CN105997051A - Intelligent terminal for reconstructing 12-lead electrocardiosignals by utilizing three-lead electrocardiosignals - Google Patents
Intelligent terminal for reconstructing 12-lead electrocardiosignals by utilizing three-lead electrocardiosignals Download PDFInfo
- Publication number
- CN105997051A CN105997051A CN201610340786.0A CN201610340786A CN105997051A CN 105997051 A CN105997051 A CN 105997051A CN 201610340786 A CN201610340786 A CN 201610340786A CN 105997051 A CN105997051 A CN 105997051A
- Authority
- CN
- China
- Prior art keywords
- electrocardiosignal
- lead
- intelligent terminal
- group
- layer
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—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
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
- A61B5/6898—Portable consumer electronic devices, e.g. music players, telephones, tablet computers
-
- 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
-
- G06F19/32—
-
- G06F19/3418—
-
- 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
Abstract
The invention discloses an intelligent terminal for reconstructing 12-lead electrocardiosignals by utilizing three-lead electrocardiosignals. The intelligent terminal comprises a processor and a bluetooth communication module, wherein a signal receiving module, a signal extracting and processing module, a neural network training module and a reconstructing module are loaded to the processor. According to the intelligent terminal, the reconstructed model is accurately established by utilizing an artificial neural network learning algorithm and through a Levenberg-Marquardt optimizing way, through the restoration for the system model, the purpose of accurately reconstructing 12-lead data by utilizing the three-lead monitoring data is achieved; the advantages of a 12-lead system and 3-lead system are effectively mixed, so that patients and doctors can easily accept the operation, and the diagnosis is accurately carried out.
Description
Technical field
The invention belongs to technical field of medical equipment, be specifically related to a kind of lead the reconstruct 12 lead heart for three
The intelligent terminal of the signal of telecommunication.
Background technology
" China cardiovascular diseases the report 2012 " data issued according to country cardiovascular diseases center show, China's heart
Angiopathy now suffers from number up to 2.9 hundred million, just has 2 people to suffer from cardiovascular diseases, every year in the most every 10 adults
About 3,500,000 people die from cardiovascular diseases, are equivalent to just have 1 people to die from cardiovascular diseases every 10 seconds.And another by
The clinical studies show that the outer cardiovascular diseases's hospital organization of country's cardiovascular diseases's center complex mound is implemented, in China,
The number of hospitalized of cardiovascular patient adds more than four times during the decade calendar year 2001 to 2010 year.Calendar year 2001
There are 3.7 people because of in the most every 100,000 people that heart disease is in hospital, just soared to 15.8 people by 2010.
So the sickness rate of cardiac to be reduced and mortality rate, the daily cardiac monitoring to patient just seems
Abnormal important.At present dynamic ecg monitoring has become as on medicinal and diagnoses, monitors the normal of heart disease
By method, especially arrhythmia, latent coronary heart disease and the diagnosis of sudden cardiac event and forecast are had
Significance.In recent years, multiple portable remote electrocardio based on Holter system is had developed both at home and abroad
Custodial care facility, remote electrocardiogram monitor technology has been obtained for tremendous development so that the application of dynamic ecg monitoring
Popularized and extended.
Current more lead system is 12 lead system (such as Mason-Likar) and three lead systems,
Three lead systems are only applicable to ARR monitoring;Compare three to lead, use the detection of 12 lead kinetocardiogram
Arrhythmia and coronary heart disease ST section are abnormal, and clinical effectiveness is more notable, so the electrocardiograph that more hospital uses
Or holter monitoring is the electrocardiosignal of 12 lead mostly.12 lead system have I, II, III, V1,
The electrode signal of V2, V3, V4, V5, V6, AVF, AVR and AVL totally ten two passages;Its acceptance of the bid
It is indirectly bipolar lead that quasi-I, II, III lead, I lead be right hand negative pole RA (-) to left hand positive pole LA (+),
II lead be RA (-) to left foot positive pole LF (+), III lead be left hand negative pole LA (-) to LF (+);V1~V6
Unipolar chest lead is semi-direct unipolar lead;AVF, AVR, AVL one pole augmented limb lead is indirect
Unipolar lead, AVR lead be right hand positive pole RA (+) to LA (-) & left foot negative pole LF (-), AVL leads
Be LA (+) to RA (-) &LF (-), AVF lead be LF (+) to RA (-) &LA (-).But allow patient exist voluntarily
Family wears the electrocardiogram equipment of 12 lead, naturally lacks convenience and accuracy, owing to conducting wire is too much, to day
Normal life will also result in certain impact, and this situation is disadvantageous to the Morbidity control of patient.
Summary of the invention
For the problems referred to above, the invention provides the intelligence of a kind of reconstruct 12 lead electrocardiosignal of leading for three
Energy terminal, it is possible to reconstruct 12 lead data accurately by three Monitoring Data led.
The intelligent terminal of a kind of reconstruct 12 lead electrocardiosignal of leading for three, leads to including processor and bluetooth
News module, described processor is loaded with following functions module:
Signal receiving module, provides for collecting cardioelectric monitor device by the bluetooth communication module in intelligent terminal
Electrocardiogram (ECG) data;Described electrocardiogram (ECG) data includes that the m group three that cardioelectric monitor device collects in advance is led electrocardio
When signal and the m group 12 lead electrocardiosignal of synchronization correspondence and user's routine testing thereof, cardioelectric monitor device is adopted
What collection obtained three leads electrocardiosignal, and m is the natural number more than 1;
Signal extraction processing module, for extract from described 12 lead electrocardiosignal about I, II,
The electrocardiosignal of eight passages of V1, V2, V3, V4, V5 and V6 forms as one group of electrocardio monitoring data,
Traversal obtains m group electrocardio monitoring data, and then lead m group three electrocardiosignal and m group electrocardio monitoring data
Carry out pretreatment;
Neural metwork training module, for leading electrocardiosignal and m group electrocardio according to pretreated m group three
Monitoring data is trained by artificial neural network learning algorithm, obtains about 12 lead electrocardiosignal
Reconstruction model;
Reconstructed module, for by user's routine testing obtains, three electrocardiosignaies of leading substitute into above-mentioned reconstruction model
In obtain synchronizing the corresponding electrocardio about eight passages of I, II, V1, V2, V3, V4, V5 and V6 and believe
Number, and then calculate remaining III, AVF, AVR and AVL according to the electrocardiosignal of wherein two passages of I and II
The electrocardiosignal of four passages, finally give user about I, II, III, V1, V2, V3, V4, V5,
V6, AVF, AVR and AVL 12 12 lead electrocardiosignal of passage, and then 12 that reconstruct is obtained
Electrocardiosignal of leading is sent to doctor's mobile phone, cloud server or hospital system service by WIFI or GPRS
Device is for diagnosis.
The artificial neural network learning algorithm that described neural metwork training module is used with
Levenberg-Marquardt algorithm is as optimizing direction.The method is than Gauss-Newton method and gradient descent method
More reliable, it is also possible to be considered as Gauss-Newton method based on trust region, it can be used to solve non-linear
Least square problem.
The detailed process that described neural metwork training module is trained by artificial neural network learning algorithm
As follows:
(1) electrocardiosignal of leading pretreated for m group three is divided into training set and test set and training set to be more than
Test set;
(2) one neutral net being made up of input layer, hidden layer and output layer of structure is initialized;
(3) from training set appoint take one group three lead electrocardiosignal input above-mentioned neural computing obtain correspondence
Comprise the electrocardio output data of eight passages of I, II, V1, V2, V3, V4, V5 and V6, calculate this heart
Electricity output data and this three lead the cumulative error between the electrocardio monitoring data corresponding to electrocardiosignal;
(4) according to this cumulative error by Levenberg-Marquardt algorithm to input layer in neutral net with
Coefficient in neuron function is modified between hidden layer and between hidden layer and output layer, and then from instruction
Practice to concentrate to appoint and take off one group of three electrocardiosignal revised neutral net of substitution of leading;
(5) travel through all three in training set according to step (3) and step (4) to lead electrocardiosignal, take
Neutral net corresponding during cumulative error minimum is reconstruction model.
In the neutral net that described neural metwork training module initialization builds, input layer is by 3 neural tuples
Becoming, hidden layer is made up of 10 neurons, and output layer is made up of 8 neurons.
In the neutral net that described neural metwork training module initialization builds between input layer and hidden layer with
And the neuron function between hidden layer and output layer is expressed as follows:
Wherein: aiFor the output of hidden layer i-th neuron, ekFor the output of output layer kth neuron, xjFor
The output of input layer jth neuron,For input layer jth neuron and hidden layer i-th neuron it
Between weight coefficient,For the intercept coefficient of hidden layer i-th neuron,Neural for output layer kth
Weight coefficient between unit and hidden layer i-th neuron,For the intercept coefficient of output layer kth neuron,
G () is tansig function, and i, j and k are natural number and 1≤i≤10,1≤j≤3,1≤k≤8.
In test set three are led by the reconstruction model that described neural metwork training module obtains for training
Electrocardiosignal substitute into one by one this reconstruction model obtain correspondence comprise I, II, V1, V2, V3, V4, V5 and
The electrocardio output data of eight passages of V6, make each group three electrocardio led corresponding to electrocardiosignal in test set
Output data compare with electrocardio monitoring data, if if the accuracy of test set is more than or equal to threshold value, then
This reconstruction model finally determines;If the accuracy of test set is less than if threshold value, then cardioelectric monitor device is utilized to adopt
Collect more three and lead electrocardiosignal and 12 lead electrocardiosignal to increase the training input of neutral net.
Described reconstructed module calculates the electrocardio of tetra-passages of III, AVF, AVR and AVL by below equation
Signal:
Wherein: V (I), V (II), V (III), V (AVF), V (AVR) and V (AVL) correspond to I passage respectively, II leads to
Road, III passage, AVF passage, AVR passage and the electrocardiosignal of AVL passage.
Described intelligent terminal can be smart mobile phone, panel computer or PC.
Intelligent terminal of the present invention utilizes artificial neural network learning algorithm with the optimization of Levenberg-Marquardt
Reconstruction model is set up by mode accurately, by the reduction to system model, it is achieved that utilize three prisons led
Survey data, reconstruct 12 lead data exactly.
The reconstructing method of intelligent terminal of the present invention has dramatically different with existing 12 lead reconstructing method, and existing ten
Two reconstructing methods that lead are to lead by the part in standard 12 lead to reconstruct remaining and lead;And this
Bright is to carry out reconstruction of standard 12 lead signal by Holter tri-lead signals the most unrelated with standard 12 lead,
Therefore the present invention has merged the advantage that 12 lead and three leads effectively, patient and doctor is made to be easier to accept,
And can Accurate Diagnosis.
Accompanying drawing explanation
Fig. 1 is the structural representation of intelligent terminal in cardioelectric monitor system of the present invention.
Fig. 2 is the artificial nerve network model schematic diagram in 12 lead electrocardiosignal restructuring procedure of the present invention.
Fig. 3 (a)~Fig. 3 (c) corresponds to the electro-cardiologic signal waveforms schematic diagram of three passages.
Fig. 4 (a)~Fig. 4 (l) corresponds to present invention reconstruct and obtains the electro-cardiologic signal waveforms schematic diagram of 12 passages.
Detailed description of the invention
In order to more specifically describe the present invention, below in conjunction with the accompanying drawings and the detailed description of the invention skill to the present invention
Art scheme is described in detail.
As it is shown in figure 1, the present embodiment is adopted for three intelligent terminal leading reconstruct 12 lead electrocardiosignal
With smart mobile phone, in this smart mobile phone, include processor and bluetooth communication module, bluetooth communication module and place
Reason device is connected;Processor includes signal receiving module, signal extraction processing module, neural metwork training module
And reconstructed module;Wherein:
Bluetooth communication module communicates with cardioelectric monitor device for smart mobile phone, and order is sent by smart mobile phone
To cardioelectric monitor device, cardioelectric monitor device response command uploads electrocardiogram (ECG) data to smart mobile phone.
Signal receiving module is for receiving the electrocardiogram (ECG) data from cardioelectric monitor device by bluetooth communication module;The heart
Electricity data include the m group three that cardioelectric monitor device collects in advance lead electrocardiosignal and synchronize correspondence m
Group 12 lead electrocardiosignal and cardioelectric monitor device collects during user's routine testing three leads electrocardio letter
Number.
Signal extraction processing module for extract from 12 lead electrocardiosignal about I, II, V1, V2,
The electrocardiosignal of eight passages of V3, V4, V5 and V6 forms as one group of electrocardio monitoring data, and traversal obtains
M group electrocardio monitoring data, and then m group three is led electrocardiosignal and m group electrocardio monitoring data carries out pre-place
Reason;Preprocessing process carries out form conversion and normalized, obtains the initial data of appropriate format and scope.
In the present embodiment, data sampling rate is 250, and AD conversion figure place is 24bit, will sampling by down-sampled algorithm
Rate reduces to 200, by data compression algorithm, 24bit data is converted to 16bit, obtains the data that capacity is less,
But the demand of neural metwork training module need to be met.Normalization algorithm uses linear transformation algorithm, its expression formula
For:
Wherein: x is input vector, max is the maximum of x, and min is the minima of x, after f (x) is normalization
Output vector.
Neural metwork training module according to pretreated m group three lead electrocardiosignal and m group electrocardio supervision number
It is trained according to by artificial neural network learning algorithm, obtains the reconstruct mould about 12 lead electrocardiosignal
Type;Specific implementation is as follows:
Step 1: after electrocardiogram (ECG) data is carried out pretreatment, builds and obtains m group electrocardio training signal composition
Sample database, is divided into training set and test set randomly by sample database.
Step 2: set up neural network model according to artificial neural network learning algorithm: neural network model has defeated
Entering layer, hidden layer and output layer three layers, the input and output of input layer are three-channel correlation coefficient, hidden layer
And being attached by formula (1) between output layer, input layer is formula with the neural transferring function of hidden layer
(2), output layer be output as output 8 autonomous channels, so being made up of 8 neurons, hidden layer by
10 neurons are constituted, simultaneously by the weights coefficient initialization of each interlayer;Fig. 2 is the ANN set up
Network model.
Wherein: g (z) is tansig function.
Step 3: one group of sample in the training set of electrocardio training sample is input to the god under current weight coefficient
Through network, calculate the output of each node of input layer, hidden layer and output layer successively.
Step 4: calculate output layer output and the electrocardio training sample of all electrocardio training samples according to formula (3)
Cumulative error E between expected resulttrain, according to Levenberg-Marquardt algorithm, repair with formula (4)
Positive hidden layer and each internodal weights coefficient of output layer, revise input layer and each node of hidden layer with formula (5)
Between weights coefficient.
Wherein: E is cumulative error,Export through the kth of the output layer of neutral net for single training sample,
okFor the kth expected result of single training sample, m is training set total sample number, and p is that output layer output is total
Number.
Wherein: whoT () is the weights coefficient that the t time sample is input to during neutral net between hidden layer and output layer,For single training sample through the output of the output layer of neutral net, o is the expected result of single training sample,
xhFor the output of hidden layer, α is learning rate.
Wherein: wihT () is the weights coefficient that the t time sample is input to during neutral net between input layer and hidden layer,For single training sample through the output of the output layer of neutral net, o is the expected result of single training sample,
xiOutput for input layer.
Step 5: travel through the training set of all electrocardio training samples with step 3 and step 4, then get Etrain?
Hour weights coefficient sets, and test with test set neutral net, if the accuracy of test is higher than threshold value
Then train;If it is not, increase electrocardio training sample, and repeat step 3~step 5.
In present embodiment, learning rate α=0.05.
Reconstructed module is for the weights proportion according to each layer of neutral net, the system function of reduction reconstruction model;
Its triple channel electrocardiosignal section obtained according to user's routine testing utilizes above-mentioned reconstruction model to lead standard 12
Each independent leads in connection calculates, thus obtain synchronize electrocardiosignal I of eight independent leads, II,
V1, V2, V3, V4, V5 and V6.By the electrocardiosignal of eight independent leads, using leads as follows turns
Change formula and calculate tetra-electrocardiosignaies led of III, AVR, AVL, AVF.
Three Lead ambulatory electrocardiograms collected shown in Fig. 3.Through data collection, packet, nerve
Network training calculates 12 data led after going out 8 data led, draw standard 12 lead electrocardiogram, such as Fig. 4
Shown in;The electrocardiogram that this is calculated contrasts with the electrocardiogram of actual acquisition, and in Fig. 4, solid line represents and makes
Lead with the 12 of standard the collection data of holter monitoring, and dotted line is 3 12 reconstructed of leading leads number
According to.Original 12 lead curve is the most identical with reconstruct 12 lead curve, and this algorithm experimental effect is obvious.
The above-mentioned description to embodiment is to be understood that for ease of those skilled in the art and apply
The present invention.Above-described embodiment obviously easily can be made various amendment by person skilled in the art,
And General Principle described herein is applied in other embodiments without through performing creative labour.Therefore,
The invention is not restricted to above-described embodiment, those skilled in the art, according to the announcement of the present invention, do for the present invention
The improvement and the amendment that go out all should be within protection scope of the present invention.
Claims (8)
1. an intelligent terminal for reconstruct 12 lead electrocardiosignal of leading for three, including processor and bluetooth
Communication module, it is characterised in that described processor is loaded with following functions module:
Signal receiving module, provides for collecting cardioelectric monitor device by the bluetooth communication module in intelligent terminal
Electrocardiogram (ECG) data;Described electrocardiogram (ECG) data includes that the m group three that cardioelectric monitor device collects in advance is led electrocardio
When signal and the m group 12 lead electrocardiosignal of synchronization correspondence and user's routine testing thereof, cardioelectric monitor device is adopted
What collection obtained three leads electrocardiosignal, and m is the natural number more than 1;
Signal extraction processing module, for extract from described 12 lead electrocardiosignal about I, II,
The electrocardiosignal of eight passages of V1, V2, V3, V4, V5 and V6 forms as one group of electrocardio monitoring data,
Traversal obtains m group electrocardio monitoring data, and then lead m group three electrocardiosignal and m group electrocardio monitoring data
Carry out pretreatment;
Neural metwork training module, for leading electrocardiosignal and m group electrocardio according to pretreated m group three
Monitoring data is trained by artificial neural network learning algorithm, obtains about 12 lead electrocardiosignal
Reconstruction model;
Reconstructed module, for by user's routine testing obtains, three electrocardiosignaies of leading substitute into above-mentioned reconstruction model
In obtain synchronizing the corresponding electrocardio about eight passages of I, II, V1, V2, V3, V4, V5 and V6 and believe
Number, and then calculate remaining III, AVF, AVR and AVL according to the electrocardiosignal of wherein two passages of I and II
The electrocardiosignal of four passages, finally give user about I, II, III, V1, V2, V3, V4, V5,
V6, AVF, AVR and AVL 12 12 lead electrocardiosignal of passage, and then 12 that reconstruct is obtained
Electrocardiosignal of leading is sent to doctor's mobile phone, cloud server or hospital system service by WIFI or GPRS
Device is for diagnosis.
Intelligent terminal the most according to claim 1, it is characterised in that: described neural metwork training mould
The artificial neural network learning algorithm that block is used is using Levenberg-Marquardt algorithm as optimizing direction.
Intelligent terminal the most according to claim 1, it is characterised in that: described neural metwork training mould
The detailed process that block is trained by artificial neural network learning algorithm is as follows:
(1) electrocardiosignal of leading pretreated for m group three is divided into training set and test set and training set to be more than
Test set;
(2) one neutral net being made up of input layer, hidden layer and output layer of structure is initialized;
(3) from training set appoint take one group three lead electrocardiosignal input above-mentioned neural computing obtain correspondence
Comprise the electrocardio output data of eight passages of I, II, V1, V2, V3, V4, V5 and V6, calculate this heart
Electricity output data and this three lead the cumulative error between the electrocardio monitoring data corresponding to electrocardiosignal;
(4) according to this cumulative error by Levenberg-Marquardt algorithm to input layer in neutral net with
Coefficient in neuron function is modified between hidden layer and between hidden layer and output layer, and then from instruction
Practice to concentrate to appoint and take off one group of three electrocardiosignal revised neutral net of substitution of leading;
(5) travel through all three in training set according to step (3) and step (4) to lead electrocardiosignal, take
Neutral net corresponding during cumulative error minimum is reconstruction model.
Intelligent terminal the most according to claim 3, it is characterised in that: described neural metwork training mould
In the neutral net that initialization block builds, input layer is made up of 3 neurons, and hidden layer is by 10 neural tuples
Becoming, output layer is made up of 8 neurons.
Intelligent terminal the most according to claim 4, it is characterised in that: described neural metwork training mould
God between input layer and hidden layer and between hidden layer and output layer in the neutral net that initialization block builds
It is expressed as follows through meta-function:
Wherein: aiFor the output of hidden layer i-th neuron, ekFor the output of output layer kth neuron, xjFor
The output of input layer jth neuron,For input layer jth neuron and hidden layer i-th neuron it
Between weight coefficient,For the intercept coefficient of hidden layer i-th neuron,Neural for output layer kth
Weight coefficient between unit and hidden layer i-th neuron,For the intercept coefficient of output layer kth neuron,
G () is tansig function, and i, j and k are natural number and 1≤i≤10,1≤j≤3,1≤k≤8.
Intelligent terminal the most according to claim 3, it is characterised in that: described neural metwork training mould
The reconstruction model that block obtains for training, electrocardiosignal of three in test set being led substitutes into this reconstruct mould one by one
Type obtains the electrocardio output data that correspondence comprises eight passages of I, II, V1, V2, V3, V4, V5 and V6,
The electrocardio output data that in test set, each group three is led corresponding to electrocardiosignal are made to carry out with electrocardio monitoring data
Relatively, if the accuracy of test set is more than or equal to if threshold value, then this reconstruction model finally determines;If test
The accuracy of collection less than if threshold value, then utilizes cardioelectric monitor device collection more three to lead electrocardiosignal and ten
Two lead electrocardiosignal to increase the training input of neutral net.
Intelligent terminal the most according to claim 1, it is characterised in that: described reconstructed module by with
The electrocardiosignal of lower formula calculating tetra-passages of III, AVF, AVR and AVL:
Wherein: V (I), V (II), V (III), V (AVF), V (AVR) and V (AVL) correspond to I passage respectively, II leads to
Road, III passage, AVF passage, AVR passage and the electrocardiosignal of AVL passage.
Intelligent terminal the most according to claim 1, it is characterised in that: described intelligent terminal is intelligence
Mobile phone, panel computer or PC.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610340786.0A CN105997051A (en) | 2016-05-20 | 2016-05-20 | Intelligent terminal for reconstructing 12-lead electrocardiosignals by utilizing three-lead electrocardiosignals |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610340786.0A CN105997051A (en) | 2016-05-20 | 2016-05-20 | Intelligent terminal for reconstructing 12-lead electrocardiosignals by utilizing three-lead electrocardiosignals |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105997051A true CN105997051A (en) | 2016-10-12 |
Family
ID=57095874
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610340786.0A Pending CN105997051A (en) | 2016-05-20 | 2016-05-20 | Intelligent terminal for reconstructing 12-lead electrocardiosignals by utilizing three-lead electrocardiosignals |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105997051A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106725447A (en) * | 2016-12-09 | 2017-05-31 | 浙江铭众科技有限公司 | A kind of three lead electrocardioelectrodes based on feedforward neural network fitting connect method of discrimination |
CN113693610A (en) * | 2021-08-31 | 2021-11-26 | 平安科技(深圳)有限公司 | Few-lead electrocardiogram data processing method and device, storage medium and computer equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001070105A2 (en) * | 2000-03-22 | 2001-09-27 | Bojovic Bosko | Method and system for ecg recording via telephone |
CN101152081A (en) * | 2006-09-29 | 2008-04-02 | 通用电气公司 | Method and apparatus with reduced electrode system specific ecg interpretation |
US20100256511A1 (en) * | 2009-04-06 | 2010-10-07 | Fabienne Poree | Reconstruction of a surface electrocardiogram from an endocardial electrogram using non-linear filtering |
CN102106728A (en) * | 2011-01-27 | 2011-06-29 | 孙迎春 | Four electrode plates-based 18-lead electrocardiogram tracing method for exercise electrocardiogram |
CN203483416U (en) * | 2013-09-12 | 2014-03-19 | 苏州百慧华业精密仪器有限公司 | Double-lead-system dynamic electrocardiogram recorder |
CN104463326A (en) * | 2014-12-09 | 2015-03-25 | 浙江大学 | Standard 12-lead ecg signal reconstruction method |
CN105496392A (en) * | 2015-12-11 | 2016-04-20 | 浙江铭众科技有限公司 | Three-lead ECG (electrocardiogram) monitoring system with electrode connection distinguishing function |
-
2016
- 2016-05-20 CN CN201610340786.0A patent/CN105997051A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001070105A2 (en) * | 2000-03-22 | 2001-09-27 | Bojovic Bosko | Method and system for ecg recording via telephone |
CN101152081A (en) * | 2006-09-29 | 2008-04-02 | 通用电气公司 | Method and apparatus with reduced electrode system specific ecg interpretation |
US20100256511A1 (en) * | 2009-04-06 | 2010-10-07 | Fabienne Poree | Reconstruction of a surface electrocardiogram from an endocardial electrogram using non-linear filtering |
CN102106728A (en) * | 2011-01-27 | 2011-06-29 | 孙迎春 | Four electrode plates-based 18-lead electrocardiogram tracing method for exercise electrocardiogram |
CN203483416U (en) * | 2013-09-12 | 2014-03-19 | 苏州百慧华业精密仪器有限公司 | Double-lead-system dynamic electrocardiogram recorder |
CN104463326A (en) * | 2014-12-09 | 2015-03-25 | 浙江大学 | Standard 12-lead ecg signal reconstruction method |
CN105496392A (en) * | 2015-12-11 | 2016-04-20 | 浙江铭众科技有限公司 | Three-lead ECG (electrocardiogram) monitoring system with electrode connection distinguishing function |
Non-Patent Citations (3)
Title |
---|
徐冠等: "基于LM算法的神经网络在冠心病诊断中的应用", 《微电子学与计算机 》 * |
陈方剑: "标准12导联心电信号重建方法研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
黄豪彩等: "基于LM算法的神经网络系统辨识", 《组合机床与自动化加工技术 》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106725447A (en) * | 2016-12-09 | 2017-05-31 | 浙江铭众科技有限公司 | A kind of three lead electrocardioelectrodes based on feedforward neural network fitting connect method of discrimination |
CN106725447B (en) * | 2016-12-09 | 2017-12-12 | 浙江铭众科技有限公司 | A kind of three lead electrocardioelectrodes based on feedforward neural network fitting connect method of discrimination |
CN113693610A (en) * | 2021-08-31 | 2021-11-26 | 平安科技(深圳)有限公司 | Few-lead electrocardiogram data processing method and device, storage medium and computer equipment |
CN113693610B (en) * | 2021-08-31 | 2022-10-14 | 平安科技(深圳)有限公司 | Method and device for processing few-lead electrocardiogram data, storage medium and computer equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3692904A1 (en) | Method and device for self-learning dynamic electrocardiography analysis employing artificial intelligence | |
EP3692900A1 (en) | Artificial intelligence self-learning-based static electrocardiography analysis method and apparatus | |
CN104463326B (en) | Standard 12-lead ecg signal reconstruction method | |
CN107788976A (en) | Sleep monitor system based on Amplitude integrated electroencephalogram | |
CN105078445A (en) | Old people healthy service system based on healthy service robot | |
CN105496392B (en) | A kind of have electrode and connect the three of discrimination function and lead cardioelectric monitor system | |
CN109998522A (en) | A kind of exercise load detection device and method based on wearable dynamic electrocardiogram | |
CN105769173A (en) | Electrocardiogram monitoring system with electrocardiosignal denoising function | |
CN107616791A (en) | The lead electrocardio piecewise-linear reconstruction method of standard 12 based on adaptive electrocardiosignal region segmentation | |
CN105943022B (en) | A kind of cardioelectric monitor system that there are three leads to reconstruct 12 lead function | |
CN105380643B (en) | A kind of three connection method of discrimination leading electrocardioelectrode | |
CN106073753A (en) | 18 lead holographic dynamic and static ecg analysis method and system | |
CN106056045B (en) | Method of reconstructing 12-lead electrocardiosignals through 3-lead | |
Yin et al. | Influence of optimization design based on artificial intelligence and internet of things on the electrocardiogram monitoring system | |
CN111557660A (en) | Arrhythmia identification method under sub-population deep learning framework | |
CN105796091B (en) | A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise | |
CN105997051A (en) | Intelligent terminal for reconstructing 12-lead electrocardiosignals by utilizing three-lead electrocardiosignals | |
CN204971271U (en) | Old person health service system based on health service robot | |
CN106983502A (en) | Disease diagnosing system and its application method | |
CN114145744A (en) | Cross-device forehead electroencephalogram emotion recognition method and system | |
Li et al. | Detection of muscle fatigue by fusion of agonist and synergistic muscle semg signals | |
Jiang et al. | Enhanced machine learning feature selection algorithm for cardiac arrhythmia in a personal healthcare application | |
CN202365773U (en) | Remote wireless electrocardio real-time monitoring system | |
CN106618551B (en) | A kind of intelligent terminal for being used for the connection of three lead electrocardioelectrodes and differentiating | |
CN203122389U (en) | 12 lead remote electrocardiogram diagnostic system transmitted through mobile phone |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161012 |