information, and finally determining atrial fibrillation fragments;
finally, the atrial fibrillation attack frequency and duration are quantized, and typical atrial fibrillation fragments and quantized results are output.
Example IV
An object of the present embodiment is to provide an electronic apparatus.
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 following steps when executing the program:
acquiring an electrocardiographic waveform signal, wherein the acquired electrocardiographic waveform signal comes from wearable electrocardiographic monitoring equipment and other various forms, including non-contact electrocardiographic monitoring equipment, and performing unified dimension processing on the electrocardiographic waveform signal;
positioning suspected atrial fibrillation is carried out on the processed electrocardiosignals, characteristic point R wave detection is carried out on the processed electrocardiosignals, RR intervals are extracted, delta RR intervals are obtained after the RR intervals are differentiated, and the electrocardiosignals with irregular RR intervals are screened out to be the suspected atrial fibrillation through the distribution of the RR intervals, namely, the heartbeat distribution of which is larger than 10mv is calculated to be the suspected atrial fibrillation; partial premature beat is screened from suspected atrial fibrillation fragments through the distribution of delta RR intervals, namely the delta RR intervals are calculated to have the distribution in the space of more than 700mv and the spatial distribution in the space of 100-700mv is less than 40%;
further atrial fibrillation determination is carried out on the obtained suspected atrial fibrillation fragments, a plurality of RR interval indexes are calculated, RR interval indexes with atrial fibrillation different from other arrhythmia diseases are selected, and an atrial fibrillation diagnosis model is established to carry out atrial fibrillation determination;
performing fine screening on atrial fibrillation fragments screened by the RR interval model through P-wave information, and finally determining atrial fibrillation fragments;
finally, the atrial fibrillation attack frequency and duration are quantized, and typical atrial fibrillation fragments and quantized results are output.
Example five
The embodiment provides an paroxysmal atrial fibrillation scanning system aiming at long-range electrocardio monitoring, which comprises an electrocardiosignal acquisition device and electronic equipment;
the electrocardiosignal acquisition device is used for acquiring human electrocardiosignals and transmitting the human electrocardiosignals to the computing device, as shown in fig. 7;
the electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps when executing the program comprising:
acquiring an electrocardiographic waveform signal, wherein the acquired electrocardiographic waveform signal comes from wearable electrocardiographic monitoring equipment and other various forms, including non-contact electrocardiographic monitoring equipment, and performing unified dimension processing on the electrocardiographic waveform signal;
positioning suspected atrial fibrillation is carried out on the processed electrocardiosignals, characteristic point R wave detection is carried out on the processed electrocardiosignals, RR intervals are extracted, delta RR intervals are obtained after the RR intervals are differentiated, and the electrocardiosignals with irregular RR intervals are screened out to be the suspected atrial fibrillation through the distribution of the RR intervals, namely, the heartbeat distribution of which is larger than 10mv is calculated to be the suspected atrial fibrillation; partial premature beat is screened from suspected atrial fibrillation fragments through the distribution of delta RR intervals, namely the delta RR intervals are calculated to have the distribution in the space of more than 700mv and the spatial distribution in the space of 100-700mv is less than 40%;
further atrial fibrillation determination is carried out on the obtained suspected atrial fibrillation fragments, a plurality of RR interval indexes are calculated, RR interval indexes with atrial fibrillation different from other arrhythmia diseases are selected, and an atrial fibrillation diagnosis model is established to carry out atrial fibrillation determination;
performing fine screening on atrial fibrillation fragments screened by the RR interval model through P-wave information, and finally determining atrial fibrillation fragments;
finally, the atrial fibrillation attack frequency and duration are quantized, and typical atrial fibrillation fragments and quantized results are output.
The steps involved in the devices of the second to fifth embodiments correspond to the first embodiment of the method, and the detailed description of the embodiments can be found in the related description section of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media including one or more sets of instructions; it should also be understood to include any medium capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any one of the methods of the present invention.
Experimental effect:
the invention improves the atrial fibrillation detection algorithm based on RR interval characteristics, and increases P-wave information on the basis of the detection algorithm to judge atrial fibrillation, so that a set of paroxysmal atrial fibrillation scanning method aiming at long-range electrocardio monitoring is developed.
Test data: chinese Physiological Signal Challenge (CPSC) database in 2020 and long-range wearable ECG database (collected in laboratory).
The test of the model was performed using a 12-coat time window.
Five-fold cross-validation was performed on dataset 1 of the national physiological signal challenge (CPSC) database in 2020, and the accuracy of the test was found to be improved by 6.45% compared with the test of the atrial fibrillation detection algorithm based on RR interval features, and the test result on dataset 2 was improved by 3.86% compared with the test of the atrial fibrillation detection algorithm based on RR interval features. The best results were obtained by scanning over 24-h hours of wearable paroxysmal atrial fibrillation data: the accuracy of atrial fibrillation scan is 99.33%, the false detection rate of the corresponding atrial fibrillation is 0.01%, and the worst result is: the accuracy of atrial fibrillation scan was 88.75% and the false detection rate of the corresponding atrial fibrillation was 14.06%. These results demonstrate that: the method can well scan the paroxysmal atrial fibrillation, and has clinical application value.
One or more of the above embodiments have the following technical effects:
1. the method firstly performs suspected positioning of atrial fibrillation, eliminates sinus rhythm and premature beat signals, and reduces complexity and task amount for the subsequent atrial fibrillation detection;
2. the atrial fibrillation detection algorithm based on the RR interval can erroneously detect a plurality of non-atrial fibrillation fragments as atrial fibrillation, and the method adds P-wave information for further screening, so that the accuracy of atrial fibrillation detection is improved;
3. because the P wave is very weak and is easily influenced by noise, the detection precision of the P wave is not very high, particularly, a long-range monitoring signal is generally monitored by using a wearable device, and in the ECG collected by the wearable device, the P wave is greatly influenced by the noise.
4. The algorithm is applied to long-range scanning of atrial fibrillation, the occurrence frequency and the occurrence time of atrial fibrillation are counted, and the method has important value for atrial fibrillation radio frequency ablation patients, and has important value for atrial fibrillation operation selection, medicine intervention and diagnosis and treatment of various clinical complications, and a clinician can be guided to conduct personalized treatment schemes.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in general-purpose computer means, alternatively they may be implemented in program code executable by computing means, so that they may be stored in storage means for execution by the computing means.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (5)
1. A method of paroxysmal atrial fibrillation scanning for long-range electrocardiographic monitoring, the method being performed by a computer, comprising the steps of:
s1: acquiring an electrocardiographic waveform signal, and performing unified dimension processing on the electrocardiographic waveform signal;
s2: positioning suspected atrial fibrillation is carried out on the processed electrocardiosignal, characteristic point R wave detection is carried out on the processed electrocardiosignal, RR intervals are extracted, the RR intervals are differentiated to obtain an fatter RR interval, and the suspected atrial fibrillation is positioned through the distribution of the RR intervals and the fatter RR interval;
s3: further atrial fibrillation determination is carried out on the obtained suspected atrial fibrillation fragments, and a plurality of RR interval indexes are calculated, wherein the RR interval indexes comprise: coefficient sample entropy, atrial fibrillation entropy, normalized fuzzy entropy and sample entropy, selecting RR interval indexes of atrial fibrillation different from other arrhythmia diseases, and establishing an atrial fibrillation detection model based on RR intervals;
s4: screening the atrial fibrillation fragments screened by the RR interval model through P-wave information, and finally determining the atrial fibrillation fragments;
s5: finally, quantifying the atrial fibrillation attack frequency and duration, and outputting typical atrial fibrillation fragments and quantified results;
screening out the electrocardiosignals with irregular RR intervals as suspected atrial fibrillation, namely calculating heartbeat distribution with RR intervals larger than 10mv as the suspected atrial fibrillation; screening partial premature beat from suspected atrial fibrillation fragments by distributing the fatter RR intervals, namely calculating that the fatter RR intervals are distributed in a space of more than 700mv and the spatial distribution of 100-700mv is less than 40%; means for measuring P-wave information include DTW and LSTM-AE, without using a P-wave detector; for a long-range electrocardiosignal, 1/2 ECG signal is selected from the electrocardiosignals of the previous 5 minutes as a template, DTW is carried out, and the distance between the P-peak forward signal and the template is extracted as an index; LSTM-AE is directly carried out on 1/2 ECG signals, 1/2 ECG signals are compressed to 4 points, box graphs are carried out on the distribution of the 4 points, and points with obvious difference distribution on P waves and F waves are selected as characteristics.
2. The method of claim 1, wherein the electrocardiographic waveform signal is from a wearable electrocardiographic monitoring device or a non-contact electrocardiographic monitoring device.
3. A paroxysmal atrial fibrillation scanning system for long-range electrocardiographic monitoring, the system for implementing the paroxysmal atrial fibrillation scanning method for long-range electrocardiographic monitoring according to any one of claims 1-2, comprising:
the data acquisition module acquires an electrocardio waveform signal;
the data preprocessing module is used for carrying out unified dimension processing on the obtained electrocardiographic waveform signals;
the atrial fibrillation signal analysis module is used for carrying out characteristic point R wave detection by adopting the processed electrocardiographic waveform, extracting RR intervals, differentiating the RR intervals to obtain an fatter RR interval, screening out irregular electrocardiographic signals of the RR intervals as suspected atrial fibrillation through the distribution of the RR intervals, namely calculating the heartbeat distribution of which the RR intervals are more than 10mv as the suspected atrial fibrillation; screening partial premature beat from suspected atrial fibrillation fragments by distributing the fatter RR intervals, namely calculating that the fatter RR intervals are distributed in a space of more than 700mv and the spatial distribution of 100-700mv is less than 40%;
the atrial fibrillation signal scanning module is used for screening atrial fibrillation fragments screened by the RR interval model through P-wave information, and finally determining the atrial fibrillation fragments;
and the atrial fibrillation signal statistics output module is used for quantifying the atrial fibrillation attack frequency and the atrial fibrillation duration and outputting typical atrial fibrillation fragments and quantified results.
4. A computer-readable storage medium having stored thereon a computer program, characterized by: the method is used for fingerprint similarity calculation, and the program when executed by a processor realizes the paroxysmal atrial fibrillation scanning method aiming at long-range electrocardiographic monitoring according to any one of claims 1 to 2.
5. An electronic device, characterized in that: a computer program comprising a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the paroxysmal atrial fibrillation scanning method for long-range electrocardiographic monitoring of any one of claims 1 to 2 when said program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210032416.6A CN114343666B (en) | 2022-01-12 | 2022-01-12 | Paroxysmal atrial fibrillation scanning method and system for long-range electrocardiographic monitoring, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210032416.6A CN114343666B (en) | 2022-01-12 | 2022-01-12 | Paroxysmal atrial fibrillation scanning method and system for long-range electrocardiographic monitoring, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114343666A CN114343666A (en) | 2022-04-15 |
| CN114343666B true CN114343666B (en) | 2023-09-26 |
Family
ID=81108357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210032416.6A Active CN114343666B (en) | 2022-01-12 | 2022-01-12 | Paroxysmal atrial fibrillation scanning method and system for long-range electrocardiographic monitoring, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114343666B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102805620A (en) * | 2012-08-16 | 2012-12-05 | 深圳市邦健电子有限公司 | Method and device for detecting atrial fibrillation |
| CN104367318A (en) * | 2014-11-07 | 2015-02-25 | 北京海思敏医疗技术有限公司 | Detection method and device for atrial fibrillation |
| CN106264518A (en) * | 2016-08-04 | 2017-01-04 | 东莞市第三人民医院 | A kind of based on finger tip Electrocardiographic atrial fibrillation detection method and device |
| CN109770893A (en) * | 2019-03-08 | 2019-05-21 | 东南大学 | The method and device of atrial fibrillation position are quickly positioned in a kind of Holter analysis system |
| CN110840402A (en) * | 2019-11-19 | 2020-02-28 | 山东大学 | Atrial fibrillation signal identification method and system based on machine learning |
| CN113343805A (en) * | 2021-05-26 | 2021-09-03 | 南京医科大学 | Atrial fibrillation rhythm identification method based on RR interphase electrocardiogram data and ensemble learning |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7596405B2 (en) * | 2005-03-07 | 2009-09-29 | United Therapeutics Corporation | Atrial fibrillation detection |
| WO2009018570A2 (en) * | 2007-08-02 | 2009-02-05 | The Research Foundation Of State University Of New York | Rr interval monitoring and blood pressure culff utilizing same |
| WO2019046294A1 (en) * | 2017-08-28 | 2019-03-07 | University Of South Florida | System and method for the prediction of atrial fibrillation (af) |
-
2022
- 2022-01-12 CN CN202210032416.6A patent/CN114343666B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102805620A (en) * | 2012-08-16 | 2012-12-05 | 深圳市邦健电子有限公司 | Method and device for detecting atrial fibrillation |
| CN104367318A (en) * | 2014-11-07 | 2015-02-25 | 北京海思敏医疗技术有限公司 | Detection method and device for atrial fibrillation |
| CN106264518A (en) * | 2016-08-04 | 2017-01-04 | 东莞市第三人民医院 | A kind of based on finger tip Electrocardiographic atrial fibrillation detection method and device |
| CN109770893A (en) * | 2019-03-08 | 2019-05-21 | 东南大学 | The method and device of atrial fibrillation position are quickly positioned in a kind of Holter analysis system |
| CN110840402A (en) * | 2019-11-19 | 2020-02-28 | 山东大学 | Atrial fibrillation signal identification method and system based on machine learning |
| CN113343805A (en) * | 2021-05-26 | 2021-09-03 | 南京医科大学 | Atrial fibrillation rhythm identification method based on RR interphase electrocardiogram data and ensemble learning |
Non-Patent Citations (2)
| Title |
|---|
| Integration of Results From Convolutional Neural Network in a Support Vector Machine for the Detection of Atrial Fibrillation;Caiyun Ma等人;IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT;第70卷;全文 * |
| Multi-Label Classification of Arrhythmia for Long-Term Electrocardiogram Signals With Feature Learning;Yuwen Li等人;IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,;第70卷;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114343666A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109171712B (en) | Atrial fibrillation identification method, atrial fibrillation identification device, atrial fibrillation identification equipment and computer readable storage medium | |
| CN107358196B (en) | Heart beat type classification method and device and electrocardiograph | |
| Babaeizadeh et al. | Improvements in atrial fibrillation detection for real-time monitoring | |
| EP1802230B1 (en) | Monitoring physiological activity using partial state space reconstruction | |
| CN109411042B (en) | Electrocardio information processing method and electrocardio workstation | |
| US8321005B2 (en) | System for continuous cardiac pathology detection and characterization | |
| CN106815570B (en) | Electrocardiosignal ST-T segment identification method based on dynamic pattern identification | |
| CN112528783B (en) | Electrocardiogram and heart beat data clustering method, device, electronic equipment and medium | |
| CN111358459A (en) | Arrhythmia identification method, device, equipment and storage medium | |
| CN113995419B (en) | Atrial fibrillation risk prediction system based on heartbeat rhythm signal and application thereof | |
| CN110840443B (en) | Electrocardiosignal processing method, electrocardiosignal processing device and electronic equipment | |
| Li et al. | Probability density distribution of delta RR intervals: a novel method for the detection of atrial fibrillation | |
| Ma et al. | A multistep paroxysmal atrial fibrillation scanning strategy in long-term ECGs | |
| CN111832537A (en) | Abnormal electrocardiosignal identification method and abnormal electrocardiosignal identification device | |
| CN111528833B (en) | Rapid identification and processing method and system for electrocardiosignals | |
| CN114343666B (en) | Paroxysmal atrial fibrillation scanning method and system for long-range electrocardiographic monitoring, storage medium and electronic equipment | |
| CN111839505A (en) | Atrial fibrillation classification method based on cardiovascular system electrical-mechanical activity information | |
| CN115337018B (en) | Electrocardiogram signal classification method and system based on overall dynamic characteristics | |
| CN108836312B (en) | Clutter rejection method and system based on artificial intelligence | |
| US20190374123A1 (en) | Predicting atrial fibrillation or stroke using p-wave analysis | |
| Zhang et al. | Evaluation of single-lead ECG signal quality with different states of motion | |
| Nankani et al. | R-peak detection from ECG signals using fractal based mathematical morphological operators | |
| KR101515725B1 (en) | Apparatus and method for diagnosing cardiac disorder | |
| RU2791006C1 (en) | System and method for automated electrocardiogram analysis and interpretation | |
| CN111685754B (en) | Heart rate calculation method and system for wearable ECG acquisition equipment |
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 |