CN113040781A - I-lead electrocardiogram data identification method and system - Google Patents
I-lead electrocardiogram data identification method and system Download PDFInfo
- Publication number
- CN113040781A CN113040781A CN202110268180.1A CN202110268180A CN113040781A CN 113040781 A CN113040781 A CN 113040781A CN 202110268180 A CN202110268180 A CN 202110268180A CN 113040781 A CN113040781 A CN 113040781A
- Authority
- CN
- China
- Prior art keywords
- data
- lead
- lead electrocardiogram
- neural network
- electrocardiogram data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000003062 neural network model Methods 0.000 claims abstract description 55
- 238000012545 processing Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 20
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000006835 compression Effects 0.000 claims description 6
- 238000007906 compression Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 6
- 208000024172 Cardiovascular disease Diseases 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 206010003658 Atrial Fibrillation Diseases 0.000 description 1
- 206010003662 Atrial flutter Diseases 0.000 description 1
- 208000000418 Premature Cardiac Complexes Diseases 0.000 description 1
- 208000007888 Sinus Tachycardia Diseases 0.000 description 1
- 206010040741 Sinus bradycardia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002861 ventricular Effects 0.000 description 1
- 230000000007 visual 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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (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 invention discloses an I-lead electrocardiogram data identification method and a system, wherein the method comprises the steps of constructing an I-lead electrocardiogram data identification neural network model, arranging the constructed I-lead electrocardiogram data identification neural network model in I-lead electrocardiogram equipment, collecting I-lead electrocardiogram data to be identified, identifying through the I-lead electrocardiogram data identification neural network model, identifying a judgment result of the I-lead electrocardiogram data to be identified, and displaying by the I-lead electrocardiogram equipment according to the judgment result; by constructing the I-lead electrocardiogram data recognition neural network model and arranging the I-lead electrocardiogram data recognition neural network model in the I-lead electrocardiogram equipment, the I-lead electrocardiogram equipment can autonomously recognize the collected I-lead electrocardiogram data and avoid sending the collected I-lead electrocardiogram data to a cloud server for processing.
Description
Technical Field
The invention relates to the technical field of electrocardiogram data identification, in particular to an I-lead electrocardiogram data identification method and system.
Background
Cardiovascular diseases are one of the most difficult diseases to cure at present, and in order to prevent cardiovascular diseases well, electrocardiographic data are generally monitored and analyzed in real time, so that the cardiovascular diseases are prevented by identifying whether the electrocardiographic data are abnormal or not.
However, the multi-lead electrocardiograph device collects electrocardiograph data and sends the electrocardiograph data to the cloud server for operation, the multi-lead electrocardiograph device is required to be connected with a network or a mobile phone for use, when the network is unavailable, the situation that the multi-lead electrocardiograph device cannot be sent to the cloud server for operation and identification exists, the multi-lead electrocardiograph device is connected with the mobile phone, complex steps such as terminal device connection and account application are often required in mobile phone application, and the usage is not visual and convenient for the old.
Disclosure of Invention
In view of the above, the invention provides an I-lead electrocardiographic data identification method and system, which can solve the defects that no network is available for calculation and identification and the use is troublesome in the conventional electrocardiographic data identification.
The technical scheme of the invention is realized as follows:
an I-lead electrocardiogram data identification method, which is based on an I-lead electrocardiogram device, comprises the following steps:
step S1, constructing an I-lead electrocardiogram data recognition neural network model, wherein the input end of the I-lead electrocardiogram data recognition neural network model is I-lead electrocardiogram data, and the output end of the I-lead electrocardiogram data recognition neural network model is a judgment result of whether the I-lead electrocardiogram data is abnormal;
step S2, arranging the constructed I-lead electrocardiogram data recognition neural network model in I-lead electrocardiogram equipment;
step S3, I-lead electrocardiograph equipment collects I-lead electrocardiograph data to be identified and identifies the I-lead electrocardiograph data through an I-lead electrocardiograph data identification neural network model;
and step S4, the I-lead electrocardiogram data recognition neural network model outputs the judgment result of the I-lead electrocardiogram data to be recognized, and the I-lead electrocardiogram equipment displays according to the judgment result.
As a further alternative of the I-lead electrocardiographic data identification method, the constructing an I-lead electrocardiographic data identification neural network model in step S1 specifically includes the following steps:
step S11, collecting I-lead electrocardiogram data and corresponding electrocardiogram judgment results;
step S12, preprocessing the I-lead electrocardiogram data to obtain a training data matrix;
and step S13, inputting the training data matrix and the electrocardio judgment result into a deep convolution neural network model for training to obtain an I-lead electrocardio data recognition neural network model.
As a further alternative of the I-lead electrocardiogram data identification method, the deep convolutional neural network model adopts a ResECG11 deep convolutional neural network.
As a further alternative of the I-lead electrocardiogram data identification method, the ResECG11 deep convolutional neural network comprises a convolutional layer, a normalization layer, an orthogonal linear unit layer, an identity mapping module and a full connection layer.
As a further alternative of the I-lead electrocardiographic data recognition method, the step S12 includes the steps of:
step S121, intercepting the I-lead electrocardiogram data to obtain intercepted I-lead electrocardiogram data;
and S122, processing the intercepted I-lead electrocardiogram data through a linear interpolation algorithm to obtain a training data matrix.
As a further alternative of the I-lead electrocardiographic data recognition method, the step S2 includes the steps of:
step S21, carrying out quantitative compression on the I-lead electrocardiogram data recognition neural network model;
and step S22, burning the I-lead electrocardiogram data recognition neural network model after quantization compression into an AI chip of the I-lead electrocardiogram equipment.
As a further alternative of the I-lead electrocardiographic data recognition method, the step S3 includes the steps of:
step S31, collecting I-lead electrocardiogram data to be identified by I-lead electrocardiogram equipment;
step S32, preprocessing the I-lead electrocardiogram data to be recognized to obtain a data matrix to be recognized;
and step S33, inputting the data matrix to be recognized into an I-lead electrocardiogram data recognition neural network model for recognition.
As a further alternative of the I-lead electrocardiographic data recognition method, the step S32 includes the steps of:
step S321, intercepting the I-lead electrocardiogram data to be identified to obtain intercepted I-lead electrocardiogram data to be identified;
and step S322, processing the intercepted I-lead electrocardiogram data to be identified through a linear interpolation algorithm to obtain a data matrix to be identified.
As a further alternative of the I-lead electrocardiographic data recognition method, the step S4 includes the steps of:
step S41, the I-lead electrocardiogram data recognition neural network model outputs the judgment result of the I-lead electrocardiogram data to be recognized, wherein the judgment result comprises the normal I-lead electrocardiogram data to be recognized and the abnormal I-lead electrocardiogram data to be recognized;
and step S42, if the judgment result is that the I-lead electrocardiogram data to be identified is normal, the display data of the I-lead electrocardiogram equipment is normal, and if the judgment result is that the I-lead electrocardiogram data to be identified is abnormal, the display data of the I-lead electrocardiogram equipment is abnormal, and the user is prompted to see a doctor in time.
An I-lead electrocardiogram data identification system, which applies any one of the identification methods.
The invention has the beneficial effects that: through constructing the I-lead electrocardiogram data recognition neural network model, and setting the I-lead electrocardiogram data recognition neural network model in the I-lead electrocardiogram equipment, the I-lead electrocardiogram equipment can autonomously recognize the collected I-lead electrocardiogram data, and the situation that the collected I-lead electrocardiogram data cannot be sent to a cloud server for processing is avoided, so that the situation that operation recognition cannot be carried out in the cloud server without a network in the prior art is avoided, in addition, the effect of all-weather use can be realized by adopting the I-lead electrocardiogram equipment, the operation steps of the old are reduced, and the convenience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of an I-lead ECG data identification method of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an I-lead electrocardiographic data identification method is based on an I-lead electrocardiographic device and comprises the following steps:
step S1, constructing an I-lead electrocardiogram data recognition neural network model, wherein the input end of the I-lead electrocardiogram data recognition neural network model is I-lead electrocardiogram data, and the output end of the I-lead electrocardiogram data recognition neural network model is a judgment result of whether the I-lead electrocardiogram data is abnormal;
step S2, arranging the constructed I-lead electrocardiogram data recognition neural network model in I-lead electrocardiogram equipment;
step S3, I-lead electrocardiograph equipment collects I-lead electrocardiograph data to be identified and identifies the I-lead electrocardiograph data through an I-lead electrocardiograph data identification neural network model;
and step S4, the I-lead electrocardiogram data recognition neural network model outputs the judgment result of the I-lead electrocardiogram data to be recognized, and the I-lead electrocardiogram equipment displays according to the judgment result.
In this embodiment, through constructing the I-lead electrocardiographic data recognition neural network model, and set the I-lead electrocardiographic data recognition neural network model in the I-lead electrocardiographic device, the I-lead electrocardiographic device can autonomously recognize the acquired I-lead electrocardiographic data, and the situation that the acquired I-lead electrocardiographic data cannot be sent to the cloud server for processing is avoided, so that the situation that the operation recognition cannot be carried out in the cloud server without a network in the prior art is avoided, in addition, through adopting the I-lead electrocardiographic device, the all-weather use effect can be realized, the operation steps of the old are reduced, and the convenience is improved.
Preferably, the constructing of the I-lead electrocardiographic data recognition neural network model in step S1 specifically includes the following steps:
step S11, collecting I-lead electrocardiogram data and corresponding electrocardiogram judgment results;
step S12, preprocessing the I-lead electrocardiogram data to obtain a training data matrix;
and step S13, inputting the training data matrix and the electrocardio judgment result into a deep convolution neural network model for training to obtain an I-lead electrocardio data recognition neural network model.
In the embodiment, the I-lead electrocardiogram data is preprocessed, so that the data acquired each time can obtain the input data with the same time length and the same sampling rate, an accurate training data matrix is obtained according to the input data, and the accurate training matrix data is input into the deep convolution neural network model for training, so that the identification accuracy of the I-lead electrocardiogram data identification neural network model can be improved; it should be noted that the same time length is 30s, the same sampling rate is 320Hz, and the shape of the training data matrix is [1, 9600 ].
Preferably, the deep convolutional neural network model adopts ResECG11 deep convolutional neural network.
In the embodiment, the ResECG11 deep convolution neural network is adopted, so that the characteristics of the I-lead electrocardiogram data can be accurately extracted, the training effect can be improved, and the identification effect of the constructed I-lead electrocardiogram data identification neural network model is further improved.
Preferably, the ResECG11 deep convolutional neural network includes a convolutional layer, a normalization layer, an orthogonal linear unit layer, an identity mapping module, and a fully connected layer.
In the embodiment, the I lead electrocardiogram data is abstracted and extracted by the convolution layer, and after multi-channel abstraction, then, the normalization is equivalent to the redistribution of the obtained data in the standard normal distribution through a normalization layer, also a process for optimizing the training effect, aiming at reducing the occurrence of model collapse in the training process, thereby obtaining a better model, the process of gradually improving the expressive force can be better realized in the residual error network, and the orthogonal linear unit layer is a process of communicating each residual error block and weighting the output of the last-stage residual error block, so that important information can be more uniformly transmitted backwards, and the total weight quantity is reduced, a better effect is obtained, and the final full-connection layer carries out linear output on the characteristics to obtain a final state value, wherein the range is between 0 and 1.
Preferably, the step S12 includes the steps of:
step S121, intercepting the I-lead electrocardiogram data to obtain intercepted I-lead electrocardiogram data;
and S122, processing the intercepted I-lead electrocardiogram data through a linear interpolation algorithm to obtain a training data matrix.
