CN109875547A - A kind of intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring system and method - Google Patents
A kind of intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring system and method Download PDFInfo
- Publication number
- CN109875547A CN109875547A CN201910128989.7A CN201910128989A CN109875547A CN 109875547 A CN109875547 A CN 109875547A CN 201910128989 A CN201910128989 A CN 201910128989A CN 109875547 A CN109875547 A CN 109875547A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- cardiovascular
- internal medicine
- acquisition
- 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
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention belongs to Internal Medicine-Cardiovascular Dept.s to nurse surveillance technology field, disclosing a kind of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system and method, the intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring system includes: electrocardiogram acquisition module, blood oxygen acquisition module, blood pressure acquisition module, central control module, health model building module, threshold value judgment module, condition assessment module, alarm modules, cloud service module, display module.The shortcomings that present invention constructs module for the combination of invasive attribute and noninvasive attribute by health model, and the healthy hierarchical mode for cardiovascular patient obtained, accuracy is higher, and efficiency is also higher, overcomes previous model foundation；Meanwhile the cardiovascular disease state of an illness and development trend can be assessed by condition assessment module in time, user experience is good, at low cost, easy to operate, realizes control progression of the disease convenient for cardiovascular patient.
Description
Technical field
The invention belongs to Internal Medicine-Cardiovascular Dept. nursing surveillance technology field more particularly to a kind of intelligent Internal Medicine-Cardiovascular Dept. nursing prisons
Viewing system and method.
Background technique
Heart is a hollow flesh sexual organ, positioned at the middle part in thoracic cavity, is divided into left and right two chambers by an interval, each
Chamber is divided into ventricle two parts of superposed atrium and lower part again.Atrium is collected into heart blood, and ventricular ejection goes out the heart.Ventricle
Inlet and outlet have a valve, guarantee blood one-way flow.Human body is under different physiological status, the metabolism of each organ-tissue
It is horizontal different, it is also different to the needs of blood flow.Cardiovascular activity can change the heart and arrange blood in the case where the nerve and body fluid of body are reconciled
Amount and peripheral resistance, coordinate the Blood flow distribution between each organ-tissue, to meet each organ-tissue to the needs of blood flow.Painstaking effort
Pipe is made of the heart and blood vessel, and blood vessel includes artery, vein and capillary again.However, existing Internal Medicine-Cardiovascular Dept. nursing process
Is expended to cardiovascular detection process, obtained result index is few, causes result not accurate enough the time；Meanwhile Bu Nengji
When the cardiovascular state of an illness is assessed.
In conclusion problem of the existing technology is:
Existing Internal Medicine-Cardiovascular Dept. nursing process expends the time to cardiovascular detection process, and obtained result index is but not
It is more, cause result not accurate enough；Meanwhile the cardiovascular state of an illness cannot be assessed in time.
Data comparison low efficiency, operation of poor quality, system are slow in the prior art, reduce precision of analysis；It is existing
Have the delay of heterogeneous schemas and process of caching to data in technology in storage system, can not efficiently and accurately completion to acquisition
Data stored, reduce data storage accuracy；The clarity of electrocardiogram is poor in the prior art, is easy by spot
Influence of the noise to initial electrocardiogram, so that distortion, influences further medical judgment.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system and sides
Method.
The invention is realized in this way it is a kind of intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring method the following steps are included:
Step 1 acquires patient ECG's data using cardioelectric monitor equipment by electrocardiogram acquisition module；Pass through blood oxygen
Acquisition module acquires blood oxygen saturation data information using Oximetry instrument；It is acquired by blood pressure acquisition module using sphygmomanometer
Patient blood pressure data's information；
Step 2, central control module construct module by health model and utilize model construction program construction cardiovascular patient
Person's health hierarchical mode；
Step 3, by threshold value judgment module using data comparison procedures judgement acquisition data and set normal threshold value into
Row comparative analysis；
Step 4 utilizes appraisal procedure according to the electrocardiogram (ECG) data of acquisition to the cardiovascular disease state of an illness by condition assessment module
It is assessed；
Step 5 carries out timely alarm beyond threshold value and assessment result according to judgement using alarm device by alarm modules
Notice；
Step 6 by cloud service module using the data of Cloud Server storage acquisition, and concentrates big data computing resource
Acquisition data are handled；
Step 7, display module show the heart of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system interface and acquisition using display
Electrograph, blood oxygen saturation, blood pressure data information.
Further, the health model building module construction method includes:
(1) detection obtains the invasive attribute and noninvasive attribute of cardiovascular patient individual, and records enough individual
Data；
(2) the invasive attribute in above-mentioned steps is brought into disease prediction model, to obtain the assessment result to data；
(3) assessment result in the noninvasive attribute and step (2) in step (1) is saved to health evaluation model training
Collection；
(4) data in analytical calculation health evaluation model training set are to establish healthy hierarchical mode to be tested；
(5) using the extrapolation accuracy of the above-mentioned healthy hierarchical mode to be tested of data test detected in step (1), if
Extrapolation accuracy falls short of the target, then returns to (3) step and re-execute, until extrapolation accuracy touches the mark.
Further, the step (4) specifically: the data in analytical calculation health evaluation model training set, execution are based on
The data mining of machine learning is to establish healthy hierarchical mode to be tested.
Further, the condition assessment module estimation method includes:
1) electrocardiosignal is obtained by cardioelectric monitor equipment；It is described according to electrocardiosignal, obtain corresponding cardiovascular disease
Condition assessment result includes: that the one or more features index of electrocardiosignal is calculated according to electrocardiosignal, according to electrocardiosignal
Characteristic index obtains corresponding cardiovascular disease condition assessment result；
2) characteristic index of electrocardiosignal and the pattern function of cardiovascular disease state of an illness corresponding relationship are pre-established, by electrocardio
The characteristic index input model function of signal, obtains corresponding cardiovascular disease condition assessment result；
3) according to the electrocardiosignal, corresponding cardiovascular disease condition assessment result is obtained.
Further, the characteristic index of the electrocardiosignal, comprising: to the pRRx sequence of electrocardiosignal carry out linear analysis with
One or more linear characteristic indexs are obtained, and/or carry out nonlinear analysis, to obtain one or more nonlinear features
Index；Wherein the pRRx sequence of any one section of electrocardiosignal is calculated in the following manner: calculating phase in this section of electrocardiosignal
The ratio of the quantity of quantity of the difference of adjacent RR interphase greater than threshold value x milliseconds and whole RR interphase, passes through the different threshold value of setting value
X, obtains the corresponding ratio of each threshold value x, these ratios constitute the pRRx sequence；
The characteristic index that the linear analysis obtains: the standard deviation SDRR of mean value AVRR, the pRRx sequence of pRRx sequence,
In pRRx sequence in root mean square rMSSD, pRRx sequence of adjacent pRRx difference in the standard deviation SDSD of adjacent pRRx difference extremely
Few one；And/or
The nonlinear characteristic index includes carrying out the obtained characteristic index of Entropy Analysis Method to the pRRx sequence,
It include: pRRx sequence histogram distributed intelligence entropy Sdh, pRRx sequence power spectrum histogram distributed intelligence entropy Sph, pRRx sequence power spectrum
At least one of full frequency band distributed intelligence entropy Spf；And/or the nonlinear characteristic index include the pRRx sequence into
Row fractal dimension, which calculates, analyzes obtained characteristic index, comprising: structure function method calculates resulting fractal dimension D sf, correlation
Function method calculates resulting fractal dimension D cf, variate-difference method calculates resulting fractal dimension D vm, mean square root method calculates resulting point
At least one of shape dimension Drms.
Further, the model letter of the characteristic index for pre-establishing electrocardiosignal and cardiovascular disease state of an illness corresponding relationship
Number, comprising:
When obtaining the physiological parameter of different state of an illness stage cardiovascular patients in advance, and acquiring the physiological parameter pair
Electrocardiosignal before the time point answered；
Obtain the characteristic index of these electrocardiosignals；
Using the characteristic index of these electrocardiosignals and the corresponding physiological parameter of these electrocardiosignals as input, carry out
Machine learning obtains the characteristic index of electrocardiosignal and the pattern function of cardiovascular disease state of an illness corresponding relationship.
Further, display module shows the heart of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system interface and acquisition using display
Electrograph, blood oxygen saturation in blood pressure data information, carry out: 1) extracting the curve of spectrum of each pixel of high spectrum image；
2) color matching function of smoothed out curve of spectrum combination CIE1931 standard colorimetric system is calculated to CIEXYZ tri-
Values calculates the CIEXYZ tristimulus values of each pixel to homogeneous color aware space according to the white point of display equipment
Lightness, chroma and the tone of CIEL*C*h*, and demand setting brightness coefficient, chroma coefficient and tone coefficient are reappeared according to color；
3) modulated lightness, chroma and tone are combined to the gamma factor and primary colors tristimulus of display equipment triple channel
Value calculates to the digital drive values of each pixel, realizes that electrocardiogram, blood oxygen saturation, the blood pressure data of acquisition are shown.
Further, for each pixel of hyperspectral image data, spoke brightness value is calculated by the gray value of each spectral coverage, and
It is normalized and constitutes a curve of spectrum；
For the curve of spectrum that each pixel is obtained in step 1, smoothly located using Savitzky-Golay filter
Reason, eliminates spectral noise on the basis of retaining more curvilinear characteristic, obtains the smoothed out curve of spectrum of each pixel
Further, by obtained each smoothed out curve of spectrum of pixelIn conjunction with the color of CIE1931 standard colorimetric system
With functionCIEXYZ tristimulus values under CIE1931 standard colorimetric system is calculated to obtain using following formula
(X, Y, Z), wherein Δ λ is the spectrum sample interval of imaging spectral instrument；
According to the tristimulus values (X of standard illuminants D65D65,YD65,ZD65), step 3 is obtained by each pixel by following formula
CIEXYZ tristimulus values convert to homogeneous color aware space CIEL*C*h*, obtain three Color perception parameters, i.e. lightness
ChromaAnd tone h1；
Wherein,
XD65=95.047, YD65=100, ZD65=108.883；
Brightness coefficient k is setL, chroma coefficient kCWith tone coefficient khValue, each picture is obtained by following formula modulation step four
The lightness of elementChromaAnd tone h1, obtain modulated Color perception parameter, i.e. lightnessChromaAnd tone h2,
Effect of visualization is set to meet fidelity reproduction demand, then kL=kC=1, kh=0, change kLIt realizes the demand for adjusting image light and shade, changes
Become kCIt realizes the demand for adjusting the bright-coloured degree of image, changes khRealize the demand for adjusting image white balance；
According to the white point tristimulus values (X of display equipmentW,YW,ZW), by following formula, by the lightness of obtained each pixelIt is color
DegreeAnd tone h2It converts to CIEXYZ value (X', Y', Z') to be shown on the display device；
According to the primary colors tristimulus values (X of display equipment red, green, blue triple channelRmax,YRmax,ZRmax)、(XGmax,YGmax,
ZGmax、(XBmax,YBmax,ZBmax) in conjunction with the gamma factor γ of triple channelR、γG、γB, it is established that such as the characterization model of following formula,
By characterization model, the CIEXYZ value (X', Y', Z') for obtaining each pixel is calculated to corresponding digital drive values (dR,dG,dB),
The color visualization of high spectrum image is completed, wherein N is the display single pass storage bit number of equipment；
It uses each pixel to calculate spoke brightness value in the gray value of each spectral coverage to constitute the curve of spectrum, specifically includes following step
It is rapid:
The first step calibrates spectral imaging apparatus, and it is corresponding fixed to choose 5~10 calibration gray value D measurements
Spoke brightness value F is marked, parameter alpha, β, ε of following formula mapping expression formula are fitted using least square method, thus to the every of tested region
The gray value of each spectral coverage is substituted into following formula and calculates spoke brightness value by a pixel；
D=α Fβ+ε；
Second step, with maximum gradation value DmaxCorresponding spoke brightness value FmaxOn the basis of, by each pixel each spectral coverage spoke
Brightness value is normalized, and constitutes a curve of spectrum.
Another object of the present invention is to provide a kind of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring systems to include:
Electrocardiogram acquisition module, connect with central control module, for acquiring patient ECG by cardioelectric monitor equipment
Data；
Blood oxygen acquisition module is connect with central control module, for acquiring blood oxygen saturation number by Oximetry instrument
It is believed that breath；
Blood pressure acquisition module, connect with central control module, for acquiring patient blood pressure data's information by sphygmomanometer；
Central control module is constructed with electrocardiogram acquisition module, blood oxygen acquisition module, blood pressure acquisition module, health model
Module, threshold value judgment module, condition assessment module, alarm modules, cloud service module, display module connection, for passing through monolithic
Machine controls modules and works normally；
Health model constructs module, connect with central control module, for passing through model construction program construction cardiovascular disease
Patient health hierarchical mode；
Threshold value judgment module is connect with central control module, for judging acquisition data by data comparison procedures and setting
Fixed normal threshold value compares and analyzes；
Condition assessment module, connect with central control module, for the electrocardiogram (ECG) data pair by appraisal procedure according to acquisition
The cardiovascular disease state of an illness is assessed；
Alarm modules are connect with central control module, for the tying beyond threshold value and assessment according to judgement by alarm device
Fruit carries out timely alert notification；
Cloud service module, connect with central control module, for the data by Cloud Server storage acquisition, and concentrates big
Data computing resource handles acquisition data；
Display module is connect with central control module, for showing intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring by display
System interface and the electrocardiogram of acquisition, blood oxygen saturation, blood pressure data information.
Advantages of the present invention and good effect are as follows:
The present invention constructs module for the combination of invasive attribute and noninvasive attribute by health model, and what is obtained is directed to angiocarpy
The shortcomings that healthy hierarchical mode of patient, accuracy is higher, and efficiency is also higher, overcomes previous model foundation；Meanwhile it is logical
The cardiovascular disease state of an illness and development trend can be assessed in time by crossing condition assessment module, and user experience is good, at low cost, easy to operate,
Control progression of the disease is realized convenient for cardiovascular patient.
The present invention is using data comparison procedures judgement acquisition data and sets normal task of the threshold value based on ant group optimization
Load balance scheduling algorithm compares and analyzes, and improves and compares small efficiency and quality, and the efficient operation of promotion system improves analysis
As a result accuracy；The present invention reduced or remitted in such a way that Cloud Server is using caching distribution heterogeneous schemas in storage system and
Delay of the process of caching to data is efficiently completed to store the data of acquisition, improves the accuracy of storage；Of the invention is aobvious
Show that device is used based on the noise reduction filtering function in NSCT subband, model is constructed to electrocardiogram speckle noise, effectively improves electrocardiogram
Clarity, remove influence of the speckle noise to initial electrocardiogram.
The present invention is suitable for the multiple types such as display, television set, projector and shows that the high spectrum image of equipment was presented
Journey can effectively introduce the influence in terms of different display equipment room color parameters, keep distinct device aobvious with different digital driving value
Show identical Color perception parameter, efficiently solves the problems, such as that color effect of visualization is different because of equipment；Further it is proposed that
With lightness factor kL, chroma coefficient kCWith tone coefficient khThe method for adjusting Color perception parameter, can be by formulating to bright
The modulation requirement of the parameters such as degree, chroma, tone meets different types of color reproduction demand.The present invention is directed to high spectrum image
Color visualization is carried out, color reappears result and human eye visual perception consistency is good, and method implements simple, practical, strong applicability.
Detailed description of the invention
Fig. 1 is intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring method flow diagram provided in an embodiment of the present invention.
Fig. 2 is intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system structural block diagram provided in an embodiment of the present invention.
In figure: 1, electrocardiogram acquisition module；2, blood oxygen acquisition module；3, blood pressure acquisition module；4, central control module；5,
Health model constructs module；6, threshold value judgment module；7, condition assessment module；8, alarm modules；9, cloud service module；10, it shows
Show module.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description includes.
Existing Internal Medicine-Cardiovascular Dept. nursing process expends the time to cardiovascular detection process, and obtained result index is but not
It is more, cause result not accurate enough；Meanwhile the cardiovascular state of an illness cannot be assessed in time.
Data comparison low efficiency, operation of poor quality, system are slow in the prior art, reduce precision of analysis；It is existing
Have the delay of heterogeneous schemas and process of caching to data in technology in storage system, can not efficiently and accurately completion to acquisition
Data stored, reduce data storage accuracy；The clarity of electrocardiogram is poor in the prior art, is easy by spot
Influence of the noise to initial electrocardiogram, so that distortion, influences further medical judgment.
To solve the above problems, being explained in detail with reference to the accompanying drawing to structure of the invention.
As shown in Figure 1, it is provided by the invention intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring method the following steps are included:
S101 acquires patient ECG's data using cardioelectric monitor equipment；It is saturated using Oximetry instrument acquisition blood oxygen
The data information of degree；Patient blood pressure data's information is acquired using sphygmomanometer.
S102 utilizes model construction program construction cardiovascular patient health hierarchical mode.
S103 judges that acquisition data and task of the normal threshold value of setting based on ant group optimization are negative using data comparison procedures
Equalized scheduling algorithm is carried to compare and analyze.
S104 assesses the cardiovascular disease state of an illness according to the electrocardiogram (ECG) data of acquisition using appraisal procedure.
S105 carries out timely alert notification beyond threshold value and assessment result according to judgement using alarm device.
S106 stores the data of acquisition in such a way that Cloud Server is using caching distribution, and concentrates big data
Computing resource handles acquisition data.
S107 shows intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system interface and blood oxygen saturation, blood pressure number using display
It is believed that ceasing and using the electrocardiogram based on the noise reduction filtering function display acquisition in NSCT subband.
It is provided in an embodiment of the present invention normal using data comparison procedures judgement acquisition data and setting in step S103
Threshold value is compared and analyzed based on the task load equalized scheduling algorithm of ant group optimization, is improved to specific efficiency and quality, is promoted system
The efficient operation of system improves the accuracy of analysis result；The task load equalized scheduling algorithm of specific ant group optimization are as follows:
Equipped with n ant, the assigning process of task-set is indicated with the primary travelling of ant, the ant in the primary travelling of ant
Ant needs m to walk, and often make a move expression one task of distribution, material is thus formed the matrix of a n × m, step that ant is walked
Number is S；When the primary travelling of all ants completion, it is considered as algorithm circulation primary；The number of algorithm circulation is indicated with Nc；
Initial time, the pheromone amount that each intelligence Internal Medicine-Cardiovascular Dept. is nursed in monitoring system is equal, if
M is the number that intelligent Internal Medicine-Cardiovascular Dept. nurses monitoring system；
So ant k selects the probability of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system j completion task i are as follows:
Wherein, allowedkIndicate the set of the also non-selected intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system of ant；
τijIt (t) is intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system VMj in t moment pheromone concentration value,
LBij (t) is the load balancing factor for indicating VMj, for maintaining the negative of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system
It carries balanced；The load balancing factor LBij of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system is smaller, then selects in intelligence angiocarpy
Section nurse monitoring system execute next task probability it is higher, that is, the integration capability of VMj is stronger, and desired value is also
It is high；
The two coefficients of α, β indicate: the load journey of control pheromones and intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system
Weighted index and alpha+beta=1 shared by degree and the efficiency value of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system.
It is provided in an embodiment of the present invention to reduce or remit storage system in such a way that Cloud Server is using caching distribution in step S106
The delay of heterogeneous schemas and process of caching to data in system is efficiently completed to store the data of acquisition, improves storage
Accuracy；
When cache size is C, the average cache hit rate h ≈ C/Z of random access load, then one stores being averaged for equipment
Access delay TavgFor Tavg=h × Tcache+(1-h)×Tdisk
Wherein, TcacheIt is the delay that I/O requests access to caching, TdiskIt is the delay that I/O requests access to storage equipment；
The average access latency of Cloud Server can simplify as Tavg=(1-h) × Tdisk, by the caching of random access load
Hit rate expression formula h=C/Z substitutes into Tavg=h × Tcache+(1-h)×Tdisk, slow when acquisition Cloud Server access delay is equal
Deposit allocation plan, including formula:
In step S107, display provided in an embodiment of the present invention is used based on the noise reduction filtering function in NSCT subband,
Model, as the additive noise representation of Multiplicative noise model are constructed to electrocardiogram speckle noise, effectively improve the clear of electrocardiogram
Clear degree removes influence of the speckle noise to initial electrocardiogram, specifically:
gn=sn·un=sn+sn·(un- 1)=sn+sn·u'n=sn+vn
In formula: n indicates location of pixels,
gnIndicate the noisy acoustic image observed,
snIndicate muting ideal image,
unThe multiplying property speckle noise for being 1 for mean value,
vnNoise is determined for the equivalent additive signal of 0 mean value；
Coefficient is obtained after carrying out NSCT transformation to electrocardiogram according to the linear behavio(u)r that NSCT is converted are as follows:
In formula: subscript C indicates to carry out the transformed coefficient of NSCT；
In NSCT high-frequency sub-band, the probability density of the actual signal part in coefficient is indicated using laplacian distribution
Function, it may be assumed that
In formula: υ is the form parameter of broad sense laplacian distribution, and λ is scale parameter；The numerical value of distribution parameter υ and λ can be by
Each sub-band coefficients data are calculated.
In embodiments of the present invention, display module shows that intelligent Internal Medicine-Cardiovascular Dept. nurses monitoring system interface using display
And acquisition electrocardiogram, blood oxygen saturation, in blood pressure data information, carry out: 1) extract the spectrum of each pixel of high spectrum image
Curve；
2) color matching function of smoothed out curve of spectrum combination CIE1931 standard colorimetric system is calculated to CIEXYZ tri-
Values calculates the CIEXYZ tristimulus values of each pixel to homogeneous color aware space according to the white point of display equipment
Lightness, chroma and the tone of CIEL*C*h*, and demand setting brightness coefficient, chroma coefficient and tone coefficient are reappeared according to color；
3) modulated lightness, chroma and tone are combined to the gamma factor and primary colors tristimulus of display equipment triple channel
Value calculates to the digital drive values of each pixel, realizes that electrocardiogram, blood oxygen saturation, the blood pressure data of acquisition are shown.
For each pixel of hyperspectral image data, spoke brightness value is calculated by the gray value of each spectral coverage, and returned
One changes one curve of spectrum of composition；
For the curve of spectrum that each pixel is obtained in step 1, smoothly located using Savitzky-Golay filter
Reason, eliminates spectral noise on the basis of retaining more curvilinear characteristic, obtains the smoothed out curve of spectrum of each pixel
By obtained each smoothed out curve of spectrum of pixelIn conjunction with the color matching function of CIE1931 standard colorimetric systemUsing following formula calculate under CIE1931 standard colorimetric system CIEXYZ tristimulus values (X, Y,
Z), wherein Δ λ be imaging spectral instrument spectrum sample interval；
According to the tristimulus values (X of standard illuminants D65D65,YD65,ZD65), step 3 is obtained by each pixel by following formula
CIEXYZ tristimulus values convert to homogeneous color aware space CIEL*C*h*, obtain three Color perception parameters, i.e. lightnessChromaAnd tone h1；
Wherein,
XD65=95.047, YD65=100, ZD65=108.883；
Brightness coefficient k is setL, chroma coefficient kCWith tone coefficient khValue, each picture is obtained by following formula modulation step four
The lightness of elementChromaAnd tone h1, obtain modulated Color perception parameter, i.e. lightnessChromaAnd tone h2,
Effect of visualization is set to meet fidelity reproduction demand, then kL=kC=1, kh=0, change kLIt realizes the demand for adjusting image light and shade, changes
Become kCIt realizes the demand for adjusting the bright-coloured degree of image, changes khRealize the demand for adjusting image white balance；
According to the white point tristimulus values (X of display equipmentW,YW,ZW), by following formula, by the lightness of obtained each pixelIt is color
DegreeAnd tone h2It converts to CIEXYZ value (X', Y', Z') to be shown on the display device；
According to the primary colors tristimulus values (X of display equipment red, green, blue triple channelRmax,YRmax,ZRmax)、(XGmax,YGmax,
ZGmax、(XBmax,YBmax,ZBmax) in conjunction with the gamma factor γ of triple channelR、γG、γB, it is established that such as the characterization model of following formula,
By characterization model, the CIEXYZ value (X', Y', Z') for obtaining each pixel is calculated to corresponding digital drive values (dR,dG,dB),
The color visualization of high spectrum image is completed, wherein N is the display single pass storage bit number of equipment；
It uses each pixel to calculate spoke brightness value in the gray value of each spectral coverage to constitute the curve of spectrum, specifically includes following step
It is rapid:
The first step calibrates spectral imaging apparatus, and it is corresponding fixed to choose 5~10 calibration gray value D measurements
Spoke brightness value F is marked, parameter alpha, β, ε of following formula mapping expression formula are fitted using least square method, thus to the every of tested region
The gray value of each spectral coverage is substituted into following formula and calculates spoke brightness value by a pixel；
D=α Fβ+ε；
Second step, with maximum gradation value DmaxCorresponding spoke brightness value FmaxOn the basis of, by each pixel each spectral coverage spoke
Brightness value is normalized, and constitutes a curve of spectrum.
As shown in Fig. 2, it is provided by the invention intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring system include: electrocardiogram acquisition module 1,
Blood oxygen acquisition module 2, blood pressure acquisition module 3, central control module 4, health model building module 5, threshold value judgment module 6, disease
Feelings evaluation module 7, alarm modules 8, cloud service module 9, display module 10.
Electrocardiogram acquisition module 1 is connect with central control module 4, for acquiring patient's electrocardio by cardioelectric monitor equipment
Diagram data；
Blood oxygen acquisition module 2 is connect with central control module 4, for acquiring blood oxygen saturation by Oximetry instrument
Data information；
Blood pressure acquisition module 3 is connect with central control module 4, for acquiring patient blood pressure data's information by sphygmomanometer；
Central control module 4, with electrocardiogram acquisition module 1, blood oxygen acquisition module 2, blood pressure acquisition module 3, health model
It constructs module 5, threshold value judgment module 6, condition assessment module 7, alarm modules 8, cloud service module 9, display module 10 to connect, use
It is worked normally in controlling modules by single-chip microcontroller；
Health model constructs module 5, connect with central control module 4, for cardiovascular by model construction program construction
Patient's health hierarchical mode；
Threshold value judgment module 6 is connect with central control module 4, for by data comparison procedures judgement acquisition data and
Normal threshold value is set to compare and analyze；
Condition assessment module 7 is connect with central control module 4, for the electrocardiogram (ECG) data by appraisal procedure according to acquisition
The cardiovascular disease state of an illness is assessed；
Alarm modules 8 are connect with central control module 4, for exceeding threshold value and assessment according to judgement by alarm device
As a result timely alert notification is carried out；
Cloud service module 9 is connect with central control module 4, for the data by Cloud Server storage acquisition, and is concentrated
Big data computing resource handles acquisition data；
Display module 10 is connect with central control module 4, for showing intelligent Internal Medicine-Cardiovascular Dept. nursing prison by display
The electrocardiogram of viewing system interface and acquisition, blood oxygen saturation, blood pressure data information.
Health model provided by the invention constructs 5 construction method of module
(1) detection obtains the invasive attribute and noninvasive attribute of cardiovascular patient individual, and records enough individual
Data；
(2) the invasive attribute in above-mentioned steps is brought into disease prediction model, to obtain the assessment result to data；
(3) assessment result in the noninvasive attribute and step (2) in step (1) is saved to health evaluation model training
Collection；
(4) data in analytical calculation health evaluation model training set are to establish healthy hierarchical mode to be tested；
(5) using the extrapolation accuracy of the above-mentioned healthy hierarchical mode to be tested of data test detected in step (1), if
Extrapolation accuracy falls short of the target, then returns to (3) step and re-execute, until extrapolation accuracy touches the mark.
Step (4) provided by the invention specifically: the data in analytical calculation health evaluation model training set, execution are based on
The data mining of machine learning is to establish healthy hierarchical mode to be tested.
7 appraisal procedure of condition assessment module provided by the invention includes:
1) electrocardiosignal is obtained by cardioelectric monitor equipment；It is described according to electrocardiosignal, obtain corresponding cardiovascular disease
Condition assessment result includes: that the one or more features index of electrocardiosignal is calculated according to electrocardiosignal, according to electrocardiosignal
Characteristic index obtains corresponding cardiovascular disease condition assessment result；
2) characteristic index of electrocardiosignal and the pattern function of cardiovascular disease state of an illness corresponding relationship are pre-established, by electrocardio
The characteristic index input model function of signal, obtains corresponding cardiovascular disease condition assessment result；
3) according to the electrocardiosignal, corresponding cardiovascular disease condition assessment result is obtained.
The characteristic index of electrocardiosignal provided by the invention, comprising: linear analysis is carried out to the pRRx sequence of electrocardiosignal
To obtain one or more linear characteristic indexs, and/or nonlinear analysis is carried out, to obtain one or more nonlinear spies
Levy index；Wherein the pRRx sequence of any one section of electrocardiosignal is calculated in the following manner: calculating in this section of electrocardiosignal
The ratio of the quantity of quantity of the difference of adjacent R R interphase greater than threshold value x milliseconds and whole RR interphase, passes through the different threshold of setting value
Value x, obtains the corresponding ratio of each threshold value x, these ratios constitute the pRRx sequence；
The characteristic index that the linear analysis obtains: the standard deviation SDRR of mean value AVRR, the pRRx sequence of pRRx sequence,
In pRRx sequence in root mean square rMSSD, pRRx sequence of adjacent pRRx difference in the standard deviation SDSD of adjacent pRRx difference extremely
Few one；And/or
The nonlinear characteristic index includes carrying out the obtained characteristic index of Entropy Analysis Method to the pRRx sequence,
It include: pRRx sequence histogram distributed intelligence entropy Sdh, pRRx sequence power spectrum histogram distributed intelligence entropy Sph, pRRx sequence power spectrum
At least one of full frequency band distributed intelligence entropy Spf；And/or the nonlinear characteristic index include the pRRx sequence into
Row fractal dimension, which calculates, analyzes obtained characteristic index, comprising: structure function method calculates resulting fractal dimension D sf, correlation
Function method calculates resulting fractal dimension D cf, variate-difference method calculates resulting fractal dimension D vm, mean square root method calculates resulting point
At least one of shape dimension Drms.
The model of the characteristic index provided by the invention for pre-establishing electrocardiosignal and cardiovascular disease state of an illness corresponding relationship
Function, comprising:
When obtaining the physiological parameter of different state of an illness stage cardiovascular patients in advance, and acquiring the physiological parameter pair
Electrocardiosignal before the time point answered；
Obtain the characteristic index of these electrocardiosignals；
Using the characteristic index of these electrocardiosignals and the corresponding physiological parameter of these electrocardiosignals as input, carry out
Machine learning obtains the characteristic index of electrocardiosignal and the pattern function of cardiovascular disease state of an illness corresponding relationship.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (10)
1. a kind of intelligence Internal Medicine-Cardiovascular Dept. nurses monitoring method, which is characterized in that the intelligence Internal Medicine-Cardiovascular Dept. nurses monitoring side
Method the following steps are included:
Step 1 acquires patient ECG's data using cardioelectric monitor equipment by electrocardiogram acquisition module；It is acquired by blood oxygen
Module acquires blood oxygen saturation data information using Oximetry instrument；Patient is acquired using sphygmomanometer by blood pressure acquisition module
Blood pressure data information；
Step 2, central control module are constructed module by health model and are good for using model construction program construction cardiovascular patient
Health hierarchical mode；
Step 3, using data comparison procedures judges acquisition data by threshold value judgment module and sets normal threshold value to carry out pair
Than analysis；
Step 4 carries out the cardiovascular disease state of an illness according to the electrocardiogram (ECG) data of acquisition using appraisal procedure by condition assessment module
Assessment；
Step 5, by alarm modules using alarm device according to the logical beyond threshold value and the timely alarm of assessment result progress of judgement
Know；
Step 6 by cloud service module using the data of Cloud Server storage acquisition, and concentrates big data computing resource to adopting
Collection data are handled；
Step 7, display module show the electrocardio of intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system interface and acquisition using display
Figure, blood oxygen saturation, blood pressure data information.
2. intelligence Internal Medicine-Cardiovascular Dept. as described in claim 1 nurses monitoring method, which is characterized in that the health model building
Module construction method includes:
(1) detection obtains the invasive attribute and noninvasive attribute of cardiovascular patient individual, and records the data of enough individual；
(2) the invasive attribute in above-mentioned steps is brought into disease prediction model, to obtain the assessment result to data；
(3) assessment result in the noninvasive attribute and step (2) in step (1) is saved to health evaluation model training set；
(4) data in analytical calculation health evaluation model training set are to establish healthy hierarchical mode to be tested；
(5) using the extrapolation accuracy of the above-mentioned healthy hierarchical mode to be tested of data test detected in step (1), if extrapolation
Precision falls short of the target, then returns to (3) step and re-execute, until extrapolation accuracy touches the mark.
3. intelligence Internal Medicine-Cardiovascular Dept. as claimed in claim 2 nurses monitoring method, which is characterized in that the step (4) is specific
Are as follows: it is to be measured to establish to execute the data mining based on machine learning for the data in analytical calculation health evaluation model training set
Try healthy hierarchical mode.
4. intelligence Internal Medicine-Cardiovascular Dept. as described in claim 1 nurses monitoring method, which is characterized in that the condition assessment module
Appraisal procedure includes:
1) electrocardiosignal is obtained by cardioelectric monitor equipment；It is described according to electrocardiosignal, obtain the corresponding cardiovascular disease state of an illness
Assessment result includes: that the one or more features index of electrocardiosignal is calculated according to electrocardiosignal, according to the feature of electrocardiosignal
Index obtains corresponding cardiovascular disease condition assessment result；
2) characteristic index of electrocardiosignal and the pattern function of cardiovascular disease state of an illness corresponding relationship are pre-established, by electrocardiosignal
Characteristic index input model function, obtain corresponding cardiovascular disease condition assessment result；
3) according to the electrocardiosignal, corresponding cardiovascular disease condition assessment result is obtained.
5. intelligence Internal Medicine-Cardiovascular Dept. as claimed in claim 4 nurses monitoring method, which is characterized in that the spy of the electrocardiosignal
Levy index, comprising: to the pRRx sequence progress linear analysis of electrocardiosignal to obtain one or more linear characteristic indexs,
And/or nonlinear analysis is carried out, to obtain one or more nonlinear characteristic indexs；Wherein any one section of electrocardiosignal
PRRx sequence is calculated in the following manner: the difference for calculating adjacent R R interphase in this section of electrocardiosignal is greater than threshold value x milliseconds
The ratio of the quantity of quantity and whole RR interphase obtains the corresponding ratio of each threshold value x by the different threshold value x of setting value,
These ratios constitute the pRRx sequence；
The characteristic index that the linear analysis obtains: standard deviation SDRR, the pRRx sequence of mean value AVRR, the pRRx sequence of pRRx sequence
In column in root mean square rMSSD, pRRx sequence of adjacent pRRx difference adjacent pRRx difference at least one of standard deviation SDSD；
The nonlinear characteristic index includes that the obtained characteristic index of Entropy Analysis Method, packet are carried out to the pRRx sequence
Include: it is complete that pRRx sequence histogram distributed intelligence entropy Sdh, pRRx sequence power composes histogram distributed intelligence entropy Sph, pRRx sequence power spectrum
At least one of frequency range distributed intelligence entropy Spf；And/or the nonlinear characteristic index includes that the pRRx sequence carries out
Fractal dimension, which calculates, analyzes obtained characteristic index, comprising: structure function method calculates resulting fractal dimension D sf, related letter
Number method calculates resulting fractal dimension D cf, variate-difference method calculates resulting fractal dimension D vm, mean square root method calculates resulting point of shape
At least one of dimension Drms.
6. intelligence Internal Medicine-Cardiovascular Dept. nurses monitoring method as claimed in claim 4, which is characterized in that described to pre-establish electrocardio letter
Number characteristic index and cardiovascular disease state of an illness corresponding relationship pattern function, comprising:
The physiological parameter of different state of an illness stage cardiovascular patients is obtained in advance, and is acquired corresponding when the physiological parameter
Electrocardiosignal before time point；
Obtain the characteristic index of these electrocardiosignals；
Using the characteristic index of these electrocardiosignals and the corresponding physiological parameter of these electrocardiosignals as input, machine is carried out
Study, obtains the characteristic index of electrocardiosignal and the pattern function of cardiovascular disease state of an illness corresponding relationship.
7. intelligence Internal Medicine-Cardiovascular Dept. as described in claim 1 nurses monitoring method, which is characterized in that display module utilizes display
Device shows the electrocardiogram at intelligent Internal Medicine-Cardiovascular Dept. nursing monitoring system interface and acquisition, blood oxygen saturation, in blood pressure data information,
It carries out: 1) extracting the curve of spectrum of each pixel of high spectrum image；
2) color matching function of smoothed out curve of spectrum combination CIE1931 standard colorimetric system is calculated to CIEXYZ tristimulus
Value calculates the CIEXYZ tristimulus values of each pixel to homogeneous color aware space CIEL*C* according to the white point of display equipment
Lightness, chroma and the tone of h*, and demand setting brightness coefficient, chroma coefficient and tone coefficient are reappeared according to color；
3) modulated lightness, chroma and tone are combined to the gamma factor and primary colors tristimulus values of display equipment triple channel, meter
It calculates to the digital drive values of each pixel, realizes that electrocardiogram, blood oxygen saturation, the blood pressure data of acquisition are shown.
8. intelligence Internal Medicine-Cardiovascular Dept. as claimed in claim 7 nurses monitoring method, which is characterized in that for high spectrum image number
According to each pixel, spoke brightness value is calculated by the gray value of each spectral coverage, and be normalized constitute a curve of spectrum；
For the curve of spectrum that each pixel is obtained in step 1, it is smoothed using Savitzky-Golay filter,
Spectral noise is eliminated on the basis of retaining more curvilinear characteristic, obtains the smoothed out curve of spectrum of each pixel
9. intelligence Internal Medicine-Cardiovascular Dept. as claimed in claim 7 nurses monitoring method, which is characterized in that obtained each pixel is smooth
The curve of spectrum afterwardsIn conjunction with the color matching function of CIE1931 standard colorimetric systemUsing
Following formula calculates to obtain CIEXYZ tristimulus values (X, Y, Z) under CIE1931 standard colorimetric system, and wherein Δ λ is imaging spectral instrument
Spectrum sample interval；
10. a kind of intelligence Internal Medicine-Cardiovascular Dept. nurses monitoring system, which is characterized in that intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring system
System includes:
Electrocardiogram acquisition module, connect with central control module, for acquiring patient ECG's data by cardioelectric monitor equipment；
Blood oxygen acquisition module is connect with central control module, for acquiring blood oxygen saturation data letter by Oximetry instrument
Breath；
Blood pressure acquisition module, connect with central control module, for acquiring patient blood pressure data's information by sphygmomanometer；
Central control module, with electrocardiogram acquisition module, blood oxygen acquisition module, blood pressure acquisition module, health model building module,
Threshold value judgment module, condition assessment module, alarm modules, cloud service module, display module connection, for being controlled by single-chip microcontroller
Modules work normally；
Health model constructs module, connect with central control module, for passing through model construction program construction cardiovascular patient
Healthy hierarchical mode；
Threshold value judgment module is connect with central control module, for judging acquisition data and setting just by data comparison procedures
Normal threshold value compares and analyzes；
Condition assessment module, connect with central control module, for passing through appraisal procedure according to the electrocardiogram (ECG) data of acquisition to painstaking effort
Pipe disease condition is assessed；
Alarm modules connect with central control module, for by alarm device according to judgement beyond threshold value and assessment result into
The timely alert notification of row；
Cloud service module, connect with central control module, for the data by Cloud Server storage acquisition, and concentrates big data
Computing resource handles acquisition data；
Display module is connect with central control module, for showing that intelligent Internal Medicine-Cardiovascular Dept. nurses monitoring system by display
The electrocardiogram of interface and acquisition, blood oxygen saturation, blood pressure data information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910128989.7A CN109875547A (en) | 2019-02-19 | 2019-02-19 | A kind of intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910128989.7A CN109875547A (en) | 2019-02-19 | 2019-02-19 | A kind of intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109875547A true CN109875547A (en) | 2019-06-14 |
Family
ID=66928737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910128989.7A Pending CN109875547A (en) | 2019-02-19 | 2019-02-19 | A kind of intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109875547A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111166958A (en) * | 2020-02-20 | 2020-05-19 | 青岛市市立医院 | Portable uropoiesis is flushing pipe heating heat preservation device for surgery |
| CN112450878A (en) * | 2020-10-16 | 2021-03-09 | 中国人民解放军63919部队 | Sleep detection method, system and storage medium |
| CN114496209A (en) * | 2022-02-18 | 2022-05-13 | 青岛市中心血站 | Blood donation intelligent decision method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336900A (en) * | 2013-06-26 | 2013-10-02 | 广州军区广州总医院 | Method of establishing health layering model for cardiovascular patient |
| CN105046646A (en) * | 2015-05-29 | 2015-11-11 | 西安电子科技大学 | Color visualization method of high spectral image |
| 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 |
-
2019
- 2019-02-19 CN CN201910128989.7A patent/CN109875547A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336900A (en) * | 2013-06-26 | 2013-10-02 | 广州军区广州总医院 | Method of establishing health layering model for cardiovascular patient |
| CN105046646A (en) * | 2015-05-29 | 2015-11-11 | 西安电子科技大学 | Color visualization method of high spectral image |
| 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 |
Non-Patent Citations (3)
| Title |
|---|
| 李勇: "一种适用于异构存储系统的缓存管理算法", 《计算机研究与发展》 * |
| 赵梦: "云计算环境下基于蚁群优化的任务负载均衡调度算法", 《电子设计工程》 * |
| 闫晟: "一种基于NSCT变换的超声图像降噪新算法", 《仪器仪表学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111166958A (en) * | 2020-02-20 | 2020-05-19 | 青岛市市立医院 | Portable uropoiesis is flushing pipe heating heat preservation device for surgery |
| CN112450878A (en) * | 2020-10-16 | 2021-03-09 | 中国人民解放军63919部队 | Sleep detection method, system and storage medium |
| CN114496209A (en) * | 2022-02-18 | 2022-05-13 | 青岛市中心血站 | Blood donation intelligent decision method and system |
| CN114496209B (en) * | 2022-02-18 | 2022-09-27 | 青岛市中心血站 | Intelligent decision-making method and system for blood donation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109875547A (en) | A kind of intelligence Internal Medicine-Cardiovascular Dept. nursing monitoring system and method | |
| US10806354B2 (en) | Method and apparatus for estimating heart rate | |
| CN105636506B (en) | Automatic camera for long-range photo-plethysmographic method is adjusted | |
| US10709342B2 (en) | System and method for spatial cardiovascular monitoring | |
| US7764815B2 (en) | Method of digital image analysis for isolating a region of interest within a tongue image and health monitoring method and apparatus using the tongue image | |
| RU2589389C2 (en) | Device and method of extracting information from characteristic signals | |
| CN101557758B (en) | Optical sensor device and image processing unit for measuring chemical concentrations, chemical saturations and biophysical parameters | |
| CN103702014B (en) | Non-contact physiological parameter detection method, system and device | |
| Bradley et al. | Retina-V1 model of detectability across the visual field | |
| US9241674B2 (en) | Distortion reduced signal detection | |
| US10013811B2 (en) | Hyperspectral image visualization in patients with medical conditions | |
| JP2016529993A (en) | Method and display for long-term physiological signal quality indication | |
| CN111714144A (en) | Mental stress analysis method based on video non-contact measurement | |
| CN111387966B (en) | Signal wave reconstruction method and heart rate variability information detection device | |
| CN112890792A (en) | Cloud computing cardiovascular health monitoring system and method based on network camera | |
| CN103501692A (en) | Monitoring volaemic condition in a human or animal subject | |
| JP4141133B2 (en) | Apparatus and method for displaying periodic data | |
| Mitsuhashi et al. | Video-based stress level measurement using imaging photoplethysmography | |
| CN112788200A (en) | Method and device for determining frequency spectrum information, storage medium and electronic device | |
| Kassab et al. | Effects of region of interest size on heart rate assessment through video magnification | |
| US11185253B2 (en) | Pattern recognition system for quantifying the likelihood of the contribution of multiple possible forms of chronic disease to patient reported dyspnea | |
| US10674921B2 (en) | Method and device for computing optical hemodynamic blood pressure | |
| US7698234B2 (en) | Cardiac perfusion analysis | |
| KR20210048749A (en) | Method and apparatus for measuring blood pressure using skin images | |
| DE102019101353A1 (en) | INTELLIGENT PERSONAL PORTABLE BLOOD PRESSURE MEASUREMENT SYSTEM AND METHOD FOR CALIBRATING THE BLOOD PRESSURE MEASUREMENT IN USE |
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: 20190614 |