CN110236522A - Human health screening method, system and Medical Devices based on single lead electrocardiogram - Google Patents
Human health screening method, system and Medical Devices based on single lead electrocardiogram Download PDFInfo
- Publication number
- CN110236522A CN110236522A CN201910454467.6A CN201910454467A CN110236522A CN 110236522 A CN110236522 A CN 110236522A CN 201910454467 A CN201910454467 A CN 201910454467A CN 110236522 A CN110236522 A CN 110236522A
- Authority
- CN
- China
- Prior art keywords
- characteristic
- single lead
- data
- lead electrocardiogram
- health
- 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
- A61B5/24—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
-
- 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
- A61B5/7246—Details of waveform analysis using correlation, e.g. template matching or determination of similarity
-
- 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
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The present invention relates to medical system technical fields, disclose a kind of human health screening method, system and Medical Devices based on single lead electrocardiogram.The human health screening method based on single lead electrocardiogram includes: to acquire the single lead electrocardiogram of user；Analyze the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of acquisition；The characteristic of the pRRx sequence of analysis and health detection model trained in advance are subjected to characteristic matching；And the health detection data of user are generated according to the result of characteristic matching.The present invention can based on it is portable can real-time monitoring cardioelectric monitor equipment and human health screening method, daily monitoring can be carried out to user and does human health screening, be conducive to find the potential serious disease risk of user in time, remind user that hospital is gone to do corresponding inspection, diagnosis and treatment in time in time.
Description
Technical field
The present invention relates to technical field of medical equipment more particularly to a kind of human health screening sides based on single lead electrocardiogram
Method, system and Medical Devices.
Background technique
The health detection of Hospitals at Present and the process complexity of diagnosis are cumbersome, it usually needs are individually lined up and carry out multiple projects
Routine inspection such as draws blood, electrocardiogram etc., convenience, comfort, working efficiency and the user experience of entire health data detection
It is bad.And the not high user of the health examination frequency is easy to omit illness, and miss the best opportunity of prevention and treatment.
Summary of the invention
In consideration of it, the present invention provides a kind of human health screening method, system and Medical Devices based on single lead electrocardiogram, solution
The convenience of certainly existing health examination, comfort, working efficiency and the bad technical problem of user experience.
According to an embodiment of the present invention, a kind of human health screening method based on single lead electrocardiogram is provided, comprising: acquisition
The single lead electrocardiogram of user；Analyze the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of acquisition；It will analysis
The characteristic of pRRx sequence carry out characteristic matching with health detection model trained in advance；And the knot according to characteristic matching
The health detection data of fruit generation user.
Preferably, the human health screening method based on single lead electrocardiogram further includes trained health detection model,
Further comprise: the physiological parameter and corresponding single lead electrocardiogram of acquisition different user different time；Analyze the list of acquisition
The characteristic of lead electrocardiogram center telecommunications pRRx sequence；By training pattern algorithm to the physiological parameter of acquisition and right
The characteristic for the pRRx sequence that should be analyzed carries out machine learning and training, to generate the characteristic and physiology ginseng of pRRx sequence
The pattern function of number corresponding relationship；And the pattern function based on generation and the physiological parameter data of acquisition generate health detection mould
Type.
Preferably, after the health detection data for generating user according to the result of characteristic matching, further includes: obtain
Health monitoring data of the user in multiple times；The health monitoring data of the multiple times obtained are analyzed to obtain the health of user
Trend data；And it is reported according to the health monitoring data of acquisition and the health detection of healthy trend data acquisition user.
Preferably, the characteristic of the pRRx sequence is that linear character and entropy nonlinear characteristic, fractal dimension are non-thread
Property one of feature or combination, wherein the linear character is the average value of pRRx sequence, standard deviation, flanking sequence difference
One of the standard deviation or combination of root mean square, flanking sequence difference, the fractal dimension nonlinear characteristic are that pRRx sequence is straight
In square distributed intelligence entropy, pRRx sequence power spectrum histogram distributed intelligence entropy and pRRx sequence power spectrum full frequency band distributed intelligence entropy
A kind of or combination, the fractal dimension nonlinear characteristic are that structure function method calculates resulting fractal dimension, correlation function algorithm meter
Calculate resulting fractal dimension, variate-difference method calculates resulting fractal dimension and mean square root method calculates one of resulting fractal dimension
Or combination.
Preferably, the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of the analysis acquisition, comprising: meter
The difference for calculating the adjacent pRRx sequence of single lead electrocardiogram center telecommunications number of acquisition is adjacent with whole greater than threshold value x milliseconds of quantity
The ratio of the quantity of pRRx sequence；And the corresponding ratio shape of each threshold value x is obtained by the way that the different threshold value x of setting value is corresponding
At pRRx sequence.
According to another embodiment of the invention, a kind of human health screening system based on single lead electrocardiogram is also provided, is wrapped
It includes: electrocardiogram acquisition device, for acquiring the single lead electrocardiogram of user；Feature analyzing apparatus, for analyzing the electrocardiogram
The characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of acquisition device acquisition；Characteristic matching device is used for institute
The health of the characteristic and the training in advance of health detection training pattern device of stating the pRRx sequence of feature analyzing apparatus analysis is examined
It surveys model and carries out characteristic matching；And detection data generating means, for according to the matched knot of characteristic matching device characteristic
The health detection data of fruit generation user.
Preferably, the health data detection system based on single lead electrocardiogram further includes health detection training pattern
Device, further comprising: data acquisition unit, for acquire different user different time physiological parameter and corresponding list
Lead electrocardiogram；Data analysis unit, for analyzing the single lead electrocardiogram center telecommunications number of the data acquisition unit acquisition
The characteristic of pRRx sequence；Pattern function training unit, for being adopted by training pattern algorithm to the data acquisition unit
The characteristic of the physiological parameter of collection and the pRRx sequence of the data analysis unit correspondence analysis carries out machine learning and instruction
Practice, to generate the characteristic of pRRx sequence and the pattern function of physiological parameter corresponding relationship；And health detection model generates
Unit, the physiology ginseng of pattern function and data acquisition unit acquisition for being generated based on the pattern function training unit
Number data generate health detection model.
Preferably, the health data detection system based on single lead electrocardiogram further includes that examining report generates dress
It sets, further comprising: data capture unit, for obtaining user in the health monitoring data of multiple times；Trend analysis list
Member, for analyzing the health monitoring data for multiple times that the data capture unit obtains to obtain the healthy trend number of user
According to；And examining report generation unit, health monitoring data and the trend for being obtained according to the data capture unit
The health detection report of the healthy trend data acquisition user of analytical unit analysis.
Preferably, the characteristic of the pRRx sequence is that linear character and entropy nonlinear characteristic, fractal dimension are non-thread
Property one of feature or combination, wherein the linear character is the average value of pRRx sequence, standard deviation, flanking sequence difference
One of the standard deviation or combination of root mean square, flanking sequence difference, the fractal dimension nonlinear characteristic are that pRRx sequence is straight
In square distributed intelligence entropy, pRRx sequence power spectrum histogram distributed intelligence entropy and pRRx sequence power spectrum full frequency band distributed intelligence entropy
A kind of or combination, the fractal dimension nonlinear characteristic are that structure function method calculates resulting fractal dimension, correlation function algorithm meter
Calculate resulting fractal dimension, variate-difference method calculates resulting fractal dimension and mean square root method calculates one of resulting fractal dimension
Or combination.
Another embodiment according to the present invention, also provides a kind of Medical Devices, the Medical Devices include it is above-mentioned based on
The human health screening system of single lead electrocardiogram.
Human health screening method, system and Medical Devices provided by the invention based on single lead electrocardiogram, acquire user's
Single lead electrocardiogram；Analyze the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of acquisition；By the pRRx of analysis
The characteristic of sequence carries out characteristic matching with health detection model trained in advance；And it is generated according to the result of characteristic matching
The health detection data of user.The present invention can based on it is portable can real-time monitoring cardioelectric monitor equipment and human health screening method,
Daily monitoring can be carried out to user and does human health screening, be conducive to find the potential serious disease risk of user in time, reminded user
Hospital is gone to do corresponding inspection, diagnosis and treatment in time in time.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described.It should be evident that drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the flow diagram of the human health screening method based on single lead electrocardiogram in one embodiment of the invention.
Fig. 2 is the flow diagram that the characteristic of pRRx sequence is analyzed in one embodiment of the invention.
Fig. 3 is the flow diagram of training health detection model in one embodiment of the invention.
Fig. 4 is the flow diagram that the health detection report of user is generated in one embodiment of the invention.
Fig. 5 is the structural representation of the health data detection system based on single lead electrocardiogram in another embodiment of the present invention
Figure.
Fig. 6 is the structural schematic diagram of health detection training pattern device in another embodiment of the present invention.
Fig. 7 is the structural schematic diagram of examining report generating means in another embodiment of the present invention.
Fig. 8 is the structural schematic diagram of Medical Devices in further embodiment of the present invention.
Specific embodiment
Further more detailed description is made to technical solution of the present invention with reference to the accompanying drawings and detailed description.It is aobvious
So, described embodiment is only a part of the embodiments of the present invention, instead of all the embodiments.Based in the present invention
Embodiment, those of ordinary skill in the art's every other embodiment obtained without creative labor,
It all should belong to the scope of protection of the invention.
In the description of the present invention, it is to be understood that, term " first ", " second " etc. are used for description purposes only, without
It can be interpreted as indication or suggestion relative importance.In the description of the present invention, it should be noted that unless otherwise specific regulation
And restriction, term " connected ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection,
Or it is integrally connected；It can be mechanical connection, be also possible to be electrically connected；It can be directly connected, intermediary can also be passed through
It is indirectly connected.For the ordinary skill in the art, above-mentioned term can be understood in the present invention in conjunction with concrete condition
Concrete meaning.In addition, in the description of the present invention, unless otherwise indicated, the meaning of " plurality " is two or more.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Fig. 1 is the process signal of the health data detection method based on single lead electrocardiogram in one embodiment of the invention
Figure.As shown, the human health screening method based on single lead electrocardiogram, comprising:
Step S101: the single lead electrocardiogram of user is acquired.
In the present embodiment, when needing to carry out health data detection to user, general single lead electrocardio letter can be selected
The single lead electrocardiogram of number acquisition equipment acquisition user, collection process is simple and hurtless measure, carries out each project without being lined up
Routine inspection improves convenience, comfort, working efficiency and the user experience of health examination.
Step S102: the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of acquisition is analyzed.
In the present embodiment, the characteristic for the single lead electrocardiogram center telecommunications pRRx sequence that further analysis acquires
According to.Referring to fig. 2, the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of the analysis acquisition, comprising:
Step S201: the difference for calculating the adjacent pRRx sequence of single lead electrocardiogram center telecommunications number of acquisition is greater than threshold value x milli
The quantity of second and all ratio of the quantity of adjacent pRRx sequences.
Step S202: pRRx sequence is formed by the corresponding corresponding ratio of each threshold value x that obtains of the different threshold value x of setting value
Column.
In the present embodiment, the difference for calculating the adjacent pRRx sequence of single lead electrocardiogram center telecommunications number of acquisition first is greater than
Then the ratio of the quantity of the quantity and whole adjacent pRRx sequences that x millisecond of threshold value is obtained by the different threshold value x correspondence of setting value
It takes the corresponding ratio of each threshold value x and forms pRRx sequence, its calculation formula is:
In the present embodiment, the characteristic of the pRRx sequence is linear character and entropy nonlinear characteristic, FRACTAL DIMENSION
One of number nonlinear characteristic or combination.
The linear character is the average value AVRR of pRRx sequence, the root mean square of standard deviation SDRR, flanking sequence difference
RMSSD, one of the standard deviation SDSD of flanking sequence difference or combination.
The fractal dimension nonlinear characteristic is pRRx sequence histogram distributed intelligence entropy, the spectrum histogram distribution of pRRx sequence power
One of comentropy and pRRx sequence power spectrum full frequency band distributed intelligence entropy or combination.
For the stochastic variable collection A of probability-distribution function p (x), shown in the definition of entropy such as formula (2):
H (A)=- ∑ pA(x)logpA(x) (2)
The feature that can be obtained includes:
(1) pRRx sequence histogram distributed intelligence entropy SdhIt is the numeric distribution comentropy to pRRx sequence；
(2) pRRx sequence power composes histogram distributed intelligence entropy SphIt is to carry out discrete Fourier transform to pRRx sequence to obtain function
Rate spectrum, then calculates its comentropy according to the numeric distribution of power spectrum sequence；
(3) pRRx sequence power composes full frequency band distributed intelligence entropy SpfIt is to carry out discrete Fourier transform to pRRx sequence to obtain
Power spectrum, in full frequency band [fs/ N, fs/ 2] (sample frequency of signal is fs, sampling number N) and i-1 branch f of interior insertion1,
f2..., fm-1, full frequency band is divided into i frequency sub-band.Using the sum of power density in each frequency range as the power of the frequency range
Density then obtains m power density.This i power density is normalized to obtain the Probability p of each frequency range appearancei, then ∑ipi=
1, shown in corresponding power spectrum full frequency band entropy such as formula (3):
In the present embodiment, the fractal dimension nonlinear characteristic is that structure function method calculates resulting fractal dimension, phase
It closes function method and calculates resulting fractal dimension, the resulting fractal dimension of variate-difference method calculating and the resulting FRACTAL DIMENSION of mean square root method calculating
One of number or combination.
In the present embodiment, nonlinear analysis is carried out to the pRRx sequence of every section of electrocardiosignal, following four can also be used
The kind available following characteristic index of fractal dimension calculation and analysis methods:
(1) structure function method calculates resulting fractal dimension Dsf, wherein structure function method refers to for given sequence z
(x), defining increment variance is structure function, relationship are as follows:
For several scales τ, corresponding S (τ) is calculated to the discrete value of sequence z (x), then draws logS (τ)-
The function curve of log τ carries out linear fit in non-scaling section, obtains slope, then correspond to fractal dimension DsfWith the conversion of slope
Shown in relationship such as formula (5):
(2) correlation function algorithm calculates resulting fractal dimension Dcf, wherein correlation function algorithm refers to for given sequence z
(x), correlation function C (τ) is defined as shown in formula (6):
C (τ)=AVE (z (x+ τ) * z (x)), τ=1,2,3 ..., N-1 (6)
Wherein, AVE () indicates average, and τ indicates two o'clock distance.Correlation function is power type at this time, since there is no feature
Length is then distributed as a point shape, there is C (τ) α τ-α.At this moment, the function curve for drawing logC (τ)-log τ carries out line in non-scaling section
Property fitting, obtain slope, then correspond to fractal dimension DcfShown in transforming relationship such as formula (7) with slope:
Dcf=2- α (7)
(3) variate-difference method calculates resulting fractal dimension Dvm, wherein the rectangle frame that variate-difference method is τ with width is end to end to incite somebody to action
Fractal curve covers, and the difference of the maximum value and minimum value that enable i-th of frame inner curve is H (i), the as height of rectangle.It will
The height and width of all rectangles are multiplied to obtain gross area S (τ).The size for changing τ, obtains a series of S (τ).As shown in formula (8):
The function curve for drawing log N (τ)-log τ carries out linear fit in non-scaling section and obtains slope, then and corresponding point
Shape dimension DvmShown in transforming relationship such as formula (7) with slope.
(4) mean square root method calculates resulting fractal dimension Drms, wherein mean square root method with width be τ rectangle frame it is end to end
Fractal curve is covered, the difference of the maximum value and minimum value that enable i-th of frame inner curve is H (i), the as height of rectangle
Degree.Calculate the root-mean-square value S (τ) of these rectangular elevations.The size for changing τ, obtains a series of S (τ).Draw log S (τ)-
The function curve of log τ carries out linear fit in non-scaling section and obtains slope, then corresponds to fractal dimension DrmsWith turning for slope
Shown in change relationship such as formula (7).
Step S103: the characteristic of the pRRx sequence of analysis and health detection model trained in advance are subjected to feature
Match.
Referring to Fig. 3, before carrying out characteristic matching, need to train health detection model in advance.The trained health detection
Model, comprising:
Step S301: the physiological parameter and corresponding single lead electrocardiogram of acquisition different user different time.
Step S302: the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of acquisition is analyzed.
Step S303: by training pattern algorithm to the feature of the physiological parameter of acquisition and the pRRx sequence of correspondence analysis
Data carry out machine learning and training, to generate the characteristic of pRRx sequence and the pattern function of physiological parameter corresponding relationship.
Step S304: the physiological parameter data of pattern function and acquisition based on generation generates health detection model.
In the present embodiment, acquire first different user different time physiological parameter and corresponding single lead electrocardio
Then figure analyzes the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of acquisition, then passes through training pattern algorithm
The characteristic of the pRRx sequence of physiological parameter and correspondence analysis to acquisition carries out machine learning and training, to generate pRRx
The characteristic of sequence and the pattern function of physiological parameter corresponding relationship, are based ultimately upon the pattern function of generation and the physiology of acquisition
Supplemental characteristic generates health detection model.
Wherein, the physiological parameter includes but is not limited to: age, gender, medical history, blood glucose, body mass index, blood pressure, urine are normal
Rule, blood potassium, hemoglobin, blood routine, serum creatinine, blood lipid, uric acid, hemodynamic monitoring result, echocardiogram or neck
Artery ultrasound, Urine proteins, dried flank meat piece, electrocardiogram, eyeground, smoking history, intracardiac electrophysiology inspection result, Coronary Angiography,
Disease type, stage, complication quantity and severity etc..
After analysis gets characteristic and the health detection model of user, further by the characteristic of analysis acquisition
Characteristic matching is carried out with health detection model trained in advance.Specifically, all characteristics that analysis is obtained are item by item and in advance
First all feature templates in trained health detection model carry out similarity mode, when discovery specific feature data and wherein one
When a feature templates similarity is more than preset threshold, the two characteristic matching success is judged, otherwise the failure of both judgements characteristic matching.
Step S104: the health detection data of user are generated according to the result of characteristic matching.
In the present embodiment, when the characteristic of analysis acquisition and special characteristic mould in health detection model trained in advance
When plate matches, according to the characteristic of the health detection model center electric signal pRRx sequence and physiological parameter corresponding relationship
Pattern function, the corresponding physiological parameter data of the exportable special characteristic template and the detection for generating active user's health
Data can be assessed conveniently and efficiently based on health detection data, to the health status of user, to there is the case where disease risks
Screening is carried out, reminds user to see a doctor in time and makes a definite diagnosis and treated in the best opportunity.
Referring to fig. 4, in further embodiments, on the basis of the above embodiments, the health of user can further be generated
Examining report.The health detection report for generating user, comprising:
Step S401: user is obtained in the health monitoring data of multiple times.
Step S402: the health monitoring data of multiple times of acquisition are analyzed to obtain the healthy trend data of user.
Step S403: it is reported according to the health monitoring data of acquisition and the health detection of healthy trend data acquisition user.
In the present embodiment, single lead electrocardiogram detection can be carried out in multiple times for same user, obtains user and exists
The health monitoring data of multiple times analyze the health monitoring data of multiple times of acquisition to obtain the healthy trend number of user
According to, and reported according to the health monitoring data of acquisition and the health detection of healthy trend data acquisition user, it can be based on portable
Can real-time monitoring cardioelectric monitor equipment and human health screening method, daily monitoring can be carried out to user and do human health screening, is had
Conducive to the timely discovery potential serious disease risk of user, remind user that hospital is gone to do corresponding inspection, diagnosis and treatment in time in time.
Fig. 5 is the structural representation of the health data detection system based on single lead electrocardiogram in another embodiment of the present invention
Figure.Based on above method embodiment, the health data detection system 100 based on single lead electrocardiogram of the present embodiment, including the heart
Electrograph acquisition device 10, feature analyzing apparatus 20, characteristic matching device 30 and detection data generating means 40.
In the present embodiment, when needing to carry out health data detection to user, the electrocardiogram acquisition device can be passed through
The single lead electrocardiogram of 10 such as general single lead ecg signal acquiring equipment acquisition users, collection process are simple and noninvasive
Wound improves convenience, comfort, working efficiency and the use of health examination without being lined up the routine inspection for carrying out each project
Family experience.
In the present embodiment, the feature analyzing apparatus 20 further analyzes the list that the electrocardiogram acquisition device 10 acquires
The characteristic of lead electrocardiogram center telecommunications pRRx sequence.The feature analyzing apparatus 20 includes the list for calculating acquisition first
The difference of the adjacent pRRx sequence of lead electrocardiogram center telecommunications number number of adjacent pRRx sequence greater than threshold value x milliseconds of quantity and all
Then the ratio of amount forms pRRx sequence by the corresponding corresponding ratio of each threshold value x that obtains of the different threshold value x of setting value,
Its calculation formula is:
In the present embodiment, the characteristic of the pRRx sequence is linear character and entropy nonlinear characteristic, FRACTAL DIMENSION
One of number nonlinear characteristic or combination.
The linear character is the average value AVRR of pRRx sequence, the root mean square of standard deviation SDRR, flanking sequence difference
RMSSD, one of the standard deviation SDSD of flanking sequence difference or combination.
The fractal dimension nonlinear characteristic is pRRx sequence histogram distributed intelligence entropy, the spectrum histogram distribution of pRRx sequence power
One of comentropy and pRRx sequence power spectrum full frequency band distributed intelligence entropy or combination.
For the stochastic variable collection A of probability-distribution function p (x), shown in the definition of entropy such as formula (2):
H (A)=- ∑ pA(x)log pA(x) (2)
The feature that can be obtained includes:
(4) pRRx sequence histogram distributed intelligence entropy SdhIt is the numeric distribution comentropy to pRRx sequence；
(5) pRRx sequence power composes histogram distributed intelligence entropy SphIt is to carry out discrete Fourier transform to pRRx sequence to obtain function
Rate spectrum, then calculates its comentropy according to the numeric distribution of power spectrum sequence；
(6) pRRx sequence power composes full frequency band distributed intelligence entropy SpfIt is to carry out discrete Fourier transform to pRRx sequence to obtain
Power spectrum, in full frequency band [fs/ N, fs/ 2] (sample frequency of signal is fs, sampling number N) and i-1 branch f of interior insertion1,
f2..., fm-1, full frequency band is divided into i frequency sub-band.Using the sum of power density in each frequency range as the power of the frequency range
Density then obtains m power density.This i power density is normalized to obtain the Probability p of each frequency range appearancei, then ∑ipi=
1, shown in corresponding power spectrum full frequency band entropy such as formula (3):
In the present embodiment, the fractal dimension nonlinear characteristic is that structure function method calculates resulting fractal dimension, phase
It closes function method and calculates resulting fractal dimension, the resulting fractal dimension of variate-difference method calculating and the resulting FRACTAL DIMENSION of mean square root method calculating
One of number or combination.
In the present embodiment, nonlinear analysis is carried out to the pRRx sequence of every section of electrocardiosignal, following four can also be used
The kind available following characteristic index of fractal dimension calculation and analysis methods:
(5) structure function method calculates resulting fractal dimension Dsf, wherein structure function method refers to for given sequence z
(x), defining increment variance is structure function, relationship are as follows:
For several scales τ, corresponding S (τ) is calculated to the discrete value of sequence z (x), then draws log S (τ)-
The function curve of log τ carries out linear fit in non-scaling section, obtains slope, then correspond to fractal dimension DsfWith the conversion of slope
Shown in relationship such as formula (5):
(6) correlation function algorithm calculates resulting fractal dimension Dcf, wherein correlation function algorithm refers to for given sequence z
(x), correlation function C (τ) is defined as shown in formula (6):
C (τ)=AVE (z (x+ τ) * z (x)), τ=1,2,3 ..., N-1 (6)
Wherein, AVE () indicates average, and τ indicates two o'clock distance.Correlation function is power type at this time, since there is no feature
Length is then distributed as a point shape, there is C (τ) α τ-α.At this moment, the function curve for drawing log C (τ)-log τ carries out line in non-scaling section
Property fitting, obtain slope, then correspond to fractal dimension DcfShown in transforming relationship such as formula (7) with slope:
Dcf=2- α (7)
(7) variate-difference method calculates resulting fractal dimension Dvm, wherein the rectangle frame that variate-difference method is τ with width is end to end to incite somebody to action
Fractal curve covers, and the difference of the maximum value and minimum value that enable i-th of frame inner curve is H (i), the as height of rectangle.It will
The height and width of all rectangles are multiplied to obtain gross area S (τ).The size for changing τ, obtains a series of S (τ).As shown in formula (8):
The function curve for drawing log N (τ)-log τ carries out linear fit in non-scaling section and obtains slope, then and corresponding point
Shape dimension DvmShown in transforming relationship such as formula (7) with slope.
(8) mean square root method calculates resulting fractal dimension Drms, wherein mean square root method with width be τ rectangle frame it is end to end
Fractal curve is covered, the difference of the maximum value and minimum value that enable i-th of frame inner curve is H (i), the as height of rectangle
Degree.Calculate the root-mean-square value S (τ) of these rectangular elevations.The size for changing τ, obtains a series of S (τ).Draw log S (τ)-
The function curve of log τ carries out linear fit in non-scaling section and obtains slope, then corresponds to fractal dimension DrmsWith the conversion of slope
Shown in relationship such as formula (7).
It is needed before the characteristic matching device 30 carries out characteristic matching through health detection training pattern referring to Fig. 6
Device 50 trains health detection model in advance.The health detection training pattern device 50 includes data acquisition unit 501, data
Analytical unit 502, pattern function training unit 503 and health detection model generation unit 504.
In the present embodiment, first the data acquisition unit 501 acquire the physiological parameter of different user different time with
And corresponding single lead electrocardiogram, then the data analysis unit 502 analyzes singly leading for the acquisition of data acquisition unit 501
Join the characteristic of electrocardiogram center telecommunications pRRx sequence, the pattern function training unit 503 is calculated by training pattern again
The pRRx sequence for 502 correspondence analysis of physiological parameter and the data analysis unit that method acquires the data acquisition unit 501
The characteristic of column carries out machine learning and training, to generate the characteristic of pRRx sequence and the mould of physiological parameter corresponding relationship
Type function, the model letter that the final health detection model generation unit 504 is generated based on the pattern function training unit 503
The physiological parameter data of the several and data acquisition unit 501 acquisition generates health detection model.
Wherein, the physiological parameter includes but is not limited to: age, gender, medical history, blood glucose, body mass index, blood pressure, urine are normal
Rule, blood potassium, hemoglobin, blood routine, serum creatinine, blood lipid, uric acid, hemodynamic monitoring result, echocardiogram or neck
Artery ultrasound, Urine proteins, dried flank meat piece, electrocardiogram, eyeground, smoking history, intracardiac electrophysiology inspection result, Coronary Angiography,
Disease type, stage, complication quantity and severity etc..
After the feature analyzing apparatus 20 analysis gets characteristic and the health detection model of user, the feature
The characteristic and the health detection training pattern device that coalignment 30 further obtains the analysis of feature analyzing apparatus 20
The 50 health detection models trained in advance carry out characteristic matching.Specifically, the characteristic matching device 30 is by the signature analysis
Health of all characteristics that the analysis of device 20 obtains item by item with the health detection training pattern device 50 training in advance is examined
All feature templates surveyed in model carry out similarity mode, when discovery specific feature data is similar to one of feature templates
When degree is more than preset threshold, the two characteristic matching success is judged, otherwise the failure of both judgements characteristic matching.
In the present embodiment, when the characteristic that the characteristic matching device 30 obtains the feature analyzing apparatus 20 analysis
It is described according in the health detection model trained in advance with the health detection training pattern device 50 when special characteristic template matching
Detection data generating means 40 are according to the characteristic and physiological parameter of the health detection model center electric signal pRRx sequence
The pattern function of corresponding relationship, the corresponding physiological parameter data of the exportable special characteristic template and generate active user's body
The detection data of health, improves convenience, comfort, working efficiency and the user experience of human health screening.
In some embodiments, health detection is generated according to the result of characteristic matching in the detection data generating means 40
After data, when the detection data of generation exceeds default fence coverage, also further by text, voice or police can be jumped out
The modes such as report window remind detection data, in further embodiments, on the basis of the above embodiments, can be into one referring to Fig. 7
Step includes examining report generating means 70 comprising data capture unit 701, trend analysis unit 702 and examining report generate
Unit 703.
In the present embodiment, single lead electrocardiogram detection can be carried out in multiple times for same user, the data obtain
Unit 701 is taken to obtain health monitoring data of the user in multiple times, the trend analysis unit 702 analyzes the data acquisition
To obtain the healthy trend data of user, the examining report generates the health monitoring data for multiple times that unit 701 obtains
Unit 703 is reported according to health monitoring data and the health detection of healthy trend data acquisition user, can carry out day to user
Human health screening is often monitored and done, is conducive to find the potential serious disease risk of user in time, reminds user that hospital is gone to do accordingly in time
It checks, diagnose and treats in time.
Fig. 8 is the structural schematic diagram of Medical Devices in further embodiment of the present invention.As shown, the present invention is further implemented
Example also provides a kind of Medical Devices 200, and the Medical Devices 200 include strong based on single lead electrocardiogram in above-described embodiment
Health data detection system 100 can carry out daily monitoring to user and do human health screening, be conducive to find that user is potential in time
Serious disease risk reminds user that hospital is gone to do corresponding inspection, diagnosis and treatment in time in time.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The descriptions such as example " or " some examples " mean particular features, structures, materials, or characteristics described in conjunction with this embodiment or example
It is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are different
Surely identical embodiment or example is referred to.Moreover, particular features, structures, materials, or characteristics described can be any
It can be combined in any suitable manner in one or more embodiment or examples.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle of the present invention and objective, this
The range of invention is defined by the claims and their equivalents.
Claims (10)
1. a kind of human health screening method based on single lead electrocardiogram characterized by comprising
Acquire the single lead electrocardiogram of user；
Analyze the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of acquisition；
The characteristic of the pRRx sequence of analysis and health detection model trained in advance are subjected to characteristic matching；And
The health detection data of user are generated according to the result of characteristic matching.
2. the human health screening method according to claim 1 based on single lead electrocardiogram, which is characterized in that further include training
Health detection model, further comprising:
Acquire the physiological parameter and corresponding single lead electrocardiogram of different user different time；
Analyze the characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of acquisition；
Machine is carried out by characteristic of the training pattern algorithm to the physiological parameter of acquisition and the pRRx sequence of correspondence analysis
Study and training, to generate the characteristic of pRRx sequence and the pattern function of physiological parameter corresponding relationship；And
The physiological parameter data of pattern function and acquisition based on generation generates health detection model.
3. the health data detection method according to claim 1 or 2 based on single lead electrocardiogram, which is characterized in that
After the health detection data for generating user according to the result of characteristic matching, further includes:
User is obtained in the health monitoring data of multiple times；
The health monitoring data of the multiple times obtained are analyzed to obtain the healthy trend data of user；And
It is reported according to the health monitoring data of acquisition and the health detection of healthy trend data acquisition user.
4. the health data detection method according to claim 1 or 2 based on single lead electrocardiogram, which is characterized in that institute
The characteristic for stating pRRx sequence is one of linear character and entropy nonlinear characteristic, fractal dimension nonlinear characteristic or group
It closes, wherein the linear character is poor for average value, standard deviation, the root mean square of flanking sequence difference, the flanking sequence of pRRx sequence
One of standard deviation of value or combination, the fractal dimension nonlinear characteristic are pRRx sequence histogram distributed intelligence entropy, pRRx
Sequence power is composed one of histogram distributed intelligence entropy and pRRx sequence power spectrum full frequency band distributed intelligence entropy or is combined, described point
Shape dimension nonlinear characteristic calculates resulting fractal dimension for structure function method, correlation function algorithm calculates resulting fractal dimension,
Variate-difference method calculates resulting fractal dimension and mean square root method calculates one of resulting fractal dimension or combination.
5. the human health screening method according to claim 1 based on single lead electrocardiogram, which is characterized in that the analysis is adopted
The characteristic of the single lead electrocardiogram center telecommunications pRRx sequence of collection, comprising:
The difference for calculating the adjacent pRRx sequence of single lead electrocardiogram center telecommunications number of acquisition is greater than threshold value x milliseconds of quantity and whole
The ratio of the quantity of adjacent pRRx sequence；And
PRRx sequence is formed by the corresponding corresponding ratio of each threshold value x that obtains of the different threshold value x of setting value.
6. a kind of human health screening system based on single lead electrocardiogram characterized by comprising
Electrocardiogram acquisition device, for acquiring the single lead electrocardiogram of user；
Feature analyzing apparatus, for analyzing the single lead electrocardiogram center telecommunications pRRx sequence of the electrocardiogram acquisition device acquisition
The characteristic of column；
Characteristic matching device, characteristic and the health detection training of the pRRx sequence for analyzing the feature analyzing apparatus
The health detection model that model equipment is trained in advance carries out characteristic matching；And
Detection data generating means, for generating the health detection of user according to the matched result of the characteristic matching device characteristic
Data.
7. the human health screening system according to claim 6 based on single lead electrocardiogram, which is characterized in that further include health
Training pattern device is detected, further comprising:
Data acquisition unit, for acquiring the physiological parameter and corresponding single lead electrocardiogram of different user different time；
Data analysis unit, for analyzing the single lead electrocardiogram center telecommunications pRRx sequence of the data acquisition unit acquisition
Characteristic；
Pattern function training unit, physiological parameter for being acquired by training pattern algorithm to the data acquisition unit and
The characteristic of the pRRx sequence of the data analysis unit correspondence analysis carries out machine learning and training, to generate pRRx sequence
Characteristic and physiological parameter corresponding relationship pattern function；And
Health detection model generation unit, pattern function and the data for being generated based on the pattern function training unit
The physiological parameter data of acquisition unit acquisition generates health detection model.
8. the human health screening system according to claim 6 or 7 based on single lead electrocardiogram, which is characterized in that further include
Examining report generating means, further comprising:
Data capture unit, for obtaining user in the health monitoring data of multiple times；
Trend analysis unit, for analyzing the health monitoring data for multiple times that the data capture unit obtains to obtain use
The healthy trend data at family；And
Examining report generation unit, health monitoring data and the trend analysis for being obtained according to the data capture unit
The health detection report of the healthy trend data acquisition user of unit analysis.
9. the health data detection system according to claim 6 or 7 based on single lead electrocardiogram, which is characterized in that institute
The characteristic for stating pRRx sequence is one of linear character and entropy nonlinear characteristic, fractal dimension nonlinear characteristic or group
It closes, wherein the linear character is poor for average value, standard deviation, the root mean square of flanking sequence difference, the flanking sequence of pRRx sequence
One of standard deviation of value or combination, the fractal dimension nonlinear characteristic are pRRx sequence histogram distributed intelligence entropy, pRRx
Sequence power is composed one of histogram distributed intelligence entropy and pRRx sequence power spectrum full frequency band distributed intelligence entropy or is combined, described point
Shape dimension nonlinear characteristic calculates resulting fractal dimension for structure function method, correlation function algorithm calculates resulting fractal dimension,
Variate-difference method calculates resulting fractal dimension and mean square root method calculates one of resulting fractal dimension or combination.
10. a kind of Medical Devices, which is characterized in that the Medical Devices include being based on as claim 6 to 9 is described in any item
The human health screening system of single lead electrocardiogram.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910454467.6A CN110236522A (en) | 2019-05-28 | 2019-05-28 | Human health screening method, system and Medical Devices based on single lead electrocardiogram |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910454467.6A CN110236522A (en) | 2019-05-28 | 2019-05-28 | Human health screening method, system and Medical Devices based on single lead electrocardiogram |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110236522A true CN110236522A (en) | 2019-09-17 |
Family
ID=67885270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910454467.6A Pending CN110236522A (en) | 2019-05-28 | 2019-05-28 | Human health screening method, system and Medical Devices based on single lead electrocardiogram |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110236522A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103054572A (en) * | 2012-12-18 | 2013-04-24 | 太原理工大学 | Blind source separation method on basis of late potential signals of single-lead cardiac ventricle |
| CN106778685A (en) * | 2017-01-12 | 2017-05-31 | 司马大大（北京）智能系统有限公司 | Electrocardiogram image-recognizing method, device and service terminal |
| CN107203692A (en) * | 2017-05-09 | 2017-09-26 | 哈尔滨工业大学（威海） | The implementation method of atrial fibrillation detection based on depth convolutional neural networks |
| EP3248542A1 (en) * | 2016-05-27 | 2017-11-29 | Comarch Healthcare Spólka Akcyjna | Method for automatic detection of atrial fibrillation and flutter |
| CN108403107A (en) * | 2018-02-06 | 2018-08-17 | 北京大学深圳研究生院 | A kind of arrhythmia cordis method of discrimination and system |
| CN108652640A (en) * | 2018-02-06 | 2018-10-16 | 北京大学深圳研究生院 | A kind of Noninvasive Blood Glucose Detection Methods and system based on electrocardiosignal |
| CN108652614A (en) * | 2018-02-06 | 2018-10-16 | 北京大学深圳研究生院 | A kind of angiocardiopathy condition assessment method and system |
| GB201814620D0 (en) * | 2018-09-07 | 2018-10-24 | Transf Ai Ltd | Analysis of cardiac data |
| CN109691995A (en) * | 2019-01-31 | 2019-04-30 | 英菲泰克(天津)科技有限公司 | The arrhythmia cordis real-time data analysis system and method for single lead electrocardiogram |
-
2019
- 2019-05-28 CN CN201910454467.6A patent/CN110236522A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103054572A (en) * | 2012-12-18 | 2013-04-24 | 太原理工大学 | Blind source separation method on basis of late potential signals of single-lead cardiac ventricle |
| EP3248542A1 (en) * | 2016-05-27 | 2017-11-29 | Comarch Healthcare Spólka Akcyjna | Method for automatic detection of atrial fibrillation and flutter |
| CN106778685A (en) * | 2017-01-12 | 2017-05-31 | 司马大大（北京）智能系统有限公司 | Electrocardiogram image-recognizing method, device and service terminal |
| CN107203692A (en) * | 2017-05-09 | 2017-09-26 | 哈尔滨工业大学（威海） | The implementation method of atrial fibrillation detection based on depth convolutional neural networks |
| CN108403107A (en) * | 2018-02-06 | 2018-08-17 | 北京大学深圳研究生院 | A kind of arrhythmia cordis method of discrimination and system |
| CN108652640A (en) * | 2018-02-06 | 2018-10-16 | 北京大学深圳研究生院 | A kind of Noninvasive Blood Glucose Detection Methods and system based on electrocardiosignal |
| CN108652614A (en) * | 2018-02-06 | 2018-10-16 | 北京大学深圳研究生院 | A kind of angiocardiopathy condition assessment method and system |
| GB201814620D0 (en) * | 2018-09-07 | 2018-10-24 | Transf Ai Ltd | Analysis of cardiac data |
| CN109691995A (en) * | 2019-01-31 | 2019-04-30 | 英菲泰克(天津)科技有限公司 | The arrhythmia cordis real-time data analysis system and method for single lead electrocardiogram |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111133526B (en) | Novel features useful in machine learning techniques, such as machine learning techniques for diagnosing medical conditions | |
| US9974488B2 (en) | Early detection of hemodynamic decompensation using taut-string transformation | |
| Pecchia et al. | Remote health monitoring of heart failure with data mining via CART method on HRV features | |
| US8388530B2 (en) | Personalized monitoring and healthcare information management using physiological basis functions | |
| Sideris et al. | Building continuous arterial blood pressure prediction models using recurrent networks | |
| US20180233227A1 (en) | Systems and methods of analyte measurement analysis | |
| Saalasti | Neural networks for heart rate time series analysis | |
| CN108478209A (en) | Ecg information dynamic monitor method and dynamic monitor system | |
| US20020143263A1 (en) | System and device for multi-scale analysis and representation of physiological data | |
| Raj et al. | A personalized point-of-care platform for real-time ECG monitoring | |
| Catley et al. | Extending CRISP-DM to incorporate temporal data mining of multidimensional medical data streams: A neonatal intensive care unit case study | |
| WO2018060162A1 (en) | Monitoring of biosignals, in particular electrocardiograms | |
| Rueda et al. | Compelling new electrocardiographic markers for automatic diagnosis | |
| Jiang et al. | Continuous blood pressure estimation based on multi-scale feature extraction by the neural network with multi-task learning | |
| Mendonça et al. | A method for sleep quality analysis based on CNN ensemble with implementation in a portable wireless device | |
| CN109036552A (en) | Tcm diagnosis terminal and its storage medium | |
| CN115630290B (en) | Cardiopulmonary coupling feature extraction method and system based on synchronous extrusion transformation | |
| CN110428893A (en) | A kind of tele-medicine vital sign data acquisition device | |
| CN110236522A (en) | Human health screening method, system and Medical Devices based on single lead electrocardiogram | |
| Ma et al. | PPG-based continuous BP waveform estimation using polarized attention-guided conditional adversarial learning model | |
| Begum et al. | ECG sensor signal analysis to represent cases in a case-based stress diagnosis system | |
| Kim et al. | Reliability of the photoplethysmographic analysis using deep neural network (dnn) algorithm | |
| CN205866740U (en) | Acquire collection system of multidimension heartbeat information in step | |
| Li et al. | Noninvasive continuous blood pressure estimation algorithm based on features of pulse waves | |
| Raj | A real-time ECG-processing platform for telemedicine applications |
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: 20190917 |