In this embodiment, the collected I-lead electrocardiographic data is intercepted, so that the input intercepted I-lead electrocardiographic data is 30 seconds, if the input is lower than the 30 second electrocardiographic data acquisition process, the acquisition process is determined to be a failed acquisition process, and the user is prompted to perform re-measurement acquisition, and the intercepted I-lead electrocardiographic data is processed into I-lead electrocardiographic data with a sampling rate of 320Hz by a linear interpolation algorithm, so as to form a training data matrix.
Preferably, the step S2 includes the steps of:
step S21, carrying out quantitative compression on the I-lead electrocardiogram data recognition neural network model;
and step S22, burning the I-lead electrocardiogram data recognition neural network model after quantization compression into an AI chip of the I-lead electrocardiogram equipment.
In this embodiment, in order to be used in a chip system, the size of the neural network model file identified by the I-lead electrocardiographic data is not too large, and a neural network model with the size of the original model 1/4 can be obtained by intercepting 32 bits into 8 bits in each weight storage space and adjusting the output result by a statistical method; the neural network is burned into a chip system through burning software provided by a chip manufacturer, and the data input of the electrocardio measuring module is accessed, so that the function of local electrocardio identification can be realized.
Preferably, the step S3 includes the steps of:
step S31, collecting I-lead electrocardiogram data to be identified by I-lead electrocardiogram equipment;
step S32, preprocessing the I-lead electrocardiogram data to be recognized to obtain a data matrix to be recognized;
and step S33, inputting the data matrix to be recognized into an I-lead electrocardiogram data recognition neural network model for recognition.
In this embodiment, by preprocessing the I-lead electrocardiographic data to be recognized, the workload of recognizing the neural network model by the I-lead electrocardiographic data can be reduced, so that the recognition accuracy and efficiency of recognizing the neural network model by the I-lead electrocardiographic data are improved.
Preferably, the step S32 includes the steps of:
step S321, intercepting the I-lead electrocardiogram data to be identified to obtain intercepted I-lead electrocardiogram data to be identified;
and step S322, processing the intercepted I-lead electrocardiogram data to be identified through a linear interpolation algorithm to obtain a data matrix to be identified.
Preferably, the step S4 includes the steps of:
step S41, the I-lead electrocardiogram data recognition neural network model outputs the judgment result of the I-lead electrocardiogram data to be recognized, wherein the judgment result comprises the normal I-lead electrocardiogram data to be recognized and the abnormal I-lead electrocardiogram data to be recognized;
and step S42, if the judgment result is that the I-lead electrocardiogram data to be identified is normal, the display data of the I-lead electrocardiogram equipment is normal, and if the judgment result is that the I-lead electrocardiogram data to be identified is abnormal, the display data of the I-lead electrocardiogram equipment is abnormal, and the user is prompted to see a doctor in time.
In this embodiment, the identified I-lead electrocardiographic data abnormality includes ventricular premature beat, atrial fibrillation, atrial flutter, complete left bundle branch conduction block, complete right bundle branch conduction block, sinus bradycardia, and sinus tachycardia, if the determination result is that the I-lead electrocardiographic data to be identified is abnormal, the I-lead electrocardiographic device displays data abnormality and prompts the user to see a doctor in time, otherwise, the I-lead electrocardiographic device displays data normality.
An I-lead electrocardiogram data identification system, which applies any one of the identification methods.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. An I-lead electrocardiogram data identification method is characterized in that the method is based on I-lead electrocardiogram equipment and comprises the following steps:
step S1, constructing an I-lead electrocardiogram data recognition neural network model, wherein the input end of the I-lead electrocardiogram data recognition neural network model is I-lead electrocardiogram data, and the output end of the I-lead electrocardiogram data recognition neural network model is a judgment result of whether the I-lead electrocardiogram data is abnormal;
step S2, arranging the constructed I-lead electrocardiogram data recognition neural network model in I-lead electrocardiogram equipment;
step S3, I-lead electrocardiograph equipment collects I-lead electrocardiograph data to be identified and identifies the I-lead electrocardiograph data through an I-lead electrocardiograph data identification neural network model;
and step S4, the I-lead electrocardiogram data recognition neural network model outputs the judgment result of the I-lead electrocardiogram data to be recognized, and the I-lead electrocardiogram equipment displays according to the judgment result.
2. The method for identifying I-lead electrocardiographic data according to claim 1, wherein the constructing of the I-lead electrocardiographic data identification neural network model in step S1 specifically includes the following steps:
step S11, collecting I-lead electrocardiogram data and corresponding electrocardiogram judgment results;
step S12, preprocessing the I-lead electrocardiogram data to obtain a training data matrix;
and step S13, inputting the training data matrix and the electrocardio judgment result into a deep convolution neural network model for training to obtain an I-lead electrocardio data recognition neural network model.
3. The method for identifying I-lead electrocardiographic data according to claim 2, wherein the deep convolutional neural network model adopts ResECG11 deep convolutional neural network.
4. The method of claim 3, wherein the ResECG11 deep convolutional neural network comprises convolutional layers, normalization layers, orthogonal linear unit layers, identity mapping modules and full connection layers.
5. The method for I lead ECG data according to claim 2 or 4, wherein the step S12 comprises the following steps:
step S121, intercepting the I-lead electrocardiogram data to obtain intercepted I-lead electrocardiogram data;
and S122, processing the intercepted I-lead electrocardiogram data through a linear interpolation algorithm to obtain a training data matrix.
6. The method for I-lead ECG data according to claim 1, wherein the step S2 comprises the following steps:
step S21, carrying out quantitative compression on the I-lead electrocardiogram data recognition neural network model;
and step S22, burning the I-lead electrocardiogram data recognition neural network model after quantization compression into an AI chip of the I-lead electrocardiogram equipment.
7. The method for I-lead ECG data according to claim 1 or 6, wherein the step S3 comprises the following steps:
step S31, collecting I-lead electrocardiogram data to be identified by I-lead electrocardiogram equipment;
step S32, preprocessing the I-lead electrocardiogram data to be recognized to obtain a data matrix to be recognized;
and step S33, inputting the data matrix to be recognized into an I-lead electrocardiogram data recognition neural network model for recognition.
8. The method for I-lead electrocardiographic data recognition according to claim 7, wherein said step S32 includes the steps of:
step S321, intercepting the I-lead electrocardiogram data to be identified to obtain intercepted I-lead electrocardiogram data to be identified;
and step S322, processing the intercepted I-lead electrocardiogram data to be identified through a linear interpolation algorithm to obtain a data matrix to be identified.
9. The method for I-lead ECG data according to claim 1, wherein the step S4 comprises the following steps:
step S41, the I-lead electrocardiogram data recognition neural network model outputs the judgment result of the I-lead electrocardiogram data to be recognized, wherein the judgment result comprises the normal I-lead electrocardiogram data to be recognized and the abnormal I-lead electrocardiogram data to be recognized;
and step S42, if the judgment result is that the I-lead electrocardiogram data to be identified is normal, the display data of the I-lead electrocardiogram equipment is normal, and if the judgment result is that the I-lead electrocardiogram data to be identified is abnormal, the display data of the I-lead electrocardiogram equipment is abnormal, and the user is prompted to see a doctor in time.
10. An I-lead electrocardiographic data recognition system, characterized in that said system employs the recognition method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110268180.1A CN113040781A (en) | 2021-03-11 | 2021-03-11 | I-lead electrocardiogram data identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110268180.1A CN113040781A (en) | 2021-03-11 | 2021-03-11 | I-lead electrocardiogram data identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113040781A true CN113040781A (en) | 2021-06-29 |
Family
ID=76511621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110268180.1A Pending CN113040781A (en) | 2021-03-11 | 2021-03-11 | I-lead electrocardiogram data identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113040781A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1423997A (en) * | 2002-12-03 | 2003-06-18 | 沈阳东软数字医疗系统股份有限公司 | Real time data collecting lossless compressing method for 12 lead ECG |
| CN107510452A (en) * | 2017-09-30 | 2017-12-26 | 扬美慧普（北京）科技有限公司 | A kind of ECG detecting method based on multiple dimensioned deep learning neutral net |
| CN108030488A (en) * | 2017-11-30 | 2018-05-15 | 北京医拍智能科技有限公司 | The detecting system of arrhythmia cordis based on convolutional neural networks |
| CN110236520A (en) * | 2019-05-20 | 2019-09-17 | 上海数创医疗科技有限公司 | ECG type recognition methods and device based on double convolutional neural networks |
| CN110472593A (en) * | 2019-08-20 | 2019-11-19 | 重庆紫光华山智安科技有限公司 | Training image acquisition methods, model training method and relevant apparatus |
-
2021
- 2021-03-11 CN CN202110268180.1A patent/CN113040781A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1423997A (en) * | 2002-12-03 | 2003-06-18 | 沈阳东软数字医疗系统股份有限公司 | Real time data collecting lossless compressing method for 12 lead ECG |
| CN107510452A (en) * | 2017-09-30 | 2017-12-26 | 扬美慧普（北京）科技有限公司 | A kind of ECG detecting method based on multiple dimensioned deep learning neutral net |
| CN108030488A (en) * | 2017-11-30 | 2018-05-15 | 北京医拍智能科技有限公司 | The detecting system of arrhythmia cordis based on convolutional neural networks |
| CN110236520A (en) * | 2019-05-20 | 2019-09-17 | 上海数创医疗科技有限公司 | ECG type recognition methods and device based on double convolutional neural networks |
| CN110472593A (en) * | 2019-08-20 | 2019-11-19 | 重庆紫光华山智安科技有限公司 | Training image acquisition methods, model training method and relevant apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11529103B2 (en) | Artificial intelligence self-learning-based automatic electrocardiography analysis method and apparatus | |
| US11517212B2 (en) | Electrocardiogram information dynamic monitoring method and dynamic monitoring system | |
| EP3847958A1 (en) | Arrhythmia detection method and apparatus, electronic device, and computer storage medium | |
| CA3071699C (en) | Detection of electrocardiographic signal | |
| EP3692900A1 (en) | Artificial intelligence self-learning-based static electrocardiography analysis method and apparatus | |
| CN110046604B (en) | Single-lead ECG arrhythmia detection and classification method based on residual error network | |
| EP4042445A1 (en) | Systems and methods for reduced lead electrocardiogram diagnosis using deep neural networks and rule-based systems | |
| CN109846474B (en) | Processing method and device of electrocardiogram and remote processing method and system of electrocardiogram | |
| CN109276242A (en) | The method and apparatus of electrocardiosignal type identification | |
| WO2022193312A1 (en) | Electrocardiogram signal identification method and electrocardiogram signal identification apparatus based on multiple leads | |
| CN112650200B (en) | Method and device for diagnosing plant station equipment faults | |
| CN110801218B (en) | Electrocardiogram data processing method and device, electronic equipment and computer readable medium | |
| CN112022141B (en) | Electrocardiosignal class detection method, electrocardiosignal class detection device and storage medium | |
| CN113229825A (en) | Deep neural network-based multi-label multi-lead electrocardiogram classification method | |
| CN107958214A (en) | Parallel parsing device, method and the mobile terminal of ECG signal | |
| EP4041073A1 (en) | Systems and methods for electrocardiogram diagnosis using deep neural networks and rule-based systems | |
| CN114711780A (en) | Multi-lead electrocardiogram signal processing method, device, equipment and storage medium | |
| CN113040781A (en) | I-lead electrocardiogram data identification method and system | |
| CN113229798B (en) | Model migration training method, device, computer equipment and readable storage medium | |
| CN114869293A (en) | Twelve-lead electrocardiogram data interpretation method and system | |
| CN114711787A (en) | Neural network-based classification diagnosis method for heart health state of driver | |
| CN105769171A (en) | Arrhythmia detection method and device | |
| CN115414049A (en) | Wearable electrocardiogram real-time diagnosis system based on deep neural network | |
| CN113647954A (en) | Cardiovascular disease identification method, device and medium of two-channel hybrid network model | |
| CN115372752A (en) | Fault detection method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |