CN110812699A - Remote defibrillation protection system and control method thereof - Google Patents
Remote defibrillation protection system and control method thereof Download PDFInfo
- Publication number
- CN110812699A CN110812699A CN201911221420.1A CN201911221420A CN110812699A CN 110812699 A CN110812699 A CN 110812699A CN 201911221420 A CN201911221420 A CN 201911221420A CN 110812699 A CN110812699 A CN 110812699A
- Authority
- CN
- China
- Prior art keywords
- defibrillation
- ventricular fibrillation
- control center
- module
- 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.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N1/00—Electrotherapy; Circuits therefor
- A61N1/18—Applying electric currents by contact electrodes
- A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
- A61N1/38—Applying electric currents by contact electrodes alternating or intermittent currents for producing shock effects
- A61N1/39—Heart defibrillators
- A61N1/3904—External heart defibrillators [EHD]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
- A61B5/0006—ECG or EEG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- 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
- A61B5/361—Detecting fibrillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
Abstract
The invention discloses a remote defibrillation protection system and a control method thereof, wherein the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring pressure data, respiration data, apical pulsation data and electrocardiogram signals of a defibrillation electrode plate; when the control center is on line, transmitting the electrocardiogram signal to the cloud platform, receiving a prediction result from the cloud platform, and when the control center is off line, inputting the current electrocardiogram signal into a ventricular fibrillation prediction model to obtain a prediction result of whether ventricular fibrillation occurs; when the defibrillation electrode slice does not fall off, respiration does not exist, the apex of the heart does not beat and ventricular fibrillation occurs, sending a defibrillation instruction to the defibrillation module and sending a starting instruction to the prompt module; and the defibrillation module is used for receiving a command of manually cancelling defibrillation, and if the command of manually cancelling defibrillation is not received within a set time after the defibrillation command is received, defibrillation is executed.
Description
Technical Field
The invention relates to the field of medical treatment, in particular to a remote defibrillation protection system and a control method thereof.
Background
Cardiovascular disease is the disease with the highest global prevalence and mortality, and the vast majority of patients with cardiovascular disease die from cardiac arrest. Sudden cardiac arrest refers to sudden cardiac arrest, resulting in severe ischemia and hypoxia of vital organs (such as brain) and termination of life. The most effective treatment method of cardiac arrest is electrical defibrillation, and for cardiac arrest patients, effective electrical defibrillation is the only pre-hospital emergency treatment method which is effective in reducing the mortality of the patients within 3-5 minutes.
Disclosure of Invention
In view of the above-mentioned deficiencies in the prior art, the present invention aims to provide a remote defibrillation protection system and a control method thereof, which can improve the survival probability of patients with cardiac arrest.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
a remote defibrillation protection system is provided, comprising:
the acquisition module is used for acquiring pressure data, respiration data, apical pulsation data and electrocardiogram signals of the defibrillation electrode slices and then transmitting the pressure data, the respiration data, the apical pulsation data and the electrocardiogram signals to the control center;
the control center is used for judging whether the defibrillation electrode plates fall off, whether respiration exists and whether apical pulsation exists according to the pressure data, the respiration data and the apical pulsation data of the defibrillation electrode plates respectively; when the control center is on-line, the electrocardiogram signals are transmitted to the cloud platform through the network, the prediction results from the cloud platform are received, and when the control center is off-line, the current electrocardiogram signals are input into ventricular fibrillation prediction models stored in the control center to obtain the prediction results of whether ventricular fibrillation occurs; when the defibrillation electrode slice does not fall off, respiration does not exist, the apex of the heart does not beat and ventricular fibrillation is predicted, sending a defibrillation instruction to the defibrillation module and sending a starting instruction to the prompt module;
the defibrillation module is used for receiving a command of manually cancelling defibrillation, and if the command of manually cancelling defibrillation is not received within a set time after the defibrillation command is received, defibrillation is executed;
the prompting module is used for receiving the starting instruction and then executing voice prompt to prompt other people not to touch the patient;
and the cloud platform is used for receiving and storing the electrocardiogram signals, inputting the current electrocardiogram signals into the ventricular fibrillation prediction model stored in the cloud platform to obtain a prediction result of whether ventricular fibrillation occurs, and if so, sending the prediction result to the control center.
Further, the ventricular fibrillation prediction model is obtained through a deep learning algorithm.
Further, the obtaining of the ventricular fibrillation prediction model by the deep learning algorithm further comprises:
acquiring a set number of electrocardiogram signals, and preprocessing the electrocardiogram signals to obtain a training set;
defining a grid parameter loss function and a cost matrix loss function of a CoSen-Bi-LSTM network model, inputting a training set into the constructed CoSen-Bi-LSTM network model for training to obtain a ventricular fibrillation prediction model, wherein the CoSen-Bi-LSTM network model comprises an input layer, a first hidden layer, a second hidden layer, an output layer and a cost sensitive layer which are sequentially connected.
Further, inputting the training set into the constructed CoSen-Bi-LSTM network model for training to obtain the ventricular fibrillation prediction model further comprises: the network is trained by adopting a random gradient descent method, gradient updating is carried out by adopting an SGD method, and the learning rate is 0.001.
Further, the grid parameters of the CoSen-Bi-LSTM network model are cross entropy loss functions.
Further, the preprocessing the training set to obtain the training set further comprises:
s1, cutting each electrocardiogram signal into a plurality of sub-electrocardiogram signals according to each 4 heartbeats in sequence;
s2, after correcting baseline drift of the sub-electrocardiogram signals by using a high-pass filter, removing high-frequency noise by using a contraction method based on wavelet transformation;
and S3, giving each sub-electrocardiogram signal class label to obtain a training set.
Further, the calculation formula of the system function of the high-pass filter is:
wherein z is a sub-electrocardiogram signal.
On the other hand, the scheme also provides a control method of the remote defibrillation protection system, which comprises the following steps:
the acquisition module acquires pressure data, respiration data, apical pulsation data and electrocardiogram signals of the defibrillation electrode slices and then sends the pressure data, the respiration data, the apical pulsation data and the electrocardiogram signals to the control center;
the control center judges whether the defibrillation electrode plate falls off, whether respiration exists and whether apical pulsation exists according to the pressure data, the respiration data and the apical pulsation data of the defibrillation electrode plate respectively;
when the control center is on line, the electrocardiogram signals are transmitted to the cloud platform through the network, the cloud platform receives and stores the electrocardiogram signals, the current electrocardiogram signals are input into ventricular fibrillation prediction models stored in the cloud platform to obtain prediction results of whether ventricular fibrillation occurs, and if yes, the prediction results are sent to the control center; when the control center is off-line, inputting the current electrocardiogram signal into a ventricular fibrillation prediction model stored in the control center to obtain a prediction result of whether ventricular fibrillation occurs;
when the defibrillation electrode slice does not fall off, respiration does not exist, the apex of the heart does not beat and ventricular fibrillation is predicted, the control center sends a defibrillation instruction to the defibrillation module and sends a starting instruction to the prompt module; the defibrillation module executes defibrillation if the defibrillation module does not receive a manual defibrillation cancelling instruction within a set time after receiving the defibrillation instruction; the prompting module receives the starting instruction and then executes voice prompt to prompt other people not to touch the patient.
The invention has the beneficial effects that: the accuracy of the sudden cardiac arrest judgment is enhanced by acquiring and judging whether respiration exists or not and whether apical pulsation exists or not and combining the ventricular fibrillation prediction model prediction result. The combination of the defibrillation module and the instruction for receiving the manual defibrillation cancellation reduces the probability of the defibrillation electrode misdischarge. Meanwhile, the effectiveness of electrical defibrillation is improved by collecting and judging whether the defibrillation electrode plate falls off or not. And the prompting module prompts people beside the defibrillator not to touch the patient before defibrillation, thereby ensuring the safety of people who contact the patient and simultaneously ensuring effective defibrillation.
Drawings
Fig. 1 is a schematic block diagram of the present invention.
Detailed Description
The following detailed description of the present invention will be provided in conjunction with the accompanying drawings to facilitate the understanding of the present invention by those skilled in the art. It should be understood that the embodiments described below are only some embodiments of the invention, and not all embodiments. All other embodiments obtained by a person skilled in the art without any inventive step, without departing from the spirit and scope of the present invention as defined and defined by the appended claims, fall within the scope of protection of the present invention.
As shown in fig. 1, the remote defibrillation-prevention system includes:
the acquisition module is used for acquiring pressure data, respiration data, apical pulsation data and electrocardiogram signals of the defibrillation electrode slices and then transmitting the pressure data, the respiration data, the apical pulsation data and the electrocardiogram signals to the control center;
the control center is used for judging whether the defibrillation electrode plates fall off, whether respiration exists and whether apical pulsation exists according to the pressure data, the respiration data and the apical pulsation data of the defibrillation electrode plates respectively; when the control center is on-line, the electrocardiogram signals are transmitted to the cloud platform through the network, the prediction results from the cloud platform are received, and when the control center is off-line, the current electrocardiogram signals are input into ventricular fibrillation prediction models stored in the control center to obtain the prediction results of whether ventricular fibrillation occurs; when the defibrillation electrode slice does not fall off, respiration does not exist, the apex of the heart does not beat and ventricular fibrillation is predicted, sending a defibrillation instruction to the defibrillation module and sending a starting instruction to the prompt module;
the defibrillation module is used for receiving a command of manually cancelling defibrillation, and if the command of manually cancelling defibrillation is not received within a set time after the defibrillation command is received, defibrillation is executed;
the prompting module is used for receiving the starting instruction and then executing voice prompt to prompt other people not to touch the patient;
and the cloud platform is used for receiving and storing the electrocardiogram signals, inputting the current electrocardiogram signals into the ventricular fibrillation prediction model stored in the cloud platform to obtain a prediction result of whether ventricular fibrillation occurs, and if so, sending the prediction result to the control center.
The acquisition module, the control center, the defibrillation module and the prompt module are all located on the wearable defibrillation device.
During implementation, the optimal control unit is connected with the mobile terminal (generally a mobile phone of a patient) through the Bluetooth module, and the electrocardiogram signal is sent to the cloud platform through the mobile terminal.
The ventricular fibrillation prediction model is obtained through a deep learning algorithm and further comprises the following steps:
(1) acquiring a set number of electrocardiogram signals, and preprocessing the electrocardiogram signals to obtain a training set:
s1, cutting each electrocardiogram signal into a plurality of sub-electrocardiogram signals according to each 4 heartbeats in sequence;
s2, after correcting baseline drift of the sub-electrocardiogram signals by using a high-pass filter, removing high-frequency noise by using a contraction method based on wavelet transformation; the system function of the high-pass filter is calculated as:
wherein z is a sub-electrocardiogram signal.
And S3, giving each sub-electrocardiogram signal label to obtain a training set, wherein the labels comprise atrial tachycardia, ventricular fibrillation, sinus arrhythmia, atrial tachycardia, atrial fibrillation, junction tachycardia, priming syndrome, atrioventricular block, ventricular block, pacemaker rhythm and normal rhythm.
(2) Defining a grid parameter loss function and a cost matrix loss function of a CoSen-Bi-LSTM network model, wherein the CoSen-Bi-LSTM network model comprises an input layer, a first hidden layer, a second hidden layer, an output layer and a cost sensitive layer which are sequentially connected, grid parameters are cross entropy loss functions, and the expression of the grid parameter loss functions is as follows:
wherein d isnIn order to be a real label, the label,
onand okAs output of the output layer, ynIs the output modified by the cost sensitive layer.
The expression of the cost matrix loss function is:
wherein E isvalTo verify the error, θ is the over-parameter of the network, ξ is the cost matrix,
μ1、μ2、σ1and σ2For cross-validation parameters, R is the confusion matrix for the current class error, S is the matrix for class-to-class separability, H is the matrix defined by the training set class distribution histogram vector H,
p is a class in c, q is a class in c, hpIs a histogram vector of class p, hqIs a histogram vector of class q, and c is the set of all classes of a given electrocardiogram data set.
And inputting the training set into the constructed CoSen-Bi-LSTM network model for training to obtain the ventricular fibrillation prediction model. Specifically, a network is trained by adopting a random gradient descent method, gradient updating is carried out by adopting an SGD method, and the learning rate is 0.001.
In the training process, calculating the input and the output of each layer of neurons, calculating the gradient of a grid parameter loss function and a cost matrix loss function according to the input and the output to perform back propagation, judging whether the value of the grid parameter loss function is smaller than a given error, if so, determining a ventricular fibrillation prediction model structure, if not, judging whether the training frequency reaches a given maximum iteration frequency, if so, determining the model structure, and if not, continuing the training.
On the other hand, the scheme also provides a control method of the remote defibrillation protection system, which comprises the following steps:
the acquisition module acquires pressure data, respiration data, apical pulsation data and electrocardiogram signals of the defibrillation electrode slices and then sends the pressure data, the respiration data, the apical pulsation data and the electrocardiogram signals to the control center;
the control center judges whether the defibrillation electrode plate falls off, whether respiration exists and whether apical pulsation exists according to the pressure data, the respiration data and the apical pulsation data of the defibrillation electrode plate respectively;
when the control center is on line, the electrocardiogram signals are transmitted to the cloud platform through the network, the cloud platform receives and stores the electrocardiogram signals, the current electrocardiogram signals are input into ventricular fibrillation prediction models stored in the cloud platform to obtain prediction results of whether ventricular fibrillation occurs, and if yes, the prediction results are sent to the control center; when the control center is off-line, inputting the current electrocardiogram signal into a ventricular fibrillation prediction model stored in the control center to obtain a prediction result of whether ventricular fibrillation occurs;
when the defibrillation electrode slice does not fall off, respiration does not exist, the apex of the heart does not beat and ventricular fibrillation is predicted, the control center sends a defibrillation instruction to the defibrillation module and sends a starting instruction to the prompt module; the defibrillation module executes defibrillation if the defibrillation module does not receive a manual defibrillation cancelling instruction within a set time after receiving the defibrillation instruction; the prompting module receives the starting instruction and then executes voice prompt to prompt other people not to touch the patient.
Claims (8)
1. A remote defibrillation protection system, comprising:
the acquisition module is used for acquiring pressure data, respiration data, apical pulsation data and electrocardiogram signals of the defibrillation electrode slices and then transmitting the pressure data, the respiration data, the apical pulsation data and the electrocardiogram signals to the control center;
the control center is used for judging whether the defibrillation electrode plates fall off, whether respiration exists and whether apical pulsation exists according to the pressure data, the respiration data and the apical pulsation data of the defibrillation electrode plates respectively; when the control center is on-line, the electrocardiogram signals are transmitted to the cloud platform through the network, the prediction results from the cloud platform are received, and when the control center is off-line, the current electrocardiogram signals are input into ventricular fibrillation prediction models stored in the control center to obtain the prediction results of whether ventricular fibrillation occurs; when the defibrillation electrode slice does not fall off, respiration does not exist, the apex of the heart does not beat and ventricular fibrillation is predicted, sending a defibrillation instruction to the defibrillation module and sending a starting instruction to the prompt module;
the defibrillation module is used for receiving a command of manually cancelling defibrillation, and if the command of manually cancelling defibrillation is not received within a set time after the defibrillation command is received, defibrillation is executed;
the prompting module is used for receiving the starting instruction and then executing voice prompt to prompt other people not to touch the patient;
and the cloud platform is used for receiving and storing the electrocardiogram signals, inputting the current electrocardiogram signals into the ventricular fibrillation prediction model stored in the cloud platform to obtain a prediction result of whether ventricular fibrillation occurs, and if yes, sending the prediction result to the control center.
2. The remote defibrillation protection system of claim 1, wherein the ventricular fibrillation prediction model is derived by a deep learning algorithm.
3. The remote defibrillation protection system of claim 2, wherein the ventricular fibrillation prediction model is derived by a deep learning algorithm further comprising:
acquiring a set number of electrocardiogram signals, and preprocessing the electrocardiogram signals to obtain a training set;
defining a grid parameter loss function and a cost matrix loss function of a CoSen-Bi-LSTM network model, inputting a training set into the constructed CoSen-Bi-LSTM network model for training to obtain a ventricular fibrillation prediction model, wherein the CoSen-Bi-LSTM network model comprises an input layer, a first hidden layer, a second hidden layer, an output layer and a cost sensitive layer which are sequentially connected.
4. The remote defibrillation protection system of claim 3, wherein the training set is input into the constructed CoSen-Bi-LSTM network model for training to obtain the ventricular fibrillation prediction model further comprises: the network is trained by adopting a random gradient descent method, gradient updating is carried out by adopting an SGD method, and the learning rate is 0.001.
5. The remote defibrillation protection system of claim 3, wherein the mesh parameters of the CoSen-Bi-LSTM network model are cross entropy loss functions.
6. The remote defibrillation protection system of claim 3, wherein preprocessing the same to obtain a training set further comprises:
s1, cutting each electrocardiogram signal into a plurality of sub-electrocardiogram signals according to each 4 heartbeats in sequence;
s2, after correcting baseline drift of the sub-electrocardiogram signals by using a high-pass filter, removing high-frequency noise by using a contraction method based on wavelet transformation;
and S3, giving each sub-electrocardiogram signal class label to obtain a training set.
7. The remote defibrillation protection system of claim 6, wherein the system function of the high pass filter is calculated by:
wherein z is a sub-electrocardiogram signal.
8. The method of controlling a remote defibrillation protection system of any one of claims 1 to 7, comprising:
the acquisition module acquires pressure data, respiration data, apical pulsation data and electrocardiogram signals of the defibrillation electrode slices and then sends the pressure data, the respiration data, the apical pulsation data and the electrocardiogram signals to the control center;
the control center judges whether the defibrillation electrode plate falls off, whether respiration exists and whether apical pulsation exists according to the pressure data, the respiration data and the apical pulsation data of the defibrillation electrode plate respectively;
when the control center is on line, transmitting an electrocardiogram signal to the cloud platform through a network, receiving and storing the electrocardiogram signal by the cloud platform, inputting the current electrocardiogram signal into the ventricular fibrillation prediction model stored in the cloud platform to obtain a prediction result of whether ventricular fibrillation occurs, and if yes, sending the prediction result to the control center; when the control center is off-line, inputting the current electrocardiogram signal into a ventricular fibrillation prediction model stored in the control center to obtain a prediction result of whether ventricular fibrillation occurs;
when the defibrillation electrode slice does not fall off, respiration does not exist, the apex of the heart does not beat and ventricular fibrillation is predicted, the control center sends a defibrillation instruction to the defibrillation module and sends a starting instruction to the prompt module; the defibrillation module executes defibrillation if the defibrillation module does not receive a manual defibrillation cancelling instruction within a set time after receiving the defibrillation instruction; the prompting module receives the starting instruction and then executes voice prompt to prompt other people not to touch the patient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911221420.1A CN110812699B (en) | 2019-12-03 | 2019-12-03 | Remote defibrillation protection system and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911221420.1A CN110812699B (en) | 2019-12-03 | 2019-12-03 | Remote defibrillation protection system and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110812699A true CN110812699A (en) | 2020-02-21 |
| CN110812699B CN110812699B (en) | 2021-09-28 |
Family
ID=69543528
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911221420.1A Active CN110812699B (en) | 2019-12-03 | 2019-12-03 | Remote defibrillation protection system and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110812699B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111420286A (en) * | 2020-04-22 | 2020-07-17 | 广州弘大医疗科技有限公司 | In-vitro intelligent defibrillation device and method |
| CN111514458A (en) * | 2020-03-12 | 2020-08-11 | 四川大学华西医院 | Wearable electrocardiogram dynamic full-true drawing and testing intelligent defibrillator and control method thereof |
| CN111657878A (en) * | 2020-07-20 | 2020-09-15 | 苏州无双医疗设备有限公司 | Implantable medical device for integrated identification of cardiac events |
| WO2023236138A1 (en) * | 2022-06-09 | 2023-12-14 | 深圳迈瑞生物医疗电子股份有限公司 | Medical device with defibrillation function, method for configuring same, and medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030023175A1 (en) * | 2001-05-22 | 2003-01-30 | Arzbaecher Robert C. | Implantable cardiac arrest monitor and alarm system |
| CN1723057A (en) * | 2002-12-13 | 2006-01-18 | 皇家飞利浦电子股份有限公司 | External defibrillator with shock activated by cessation of precordial compressions |
| CN1907214A (en) * | 2006-08-18 | 2007-02-07 | 方祖祥 | Portable remote real-time monitor with first-aid and locate function |
| CN104645499A (en) * | 2015-03-16 | 2015-05-27 | 北京品驰医疗设备有限公司 | In vitro controller of implantable medical device for patients |
| CN104683474A (en) * | 2015-03-16 | 2015-06-03 | 北京品驰医疗设备有限公司 | Remote monitoring system for implanted medical equipment |
| 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 |
| CN107890348A (en) * | 2017-11-21 | 2018-04-10 | 郑州大学 | One kind is based on deep approach of learning electrocardio tempo characteristic automation extraction and sorting technique |
| CN108186011A (en) * | 2017-12-13 | 2018-06-22 | 深圳竹信科技有限公司 | Atrial fibrillation detection method, device and readable storage medium storing program for executing |
| CN109948647A (en) * | 2019-01-24 | 2019-06-28 | 西安交通大学 | A kind of electrocardiogram classification method and system based on depth residual error network |
-
2019
- 2019-12-03 CN CN201911221420.1A patent/CN110812699B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030023175A1 (en) * | 2001-05-22 | 2003-01-30 | Arzbaecher Robert C. | Implantable cardiac arrest monitor and alarm system |
| CN1723057A (en) * | 2002-12-13 | 2006-01-18 | 皇家飞利浦电子股份有限公司 | External defibrillator with shock activated by cessation of precordial compressions |
| CN1907214A (en) * | 2006-08-18 | 2007-02-07 | 方祖祥 | Portable remote real-time monitor with first-aid and locate function |
| CN104645499A (en) * | 2015-03-16 | 2015-05-27 | 北京品驰医疗设备有限公司 | In vitro controller of implantable medical device for patients |
| CN104683474A (en) * | 2015-03-16 | 2015-06-03 | 北京品驰医疗设备有限公司 | Remote monitoring system for implanted medical equipment |
| 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 |
| CN107890348A (en) * | 2017-11-21 | 2018-04-10 | 郑州大学 | One kind is based on deep approach of learning electrocardio tempo characteristic automation extraction and sorting technique |
| CN108186011A (en) * | 2017-12-13 | 2018-06-22 | 深圳竹信科技有限公司 | Atrial fibrillation detection method, device and readable storage medium storing program for executing |
| CN109948647A (en) * | 2019-01-24 | 2019-06-28 | 西安交通大学 | A kind of electrocardiogram classification method and system based on depth residual error network |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111514458A (en) * | 2020-03-12 | 2020-08-11 | 四川大学华西医院 | Wearable electrocardiogram dynamic full-true drawing and testing intelligent defibrillator and control method thereof |
| CN111514458B (en) * | 2020-03-12 | 2023-07-18 | 四川大学华西医院 | Wearable electrocardiograph dynamic full true drawing and measurement intelligent defibrillator and control method thereof |
| CN111420286A (en) * | 2020-04-22 | 2020-07-17 | 广州弘大医疗科技有限公司 | In-vitro intelligent defibrillation device and method |
| CN111657878A (en) * | 2020-07-20 | 2020-09-15 | 苏州无双医疗设备有限公司 | Implantable medical device for integrated identification of cardiac events |
| CN111657878B (en) * | 2020-07-20 | 2022-09-09 | 苏州无双医疗设备有限公司 | Implantable medical device for integrated identification of cardiac events |
| WO2023236138A1 (en) * | 2022-06-09 | 2023-12-14 | 深圳迈瑞生物医疗电子股份有限公司 | Medical device with defibrillation function, method for configuring same, and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110812699B (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110812699B (en) | Remote defibrillation protection system and control method thereof | |
| US20230081454A1 (en) | Medical device for sensing cardiac function | |
| US9757581B2 (en) | Wearable cardioverter defibrillator components making aggregate shock/no shock determination from two or more ECG signals | |
| US10213613B2 (en) | System and method for using diagnostic pulses in connection with defibrillation therapy | |
| US9521978B2 (en) | Using chest velocity to process physiological signals to remove chest compression artifacts | |
| US11089989B2 (en) | Shockable heart rhythm classifier for defibrillators | |
| CN113811246A (en) | Machine learning based depolarization identification and arrhythmia localization visualization | |
| KR101776504B1 (en) | Apparatus for predicting of ventricular tachyarrhythmia and method therof | |
| CN103037760B (en) | The CPR compression parameter dynamically adjusted | |
| Li et al. | Identifying potentially shockable rhythms without interrupting cardiopulmonary resuscitation | |
| Gong et al. | A review of the performance of artifact filtering algorithms for cardiopulmonary resuscitation | |
| WO2015051280A1 (en) | Apparatuses and methods for classification of electrocardiogram signals during cardiopulmonary resuscitation | |
| CN113384277A (en) | Electrocardiogram data classification method and classification system | |
| Gong et al. | Removal of cardiopulmonary resuscitation artifacts with an enhanced adaptive filtering method: an experimental trial | |
| CN116421457A (en) | Cardiopulmonary resuscitation system and method based on noninvasive prediction of coronary perfusion pressure | |
| Chicote et al. | Nonlinear energy operators for defibrillation shock outcome prediction | |
| Okai et al. | A new recognition algorithm for shockable arrhythmias and its performance analysis | |
| CN113558632A (en) | System for evaluating neurological outcome after cardio-pulmonary resuscitation based on cardiocerebral electrical signals | |
| US20220032075A1 (en) | Automated external defibrillation with deep neural network | |
| Verboom | Nonlinear filters and deep learning for removing chest compression artifacts from electrocardiogram measurements during cardiac arrest | |
| Cirugeda et al. | Prediction of Early Failure in Electrical Cardioversion of Atrial Fibrillation Using Refined Multiscale Entropy | |
| Kislukhin | STOCHASTIC DESCRIPTION FOR SOME HEART RATE VARIABILITY (HRV): SINUS ARRHYTHMIA AND EXTRASYSTOLES | |
| Telyshev | An adaptive complex algorithm for shockable heart rhythm detection and its use in automated external defibrillators | |
| Ristagno et al. | Amplitude Spectrum Area as 13 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |