CN113349791A - Abnormal electrocardiosignal detection method, device, equipment and medium - Google Patents
Abnormal electrocardiosignal detection method, device, equipment and medium Download PDFInfo
- Publication number
- CN113349791A CN113349791A CN202110602679.1A CN202110602679A CN113349791A CN 113349791 A CN113349791 A CN 113349791A CN 202110602679 A CN202110602679 A CN 202110602679A CN 113349791 A CN113349791 A CN 113349791A
- Authority
- CN
- China
- Prior art keywords
- signal
- signals
- detected
- heartbeat
- waveform
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 99
- 238000001514 detection method Methods 0.000 title claims description 37
- 230000007246 mechanism Effects 0.000 claims abstract description 108
- 238000013528 artificial neural network Methods 0.000 claims abstract description 75
- 238000000034 method Methods 0.000 claims abstract description 51
- 206010003658 Atrial Fibrillation Diseases 0.000 claims abstract description 22
- 230000000747 cardiac effect Effects 0.000 claims description 31
- 238000012216 screening Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000000718 qrs complex Methods 0.000 claims description 12
- 201000010099 disease Diseases 0.000 claims description 9
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000036772 blood pressure Effects 0.000 claims description 3
- 206010003119 arrhythmia Diseases 0.000 description 9
- 230000006793 arrhythmia Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 208000019622 heart disease Diseases 0.000 description 8
- 230000005856 abnormality Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 230000000306 recurrent effect Effects 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000028161 membrane depolarization Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 210000002837 heart atrium Anatomy 0.000 description 1
- 230000010247 heart contraction Effects 0.000 description 1
- 230000000366 juvenile effect Effects 0.000 description 1
- 230000002107 myocardial effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002336 repolarization Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/25—Bioelectric electrodes therefor
- A61B5/251—Means for maintaining electrode contact with the body
- A61B5/256—Wearable electrodes, e.g. having straps or bands
-
- 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
- A61B5/25—Bioelectric electrodes therefor
- A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
- A61B5/28—Bioelectric electrodes therefor specially adapted for particular uses for electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/353—Detecting P-waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/355—Detecting T-waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/357—Detecting U-waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/358—Detecting ST segments
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/366—Detecting abnormal QRS complex, e.g. widening
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The application relates to the field of electrocardiosignal identification, and discloses a method, a device, equipment and a medium for detecting abnormal electrocardiosignals, wherein the method comprises the following steps: acquiring electrocardiosignals to be detected, which are acquired by wearable equipment; calling a neural network based on a first attention mechanism to identify the electrocardiosignal to be detected to obtain a window signal; the window signal is a signal which is used for representing continuous heartbeat in the electrocardiosignal to be detected; calling a neural network based on a second attention mechanism to segment each signal of continuous heartbeats in the window signal to obtain a heartbeat signal of each heartbeat; calling a neural network based on a third attention mechanism to identify the heartbeat signals and determining each waveform signal in the heartbeat signals; and matching the waveform signals in a database to obtain target signals, wherein the target signals are abnormal electrocardiosignals which trigger atrial fibrillation in the electrocardiosignals to be detected. The method and the device can improve the accuracy and the interpretability of the electrocardiosignal identification.
Description
Technical Field
The present application relates to the field of electrocardiographic signal identification, and in particular, to a method and an apparatus for detecting an abnormal electrocardiographic signal, a computer device, and a storage medium.
Background
The electrocardiogram plays an important role in the diagnosis of cardiovascular diseases, doctors can judge whether the heart of a patient is healthy through the electrocardiogram at present, abnormal conditions of arrhythmia can be found through analyzing the waveform of the electrocardiogram, the data volume of the electrocardiogram obtained at each time is large at present, the workload of manual analysis of the electrocardiogram obtained by doctors is too large, the electrocardiogram data cannot be checked in real time, the detection efficiency of the electrocardiogram data at present is low, and the interpretability of the obtained result is low for the classification of the electrocardiogram data at present.
Disclosure of Invention
The application mainly aims to provide a method and a device for detecting abnormal electrocardiosignals, computer equipment and a storage medium, and aims to solve the problem that electrocardio data cannot be detected and explained efficiently in real time at present.
In order to achieve the above object, the present application provides a method for detecting abnormal electrocardiographic signals, comprising:
acquiring electrocardiosignals to be detected, which are acquired by wearable equipment;
calling a neural network based on a first attention mechanism to identify the electrocardiosignals to be detected, and obtaining window signals in the electrocardiosignals to be detected; the window signal is a signal which is used for representing continuous heartbeat in the electrocardiosignal to be detected;
calling a neural network based on a second attention mechanism to segment each signal of continuous heartbeats in the window signal to obtain a heartbeat signal of each heartbeat; the segmentation is based on the starting feature and the ending feature of each heartbeat;
calling a neural network based on a third attention mechanism to identify the heartbeat signals and determining each waveform signal in the heartbeat signals;
and performing similarity matching on the waveform signal and a waveform signal which is acquired in advance in a database to obtain a target signal, wherein the target signal is an abnormal electrocardiosignal which triggers atrial fibrillation in the electrocardiosignal to be detected.
Further, after acquiring the electrocardiosignal to be detected acquired by the wearable device, the method further comprises:
acquiring characteristic data of a user wearing the wearable device; the characteristic data comprises one or more items of data of the age, the blood pressure value and historical disease data of the user;
according to the characteristic data, distributing a label for the electrocardiosignal to be detected from the incidence relation between the characteristic data which is collected in advance and the electrocardiosignal; the tag characterizes the cardiac signal;
configuring a first weight of the first attention mechanism, a second weight of a second attention mechanism, and a third weight of a third attention mechanism based on the label.
Further, the invoking of the neural network based on the first attention mechanism to identify the electrocardiographic signal to be detected includes:
calling a neural network of a first attention mechanism based on a first weight to identify the electrocardiosignal to be detected;
the invoking of the neural network based on the second attention mechanism segments each of the consecutive heart beats in the window signal, including:
calling a neural network of a second attention mechanism based on a second weight to segment each signal of continuous heartbeats in the window signal;
the invoking a third attention mechanism-based neural network to identify the heartbeat signal includes:
a neural network invoking a third attention mechanism based on a third weight identifies the heartbeat signal.
Further, the waveform signals comprise waveform signals of P waves, QRS complexes, T waves, S-T wave bands and U waves; the matching the waveform signals in the database to obtain target signals comprises:
acquiring a database corresponding to each waveform signal;
and respectively screening the waveform signals in a database corresponding to each waveform model to obtain target signals.
Further, matching the waveform signals in a database to obtain a target signal, where the target signal is an abnormal electrocardiosignal triggering atrial fibrillation in the electrocardiosignals to be detected, and the method includes:
taking the T wave and the S-T wave band as a first detection waveform signal;
judging whether a first abnormal electrocardiosignal matched with the first detection waveform signal exists in a database or not; if yes, acquiring the first abnormal electrocardiosignal as a target signal;
if not, taking the P wave, the QRS wave group and the U wave as second detection waveform signals; judging whether a second abnormal electrocardiosignal matched with the second detection waveform signal exists in a database or not; and if so, acquiring the second abnormal electrocardiosignal as a target signal.
Further, the step of screening the waveform signal from a database to obtain a target signal, where the target signal is an abnormal electrocardiographic signal triggering atrial fibrillation in the to-be-detected electrocardiographic signal, further includes:
acquiring the incidence relation between abnormal electrocardiosignals and human physiological characteristics;
matching the target signal in a human body physiological characteristic database according to the incidence relation to obtain a target human body physiological characteristic; wherein the target human physiological characteristic is physiological data that elicits the target signal.
Further, after the target signal is matched in a human body physiological characteristic database according to the association relationship to obtain the target human body physiological characteristic, the method further includes:
and feeding back the target human body physiological characteristics to a preset contact of the wearable device.
The application further provides a detection device for abnormal electrocardiosignals, which comprises:
the signal acquisition module is used for acquiring electrocardiosignals to be detected, which are acquired by wearable equipment;
the window level module is used for calling a neural network based on a first attention mechanism to identify the electrocardiosignals to be detected to obtain window signals in the electrocardiosignals to be detected; the window signal is a signal which is used for representing continuous heartbeat in the electrocardiosignal to be detected;
the heartbeat hierarchy module is used for calling a neural network based on a second attention mechanism to segment each signal of continuous heartbeats in the window signals to obtain a heartbeat signal of each heartbeat; the segmentation is based on the starting feature and the ending feature of each heartbeat;
the waveform level module is used for calling a neural network based on a third attention mechanism to identify the heartbeat signals and determining each waveform signal in the heartbeat signals;
and the abnormal matching module is used for performing similarity matching on the waveform signal and a waveform signal which is acquired in advance in a database to obtain a target signal, wherein the target signal is an abnormal electrocardiosignal which triggers atrial fibrillation in the electrocardiosignal to be detected.
The application also provides a computer device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the abnormal electrocardiosignal detection method when executing the computer program.
The present application also provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the abnormal cardiac electrical signal detection method according to any one of the above-mentioned methods.
The embodiment of the application provides a method for identifying abnormal electrocardiosignals existing in electrocardiosignals layer by layer based on a three-layer attention mechanism, which comprises the steps of acquiring electrocardiosignals to be detected acquired by wearable equipment, calling a neural network based on a first attention mechanism to identify the electrocardiosignals to be detected, wherein the first attention mechanism is a plurality of electrocardiosignal attention mechanisms, rejecting invalid signals in the electrocardiosignals to be detected by the neural network based on the first attention mechanism to obtain an effective wave group, obtaining window signals in the electrocardiosignals to be detected, calling the neural network based on a second attention mechanism to divide each continuous heartbeat signal in the window signals to obtain the electrocardiosignals formed by each heartbeat, calling the neural network based on a third attention mechanism to identify the heartbeat signals, and determining P waves, P waves and B of the heartbeat signals, After each waveform signal in each heartbeat signal is determined, the waveform signals are screened from a database, abnormal electrocardiosignals triggering atrial fibrillation in the electrocardiosignals to be detected are screened out, so that the abnormality of the electrocardiosignals is found quickly, the arrhythmia detection efficiency is improved, the electrocardiosignals with arrhythmia of a wearer of wearable equipment are identified automatically, meanwhile, the detected abnormal electrocardiosignals can provide a data basis for predicting and judging heart diseases, and the accuracy and interpretability of the electrocardiosignal identification on disease judgment are improved.
Drawings
FIG. 1 is a schematic flowchart of an embodiment of a method for detecting abnormal cardiac electrical signals according to the present application;
FIG. 2 is a schematic flowchart of another embodiment of a method for detecting abnormal cardiac electrical signals according to the present application;
FIG. 3 is a schematic structural diagram of an embodiment of an abnormal ECG signal detection device according to the present application;
FIG. 4 is a block diagram illustrating a computer device according to an embodiment of the present invention.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, an embodiment of the present application provides a method for detecting an abnormal cardiac signal, which includes steps S10-S50, and the steps of the method for detecting an abnormal cardiac signal are described in detail as follows.
And S10, acquiring the electrocardiosignal to be detected, which is acquired by the wearable equipment.
The embodiment is applied to the detection and identification scenes of electrocardiosignals, the electrocardiosignals are also called as electrocardiograms, the electrocardiograms have the function of detecting the change condition of the heart in each cardiac cycle, the wearable equipment can record the electric activity generated by myocardial tissues, the electric activity generates voltage or 'biopotentials' and then spreads to the skin, the wearable equipment measures the electric signals in a mode of being connected to the skin, and the electrocardiosignals of the human body are formed according to the recorded signals each time. In particular, the wearable device is a wearable Electrocardiogram (ECG) device.
S20, calling a neural network based on a first attention mechanism to identify the electrocardiosignals to be detected, and obtaining window signals in the electrocardiosignals to be detected; and the window signal is a signal representing continuous heartbeat in the electrocardiosignal to be detected.
In this embodiment, after obtaining the electrocardiographic signal to be detected, the electrocardiographic signal to be detected needs to be identified, the signal caused by heart beating of the electrocardiographic signal to be detected is identified, specifically, the neural network based on the first attention system is called to identify the electrocardiographic signal to be detected, wherein the first attention mechanism is a plurality of electrocardiosignal attention mechanisms, the electrocardiosignal attention mechanisms are added into the neural network, the electrocardiosignal to be detected can be identified to appear continuous heartbeat signals in the electrocardiosignals to be detected, the electrocardiosignals are composed of a series of wave groups, the neural network based on the first attention mechanism eliminates invalid signals in the electrocardiosignals to be detected to obtain effective wave groups, obtaining window signals in the electrocardiosignals to be detected, expressing window levels of the electrocardiosignals, and the window signal is a signal representing continuous heartbeat in the electrocardiosignal to be detected.
S30, calling a neural network based on a second attention mechanism to segment each signal of continuous heartbeats in the window signal to obtain a heartbeat signal of each heartbeat; the segmentation is based on the start and end features of each heartbeat.
In this embodiment, after obtaining a window signal in an electrocardiographic signal to be detected, a neural network based on a second attention mechanism is called to segment each signal of consecutive heartbeats in the window signal, the second attention mechanism is a heartbeat level attention mechanism, the heartbeat level attention mechanism is added to the neural network, the second attention mechanism records a start electrocardiographic signal and an end heartbeat signal of each heartbeat, the window signal is identified based on the neural network of the second attention mechanism to obtain an electrocardiographic signal formed by each heartbeat, the electrocardiographic signal formed by each heartbeat is defined as a heartbeat signal, that is, the electrocardiographic signal is subjected to representation of heartbeat level, so that the electrocardiographic signals formed by each heartbeat are grouped, and the electrocardiographic signal formed by each heartbeat can be specifically analyzed.
And S40, calling a neural network based on a third attention mechanism to identify the heartbeat signals, and determining each waveform signal in the heartbeat signals.
In this embodiment, after obtaining an electrocardiographic signal (i.e., a heartbeat signal) formed by each heartbeat, a neural network based on a third attention mechanism is invoked to identify the heartbeat signal, and determine each waveform signal in the heartbeat signal, where the electrocardiographic signal is composed of a series of wave groups, each wave group represents each cardiac cycle, i.e., a heartbeat signal, and one wave group includes a P wave, a QRS complex, a T wave, and a U wave. P waves are the first waves in each wave group; the QRS complex comprises three waves which are closely connected, wherein the first downward wave is called Q wave, a high-tip vertical wave following the Q wave is an R wave, and the downward wave following the R wave is an S wave; the T wave is positioned behind an S-T wave band, and the S-T wave band is a flat line from the end of a QRS complex to the beginning of the T wave; the U wave is located after the T wave. And calling a neural network based on a third attention mechanism to identify the heartbeat signal, and determining each waveform signal in the heartbeat signal, namely determining the P wave, the QRS wave group, the T wave, the S-T wave band and the U wave of the heartbeat signal.
The neural network described above includes a stacked bidirectional recurrent neural network, and the bidirectional recurrent neural network model is defined as follows:
whereinFor the hidden state and the bias of the reverse network,are hidden states and biases of the forward network. x is the number oftAnd ytRespectively, the input and output of the bi-directional recurrent neural network.
And S50, performing similarity matching on the waveform signal and a waveform signal which is acquired in advance in a database to obtain a target signal, wherein the target signal is an abnormal electrocardiosignal which triggers atrial fibrillation in the electrocardiosignal to be detected.
In this embodiment, the occurrence of many heart diseases is often accompanied by the change of one or more waveforms in the electrocardiographic signals of each heartbeat, after each waveform signal in each heartbeat signal is determined, the waveform signals are screened from the database, a large amount of waveform signal data including normal waveform signals and abnormal waveform signals are recorded in the database, the waveform signals are used as input and are subjected to similarity matching with the waveform signals of each corresponding position in the database, when the similarity with one waveform signal representing atrial fibrillation abnormality in the database meets a preset requirement, the waveform signals are determined as target signals, the target signals are abnormal electrocardiographic signals triggering atrial fibrillation in the electrocardiographic signals to be detected, so as to screen out the abnormal electrocardiographic signals in the electrocardiographic signals to be detected, and the detected abnormal electrocardiographic signals can be prediction, Determining heart disease provides a data basis.
The embodiment provides a method for recognizing abnormal electrocardiosignals existing in electrocardiosignals layer by layer based on a three-layer attention mechanism, which comprises the steps of acquiring electrocardiosignals to be detected acquired by wearable equipment, calling a neural network based on a first attention mechanism to recognize the electrocardiosignals to be detected, wherein the first attention mechanism is a plurality of electrocardiosignal attention mechanisms, removing invalid signals from the electrocardiosignals to be detected by the neural network based on the first attention mechanism to obtain an effective wave group, obtaining window signals in the electrocardiosignals to be detected, calling the neural network based on a second attention mechanism to divide each continuous heartbeat signal in the window signals to obtain the electrocardiosignals formed by each heartbeat, calling the neural network based on a third attention mechanism to recognize the heartbeat signals, and determining P waves, P waves and B of the heartbeat signals, After each waveform signal in each heartbeat signal is determined, the waveform signals are screened from a database, abnormal electrocardiosignals triggering atrial fibrillation in the electrocardiosignals to be detected are screened out, so that the abnormality of the electrocardiosignals is found rapidly, the arrhythmia detection efficiency is improved, meanwhile, the detected abnormal electrocardiosignals can provide a data basis for predicting and judging heart diseases, and the accuracy and the interpretability of the electrocardiosignal identification on the disease judgment are improved.
In an embodiment, as shown in fig. 2, after the step S10 obtains the electrocardiographic signal to be detected collected by the wearable device, the method further includes:
s11: acquiring characteristic data of a user wearing the wearable device;
s12: distributing a label for the electrocardiosignal to be detected according to the characteristic data;
s13: configuring a first weight of the first attention mechanism, a second weight of a second attention mechanism, and a third weight of a third attention mechanism based on the label.
In this embodiment, after acquiring an electrocardiographic signal to be detected acquired by a wearable device, in order to accurately identify the electrocardiographic signal to be detected acquired by the wearable device of a different user, characteristic data of the user wearing the wearable device is acquired, where the characteristic data includes one or more of age, blood pressure value, and historical disease data of the user, and then a tag is assigned to the electrocardiographic signal to be detected according to the characteristic data, for example, the tag assigned according to the age of the user is a child, a juvenile, an elderly, etc., characteristics of the electrocardiographic signals generated by characteristic data of different users are different, for example, electrocardiographic signals of a child user and an elderly user are weak, and then a first weight of a first attention mechanism, a second weight of a second attention mechanism, and a third weight of a third attention mechanism are determined based on the tag, and the three attention mechanisms are assigned different weights, the electrocardiosignal detection method can accurately detect the electrocardiosignals of users with different characteristic data in different directions.
In one embodiment, the invoking of the neural network based on the first attention mechanism identifies the cardiac signal to be detected, including:
calling a neural network of a first attention mechanism based on a first weight to identify the electrocardiosignal to be detected;
the invoking of the neural network based on the second attention mechanism segments each of the consecutive heart beats in the window signal, including:
calling a neural network of a second attention mechanism based on a second weight to segment each signal of continuous heartbeats in the window signal;
the invoking a third attention mechanism-based neural network to identify the heartbeat signal includes:
a neural network invoking a third attention mechanism based on a third weight identifies the heartbeat signal.
In this embodiment, labels of electrocardiographic signals to be detected are assigned, then different weights of different attention mechanisms in three layers of attention mechanisms, that is, identification accuracies of the different attention mechanisms are assigned, then a neural network of a first attention mechanism based on a first weight is called to identify the electrocardiographic signals to be detected, a neural network of a second attention mechanism based on a second weight is called to segment each signal of continuous heart beats in the window signals, and a neural network of a third attention mechanism based on a third weight is called to identify the heart beat signals. In one implementation, when the wearable device of the user a acquires that the electrocardiosignal data to be detected is weak and a label is allocated, the accuracy of the first attention mechanism needs to be higher, and the ratio of the allocated first weight is larger, so that the window signal in the electrocardiosignal to be detected can be effectively identified, and the identification of the electrocardiosignal to be detected with different accuracies is improved.
In one embodiment, the waveform signals include waveform signals of a P wave, a QRS complex, a T wave, an S-T wave band, and a U wave; the matching the waveform signals in the database to obtain target signals comprises:
acquiring a database corresponding to each waveform signal;
and screening in a corresponding database according to the waveform model to obtain a target signal.
In this embodiment, the waveform signals include waveform signals of a P wave, a QRS complex, a T wave, an S-T wave band and a U wave, the P wave represents potential change in depolarization processes of two atria, and the waveform is small and round; the QRS complex represents the potential change in the depolarization process of the two ventricles; the T wave represents the potential change in the repolarization process of the two ventricles, and the direction of the T wave is the same as that of the QRS main wave; the U wave is a low and wide wavelet after the T wave, and the direction of the U wave is the same as that of the T wave; the S-T band is the flat line from the end of the QRS complex to the beginning of the T wave. When the waveform signals are screened from the database, the waveform signals are screened from the database of the corresponding waveform signals according to the share of each waveform signal, the P wave is screened from the database of the P wave, and the QRS complex is screened from the database of the QRS complex, so that the data search amount of waveform screening is reduced, the calculation amount of target signal screening is reduced, the screening efficiency of the target signals is improved, and the discovery efficiency of abnormal electrocardiosignals is improved.
In one embodiment, the matching the waveform signals in the database to obtain a target signal, where the target signal is an abnormal cardiac signal triggering atrial fibrillation in the cardiac electrical signal to be detected, includes:
taking the T wave and the S-T wave band as a first detection waveform signal;
judging whether a first abnormal electrocardiosignal matched with the first detection waveform signal exists in a database or not; if yes, acquiring the first abnormal electrocardiosignal as a target signal;
if not, taking the P wave, the QRS wave group and the U wave as second detection waveform signals; judging whether a second abnormal electrocardiosignal matched with the second detection waveform signal exists in a database or not; and if so, acquiring the second abnormal electrocardiosignal as a target signal.
In the embodiment, in the electrocardiosignals of each heartbeat, an S-T wave band and a T wave are important components, and a plurality of heart diseases are often accompanied by changes of the S-T wave band and the T wave, and when the waveform signals are screened from the database to obtain target signals, the T wave and the S-T wave band are screened from the database as first detection waveform signals to judge whether first abnormal electrocardiosignals matched with the first detection waveform signals exist in the database; if yes, acquiring the first abnormal electrocardiosignal as a target signal, and screening the P wave, the QRS wave group and the U wave as second detection waveform signals from a database; judging whether a second abnormal electrocardiosignal matched with the second detection waveform signal exists in a database or not; and if so, acquiring the second abnormal electrocardiosignal as a target signal. The S-T wave band and the T wave waveform signals are preferably screened, so that the waveform signals causing heart diseases are rapidly found, and the detection efficiency of abnormal electrocardiosignals is improved.
In one embodiment, the screening the waveform signal from the database to obtain a target signal, where the target signal is an abnormal cardiac signal that triggers atrial fibrillation in the cardiac electrical signal to be detected, further includes:
acquiring the incidence relation between abnormal electrocardiosignals and human physiological characteristics;
matching the target signal in a human body physiological characteristic database according to the incidence relation to obtain a target human body physiological characteristic; wherein the target human physiological characteristic is physiological data that elicits the target signal.
In this embodiment, after obtaining a target signal, that is, an abnormal electrocardiographic signal triggering atrial fibrillation in an electrocardiographic signal to be detected, it needs to be determined what the abnormal electrocardiographic data is caused, specifically, an association relationship between the abnormal electrocardiographic signal and a physiological characteristic of a human body is obtained, the target signal is matched from a physiological characteristic database of the human body according to the association relationship, a large amount of data of the abnormal electrocardiographic signal and the physiological characteristic of the human body is collected in the physiological characteristic database of the human body, the physiological characteristic of the human body includes a physiological characteristic of the human body caused by a disease, a physiological characteristic of the human body caused by a motion, etc., a physiological characteristic of the target human body is obtained, the physiological characteristic of the target human body can determine and explain a cause of causing the target signal, that is, the physiological characteristic of the target human body is physiological data of causing the target signal, for example, the physiological characteristic a1 of the human body caused by the disease a, the abnormal electrocardiosignals which are possibly caused comprise X1, X2 and X3, and when the target signal is X1, the matched physiological characteristics of the target human body are A1, so that the reason of the generation of the abnormal electrocardiosignal A1 can be explained, and the physiological characteristic matching efficiency of the abnormal electrocardiosignals is improved.
In one embodiment, after the matching the target signal in the human physiological characteristic database according to the association relationship to obtain the target human physiological characteristic, the method further includes:
and feeding back the target human body physiological characteristics to a preset contact of the wearable device.
In this embodiment, after obtaining the physiological characteristics associated with the abnormal cardiac electrical signals, in order to improve monitoring of the arrhythmia of the human heart rate, the target human physiological characteristics are fed back to a preset contact of the wearable device, where the preset contact may be a user of the wearable device, and the user is notified of the abnormal cardiac electrical signals (i.e., the arrhythmia) of the user wearing the wearable device, so as to remind the user of the physiological characteristics that may occur; the preset contact person can also be a medical worker, the situation that the user wearing the wearable device generates abnormal electrocardiosignals (namely arrhythmia) is informed to the related medical worker, the medical worker can be rapidly reminded of the abnormal electrocardiosignals, and the monitoring efficiency of the abnormal electrocardiosignals is improved.
Referring to fig. 3, the present application further provides a device for detecting an abnormal cardiac signal, including:
the signal acquisition module 10 is used for acquiring electrocardiosignals to be detected, which are acquired by wearable equipment;
the window level module 20 is configured to invoke a first attention mechanism-based neural network to identify the to-be-detected electrocardiosignal, so as to obtain a window signal in the to-be-detected electrocardiosignal; the window signal is a signal which is used for representing continuous heartbeat in the electrocardiosignal to be detected;
the heartbeat hierarchy module 30 is configured to invoke a neural network based on a second attention mechanism to segment each signal of consecutive heartbeats in the window signal to obtain a heartbeat signal of each heartbeat;
a waveform hierarchy module 40, configured to invoke a neural network based on a third attention mechanism to identify the heartbeat signals, and determine each waveform signal in the heartbeat signals;
and the abnormal matching module 50 is used for performing similarity matching on the waveform signal and a waveform signal which is acquired in advance in a database to obtain a target signal, wherein the target signal is an abnormal electrocardiosignal which triggers atrial fibrillation in the electrocardiosignals to be detected.
As described above, it is understood that the components of the electrocardiographic signal detection device proposed in the present application can realize the functions of any of the above-described electrocardiographic signal detection methods.
In one embodiment, the signal acquisition module 10 further performs:
acquiring characteristic data of a user wearing the wearable device;
distributing a label for the electrocardiosignal to be detected according to the characteristic data;
determining a first weight of the first attention mechanism, a second weight of a second attention mechanism, and a third weight of a third attention mechanism based on the label.
In one embodiment, the waveform signals include waveform signals of a P wave, a QRS complex, a T wave, an S-T wave band, and a U wave; the anomaly matching module 40 further performs:
acquiring a database corresponding to each waveform signal;
and screening in a corresponding database according to the waveform model to obtain a target signal.
In one embodiment, the anomaly matching module 40 further performs:
taking the T wave and the S-T wave band as a first detection waveform signal;
judging whether a first abnormal electrocardiosignal matched with the first detection waveform signal exists in a database or not; if yes, acquiring the first abnormal electrocardiosignal as a target signal;
if not, taking the P wave, the QRS wave group and the U wave as second detection waveform signals; judging whether a second abnormal electrocardiosignal matched with the second detection waveform signal exists in a database or not; and if so, acquiring the second abnormal electrocardiosignal as a target signal.
In one embodiment, the device further comprises an association module for acquiring the association relationship between the abnormal electrocardiosignals and the physiological characteristics of the human body;
matching the target signal in a human body physiological characteristic database according to the incidence relation to obtain a target human body physiological characteristic; wherein the target human physiological characteristic is physiological data that elicits the target signal.
In one embodiment, the associating module further performs: and feeding back the target human body physiological characteristics to a preset contact of the wearable device.
Referring to fig. 4, a computer device, which may be a mobile terminal and whose internal structure may be as shown in fig. 4, is also provided in the embodiment of the present application. The computer equipment comprises a processor, a memory, a network interface, a display device and an input device which are connected through a system bus. Wherein, the network interface of the computer equipment is used for communicating with an external terminal through network connection. The input means of the computer device is for receiving input from a user. The computer designed processor is used to provide computational and control capabilities. The memory of the computer device includes a storage medium. The storage medium stores an operating system, a computer program, and a database. The database of the computer device is used for storing data. The computer program is executed by a processor to realize a method for detecting abnormal electrocardiosignals.
The processor executes the method for detecting the abnormal electrocardiosignals, and the method comprises the following steps: acquiring electrocardiosignals to be detected, which are acquired by wearable equipment; calling a neural network based on a first attention mechanism to identify the electrocardiosignals to be detected, and obtaining window signals in the electrocardiosignals to be detected; the window signal is a signal which is used for representing continuous heartbeat in the electrocardiosignal to be detected; calling a neural network based on a second attention mechanism to segment each signal of continuous heartbeats in the window signal to obtain a heartbeat signal of each heartbeat; calling a neural network based on a third attention mechanism to identify the heartbeat signals and determining each waveform signal in the heartbeat signals; and matching the waveform signals in a database to obtain target signals, wherein the target signals are abnormal electrocardiosignals which trigger atrial fibrillation in the electrocardiosignals to be detected.
The computer equipment provides a method for identifying abnormal electrocardiosignals in electrocardiosignals layer by layer based on a three-layer attention mechanism, the electrocardiosignals to be detected acquired by wearable equipment are acquired, then a neural network based on a first attention mechanism is called to identify the electrocardiosignals to be detected, wherein the first attention mechanism is a plurality of electrocardiosignal attention mechanisms, invalid signals in the electrocardiosignals to be detected are eliminated by the neural network based on the first attention mechanism to obtain effective wave groups, window signals in the electrocardiosignals to be detected are obtained, then the neural network based on a second attention mechanism is called to divide each continuous heartbeat signal in the window signals to obtain the electrocardiosignals formed by each heartbeat, and the neural network based on a third attention mechanism is called to identify the heartbeat signals, the method comprises the steps of determining P waves, QRS wave groups, T waves, S-T wave bands and U waves of heartbeat signals, screening the waveform signals from a database after each waveform signal in each heartbeat signal is determined, and screening abnormal electrocardiosignals which trigger atrial fibrillation in the electrocardiosignals to be detected, so that the abnormality of the electrocardiosignals is found quickly, the detection efficiency of arrhythmia is improved, meanwhile, the detected abnormal electrocardiosignals can provide a data basis for predicting and judging heart diseases, and the accuracy and the interpretability of electrocardiosignal identification on disease judgment are improved.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by the processor, implements a method for detecting abnormal cardiac electrical signals, including the steps of: acquiring electrocardiosignals to be detected, which are acquired by wearable equipment; calling a neural network based on a first attention mechanism to identify the electrocardiosignals to be detected, and obtaining window signals in the electrocardiosignals to be detected; the window signal is a signal which is used for representing continuous heartbeat in the electrocardiosignal to be detected; calling a neural network based on a second attention mechanism to segment each signal of continuous heartbeats in the window signal to obtain a heartbeat signal of each heartbeat; calling a neural network based on a third attention mechanism to identify the heartbeat signals and determining each waveform signal in the heartbeat signals; and matching the waveform signals in a database to obtain target signals, wherein the target signals are abnormal electrocardiosignals which trigger atrial fibrillation in the electrocardiosignals to be detected.
The computer readable storage medium provides a method for identifying abnormal electrocardiosignals existing in electrocardiosignals layer by layer based on a three-layer attention mechanism, the electrocardiosignals to be detected acquired by wearable equipment are acquired, then a neural network based on a first attention mechanism is called to identify the electrocardiosignals to be detected, wherein the first attention mechanism is a plurality of electrocardiosignal attention mechanisms, invalid signals in the electrocardiosignals to be detected are eliminated by the neural network based on the first attention mechanism to obtain effective wave groups, window signals in the electrocardiosignals to be detected are obtained, then the neural network based on a second attention mechanism is called to divide signals of continuous heartbeats in the window signals to obtain electrocardiosignals formed by each heartbeat, and the neural network based on a third attention mechanism is called to identify the heartbeat signals, the method comprises the steps of determining P waves, QRS wave groups, T waves, S-T wave bands and U waves of heartbeat signals, screening the waveform signals from a database after each waveform signal in each heartbeat signal is determined, and screening abnormal electrocardiosignals which trigger atrial fibrillation in the electrocardiosignals to be detected, so that the abnormality of the electrocardiosignals is found quickly, the detection efficiency of arrhythmia is improved, meanwhile, the detected abnormal electrocardiosignals can provide a data basis for predicting and judging heart diseases, and the accuracy and the interpretability of electrocardiosignal identification on disease judgment are improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above.
Any reference to memory, storage, database, or other medium provided herein and used in the embodiments may include non-volatile and/or volatile memory.
Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
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, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application and is not intended to limit the scope of the present application.
All the equivalent structures or equivalent processes performed by using the contents of the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields, are included in the scope of protection of the present application.
Claims (10)
1. A method for detecting abnormal electrocardiosignals is characterized by comprising the following steps:
acquiring electrocardiosignals to be detected, which are acquired by wearable equipment;
calling a neural network based on a first attention mechanism to identify the electrocardiosignals to be detected, and obtaining window signals in the electrocardiosignals to be detected; the window signal is a signal which is used for representing continuous heartbeat in the electrocardiosignal to be detected;
calling a neural network based on a second attention mechanism to segment each signal of continuous heartbeats in the window signal to obtain a heartbeat signal of each heartbeat; the segmentation is based on the starting feature and the ending feature of each heartbeat;
calling a neural network based on a third attention mechanism to identify the heartbeat signals and determining each waveform signal in the heartbeat signals;
and performing similarity matching on the waveform signal and a waveform signal which is acquired in advance in a database to obtain a target signal, wherein the target signal is an abnormal electrocardiosignal which triggers atrial fibrillation in the electrocardiosignal to be detected.
2. The method for detecting abnormal cardiac electrical signals according to claim 1, wherein after acquiring the cardiac electrical signals to be detected collected by the wearable device, the method further comprises:
acquiring characteristic data of a user wearing the wearable device; the characteristic data comprises one or more items of data of the age, the blood pressure value and historical disease data of the user;
according to the characteristic data, distributing a label for the electrocardiosignal to be detected from the incidence relation between the characteristic data which is collected in advance and the electrocardiosignal; the tag characterizes the cardiac signal;
configuring a first weight of the first attention mechanism, a second weight of a second attention mechanism, and a third weight of a third attention mechanism based on the label.
3. The method for detecting abnormal cardiac signals according to claim 2, wherein the invoking of the neural network based on the first attention mechanism to identify the cardiac signals to be detected comprises:
calling a neural network of a first attention mechanism based on a first weight to identify the electrocardiosignal to be detected;
the invoking of the neural network based on the second attention mechanism segments each of the consecutive heart beats in the window signal, including:
calling a neural network of a second attention mechanism based on a second weight to segment each signal of continuous heartbeats in the window signal;
the invoking a third attention mechanism-based neural network to identify the heartbeat signal includes:
a neural network invoking a third attention mechanism based on a third weight identifies the heartbeat signal.
4. The method according to claim 1, wherein the waveform signal includes waveform signals of a P-wave, a QRS complex, a T-wave, an S-T-wave, and a U-wave; the similarity matching between the waveform signal and a waveform signal which is acquired in advance in a database to obtain a target signal comprises the following steps:
acquiring a database corresponding to each waveform signal;
and respectively screening the waveform signals in a database corresponding to each waveform model to obtain target signals.
5. The method for detecting abnormal cardiac electrical signals according to claim 4, wherein the performing similarity matching between the waveform signals and pre-collected waveform signals in a database to obtain target signals, wherein the target signals are the abnormal cardiac electrical signals triggering atrial fibrillation in the cardiac electrical signals to be detected, comprises:
taking the T wave and the S-T wave band as a first detection waveform signal;
judging whether a first abnormal electrocardiosignal matched with the first detection waveform signal exists in a database or not; if yes, acquiring the first abnormal electrocardiosignal as a target signal;
if not, taking the P wave, the QRS wave group and the U wave as second detection waveform signals; judging whether a second abnormal electrocardiosignal matched with the second detection waveform signal exists in a database or not; and if so, acquiring the second abnormal electrocardiosignal as a target signal.
6. The method for detecting abnormal cardiac electrical signals according to claim 1, wherein the step of performing similarity matching between the waveform signals and waveform signals to be acquired in the database to obtain target signals, wherein the target signals are abnormal cardiac electrical signals which trigger atrial fibrillation in the cardiac electrical signals to be detected, further comprises:
acquiring the incidence relation between abnormal electrocardiosignals and human physiological characteristics;
matching the target signal in a human body physiological characteristic database according to the incidence relation to obtain a target human body physiological characteristic; wherein the target human physiological characteristic is physiological data that elicits the target signal.
7. The method according to claim 6, wherein after the target signal is matched in the human physiological characteristic database according to the association relationship to obtain the target human physiological characteristic, the method further comprises:
and feeding back the target human body physiological characteristics to a preset contact of the wearable device.
8. An abnormal cardiac signal detection device, comprising:
the signal acquisition module is used for acquiring electrocardiosignals to be detected, which are acquired by wearable equipment;
the window level module is used for calling a neural network based on a first attention mechanism to identify the electrocardiosignals to be detected to obtain window signals in the electrocardiosignals to be detected; the window signal is a signal which is used for representing continuous heartbeat in the electrocardiosignal to be detected;
the heartbeat hierarchy module is used for calling a neural network based on a second attention mechanism to segment each signal of continuous heartbeats in the window signals to obtain a heartbeat signal of each heartbeat; the segmentation is based on the starting feature and the ending feature of each heartbeat;
the waveform level module is used for calling a neural network based on a third attention mechanism to identify the heartbeat signals and determining each waveform signal in the heartbeat signals;
and the abnormal matching module is used for performing similarity matching on the waveform signal and a waveform signal which is acquired in advance in a database to obtain a target signal, wherein the target signal is an abnormal electrocardiosignal which triggers atrial fibrillation in the electrocardiosignal to be detected.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of the method for detecting abnormal cardiac electrical signals according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for detecting abnormal cardiac electrical signals according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110602679.1A CN113349791A (en) | 2021-05-31 | 2021-05-31 | Abnormal electrocardiosignal detection method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110602679.1A CN113349791A (en) | 2021-05-31 | 2021-05-31 | Abnormal electrocardiosignal detection method, device, equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113349791A true CN113349791A (en) | 2021-09-07 |
Family
ID=77530715
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110602679.1A Pending CN113349791A (en) | 2021-05-31 | 2021-05-31 | Abnormal electrocardiosignal detection method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113349791A (en) |
Citations (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1043620A (en) * | 1988-12-24 | 1990-07-11 | 沈仲元 | Portable intelligent cardioelectric monitor |
US20100081953A1 (en) * | 2008-04-21 | 2010-04-01 | International Business Machines Corporation | System and method for inferring disease similarity by shape matching of ecg time series |
CN102389303A (en) * | 2011-08-02 | 2012-03-28 | 长春华讯信息科技有限公司 | Method and device for monitoring electrocardiogram |
CN102449165A (en) * | 2009-04-03 | 2012-05-09 | 解码遗传学私营有限责任公司 | Genetic markers for risk management of atrial fibrillation and stroke |
CN104834921A (en) * | 2015-05-22 | 2015-08-12 | 清华大学深圳研究生院 | Electrocardio normality/abnormality big-data processing method and device |
CN107753014A (en) * | 2017-11-21 | 2018-03-06 | 中国科学院深圳先进技术研究院 | Electrocardiogram detecting method |
CN108701219A (en) * | 2017-03-14 | 2018-10-23 | 华为技术有限公司 | The method and device of waveform signal processing |
CN109068996A (en) * | 2016-05-18 | 2018-12-21 | 托佩拉公司 | The system and method for identifying remote source associated with biological rhythm disorder |
CN109330582A (en) * | 2018-08-31 | 2019-02-15 | 苏州心生智能科技有限公司 | Heart rate and its characteristic index detection method based on ECG Signal Analysis |
CN109508584A (en) * | 2017-09-15 | 2019-03-22 | 腾讯科技(深圳)有限公司 | The method of visual classification, the method for information processing and server |
CN109567789A (en) * | 2018-12-03 | 2019-04-05 | 东软集团股份有限公司 | Division processing method, device and the readable storage medium storing program for executing of ECG data |
WO2019140604A1 (en) * | 2018-01-18 | 2019-07-25 | 深圳迈瑞生物医疗电子股份有限公司 | Method for analyzing arrhythmia in real time, electrocardiograph monitoring device and storage medium |
CN110327032A (en) * | 2019-03-27 | 2019-10-15 | 苏州平稳芯跳医疗科技有限公司 | It is a kind of singly to lead the accurate recognizer of electrocardiosignal PQRST wave joint |
CN110547792A (en) * | 2019-07-31 | 2019-12-10 | 平安科技(深圳)有限公司 | atrial fibrillation detection method and device, computer equipment and storage medium |
CN110558971A (en) * | 2019-08-02 | 2019-12-13 | 苏州星空大海医疗科技有限公司 | Method for generating countermeasure network electrocardiogram abnormity detection based on single target and multiple targets |
CN110659759A (en) * | 2018-06-29 | 2020-01-07 | 微软技术许可有限责任公司 | Neural network based trend prediction |
CN110656169A (en) * | 2019-11-05 | 2020-01-07 | 天津市人民医院 | Diagnostic markers for atrial fibrillation |
CN110786849A (en) * | 2019-11-11 | 2020-02-14 | 菏泽学院 | Electrocardiosignal identity recognition method and system based on multi-view discriminant analysis |
CN111053552A (en) * | 2019-12-03 | 2020-04-24 | 上海理工大学 | QRS wave detection method based on deep learning |
CN111345817A (en) * | 2020-02-25 | 2020-06-30 | 广州视源电子科技股份有限公司 | QRS complex position determination method, device, equipment and storage medium |
CN111528832A (en) * | 2020-05-28 | 2020-08-14 | 四川大学华西医院 | Arrhythmia classification method and validity verification method thereof |
CN111553362A (en) * | 2019-04-01 | 2020-08-18 | 上海卫莎网络科技有限公司 | Video processing method, electronic equipment and computer readable storage medium |
US20200298002A1 (en) * | 2019-03-21 | 2020-09-24 | Medtronic, Inc. | T-wave morphology analysis for pathological event detection |
CN111920405A (en) * | 2020-09-15 | 2020-11-13 | 齐鲁工业大学 | Atrial fibrillation signal identification system and method |
CN111956214A (en) * | 2020-07-29 | 2020-11-20 | 鲁东大学 | QRS wave automatic detection method based on U-net end-to-end neural network model |
CN112022149A (en) * | 2020-09-04 | 2020-12-04 | 无锡博智芯科技有限公司 | Atrial fibrillation detection method based on electrocardiosignals |
US20210007618A1 (en) * | 2018-02-24 | 2021-01-14 | Lepu Medical Technology (Bejing) Co., Ltd. | Electrocardiogram information processing method and electrocardiogram workstation system |
CN112674780A (en) * | 2020-12-23 | 2021-04-20 | 山东省人工智能研究院 | Automatic atrial fibrillation signal detection method in electrocardiogram abnormal signals |
CN112826513A (en) * | 2021-01-05 | 2021-05-25 | 华中科技大学 | Fetal heart rate detection system based on deep learning and specificity correction on FECG |
-
2021
- 2021-05-31 CN CN202110602679.1A patent/CN113349791A/en active Pending
Patent Citations (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1043620A (en) * | 1988-12-24 | 1990-07-11 | 沈仲元 | Portable intelligent cardioelectric monitor |
US20100081953A1 (en) * | 2008-04-21 | 2010-04-01 | International Business Machines Corporation | System and method for inferring disease similarity by shape matching of ecg time series |
CN102449165A (en) * | 2009-04-03 | 2012-05-09 | 解码遗传学私营有限责任公司 | Genetic markers for risk management of atrial fibrillation and stroke |
CN102389303A (en) * | 2011-08-02 | 2012-03-28 | 长春华讯信息科技有限公司 | Method and device for monitoring electrocardiogram |
CN104834921A (en) * | 2015-05-22 | 2015-08-12 | 清华大学深圳研究生院 | Electrocardio normality/abnormality big-data processing method and device |
CN109068996A (en) * | 2016-05-18 | 2018-12-21 | 托佩拉公司 | The system and method for identifying remote source associated with biological rhythm disorder |
CN108701219A (en) * | 2017-03-14 | 2018-10-23 | 华为技术有限公司 | The method and device of waveform signal processing |
CN109508584A (en) * | 2017-09-15 | 2019-03-22 | 腾讯科技(深圳)有限公司 | The method of visual classification, the method for information processing and server |
CN107753014A (en) * | 2017-11-21 | 2018-03-06 | 中国科学院深圳先进技术研究院 | Electrocardiogram detecting method |
WO2019140604A1 (en) * | 2018-01-18 | 2019-07-25 | 深圳迈瑞生物医疗电子股份有限公司 | Method for analyzing arrhythmia in real time, electrocardiograph monitoring device and storage medium |
US20210007618A1 (en) * | 2018-02-24 | 2021-01-14 | Lepu Medical Technology (Bejing) Co., Ltd. | Electrocardiogram information processing method and electrocardiogram workstation system |
CN110659759A (en) * | 2018-06-29 | 2020-01-07 | 微软技术许可有限责任公司 | Neural network based trend prediction |
CN109330582A (en) * | 2018-08-31 | 2019-02-15 | 苏州心生智能科技有限公司 | Heart rate and its characteristic index detection method based on ECG Signal Analysis |
CN109567789A (en) * | 2018-12-03 | 2019-04-05 | 东软集团股份有限公司 | Division processing method, device and the readable storage medium storing program for executing of ECG data |
US20200298002A1 (en) * | 2019-03-21 | 2020-09-24 | Medtronic, Inc. | T-wave morphology analysis for pathological event detection |
CN110327032A (en) * | 2019-03-27 | 2019-10-15 | 苏州平稳芯跳医疗科技有限公司 | It is a kind of singly to lead the accurate recognizer of electrocardiosignal PQRST wave joint |
CN111553362A (en) * | 2019-04-01 | 2020-08-18 | 上海卫莎网络科技有限公司 | Video processing method, electronic equipment and computer readable storage medium |
CN110547792A (en) * | 2019-07-31 | 2019-12-10 | 平安科技(深圳)有限公司 | atrial fibrillation detection method and device, computer equipment and storage medium |
WO2021017313A1 (en) * | 2019-07-31 | 2021-02-04 | 平安科技(深圳)有限公司 | Atrial fibrillation detection method and apparatus, computer device, and storage medium |
CN110558971A (en) * | 2019-08-02 | 2019-12-13 | 苏州星空大海医疗科技有限公司 | Method for generating countermeasure network electrocardiogram abnormity detection based on single target and multiple targets |
CN110656169A (en) * | 2019-11-05 | 2020-01-07 | 天津市人民医院 | Diagnostic markers for atrial fibrillation |
CN110786849A (en) * | 2019-11-11 | 2020-02-14 | 菏泽学院 | Electrocardiosignal identity recognition method and system based on multi-view discriminant analysis |
CN111053552A (en) * | 2019-12-03 | 2020-04-24 | 上海理工大学 | QRS wave detection method based on deep learning |
CN111345817A (en) * | 2020-02-25 | 2020-06-30 | 广州视源电子科技股份有限公司 | QRS complex position determination method, device, equipment and storage medium |
CN111528832A (en) * | 2020-05-28 | 2020-08-14 | 四川大学华西医院 | Arrhythmia classification method and validity verification method thereof |
CN111956214A (en) * | 2020-07-29 | 2020-11-20 | 鲁东大学 | QRS wave automatic detection method based on U-net end-to-end neural network model |
CN112022149A (en) * | 2020-09-04 | 2020-12-04 | 无锡博智芯科技有限公司 | Atrial fibrillation detection method based on electrocardiosignals |
CN111920405A (en) * | 2020-09-15 | 2020-11-13 | 齐鲁工业大学 | Atrial fibrillation signal identification system and method |
CN112674780A (en) * | 2020-12-23 | 2021-04-20 | 山东省人工智能研究院 | Automatic atrial fibrillation signal detection method in electrocardiogram abnormal signals |
CN112826513A (en) * | 2021-01-05 | 2021-05-25 | 华中科技大学 | Fetal heart rate detection system based on deep learning and specificity correction on FECG |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sansone et al. | Electrocardiogram pattern recognition and analysis based on artificial neural networks and support vector machines: a review | |
EP2895063B1 (en) | A system and method for detecting the presence of a p-wave in an ecg waveform | |
US6171256B1 (en) | Method and apparatus for detecting a condition associated with acute cardiac ischemia | |
US8396541B2 (en) | Signal analysis of cardiac and other patient medical signals | |
CN109171712A (en) | Auricular fibrillation recognition methods, device, equipment and computer readable storage medium | |
Shi et al. | Inter-patient heartbeat classification based on region feature extraction and ensemble classifier | |
US20120209126A1 (en) | Method and system for detecting cardiac arrhythmia | |
WO2003094721A1 (en) | A bayesian discriminator for rapidly detecting arrhythmias | |
US20070219454A1 (en) | ECG method and system for optimal cardiac disease detection | |
Leutheuser et al. | Comparison of real-time classification systems for arrhythmia detection on Android-based mobile devices | |
De Chazal | Detection of supraventricular and ventricular ectopic beats using a single lead ECG | |
Portet | P wave detector with PP rhythm tracking: evaluation in different arrhythmia contexts | |
Zhou et al. | ECG quality assessment using 1D-convolutional neural network | |
Khatun et al. | Detection of myocardial infarction and arrhythmia from single-lead ECG data using bagging trees classifier | |
CN112971800A (en) | Deep learning-based electrocardio premature beat signal processing method, module and device | |
Sharma et al. | Bundle branch block detection using statistical features of qrs-complex and k-nearest neighbors | |
Srinivasan et al. | A new phase space analysis algorithm for cardiac arrhythmia detection | |
Alim et al. | Application of machine learning on ecg signal classification using morphological features | |
García et al. | Development of an algorithm for heartbeats detection and classification in Holter records based on temporal and morphological features | |
Pang et al. | Real time heart ischemia detection in the smart home care system | |
CN113349791A (en) | Abnormal electrocardiosignal detection method, device, equipment and medium | |
KR101468057B1 (en) | Ecg measurement apparatus and ecg measurement system | |
Bansal et al. | Template based classification of cardiac arrhythmia in ECG data | |
Bashir et al. | Highlighting the current issues with pride suggestions for improving the performance of real time cardiac health monitoring | |
Arora et al. | Characterization of a low cost, automated and field deployable 2-lead myocardial infarction detection system |
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 |