CN109199343A - A kind of appraisal procedure of auricular fibrillation, system and equipment - Google Patents
A kind of appraisal procedure of auricular fibrillation, system and equipment Download PDFInfo
- Publication number
- CN109199343A CN109199343A CN201810785816.8A CN201810785816A CN109199343A CN 109199343 A CN109199343 A CN 109199343A CN 201810785816 A CN201810785816 A CN 201810785816A CN 109199343 A CN109199343 A CN 109199343A
- Authority
- CN
- China
- Prior art keywords
- interphase
- pulse wave
- sample
- neural network
- network model
- 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
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- 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)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physiology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Cardiology (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The embodiment of the present invention provides the appraisal procedure, system and equipment of a kind of auricular fibrillation, obtains pulse wave by the camera based on mobile intelligent terminal；Preset quantity RR interphase is extracted based on pulse wave, preset quantity RR interphase is formed into RR interval series；RR interval series are input to the neural network model trained, export the probability of auricular fibrillation；It is assisted without extras and health care professional, the phenomenon that auricular fibrillation of active user can be analyzed and be assessed merely with the camera of intelligent terminal, so that this method, system and equipment have better convenience and real-time；And neural network model is utilized, a possibility that capable of effectively analyzing user data, meet the requirement of accuracy, reduce false assessment.
Description
Technical field
The present embodiments relate to health assessment technology field, more particularly, to a kind of auricular fibrillation appraisal procedure,
System and equipment.
Background technique
Auricular fibrillation (AF) is a kind of relatively common rhythm of the heart phenomenon, and the size of population for the phenomenon occur accounts for total population quantity
1-2%, and increase along with the growth at age, the phenomenon that auricular fibrillation with many cardiopathic morbidity and mortality phases
It closes, is to diagnose the important evidence of many diseases, such as embolic stroke.Therefore, the earlier evaluations of auricular fibrillation are in prevention
Wind and the risk for reducing related complication are of great significance.
The assessment of auricular fibrillation at this stage relies primarily on electrocardiogram, based on the off-note of patients with atrial fibrillation electrocardiogram, detection
There are mainly three types of methods for the research of atrial fibrillation: 1, the method based on atrial activity analysis；2, the method based on ventricle response analysis；3,
The combined method of both the above method.Method based on atrial activity analysis is mainly by lacking P wave in the interval TQ or f occur
The analysis of wave, but since T wave amplitude is small, vulnerable to influence of noise.Method based on ventricle response analysis is most main in previous research
The method wanted, this method can lead to false assessment when heart rate is controlled by drug or pacemaker.In conjunction with above two method
Combined method includes method and fuzzy logic classifier method based on the section RR Markov model.
The continuous observation of the main professional equipment progress dynamic ECG by hospital of the assessment of above auricular fibrillation, one
Aspect acquisition electrocardiogram needs extras and health care professional, is not easy to detect the health status of heart whenever and wherever possible, separately
On the one hand, the accuracy of assessment is not high, be easy to cause the assessment of mistake.
Summary of the invention
In order to overcome the above problem or at least be partially solved the above problem, the embodiment of the present invention provides a kind of atrial fibrillation
Dynamic appraisal procedure, system and equipment.
The embodiment of the present invention provides a kind of appraisal procedure of auricular fibrillation, comprising: the camera based on mobile intelligent terminal
Obtain pulse wave；Preset quantity RR interphase is extracted based on pulse wave, preset quantity RR interphase is formed into RR interphase sequence
Column；RR interval series are input to the neural network model trained, export the probability of auricular fibrillation.
Wherein, the camera based on mobile intelligent terminal obtains pulse wave, comprising: controls the camera shooting of mobile intelligent terminal
Head flash of light light irradiation parteriole；Control the reflected light of the camera acquisition camera flash of light light irradiation parteriole of mobile intelligent terminal
Strength Changes；Pulse wave is obtained according to the Strength Changes of the reflected light of camera acquisition.
Wherein, preset quantity RR interphase is extracted based on pulse wave, comprising: determine the peak point in pulse wave；It mentions
Take the time interval between adjacent peak point, using the time interval between the adjacent peak point of continuous preset quantity as
Preset quantity RR interphase.
Wherein, before based on pulse wave extraction preset quantity RR interphase, further includes: carried out at denoising to pulse wave
Reason.
Wherein, the training step of neural network model includes: and extracts each using every RR interval series as a sample
Temporal signatures, frequency domain character and the nonlinear characteristic of sample, wherein every RR interval series include preset quantity RR interphase；
The sample of preset ratio in sample set is formed into training set, by the temporal signatures of sample each in training set, frequency domain character and non-
Linear character and the corresponding label of each sample are input to neural network model, are trained to neural network model.
Wherein, by temporal signatures, frequency domain character and the nonlinear characteristic of sample each in training set and each sample pair
The label answered is input to neural network model, after being trained to neural network model, further includes: by training set in sample set
Sample in addition forms test set, by temporal signatures, frequency domain character and the nonlinear characteristic of sample each in test set and often
The corresponding label of one sample is input to neural network model, tests neural network model.
The embodiment of the present invention also provides a kind of assessment system of auricular fibrillation, comprising: mobile intelligent terminal, pulse wave obtain
Modulus block, RR interphase extraction module and auricular fibrillation evaluation module；Pulse wave obtains module, for being based on mobile intelligent terminal
Camera obtain pulse wave；RR interphase extraction module will be pre- for extracting preset quantity RR interphase based on pulse wave
If quantity RR interphase forms RR interval series；Auricular fibrillation evaluation module has been trained for being input to RR interval series
Neural network model exports the probability of auricular fibrillation.
Wherein, which further includes pulse wave denoising module；Pulse wave denoises module, for carrying out to pulse wave
Denoising.
The embodiment of the present invention also provides a kind of assessment equipment of auricular fibrillation, comprising: at least one processor, at least one
Memory and communication bus；Wherein: processor and memory complete mutual communication by communication bus；Memory is stored with
The program instruction that can be executed by processor, processor caller are instructed to execute the above method.
The embodiment of the present invention also provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage
Medium storing computer program, the computer program make computer execute above-mentioned method.
Appraisal procedure, system and the equipment of a kind of auricular fibrillation provided in an embodiment of the present invention, by being based on intelligent movable
The camera of terminal obtains pulse wave；Preset quantity RR interphase is extracted based on pulse wave, by preset quantity RR interphase
Form RR interval series；RR interval series are input to the neural network model trained, export the probability of auricular fibrillation；To
It does not need extras and health care professional assists, it can be to the heart of active user merely with the camera of intelligent terminal
The dynamic phenomenon of atrial fibrillation is analyzed and is assessed, so that this method, system and equipment have better convenience and real-time；And
Using neural network model, user data can be effectively analyzed, meets the requirement of accuracy, reduces the possibility of false assessment
Property.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow chart according to the appraisal procedure of the auricular fibrillation of the embodiment of the present invention；
Fig. 2 is the schematic diagram according to the assessment system of the auricular fibrillation of the embodiment of the present invention；
Fig. 3 is the schematic diagram according to the assessment equipment of the auricular fibrillation of the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
The embodiment of the present invention provides a kind of appraisal procedure of auricular fibrillation, with reference to Fig. 1, comprising: S11 is based on intelligent movable
The camera of terminal obtains pulse wave；S12 extracts preset quantity RR interphase based on pulse wave, by preset quantity RR
Interphase forms RR interval series；RR interval series are input to the neural network model trained, export auricular fibrillation by S13
Probability.
Specifically, auricular fibrillation is related with heart rate, thus under normal conditions can by electrocardiogram realize to auricular fibrillation this
One phenomenon is assessed.
Since heart rate can also be embodied by pulse, the appraisal procedure of the auricular fibrillation of the present embodiment utilizes camera
Camera function shoots the beating of human pulse by certain mode, so that it may by shooting obtained data acquisition to pulse
Waveform；Since mobile intelligent terminal carries camera, pulse wave is obtained using the camera of mobile intelligent terminal, it can
Achieve the purpose that make full use of mobile intelligent terminal at one's side, reaches better convenience and real-time, such as intelligent movable end
End includes mobile phone, tablet computer, palm PC etc..
Electrocardiogram RR interphase refers to that the time interval between two adjacent R waves of ecg wave form, RR interphase are substantially generation
The numerical value of table period, the RR interval series comprising multiple RR interphases can regard the numerical value of a sequence as, can show one
Fixed rule is come, and is analyzed by the neural network model trained RR interval series, so that it may obtain auricular fibrillation
Probability.
In the present embodiment, pulse wave can also reflect ecg wave form to a certain extent, can also be extracted by pulse wave
RR interval series to RR interphase, preset quantity RR interphase composition are input to the neural network model trained, and can finally obtain
To the probability of auricular fibrillation, the preset quantity of RR interphase excessively will increase calculation amount in RR interval series, and few then will affect is commented excessively
Estimate precision, in the present embodiment, preset quantity may be selected 32.
The present embodiment obtains pulse wave by the camera based on mobile intelligent terminal；It is extracted based on pulse wave default
Preset quantity RR interphase is formed RR interval series by quantity RR interphase；RR interval series are input to the nerve trained
Network model exports the probability of auricular fibrillation；It is assisted without extras and health care professional, merely with intelligent end
The camera of end equipment can be analyzed and be assessed to the phenomenon that auricular fibrillation of active user so that this method, system and
Equipment has better convenience and real-time；And neural network model is utilized, user data can be effectively analyzed, meet essence
The requirement of exactness, a possibility that reducing false assessment.
Based on above embodiments, the camera based on mobile intelligent terminal obtains pulse wave, comprising: control intelligent movable
The camera flash of terminal irradiates parteriole；Control the camera acquisition camera flash of light light irradiation petty action of mobile intelligent terminal
The Strength Changes of the reflected light of arteries and veins；Pulse wave is obtained according to the Strength Changes of the reflected light of camera acquisition.
Specifically, after blood is pressed into artery by human heart, slight variation can occur for the concentration of endarterial blood, warp
The intensity of reflected light after lasting illumination can also change with the variation of the concentration of blood, by camera close to parteriole,
Make camera flash prolonged exposure parteriole simultaneously, camera is just able to record down some period internal reflection luminous intensity at any time
Variation, that is, the concentration of blood changes with time；Being changed with time by the intensity of reflected light can extract
Pulse wave.When it is implemented, the Strength Changes of finger tip parteriole reflected light can be acquired, finger tip parteriole is easier close to camera shooting
Head is that the process of acquisition is more convenient more efficient.
Based on above embodiments, preset quantity RR interphase is extracted based on pulse wave, comprising: determine in pulse wave
Peak point；Extract the time interval between adjacent peak point, by between the adjacent peak point of continuous preset quantity when
Between interval be used as preset quantity RR interphase.
Wherein, before based on pulse wave extraction preset quantity RR interphase, further includes: carried out at denoising to pulse wave
Reason.
Specifically, it since pulse wave is that the intensity of reflected light of parteriole acquired by camera is extracted, needs pair
Pulse wave carries out denoising, avoids the influence of the disturbing factor in collection process.
Since RR interphase refers to the time interval between two adjacent R waves (peak point), in the present embodiment, it is first determined arteries and veins
The peak point (R wave) fought in waveform, and the time interval between adjacent peak point is extracted, in order to guarantee the accuracy of assessment,
It using the time interval between the adjacent peak point of continuous preset quantity as preset quantity RR interphase, will ensure that between RR
Preset quantity RR interphase is to ensure that the spy of RR interval series according to the sequence arrangement before and after the pulse wave time in phase sequence
Some frequency domain characters and nonlinear characteristic, it is ensured that the accuracy of assessment.
Based on above embodiments, the training step of neural network model includes: using every RR interval series as a sample
This, extracts the temporal signatures, frequency domain character and nonlinear characteristic of each sample, wherein every RR interval series include present count
Measure a RR interphase；The sample of preset ratio in sample set is formed into training set, by temporal signatures, the frequency of sample each in training set
Characteristic of field and nonlinear characteristic and the corresponding label of each sample are input to neural network model, carry out to neural network model
Training.
Wherein, by temporal signatures, frequency domain character and the nonlinear characteristic of sample each in training set and each sample pair
The label answered is input to neural network model, after being trained to neural network model, further includes: by training set in sample set
Sample in addition forms test set, by temporal signatures, frequency domain character and the nonlinear characteristic of sample each in test set and often
The corresponding label of one sample is input to neural network model, tests neural network model.
Specifically, the present embodiment is by RR interval series data normal in PostgreSQL database and with auricular fibrillation feature
RR interval series data form sample set as sample, and using the sample of wherein preset ratio as training set, by other samples
This is trained and tests to neural network model respectively using training set and test set as test set.
RR interval series are substantially sequence of values, have temporal signatures, frequency domain character and nonlinear characteristic, the present embodiment
In, extract the temporal signatures, frequency domain character and nonlinear characteristic of each sample, wherein temporal signatures, frequency domain character and non-linear
The particular content of feature is shown in Table 1, table 2 and table 3 respectively.
The particular content of the temporal signatures of 1 RR interval series of table
| 1 | RR interphase minimum value | 8 | RR interphase standardizes absolute difference |
| 2 | RR interphase mean value | 9 | The root-mean-square value of the difference of adjacent R R interphase |
| 3 | RR interphase standard deviation | 10 | The standard deviation of the difference of adjacent R R interphase |
| 4 | RR interphase mode | 11 | The difference of adjacent R R interphase is greater than the number of 50ms |
| 5 | Coefficient of variation | 12 | The difference of adjacent R R interphase is greater than the ratio of 50ms |
| 6 | RR interphase maximum deviation | 13 | Average heart rate |
| 7 | RR interphase standardizes absolute deviation |
The particular content of the frequency domain character of 2 RR interval series of table
| 1 | Ultralow band energy (VLF): 0-0.04Hz | 5 | Low high-frequency energy ratio: LF/HF |
| 2 | Low-frequency range energy (LF): 0.04-0.15Hz | 6 | Low frequency energy accounting: LF/ (TP-VLF) |
| 3 | High band energy (HF): 0.15-0.4Hz | 7 | High-frequency energy accounting: HF/ (TP-VLF) |
| 4 | Gross energy (TP): 0-0.4Hz |
The particular content of the nonlinear characteristic of 3 RR interval series of table
| 1 | Sample Entropy | 3 | Poincare Plot:SD1 |
| 2 | Sample Entropy coefficient | 4 | Poincare Plot:SD2 |
By temporal signatures, frequency domain character and the nonlinear characteristic of sample each in training set and the corresponding mark of each sample
Label are input to neural network model, are trained to neural network model.Then by the temporal signatures of sample each in test set,
Frequency domain character and nonlinear characteristic and the corresponding label of each sample are input to neural network model, to neural network model into
Row test, the label of sample is i.e. normal or has auricular fibrillation feature.
For example, the present embodiment is using the normal RR interval series data in physionet public database and has the heart
Atrial fibrillation moves the RR interval series data of feature, randomly selects 200 RR interval series therein and is trained and tests, each RR
Interval series include that 8600 groups of data are obtained after extracting temporal signatures, frequency domain character and nonlinear characteristic in 32 RR interphases.,
It is 70% according to preset ratio, the sample for participating in training and test is allocated as follows shown in table 4:
4 training set of table and test set allocation table
| Training (70%) | It tests (30%) | It amounts to | |
| Auricular fibrillation | 17(3400) | 8(1600) | 25(5000) |
| Normally | 13(2600) | 5(1000) | 18(3600) |
| It amounts to | 30(6000) | 13(2600) | 43(8600) |
The embodiment of the present invention also provides a kind of assessment system of auricular fibrillation, with reference to Fig. 2, comprising: mobile intelligent terminal 21,
Pulse wave obtains module 22, RR interphase extraction module 23 and auricular fibrillation evaluation module 24；Wherein:
Pulse wave obtains module 22, obtains pulse wave for the camera based on mobile intelligent terminal 21；
RR interphase extraction module 23, for extracting preset quantity RR interphase based on pulse wave, by preset quantity RR
Interphase forms RR interval series；
Auricular fibrillation evaluation module 24 exports the heart for RR interval series to be input to the neural network model trained
The dynamic probability of atrial fibrillation.
Wherein, which further includes pulse wave denoising module；Pulse wave denoises module, for carrying out to pulse wave
Denoising.
The system of the embodiment of the present invention can be used for executing the technology of the appraisal procedure embodiment of auricular fibrillation shown in FIG. 1
Scheme, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
The embodiment of the present invention also provides a kind of assessment equipment of auricular fibrillation, with reference to Fig. 3, comprising: at least one processor
31, at least one processor 32 and communication bus 33；Wherein: processor 31 and memory 32 are completed mutually by communication bus 33
Between communication；Memory 32 is stored with the program instruction that can be executed by processor 31, and 31 caller of processor is instructed to execute
Method provided by above-mentioned each method embodiment, for example, the camera based on mobile intelligent terminal obtains pulse wave；Base
Preset quantity RR interphase is extracted in pulse wave, preset quantity RR interphase is formed into RR interval series；By RR interval series
It is input to the neural network model trained, exports the probability of auricular fibrillation.
The embodiment of the present invention also provides a kind of computer program product, and the computer program product is non-transient including being stored in
Computer program on computer readable storage medium, the computer program include program instruction, when program instruction is by computer
When execution, computer is able to carry out method provided by above-mentioned each method embodiment, for example, based on mobile intelligent terminal
Camera obtains pulse wave；Preset quantity RR interphase is extracted based on pulse wave, preset quantity RR interphase is formed into RR
Interval series；RR interval series are input to the neural network model trained, export the probability of auricular fibrillation.
The embodiment of the present invention also provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage
Medium storing computer program, the computer program make the computer execute method provided by above-mentioned each method embodiment, example
It such as include: that the camera based on mobile intelligent terminal obtains pulse wave；Preset quantity RR interphase is extracted based on pulse wave,
Preset quantity RR interphase is formed into RR interval series；RR interval series are input to the neural network model trained, are exported
The probability of auricular fibrillation.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
Computer program instructions relevant hardware is completed, and computer program above-mentioned can store to be situated between in a computer-readable storage
In matter, which when being executed, executes step including the steps of the foregoing method embodiments；And storage medium above-mentioned includes:
The various media that can store program code such as ROM, RAM, magnetic or disk.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it is stated that: the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although ginseng
According to previous embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be with
It modifies the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；And
These are modified or replaceed, the spirit and model of technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution
It encloses.
Claims (10)
1. a kind of appraisal procedure of auricular fibrillation characterized by comprising
Camera based on mobile intelligent terminal obtains pulse wave；
Preset quantity RR interphase is extracted based on the pulse wave, the preset quantity RR interphase is formed into RR interphase sequence
Column；
The RR interval series are input to the neural network model trained, export the probability of auricular fibrillation.
2. the method according to claim 1, wherein the camera based on mobile intelligent terminal obtains pulse
Waveform, comprising:
Control the camera flash irradiation parteriole of the mobile intelligent terminal；
The camera for controlling the mobile intelligent terminal acquires the reflected light that the camera flash irradiates the parteriole
Strength Changes；
The pulse wave is obtained according to the Strength Changes of the reflected light of camera acquisition.
3. the method according to claim 1, wherein described extract preset quantity RR based on the pulse wave
Interphase, comprising:
Determine the peak point in the pulse wave；
Extract the time interval between adjacent peak point, by between the adjacent peak point of the continuous preset quantity when
Between interval be used as the preset quantity RR interphase.
4. the method according to claim 1, wherein described extract preset quantity RR based on the pulse wave
Before interphase, further includes:
Denoising is carried out to the pulse wave.
5. the method according to claim 1, wherein the training step of the neural network model includes:
Using every RR interval series as a sample, the temporal signatures, frequency domain character and nonlinear characteristic of each sample are extracted,
Wherein, every RR interval series include the preset quantity RR interphase；
The sample of preset ratio in sample set is formed into training set, by temporal signatures, the frequency domain of sample each in the training set
Feature and nonlinear characteristic and the corresponding label of each sample are input to the neural network model, to the neural network mould
Type is trained.
6. according to the method described in claim 5, it is characterized in that, the time domain by sample each in the training set is special
Sign, frequency domain character and nonlinear characteristic and the corresponding label of each sample are input to the neural network model, to the mind
After being trained through network model, further includes:
Sample other than training set described in the sample set is formed into test set, by the time domain of sample each in the test set
Feature, frequency domain character and nonlinear characteristic and the corresponding label of each sample are input to the neural network model, to described
Neural network model is tested.
7. a kind of assessment system of auricular fibrillation characterized by comprising mobile intelligent terminal, pulse wave obtain module, RR
Interphase extraction module and auricular fibrillation evaluation module；
The pulse wave obtains module, obtains pulse wave for the camera based on mobile intelligent terminal；
The RR interphase extraction module, for extracting preset quantity RR interphase based on the pulse wave, by the present count
It measures a RR interphase and forms RR interval series；
The auricular fibrillation evaluation module is exported for the RR interval series to be input to the neural network model trained
The probability of auricular fibrillation.
8. system according to claim 7, which is characterized in that the system also includes pulse waves to denoise module；
The pulse wave denoises module, for carrying out denoising to the pulse wave.
9. a kind of assessment equipment of auricular fibrillation characterized by comprising
At least one processor, at least one processor and communication bus；Wherein:
The processor and the memory complete mutual communication by the communication bus；The memory is stored with can
The program instruction executed by the processor, the processor call described program instruction to execute as claim 1 to 6 is any
The method.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer program is stored up, the computer program makes the computer execute the method as described in claim 1 to 6 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810785816.8A CN109199343A (en) | 2018-07-17 | 2018-07-17 | A kind of appraisal procedure of auricular fibrillation, system and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810785816.8A CN109199343A (en) | 2018-07-17 | 2018-07-17 | A kind of appraisal procedure of auricular fibrillation, system and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109199343A true CN109199343A (en) | 2019-01-15 |
Family
ID=64989994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810785816.8A Pending CN109199343A (en) | 2018-07-17 | 2018-07-17 | A kind of appraisal procedure of auricular fibrillation, system and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109199343A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112603327A (en) * | 2019-12-18 | 2021-04-06 | 华为技术有限公司 | Electrocardiosignal detection method, device, terminal and storage medium |
| CN113598742A (en) * | 2021-06-30 | 2021-11-05 | 合肥工业大学 | Atrial fibrillation classification model training method, atrial fibrillation identification method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103340622A (en) * | 2013-07-01 | 2013-10-09 | 上海理工大学 | Atrial fibrillation automatic detection system based on smartphone |
| US8768438B2 (en) * | 2012-06-25 | 2014-07-01 | Xerox Corporation | Determining cardiac arrhythmia from a video of a subject being monitored for cardiac function |
| CN106073755A (en) * | 2016-05-27 | 2016-11-09 | 成都信汇聚源科技有限公司 | The implementation method that in a kind of miniature holter devices, atrial fibrillation identifies automatically |
| CN106108889A (en) * | 2016-07-20 | 2016-11-16 | 杨平 | Electrocardiogram classification method based on degree of depth learning algorithm |
-
2018
- 2018-07-17 CN CN201810785816.8A patent/CN109199343A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8768438B2 (en) * | 2012-06-25 | 2014-07-01 | Xerox Corporation | Determining cardiac arrhythmia from a video of a subject being monitored for cardiac function |
| CN103340622A (en) * | 2013-07-01 | 2013-10-09 | 上海理工大学 | Atrial fibrillation automatic detection system based on smartphone |
| CN106073755A (en) * | 2016-05-27 | 2016-11-09 | 成都信汇聚源科技有限公司 | The implementation method that in a kind of miniature holter devices, atrial fibrillation identifies automatically |
| CN106108889A (en) * | 2016-07-20 | 2016-11-16 | 杨平 | Electrocardiogram classification method based on degree of depth learning algorithm |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112603327A (en) * | 2019-12-18 | 2021-04-06 | 华为技术有限公司 | Electrocardiosignal detection method, device, terminal and storage medium |
| CN113598742A (en) * | 2021-06-30 | 2021-11-05 | 合肥工业大学 | Atrial fibrillation classification model training method, atrial fibrillation identification method and system |
| CN113598742B (en) * | 2021-06-30 | 2024-03-22 | 合肥工业大学 | Atrial fibrillation classification model training method, atrial fibrillation identification method and atrial fibrillation classification model training system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nogueira et al. | Classifying heart sounds using images of motifs, MFCC and temporal features | |
| JP6786536B2 (en) | Cascade binary classifier to identify rhythms in Faraday paradoxical (ECG) signals | |
| CN109171712B (en) | Atrial fibrillation identification method, atrial fibrillation identification device, atrial fibrillation identification equipment and computer readable storage medium | |
| CN106108889B (en) | Electrocardiogram classification method based on deep learning algorithm | |
| WO2019100560A1 (en) | Artificial intelligence self-learning-based automatic electrocardiography analysis method and apparatus | |
| Odinaka et al. | ECG biometrics: A robust short-time frequency analysis | |
| WO2019100565A1 (en) | Method and device for self-learning dynamic electrocardiography analysis employing artificial intelligence | |
| US8433398B2 (en) | Signal analysis system for heart condition determination | |
| CN108186011A (en) | Atrial fibrillation detection method, device and readable storage medium storing program for executing | |
| Li et al. | Ventricular ectopic beat detection using a wavelet transform and a convolutional neural network | |
| CN112603332A (en) | Emotion cognition method based on electroencephalogram signal characteristic analysis | |
| CN109893118A (en) | A kind of electrocardiosignal classification diagnosis method based on deep learning | |
| CN110037668A (en) | The system that pulse signal time-space domain binding model judges age, health status and malignant arrhythmia identification | |
| WO2021184803A1 (en) | Blood pressure classification method and apparatus | |
| CN112568886A (en) | Detection method of heart rhythm, electronic device and computer readable storage medium | |
| CN109199343A (en) | A kind of appraisal procedure of auricular fibrillation, system and equipment | |
| WO2021164347A1 (en) | Method and apparatus for predicting blood pressure | |
| CN109106345A (en) | Pulse signal characteristic detection method and device | |
| Donoso et al. | Atrial activity selection for atrial fibrillation ECG recordings | |
| CN109091142A (en) | A kind of method, apparatus and storage medium detecting the endogenous fatigue degree of muscle | |
| CN113679369B (en) | Evaluation method of heart rate variability, intelligent wearable device and storage medium | |
| Chou et al. | Modelling arterial blood pressure waveforms for extreme bradycardia and tachycardia by curve fitting with Gaussian functions | |
| JP2023505111A (en) | Systems and methods for physiological measurements from optical data | |
| Wang et al. | Modeling and analysis of cardioimpedance signals using polynomial models and fuzzy rule-based models | |
| CN109567743A (en) | A kind of signal reconfiguring method based on EMD, device, terminal device 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |