CN106413534A - Blood-pressure continuous-measurement device, measurement model establishment method, and system - Google Patents
Blood-pressure continuous-measurement device, measurement model establishment method, and system Download PDFInfo
- Publication number
- CN106413534A CN106413534A CN201580000417.0A CN201580000417A CN106413534A CN 106413534 A CN106413534 A CN 106413534A CN 201580000417 A CN201580000417 A CN 201580000417A CN 106413534 A CN106413534 A CN 106413534A
- Authority
- CN
- China
- Prior art keywords
- pulse wave
- characteristic parameter
- blood pressure
- feature point
- pressure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/021—Measuring pressure in heart or blood vessels
-
- 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
Abstract
The invention provides a blood-pressure continuous-measurement device, a measurement model establishment method, and a system. The device comprises: a signal collector (100), used for collecting electrocardiosignals and pulse wave signals of a measured object for multiple consecutive cardiac cycles, so as to obtain two sets of synchronous electrocardiosignals and pulse wave signals; a signal reception module (210), used for receiving the two sets of synchronous electrocardiosignals and pulse wave signals; and a blood pressure computing module (220), used for extracting a first characteristic point of the pulse wave signals according to the two sets of synchronous electrocardiosignals and pulse wave signals, extracting a second characteristic point of the electrocardiosignals in a same cardiac cycle according to the first characteristic point, acquiring corresponding characteristic values according to the first characteristic point and the second characteristic point, selecting a characteristic parameter from the characteristic values according to an evaluation parameter, and acquiring a blood pressure value according to a pre-established blood pressure computing model of characteristic parameters. The device, the method and the system have the characteristics of high precision, low complexity, low cost, convenience in measurement, and high real-time quality.
Description
Technical field
The present invention relates to blood pressure measurement technology, more particularly to a kind of continuous blood pressure measurer, measurement model foundation side
Method and system.
Background technology
Compared to traditional discontinuous blood pressure measuring method, continuous BP measurement method, can in each cardiac cycle
Provide pressure value by shooting.This, for understanding blood pressure rule, prevents cardiovascular and cerebrovascular disease, has great importance.Meanwhile,
Due to continuous BP measurement method can real-time tracing by the pressure value of person, not only can reduce " white coat hypertension " and " hidden
Property hypertension " hidden danger, contribute to the daily monitoring of hyperpietic additionally it is possible to the indirect reflection effect to human body for the antihypertensive drugs
Really, to avoid the abuse of medicine.In addition, continuous BP measurement, additionally aid the analysis of blood pressure variability, this is for further
Solve tested health, the occurrence risk of assessment cardiovascular and cerebrovascular disease, there is important reference value.
However, current noninvasive continuous BP measurement equipment, it is former based on volume-compensation method and angiosthenia method mostly
Reason design.Measuring apparatus using angiosthenia method can reach higher precision, substantially can reach long period noninvasive company
The requirement of continuous blood pressure measurement.But due to the high sensitivity to displacement for the sensor, long-time sensor measurement position to be kept
It is relatively fixed relatively difficult, air bag pressue device also affects measured's comfort level, therefore base in long-time measurement process simultaneously
Blood pressure measurement device in angiosthenia still has many problems demand to change in motion measurement, long-term measurement and simplification operating aspect
Enter.Measuring apparatus using volume-compensation method can continuously measure blood pressure of often fighting, and can measure blood pressure waveform without distortion.But
Due to the effect of gasbag pressure, long-time measurement can lead to venous congestion to affect certainty of measurement, can bring to measured simultaneously
Uncomfortable.In addition, the noninvasive continuous BP measurement equipment of principle design based on volume-compensation method and angiosthenia method is heavy, price
Expensive, carry and gather equal inconvenience, be unfavorable for the daily physiology monitoring of family.
Content of the invention
Based on this it is necessary to be directed to deficiency of the prior art, a kind of continuous blood pressure measurer, measurement model is provided to build
Cube method and system.
A kind of continuous blood pressure measurer, described device includes：
Signal picker, including Electrocardial signal acquisition device and pulse wave signal collector, for synchronous acquisition measurement object
Multiple continuous cardiac cycle in electrocardiosignal and pulse wave signal, obtain two groups of synchronous electrocardiosignals and pulse wave letter
Number；
Signal receiving module, for receiving two groups of synchronous electrocardiosignals and pulse wave signal；
Blood pressure computing module, for the electrocardiosignal synchronous according to two groups and pulse wave signal, extracts described pulse wave letter
Number fisrt feature point, and according to described fisrt feature point obtain same cardiac cycle in electrocardiosignal second feature point,
Corresponding characteristic value is obtained according to described fisrt feature point and described second feature point, using assessment parameter from described characteristic value
Selected characteristic parameter, according to the blood pressure computation model of the described characteristic parameter pre-building, obtains pressure value.
Wherein in some embodiments, described blood pressure computing module includes：
Characteristic value acquiring unit, for the electrocardiosignal synchronous according to two groups and pulse wave signal, extracts described pulse wave
The fisrt feature point of signal, and the second feature of the electrocardiosignal in same cardiac cycle is obtained according to described fisrt feature point
Point；
Characteristic parameter acquiring unit, special accordingly for according to described fisrt feature point and described second feature point, obtaining
Levy parameter；With
Blood pressure calculation unit, for the blood pressure computation model according to the described characteristic parameter pre-building, obtains pressure value.
Wherein in some embodiments, described blood pressure computing module also includes：
Filter unit, for being filtered processing to described two groups synchronous electrocardiosignals and pulse wave signal respectively.
Wherein in some embodiments, described characteristic parameter includes：Pulse wave propagation time, cardiac cycle, pulse wave are received
Rise time contracting phase and pulse wave K value.
Wherein in some embodiments, the blood pressure computation model of described characteristic parameter includes multivariate linear model, described many
First linear model is：
SBP=P D G,
MAP=P E G,
DBP=P F G,
Wherein, SBP is systolic pressure, and MAP is mean blood pressure, and DBP is diastolic pressure, P=[1 PWTT EcgPeriod
PpgSystolicTime ppg_K], PWTT is described pulse wave propagation time, and EcgPeriod is described cardiac cycle,
PpgSystolicTime is the described rise time in pulse wave systole phase, and ppg_K is described pulse wave K value, and D, E and F are respectively institute
State systolic pressure, described diastolic pressure and described mean blood pressure corresponding bp coefficient matrix, G is the physiological parameter square of measurement object
Battle array,Gender is sex, and age is the age, and height is height, and weight is body weight, and BMI is physique
ArmLength is brachium to ratio.
Wherein in some embodiments, the blood pressure computation model of described characteristic parameter includes nonlinear model, described non-thread
Property model includes the nonlinear regression model (NLRM) based on SVMs, the described blood pressure computation model setting up described characteristic parameter
Process includes：
Obtain the training set between described characteristic parameter and described systolic pressure；
Construct decision function using the described nonlinear regression model (NLRM) based on SVMs and calculate optimum solution；
Obtain systolic pressure and the diastolic pressure coefficient matrix based on described data set according to described decision function；
Final pressure value is obtained according to described systolic pressure and diastolic pressure coefficient matrix.
Wherein in some embodiments, described characteristic parameter is chosen unit and is additionally operable to, and is initialized special according to described characteristic value
Levy parameter set and characteristic parameter subset；Choose multiple candidate feature subset；Special to the plurality of candidate using described valuation functions
Levy subset to be estimated, obtain the characteristic parameter conforming to a predetermined condition.
Wherein in some embodiments, described device also includes：
Memory module, for storing described characteristic value, described characteristic parameter and its corresponding pressure value；
Display module, for showing described characteristic value, described characteristic parameter and its corresponding pressure value.
Wherein in some embodiments, described device also includes：
Communication module, for receiving two groups of synchronous electrocardiosignals and the pulse wave signal of described signal picker collection,
And the various data is activations storing memory module are to external device (ED)；Or,
It is respectively provided with wireless signal Transmit-Receive Unit, signal picker and signal in signal picker and signal receiving module
Carried out data transmission by wireless signal between receiver module and communicate.
System set up by a kind of continuous BP measurement model, and described system includes：
Signal acquisition module, for receiving electrocardiosignal and pulse wave in two groups of synchronous multiple continuous cardiac cycles
Signal；
Feature point extraction module, for extracting the fisrt feature of the described pulse wave signal that described signal acquisition module obtains
Point, and the second feature point of the electrocardiosignal in same cardiac cycle is obtained according to described fisrt feature point；
Characteristic value acquisition module, for according to described fisrt feature point and described second feature point, obtaining corresponding feature
Parameter；
Model building module, for setting up the blood pressure computation model of described characteristic parameter.
A kind of continuous BP measurement method for establishing model, methods described includes：
Obtain the electrocardiosignal in synchronous multiple continuous cardiac cycle and pulse wave signal；
Extract the fisrt feature point of described pulse wave signal, and obtained according to the fisrt feature point of described pulse wave signal same
The second feature point of the electrocardiosignal in one cardiac cycle；
According to described fisrt feature point and described second feature point, obtain corresponding characteristic parameter；
Based on corresponding characteristic parameter, set up the blood pressure computation model of described characteristic parameter.
Wherein in some embodiments, described characteristic parameter includes：Pulse wave propagation time, cardiac cycle, pulse wave are received
Rise time contracting phase and pulse wave K value.
Wherein in some embodiments, the blood pressure computation model of described characteristic parameter includes multivariate linear model, described many
First linear model is：
SBP=P D G,
MAP=P E G,
DBP=P F G,
Wherein, SBP is described systolic pressure, and MAP is described mean blood pressure, and DBP is described diastolic pressure, P=[1 PWTT
EcgPeriod PpgSystolicTime ppg_K], PWTT is described pulse wave propagation time, and EcgPeriod is described aroused in interest
In the cycle, PpgSystolicTime is the described rise time in pulse wave systole phase, and ppg_K is described pulse wave K value, and D, E and F divide
Not Wei described systolic pressure, described diastolic pressure and described mean blood pressure corresponding bp coefficient matrix,
Gender is described sex, and age is the described age, and height is described height, and weight is described body weight, and BMI is described body
Matter ratio, armLength is described brachium.
Wherein in some embodiments, the blood pressure computation model of described characteristic parameter includes nonlinear model, described non-thread
Property model includes the nonlinear regression model (NLRM) based on SVMs, the non-thread based on SVMs for the described blood pressure calculation unit
Property regression model obtain pressure value process include：
Wherein in some embodiments, characteristic parameter obtaining step includes:
According to characteristic value initialization feature parameter set and characteristic parameter subset；
Select evaluation function, and multiple characteristic parameter subsets are generated according to described evaluation function；
Optimal characteristics subset of parameters is chosen from the plurality of characteristic parameter subset according to described evaluation function.
The blood pressure measuring device of above-described embodiment and blood pressure calculating method and system just can be real based on several characteristic parameters
Now the unperturbed formula of blood pressure is continuously measured.It has high precisely, low complex degree, low cost, measurement is convenient, real-time is high spy
Point.
Brief description
Fig. 1 is the structured flowchart of the continuous blood pressure measurer of one embodiment of the invention；
Fig. 2 is the structured flowchart of the continuous blood pressure measurer of another embodiment of the present invention；
Fig. 3 is the structured flowchart of the signal picker of one embodiment of the invention；
Fig. 4 is the flow chart of the continuous BP measurement method for establishing model of one embodiment of the invention；
Fig. 5 is filtered electrocardiosignal and the pulse wave signal schematic diagram of one embodiment of the invention；
Fig. 6 is the schematic diagram of the fisrt feature point of the pulse wave signal of extraction of one embodiment of the invention；
Fig. 7 is the schematic diagram of the second feature point of the electrocardiosignal of extraction of one embodiment of the invention；
Fig. 8 is the schematic diagram of the second feature point of the electrocardiosignal of extraction of another embodiment of the present invention；
Fig. 9 is the rise time in systole phase of one embodiment of the invention and the schematic diagram of fall time diastole；
Figure 10 is the pulse wave K value schematic diagram of one embodiment of the invention；
Figure 11 is the pulse wave propagation time schematic diagram of one embodiment of the invention；
Figure 12 is that the structured flowchart of system set up by the continuous BP measurement model of one embodiment of the invention.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, below in conjunction with drawings and Examples, right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only in order to explain the present invention, and
It is not used in the restriction present invention.
In the exemplary embodiment, when blood pressure is that blood flows in intravascular, the pressure of vasoactive wall, it is to promote
The power that blood flows in intravascular.Ventricular contraction, blood from ventricle flow into artery, the now pressure highest to artery for the blood,
Referred to as systolic pressure (systolic blood pressure, SBP).Ventricular diastole, arteries elastical retraction, blood is still slowly
Continuation flow forward, but drop in blood pressure, pressure now is referred to as diastolic pressure (diastolic blood pressure, DBP).The heart
Dynamic cycle (cardiac cycle) refers to initiate the initial of heartbeat next time from a heartbeat, and cardiovascular system is experienced
Process.During diastole internal pressure reduce, vena cave blood flow back enter the heart, during heart contraction internal pressure raise, by blood pump arrive move
Arteries and veins.Heart often shrinks and once constitutes a cardiac cycle with diastole.In one cardiac cycle, the time domain average value of arterial pressure is
Mean arterial pressure (mean arterial blood pressure, MAP).
Sphygmomanometry substantially can be divided into the direct method of measurement and the indirect method of measurement two big class.The direct method of measurement is will to connect pressure
The conduit of force snesor is percutaneously inserted directly into main artery or heart detection blood pressure signal, can continuously be measured.Due to this
Method directly records blood pressure, and data is the most accurate, is therefore regarded as the goldstandard of blood pressure detecting by the world, but its technical requirements is relatively
Height, and have necessarily traumatic, so being only applicable to rescue and the major operation patient of urgent patient.The indirect method of measurement is by detection
The parameters such as the beating of ductus arteriosus wall, capacity of blood vessel change obtain blood pressure indirectly.Method is simple due to this, therefore in clinic
On be used widely.
The indirect method of measurement can be divided into batch (-type) mensuration and continous way mensuration two big class again.With Korotkoff's Sound method and oscillographic method
The general principle of the batch (-type) mensuration for representing is with gas sleeve interruption artery blood flow, then by detection during venting
In characteristic point moment gas sleeve, pressure is determining pressure value.The shortcoming of this method be all with blood pressure phase of often fighting in measurement process before
Carry, record pressure value that blood pressure is a certain particular moment (only not 2 values of SBP and DBP within same cardiac cycle) and differ
Surely it is the representational pressure value of measured.Continous way mensuration is noninvasive continuous measurement blood pressure in a certain amount of time, can
Detect often fight blood pressure and continuous arterial pressure waveform, be that clinical diagnosis provides more fully foundation with treatment, particularly exist
Clinical monitoring and in particular cases observation blood pressure consecutive variations aspect have the incomparable advantage of conventional method.Hereinafter will have
Body is described with reference to the accompanying drawings each way of example of the present invention.
Terminology used in the present invention " module ", " unit " are made up of assembly, and " assembly " refers to and present system
Related entity, or the combination of software, hardware, hardware and software.For example, assembly can be entering of running on a processor
Journey, object, program and computer.As an example, the application program (application, APP) operating in mobile terminal can be
Assembly.In addition, assembly can include one or more assemblies.
As shown in figure 1, the continuous blood pressure measurer 10 of the embodiment of the present invention includes：Signal picker 100, control module
200th, memory module 300 and display module 400.
Signal picker 100 collection is related to each item data of the raw body activity of measurement object.Here, it is related to raw body activity
Various types of data (biological information) can be related to electrocardio, pulse frequency, cardiac rate, etc. data (information).Signals collecting
Device 100 has such as Electrocardial signal acquisition device 110 and pulse wave signal collector 120.Using Electrocardial signal acquisition device 110 from survey
The ECG detecting position of amount object obtains electrocardiosignal.Pulse wave signal collector 120 is from the pulse wave test section of measurement object
Position obtains pulse wave signal.In some of them embodiment of the present invention, electrocardiosignal includes electrocardiogram, and pulse wave signal includes arteries and veins
Fight waveform figure.By with reference to Fig. 3 in Electrocardial signal acquisition device 110 described in detail below and pulse wave signal collector 120
Configuration.
Control module 200 integrally control and measure device 10, and process the measurement for example being gathered by signal picker 100
The electrocardiosignal of object and pulse wave signal.Specifically, the measurement object that control module 200 is gathered based on signal picker 100
Electrocardiosignal and pulse wave signal carry out the blood pressure of computation and measurement object.Additionally, control module 200 is based on acquisition control module
240 carry out control signal collector 100 carry out signals collecting.
Describe function and the configuration of control module 200 in more detail below.Control module 200 has signal receiving module
210th, blood pressure computing module 220, display control module 230 and acquisition control module 240.
Signal receiving module 210 is used for the electrocardiosignal of measurement object and the pulse wave of receipt signal collector 100 collection
Signal.The electrocardiosignal of reception and pulse wave signal are sent to blood pressure computing module 220 to enter promoting circulation of blood by signal receiving module 210
Pressure calculates.
The electrocardiosignal that blood pressure computing module 220 is received based on signal receiving module 210 and pulse wave signal are calculated,
Obtain corresponding characteristic parameter and be calculated the blood of test object according to the blood pressure computation model of the characteristic parameter prestoring
Pressure value.Specifically, blood pressure computing module 220 is used for, according to two groups of synchronous electrocardiosignals and pulse wave signal, extracting pulse wave
The fisrt feature point of signal, and the second feature point of the electrocardiosignal in same cardiac cycle, root is obtained according to fisrt feature point
Obtain corresponding characteristic value according to fisrt feature point and second feature point, using assessment parameter selected characteristic parameter from characteristic value,
According to the blood pressure computation model of the characteristic parameter pre-building, obtain pressure value.Here characteristic parameter includes：Pulse wave is propagated
Time, cardiac cycle, rise time in pulse wave systole phase and pulse wave K value etc..Blood pressure computing module 220 is about pressure value meter
The detailed process calculated can be found in the related description of hereinafter step 404, step 406, step 408.
And in some of them embodiment of the present invention, blood pressure computing module 220 is also by calculated pressure value etc.
Information sends to display control module 230.
In some embodiments of the invention, as shown in Fig. 2 blood pressure computing module 220 includes filter unit 222, feature
Value acquiring unit 224, characteristic parameter acquiring unit 226 and blood pressure calculation unit 228.
Filter unit 222, for signal receiving module 210 is received two groups synchronous electrocardiosignals and pulse wave signal
It is filtered, to obtain filtered electrocardiosignal and pulse wave signal.Detection process in electrocardiosignal and pulse wave signal
In, due to real work situation nonideality. often contain very strong ambient noise in detection signal.These ambient noises
The various random noises causing including industrial frequency noise, myoelectricity noise, respiratory wave noise, human action and electrode polarization etc..
Characteristic value acquiring unit 224, for the filtered two groups of synchronous electrocardiosignals of filtered unit 222 and pulse wave
Signal, extracts the fisrt feature point of filtered pulse wave signal, then obtains same cardiac cycle according to fisrt feature point
The second feature point of interior electrocardiosignal.In the present embodiment, fisrt feature point includes crest and the trough of pulse wave signal.The
Two characteristic points include ecg-r wave.
Characteristic parameter acquiring unit 226, for according to fisrt feature point and described second feature point, obtaining corresponding feature
Parameter.Here characteristic parameter includes cardiac electrophysiology parameter, pulse wave physiological parameter and electrocardiograph pulse ripple physiological parameter.
Blood pressure calculation unit 228, for the blood pressure computation model according to the characteristic parameter pre-building, obtains pressure value.
Here blood pressure includes systolic pressure, diastolic pressure and mean blood pressure.
Display control module 230 controls and shows the various types of numbers being processed by control module 200 on display module 400
It is believed that breath and the result by processing these acquisition of informations.For example, display control module 230 control display module 400 show by
The calculated pressure value of blood pressure computing module 220.In addition, display control module 230 controls display module 400 to show by information
The information of electrocardiosignal that receiver module 210 receives and pulse wave signal etc..
Acquisition control module 240 control signal collector 100 carries out signals collecting.For example, acquisition control module 240 controls
Electrocardial signal acquisition device 110 gathers electrocardiosignal, and acquisition control module 240 controls pulse wave signal collector 120 synchronous simultaneously
Ground gathers the pulse wave signal in multiple continuous cardiac cycles.
Schematically joining according to the control module 200 in some embodiments disclosed by the invention described in detail above
Put, the configuration of control module 200 is not limited to the example shown in Fig. 1.As long as configuration meets above-mentioned functions it is possible to pass through any
Functional block carrys out configuration control module 200.
Next, the memory module 300 of some of them embodiment disclosed by the invention will be described.Storage there is not module 300
Store various types of data of the expression raw body activity gathering with signal picker 100 and/or each of control module 200 process
The data of type.Memory module 300 stores such as electrocardio related data and pulse wave related data.Additionally, memory module 300
Can also the calculated pressure value of data storage processing module.Memory module 300 can also be stored in following continuous blood pressures and survey
Characteristic point, characteristic parameter and physiological parameter used in amount method, and for information such as the blood pressure models about characteristic parameter.
Data processing module is referred to the characteristic point of storage, characteristic parameter and physiological parameter in memory module 300, and for relevant
The information such as the blood pressure model of characteristic parameter are calculating blood pressure.
Additionally, in FIG, although giving the example that memory module 300 is arranged in continuous blood pressure measurer 10,
It is embodiment not limited to this disclosed by the invention.For example, measurement apparatus 10 can also include the connectivity port of external device (ED) connection
(not shown), and it is connected to the external memory unit (not shown) being arranged on outside via this connectivity port.If measurement dress
Put 10 and be connected to external memory unit, then the above-mentioned various types of data storages that can will be stored in memory module 300 exist
In external memory unit.Here, connectivity port can be card connector, and external memory unit can be storage card (SD
Card).
Display module 400 show under the control of display control module 200 by control module 200 process various types of
Information.For example, display module 400 can be display.If display module 400 is display, display module 400 can example
As in the form of numeral or figure come the electrocardiogram (ECG) data measured by showing and pulse wave data and the pressure value that calculated etc..
Additionally, measurement apparatus 10 may further include the sound of the (not shown) such as composition such as loudspeaker, headphone
Frequency output module.If measurement apparatus 10 include dio Output Modules, above-mentioned by display module 400 show various types of
Information can be realized by dio Output Modules output alarm tone.Additionally, according to embodiment disclosed by the invention, measurement apparatus 10
Can also include for sending information and the communication module (not shown) from external device (ED) receive information to various external device (ED)s.Example
As, the data of various raw body activities of the measurement object that signal picker 100 can be gathered by communication module and control module obtain
To the information such as various types of data send to external device (ED).Specifically, signal picker 100 can be gathered by communication module
The electrocardiogram (ECG) data of measurement object and the information such as the pressure value that obtains of pulse wave data data processing module send to outside dress
Put.Here, the communication module time of various types of data is activations to external device (ED) can be that each measurement is related to raw body work
The real time of dynamic various types of data, or various types of data can terminate a series of blood pressure measurement process it
Jointly send afterwards.
Additionally, communication module can also receive characteristic point used in following continuous BP measurement process methods, feature ginseng
Number and physiological parameter, and for information such as the blood pressure models about characteristic parameter, and by the information Store being received upper
In the memory module 300 stated or external memory unit.Therefore, it can to update the blood pressure of these characteristic parameters via communication unit
The information such as model.
Additionally, communication module can be using wired or wireless communication mode.If communication module has wireless transmitting function,
The radio transmission method then using can be the bluetooth of such as near field communication system or the body area network being standardized
IEEE802.15.6.
Additionally, the external device (ED) via communication module and measurement apparatus 10 communication can be PC (personal computer) or intelligence
Terminal.These external device (ED)s can be realized and control module 200 identical function.Because external device (ED) has and control module
200 identical functions, then this external device (ED) the various types of data sending from measurement apparatus 10 can be carried out with control mould
Block 200 identical is processed.
Below, it is described with reference to Figure 3 Electrocardial signal acquisition device 110 and the pulse wave signal that signal picker 100 includes
The illustrative arrangement of collector 120.Fig. 3 shows the structural frames of the illustrative arrangement of signal picker 100 that figure 1 illustrates
Figure.Electrocardial signal acquisition device 110 includes electrocardioelectrode 112, ecg signal acquiring module 114 and electrocardiosignal analog-to-digital conversion module
116.Electrocardioelectrode 112 needs direct and human contact, can be made up of the copper sheet having plated one layer of silver chlorate, Main Function is handle
Human ecg signal is transmitted to electrocardiogram acquisition module up well.Electrocardiogram acquisition module 114 can adopt electrocardiogram acquisition chip,
This electrocardiogram acquisition chip includes preposition amplification, right leg drive, filtering and rearmounted amplifying circuit, at electrocardiogram acquisition module 114
Useful electrocardiosignal after reason, after analog-digital converter, is transferred to signal receiving module 210.Pulse wave signal collector 120
Including pulse wave sensor 122, pulse wave signal acquisition module 124 and pulse signal analog-digital converter 126.Pulse wave sensor
122 can be made up of light emitting diode and photodiode, can adopt two kinds of metering systems of transmission or reflection.Light emitting diode
The illumination (green glow/infrared light) of special spectrum can be launched, this illumination is mapped on human vas, be received thoroughly by photodiode
It is emitted through blood vessel or the light returned from vasoreflex, the change of the intensity of this transmission/reflection/angle light just reflects human pulse
Change, thus collect the pulse wave of human body.Pulse wave signal acquisition module 124 is come in pulse wave sensor 122 transmission
Pulse wave signal is sampled, and pulse signal analog-digital converter 126 carries out transmission after analog-to-digital conversion to the pulse wave signal of sampling
To signal receiving module 210.
Blood pressure measurement mould in measurement apparatus 10 in above-described embodiment disclosed by the invention to be described below with reference to Fig. 4
Type method for building up.
Step 402, obtains the electrocardiosignal in synchronous multiple continuous cardiac cycle and pulse wave signal.
In some of them embodiment of the present invention, the electrocardiosignal receiving and pulse wave signal are filtered locate
Reason, to remove the interference of the noise in electrocardiosignal and pulse wave signal.
Specifically, the characteristic according to electrocardiosignal and pulse wave signal, the method that can adopt wavelet transformation is to acquisition
Electrocardiosignal and pulse wave signal filtering, filtered signal is as shown in Figure 5.
Step 404, extracts the fisrt feature point of pulse wave signal, and is obtained same according to the fisrt feature point of pulse wave signal
The second feature point of the electrocardiosignal in one cardiac cycle.In some of them embodiment of the present invention, difference threshold can be adopted
Value method extracts the fisrt feature point of pulse wave signal, and this fisrt feature point includes crest and the trough of pulse wave signal.Specifically real
Existing process is as follows：
(1) obtain the radio-frequency component of pulse wave signal.
By differential process are carried out to pulse wave signal, extract its high-frequency signal.For example, according to the following formula to pulse
Ripple signal asks first derivative, dPPG (i)=PPG (i+1)-PPG (i), that is, be equivalent to and carry out high-pass filtering to it.
Wherein, PPG (i) represents the amplitude of i-th point of signal in PPG waveform, and dPPG represents the first-order difference of PPG signal.
(2) segmentation is carried out to the radio-frequency component of pulse wave signal.
Pulse frequency due to human body changes in certain scope, and in general, pulse frequency all can be more than 30 beats/min.Thus, right
Pulse wave signal waveform carries out segmentation, such as with 2s for one section, thus all can have a pulse cycle in ensureing every section.
(3) signal segment that above-mentioned steps (2) are obtained carries out threshold test.
Search the maximum of every section of signal amplitude；
Acquisition amplitude exceedes the position of all data points (BigNumber) of maximum prearranged multiple, in the present embodiment,
Prearranged multiple can be 0.3 times.
The data point of above-mentioned acquisition is traveled through, the difference searching adjacent two data point position exceedes scheduled time length
Data point.Because if the position of two data points is more than first scheduled time it becomes possible to determine that this two data points are located at
On tandem two different pulse waves.In the present embodiment, first scheduled time can be 0.2s.
(4) search the crest of pulse wave signal.
The position of the previous data point that above-mentioned (3) are detected is defined as Label such that it is able to determine pulse crest value
Position just near Label.Shown by statistics, pulse wave amplitude exceedes the data point of maximum amplitude prearranged multiple, its time
Persistence length is not over second scheduled time.Therefore, traveled through in second scheduled time after Label, found out
Maximum during this, finally determines the crest of pulse wave.In certain embodiments, second scheduled time can be 0.4s.
(5) search the trough of pulse wave signal.
Some characteristics being had in itself due to pulse wave, enabling substantially determine pulse wave trough position crest it
In the range of front second scheduled time.Then, search the minimum of a value in this interval, so that it is determined that the trough of pulse wave.
Fisrt feature point extraction is carried out by said process to pulse wave signal, the result obtaining is as shown in Figure 6.
The second feature of the electrocardiosignal in same cardiac cycle after determining fisrt feature point, is obtained according to fisrt feature point
Point.Second feature point includes cardiac electrical R wave characteristic point.The method of the acquisition of second feature point of electrocardiosignal can be realized relatively
Many, in some embodiments of the invention, it is worth most as a example method and Wavelet Transform by interval and illustrates.
(1) interval is worth method most
Because electrocardio and pulse wave are to be produced by same cardiac cycle, therefore when the peak-to-valley value of pulse wave all determines
Afterwards, cardiac electrical R ripple can just be positioned.It concretely comprises the following steps：
After the Wave crest and wave trough of the PPG that has good positioning, between two adjacent PPG peak time, traversal corresponding ECG letter
Number, the R ripple of maximizing point wherein, as ECG.Its effect is as shown in Figure 7.
(2) the R ripple detecting step based on Wavelet Transform is as follows：
Multi-resolution decomposition process：Choose quadratic spline B small echo, for morther wavelet, little multi-resolution decomposition is carried out to electrocardiosignal,
In the present embodiment, multi-resolution decomposition is 24 Scale Decompositions；
Maximum detection process：Because the extreme portions energy of R ripple concentrates on yardstick 3, the present invention will enter in yardstick 3
The detection of row maximum；The wavelet coefficient d3 of yardstick 3 is scanned, coefficient value is more than 0 and big with left adjoint point line slope
Point in 0 constitutes positive maximum Candidate Set PosC.Simultaneously by coefficient value be less than 0 and with left adjoint point line slope be less than 0 point structure
Become negative maximum Candidate Set NegC；
Binarization：First threshold (th1) and Second Threshold (th2) are determined based on Candidate Set mean value method, and will just
In maximum point Candidate Set PosC, every point more than first threshold th1 is stored in positive maximum collection Pos, and its value is set to 1.
Point less than Second Threshold th2 every in negative maximum point Candidate Set NegC is stored in negative maximum collection Neg, and its value is put
For -1；
The pairing process of positive and negative maximum pair：It is contemplated that at R crest value point after generating positive maximum collection and negative maximum collection
In maximum between interval in.So needing to carry out the pairing work of positive and negative maximum pair.Defining very big value set is
Loca, all data that positive maximum collection and negative maximum are concentrated are stored in loca.Find at adjacent 2 points in loca set
N1, N2, and N1 value is 1 for -1, N2 value, i.e. adjacent two points negative maximum points, one is negative maximum point.Define modulus maxima
Value is combined into Pair to collection.If the actual range of N1, N2 is less than at 80 points, then the physical location of N1 is stored in Pair.
Candidate point acquisition process：According to wavelet conversion characteristics, the corresponding data point of R crest value is through multi-resolution decomposition
Afterwards, zero crossing that can be corresponding to the maximum on a certain yardstick to line.But signal can produce displacement in wavelet transformation, that is,
Point corresponding to R wave crest point reality has the zero crossing that certain probability is not maximum pair, has certain distance between 2 points.But R
Wave crest point is necessarily in interval interior between them.So, in some of them embodiment of the present invention, R wave crest point is carried out
Positioning, using analysis maximum between interval range method.In interval range, the point of true amplitude maximum is set to R crest
Candidate point.Definition R wave crest point Candidate Set is R_C, and the candidate point (i.e. second feature point) meeting threshold condition is stored in Candidate Set
For in R_C.
With Wavelet Transform, electrocardiosignal is positioned, obtain waveform as shown in Figure 8.
Step 406, according to fisrt feature point and described second feature point, obtains corresponding characteristic parameter.
According to above-mentioned steps, the fisrt feature point obtaining and second feature point calculate corresponding characteristic value respectively, and these are special
Value indicative includes ecg characteristics, pulse wave characteristic, and electrocardiograph pulse ripple fusion feature.These ecg characteristics, pulse wave characteristic and the heart
Electric pulse wave fusion feature includes cardiac electrophysiology parameter, pulse wave physiological parameter and electrocardiograph pulse ripple physiological parameter.
Wherein, cardiac electrophysiology parameter mainly includes but are not limited to：
Heart rate (heart rate, HR), refers to the heart number of times beated per minute；
Cardiac electrical cycle (EcgPeriod), represents the time span of each cardiac cycle；
SDNN：The standard deviation of phase (i.e. cardiac cycle) sequence between NN；
pNN50：The number that between NN, the difference of interim two neighboring phase is more than 50 milliseconds, accounts for phase sum between all of NN
Percentage；
HRV triangle index：Between NN between total heart rate of phase and NN phase histogram height business；
LF：The integration of low-frequency range (0.04Hz-0.15Hz) in phase power spectral density plot between NN；
HF：The integration of high band (0.15Hz-0.4Hz) in phase power spectral density plot between NN；
LF/HF：The ratio of low-frequency range energy and high band energy in phase power spectral density plot between NN.
Pulse wave physiological parameter mainly includes but are not limited to：
Rise time in systole phase (ppgSystolicTime)：In same cardiac cycle, the trough of pulse wave to crest when
Between be spaced (as shown in t1 in Fig. 9)；
Fall time diastole (ppgDiastolicTime):In same period, the crest of pulse wave is to next trough
Time interval (as shown in t2 in Fig. 9)；
Pulse wave K value：The mean value (Pm-Pd) of pulse wave pressure fluctuation component, in flutter component maximum (Ps-Pd)
Shared percentage (as shown in Figure 10)；
The first derivative of pulse wave (PPG), second dervative characteristic value；
Electrocardiograph pulse ripple physiological parameter：Pulse wave propagation time (Pulse Wave Transit Time, PWTT)：It is ECG
R wave crest point to PPG initiate time interval (as Figure 11).
Further, using assessment parameter selected characteristic parameter from the characteristic value of above-mentioned acquisition.
For realizing the low complex degree matching of continuous BP measurement, uncorrelated or redundancy characteristic value need to be rejected, thus reaching
Reduce Characteristic Number, improve measuring accuracy, reduce the purpose running complexity.
In some of which embodiment of the present invention, characteristic parameter selection process is as follows：
(1) according to characteristic value initialization feature parameter set and characteristic parameter subset.
Specifically, characteristic parameter collection F={ f1,f2,...,fNInclude characteristic value acquiring unit 24 can obtain all of
Cardiac electrophysiology parameter, pulse wave physiological parameter and electrocardiograph pulse ripple physiological parameter.Characteristic parameter subset F ' it is initially set to empty set.
(2) select evaluation function, and multiple characteristic parameter subsets are generated according to this evaluation function.
In some of which embodiment of the present invention, using the evaluation function based on information gain.Wherein, information gain
Computational methods are as follows：
Assume existing characteristics subset A and character subset B, classified variable is C, then comentropy H (C) of classified variable C can
It is expressed as：
By feature FjConditional information entropy H for classified variable C (C | Fj) be expressed as：
Then select feature FjThe change of the comentropy of C in front and back becomes the information gain (Information Gain) of C, can
It is expressed as：IG(C|Fj)=H (C)-H (C | Fj).
In some embodiments of the invention, by the search to proper subspace, the feature selecting side based on decision tree
Method, is maximized based on information gain and selects a characteristic parameter as the Split Attribute of decision tree, recursively give birth to from top to bottom
Become child node, until data set is inseparable, stop decision tree and stop growing.Multiple characteristic parameter are generated by said method
Collection, above-mentioned search procedure can be using search, heuristic search or random search completely.
(3) decision tree beta pruning
Using the evaluation function based on information gain defined above, beta pruning is carried out to set up decision tree, gained is finally determined
Feature at each branch node of plan tree is optimal characteristics collection.That is, the multiple characteristic parameter subset choosings obtaining from above-mentioned steps (2)
Take optimal characteristics subset of parameters.
In some of them embodiment of the present invention, rear beta pruning is carried out to decision tree based on evaluation function, and return optimal
Fork attribute is as optimal characteristics subset of parameters.In addition, evaluation function can be selected based on screening washer and wrapper.Conventional evaluation
Function includes：Correlation, distance, information gain, uniformity, grader error rate.
In some of them embodiment of the present invention, the final characteristic parameter (i.e. optimal characteristics subset of parameters) determining includes：
Pulse wave propagation time, cardiac cycle, rise time in pulse wave systole phase and pulse wave K value.
Step 408, based on corresponding characteristic parameter, sets up the blood pressure computation model of characteristic parameter.
In some embodiments of the invention, pressure value at least includes：Systolic pressure, diastolic pressure and mean blood pressure.
The blood pressure computation model of the characteristic parameter pre-building includes multivariate linear model and nonlinear model.
In some embodiments of the invention, multivariate linear model is the multinomial physiological parameter based on human body and characteristic parameter
Set up, it can obtain the corresponding result of characteristic ginseng value.This multinomial physiological parameter includes：Sex, the age, height, body weight,
Physique than with brachium at least one.
For example, on training sample set, based on pulse wave translation time, cardiac electrical cycle, time in pulse wave systole phase, pulse
Wave characteristic K value, sets up systolic pressure (SBP), the multiple linear regression model of mean blood pressure (MAP) and diastolic pressure (DBP) is such as respectively
Under：
SBP=a1+a2×PWTT+a3×EcgPeriod+a4×PpgSystolicTime+a5× ppg_K, (1)
MAP=b1+b2×PWTT+b3×EcgPeriod+b4×PpgSystolicTime+b5× ppg_K, (2)
DBP=c1+c2×PWTT+c3×EcgPeriod+c4×PpgSystolicTime+c5× ppg_K, (3)
For different subjects, the coefficient a between themi,bi,ciDifferent.Therefore will for different subjects,
To its regression coefficient ai,bi,ciIt is analyzed.Excavated respectively by the method for the data separate statistical analysis of substantial amounts of subject
Relevance between individual regression coefficient and the tested body physiological parameter of itself, from every physiological parameter of subject, picks out
Sex (gender), age (age), height (height), body weight (weight), physique ratio (BMI) and brachium
(armLength) physiological parameter such as, sets up multilinear fitting regression model.Regression coefficient ai,bi,ciWith various physiological parameters
Relation can be expressed as：
Above-mentioned model formation (1), (2) and (3) can develop into following formula (4), (5), (6)：
SBP=P D G, (4)
MAP=P E G, (5)
DBP=P F G, (6)
Wherein, SBP is systolic pressure, and MAP is mean blood pressure, and DBP is diastolic pressure, P=[1 PWTT EcgPeriod
PpgSystolicTime ppg_K], PWTT is pulse wave propagation time, and EcgPeriod is cardiac cycle,
PpgSystolicTime is the rise time in pulse wave systole phase, and ppg_K is pulse wave K value, and D, E and F are respectively systolic pressure, relax
Open pressure and mean blood pressure corresponding bp coefficient matrix,
Gender is sex, and age is the age, and height is height, and weight is body weight, and BMI is physique ratio,
ArmLength is brachium.
On training dataset, corresponding bp coefficient matrix D, E and F can be obtained, and set up corresponding characteristic parameter
Blood pressure computation model.
In some embodiments of the invention, the model of characteristic parameter includes nonlinear model, and nonlinear model includes base
In the nonlinear regression model (NLRM) of SVMs, the step setting up the blood pressure computation model of characteristic parameter includes：
1) obtain the training set between characteristic parameter and systolic pressure.
If known training set { (x1,SBP1),(x2,SBP2),...,(xN,SBPN), wherein
Xi={ PWTTi,EcgPeriodi,PpgSystolicTimei,PPG_Ki}；
2) SVMs commonly use kernel function include linearly, multinomial inner product, Sigmoid inner product, Radial basis kernel function etc.,
Kernel function can by former feature space linearly inseparable Projection Character to another space to realize effectively classifying.In the present invention
In, RBF is selected as kernel function and slack variable (ε, C) based on extensive statistics result；
3) construct and solve optimization problem
Obtain optimal solution
4) construct decision function
Wherein, b can obtain in the following manner,
5) on training set, corresponding systolic pressure and diastolic pressure coefficient matrix can be obtainedWith
b.The computing formula of final blood pressure is represented by：
By processing to the electrocardio of input and pulse wave signal, extract corresponding characteristic value, and be updated to above-mentioned
The blood pressure computation model of the characteristic parameter obtaining, can obtain the pressure value of measurement object, such as systolic pressure, diastolic pressure and average
Blood pressure.
As shown in figure 12, also propose a kind of continuous BP measurement model in the present invention and set up system 500, this system 500 is wrapped
Include：Signal acquisition module 502, feature point extraction module 504, characteristic value acquisition module 506 and model building module 508.
Signal acquisition module 502, for receiving electrocardiosignal and arteries and veins in two groups of synchronous multiple continuous cardiac cycles
Fight ripple signal；
Feature point extraction module 504, for extracting the fisrt feature point of the pulse wave signal of signal acquisition module acquisition, and
Obtain the second feature point of the electrocardiosignal in same cardiac cycle according to fisrt feature point；
Characteristic value acquisition module 506, for according to fisrt feature point and second feature point, obtaining corresponding characteristic parameter；
Model building module 508, for setting up the blood pressure computation model of characteristic parameter.
The continuous BP measurement model of the present embodiment is set up system 500 and is used for realizing aforesaid continuous BP measurement model building
Cube method, therefore continuous BP measurement model are set up being embodied as in system and be can be found in continuous BP measurement model foundation above
The embodiment part of method, for example, signal acquisition module 502, feature point extraction module 504, characteristic value acquisition module 506 and mould
Type set up module 508 be respectively used to realize step 402 in above-mentioned continuous BP measurement method for establishing model, 404,406 and 408,
So, its specific implementation can refer to the description of hereinbefore each embodiment about step 402,404,406 and 408,
This is not repeated.
Fig. 4 is the schematic flow sheet of the continuous BP measurement method for establishing model of one embodiment of the invention.It should be appreciated that
Be although each step in the flow chart of Fig. 4 shows successively according to the instruction of arrow, but these steps are not certainty
Order according to arrow instruction executes successively.Unless expressly stated otherwise herein, the execution of these steps is not strict
Order limits, and it can execute in the other order.And, at least a portion step in Fig. 4 can include many sub-steps
Or multiple stages, these sub-steps or stage are not necessarily to complete in synchronization execution, but can be different
Moment executes, and its execution sequence is also not necessarily and carries out successively, but can be with the sub-step of other steps or other steps
Or at least a portion executed in parallel in stage or alternately execute.
Above each embodiment only implementation just for corresponding steps in illustrating is set forth, Ran Hou
In the case of logic is not conflicting, each embodiment above-mentioned be can be mutually combined and form new technical scheme, and be somebody's turn to do
New technical scheme is still in the open scope of this specific embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by the mode of software plus necessary general hardware platform naturally it is also possible to pass through hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Go out partly can embodying in the form of software product of contribution, this computer software product is carried on a non-volatile meter
In calculation machine readable storage medium (as ROM, magnetic disc, CD, server cloud space), including some instructions with so that a station terminal
Equipment (can be mobile phone, computer, server, or network equipment etc.) executes the method described in each embodiment of the present invention.
Each technical characteristic of embodiment described above can arbitrarily be combined, for making description succinct, not to above-mentioned reality
The all possible combination of each technical characteristic applied in example is all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all it is considered to be the scope of this specification record.
Embodiment described above only have expressed the several embodiments of the present invention, and its description is more concrete and detailed, but simultaneously
Can not therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
Say, without departing from the inventive concept of the premise, some deformation can also be made and improve, these broadly fall into the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be defined by claims.
Claims (15)
1. a kind of continuous blood pressure measurer, described device includes：
Signal picker is including Electrocardial signal acquisition device and pulse wave signal collector, many for synchronous acquisition measurement object
Electrocardiosignal in individual continuous cardiac cycle and pulse wave signal, obtain two groups of synchronous electrocardiosignals and pulse wave signal；
Signal receiving module, for receiving two groups of synchronous electrocardiosignals and pulse wave signal；
Blood pressure computing module, for the electrocardiosignal synchronous according to two groups and pulse wave signal, extracts described pulse wave signal
Fisrt feature point, and the second feature point of the electrocardiosignal in same cardiac cycle is obtained according to described fisrt feature point, according to
Described fisrt feature point and described second feature point obtain corresponding characteristic value, are chosen from described characteristic value using assessment parameter
Characteristic parameter, according to the blood pressure computation model of the described characteristic parameter pre-building, obtains pressure value.
2. device according to claim 1 is it is characterised in that described blood pressure computing module includes：
Characteristic value acquiring unit, for the electrocardiosignal synchronous according to two groups and pulse wave signal, extracts described pulse wave signal
Fisrt feature point, and according to described fisrt feature point obtain same cardiac cycle in electrocardiosignal second feature point；
Characteristic parameter acquiring unit, for according to described fisrt feature point and described second feature point, obtaining corresponding feature ginseng
Number；With
Blood pressure calculation unit, for the blood pressure computation model according to the described characteristic parameter pre-building, obtains pressure value.
3. device according to claim 1 is it is characterised in that described blood pressure computing module also includes：
Filter unit, for being filtered processing to described two groups synchronous electrocardiosignals and pulse wave signal respectively.
4. device according to claim 1 is it is characterised in that described characteristic parameter includes：Pulse wave propagation time, aroused in interest
Cycle, rise time in pulse wave systole phase and pulse wave K value.
5. the device according to claim 2 or 4 it is characterised in that the blood pressure computation model of described characteristic parameter include many
First linear model, described multivariate linear model is：
SBP=P D G,
MAP=P E G,
DBP=P F G,
Wherein, SBP is systolic pressure, and MAP is mean blood pressure, and DBP is diastolic pressure, P=[1 PWTT EcgPeriod
PpgSystolicTime ppg_K], PWTT is described pulse wave propagation time, and EcgPeriod is described cardiac cycle,
PpgSystolicTime is the described rise time in pulse wave systole phase, and ppg_K is described pulse wave K value, and D, E and F are respectively institute
State systolic pressure, described diastolic pressure and described mean blood pressure corresponding bp coefficient matrix, G is the physiological parameter square of measurement object
Battle array, Gender is sex, and age is the age, and height is height, and weight is body weight, and BMI is physique
ArmLength is brachium to ratio.
6. the device according to claim 2 or 4 it is characterised in that the blood pressure computation model of described characteristic parameter include non-
Linear model, described nonlinear model includes the nonlinear regression model (NLRM) based on SVMs, described blood pressure calculation unit base
Process in the nonlinear regression model (NLRM) acquisition pressure value of SVMs includes：
Obtain the training set between described characteristic parameter and described systolic pressure；
Construct decision function using the described nonlinear regression model (NLRM) based on SVMs and calculate optimum solution；
Obtain systolic pressure and the diastolic pressure coefficient matrix based on described data set according to described decision function；
Final pressure value is obtained according to described systolic pressure and diastolic pressure coefficient matrix.
7. device according to claim 2 is it is characterised in that described characteristic parameter selection unit is additionally operable to according to described spy
Value indicative initialization feature parameter set and characteristic parameter subset, choose multiple candidate feature subset, using described valuation functions to institute
State multiple candidate feature subset to be estimated, obtain the characteristic parameter conforming to a predetermined condition.
8. device according to claim 1 is it is characterised in that described device also includes：
Memory module, for storing described characteristic value, described characteristic parameter and its corresponding pressure value；
Display module, for showing described characteristic value, described characteristic parameter and its corresponding pressure value.
9. the device described in 8 is wanted it is characterised in that described device also includes according to right：
Communication module, for receiving two groups of synchronous electrocardiosignals and the pulse wave signal of described signal picker collection, and will
The various data is activations of memory module storage are to external device (ED)；Or,
It is respectively provided with wireless signal Transmit-Receive Unit in signal picker and signal receiving module, signal picker and signal receive
Carried out data transmission by wireless signal between module and communicate.
10. a kind of continuous BP measurement system, described system includes：
Signal acquisition module, for receiving the electrocardiosignal in two groups of synchronous multiple continuous cardiac cycles and pulse wave letter
Number；
Feature point extraction module, for extracting the fisrt feature point of the described pulse wave signal that described signal acquisition module obtains,
And the second feature point of the electrocardiosignal in same cardiac cycle is obtained according to described fisrt feature point；
Characteristic value acquisition module, for according to described fisrt feature point and described second feature point, obtaining corresponding characteristic parameter；
Model building module, for setting up the blood pressure computation model of described characteristic parameter.
A kind of 11. method for building up of continuous BP measurement model, methods described includes：
Obtain the electrocardiosignal in synchronous multiple continuous cardiac cycle and pulse wave signal；
Extract the fisrt feature point of described pulse wave signal, and obtained with wholeheartedly according to the fisrt feature point of described pulse wave signal
The second feature point of the electrocardiosignal in the dynamic cycle；
According to described fisrt feature point and described second feature point, obtain corresponding characteristic parameter；
Based on corresponding characteristic parameter, set up the blood pressure computation model of described characteristic parameter.
12. methods according to claim 11 are it is characterised in that described characteristic parameter includes：Pulse wave propagation time, the heart
Dynamic cycle, rise time in pulse wave systole phase and pulse wave K value.
13. methods according to claim 11 or 12 are it is characterised in that the blood pressure computation model of described characteristic parameter includes
Multivariate linear model, described multivariate linear model is：
SBP=P D G,
MAP=P E G,
DBP=P F G,
Wherein, SBP is described systolic pressure, and MAP is described mean blood pressure, and DBP is described diastolic pressure, P=[1 PWTT
EcgPeriod PpgSystolicTime ppg_K], PWTT is described pulse wave propagation time, and EcgPeriod is described aroused in interest
In the cycle, PpgSystolicTime is the described rise time in pulse wave systole phase, and ppg_K is described pulse wave K value, and D, E and F divide
Not Wei described systolic pressure, described diastolic pressure and described mean blood pressure corresponding bp coefficient matrix,
Gender is described sex, and age is the described age, and height is described height, and weight is described body weight, and BMI is described body
Matter ratio, armLength is described brachium.
14. methods according to claim 11 or 12 are it is characterised in that the blood pressure computation model of described characteristic parameter includes
Nonlinear model, described nonlinear model includes the nonlinear regression model (NLRM) based on SVMs, described sets up described feature
The step of the blood pressure computation model of parameter includes：
Obtain the training set between described characteristic parameter and described systolic pressure；
Construct decision function using the described nonlinear regression model (NLRM) based on SVMs and calculate optimum solution；
Obtain systolic pressure and the diastolic pressure coefficient matrix based on described data set according to described decision function；
Final pressure value is obtained according to described systolic pressure and diastolic pressure coefficient matrix.
15. methods according to claim 11 are it is characterised in that characteristic parameter obtaining step includes:
According to characteristic value initialization feature parameter set and characteristic parameter subset；
Select evaluation function, and multiple characteristic parameter subsets are generated according to described evaluation function；
Optimal characteristics subset of parameters is chosen from the plurality of characteristic parameter subset according to described evaluation function.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2015/086429 WO2017024457A1 (en) | 2015-08-08 | 2015-08-08 | Blood-pressure continuous-measurement device, measurement model establishment method, and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106413534A true CN106413534A (en) | 2017-02-15 |
| CN106413534B CN106413534B (en) | 2020-06-30 |
Family
ID=57982845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201580000417.0A Active CN106413534B (en) | 2015-08-08 | 2015-08-08 | Continuous blood pressure measuring device, measuring model establishing method and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106413534B (en) |
| WO (1) | WO2017024457A1 (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106974631A (en) * | 2017-03-17 | 2017-07-25 | 深圳大学 | A kind of blood pressure measuring method and device based on pulse waveform and electrocardiosignal |
| CN107361753A (en) * | 2017-08-29 | 2017-11-21 | 哈尔滨理工大学 | Health state monitoring method based on pulse wave characteristic point |
| CN107550481A (en) * | 2017-08-24 | 2018-01-09 | 京东方科技集团股份有限公司 | A kind of portable equipment and blood pressure measuring method |
| CN107692993A (en) * | 2017-11-08 | 2018-02-16 | 深圳市玉成创新科技有限公司 | A kind of blood pressure instrument |
| CN107854123A (en) * | 2017-12-13 | 2018-03-30 | 清华大学深圳研究生院 | One kind is without oversleeve continuous blood pressure monitoring method and apparatus |
| WO2018152713A1 (en) * | 2017-02-22 | 2018-08-30 | 清华大学深圳研究生院 | Data processing method for use with blood pressure measuring devices |
| CN108670231A (en) * | 2018-03-14 | 2018-10-19 | 深圳竹信科技有限公司 | Blood pressure measuring method, terminal and computer readable storage medium |
| CN108720821A (en) * | 2018-05-28 | 2018-11-02 | 京东方科技集团股份有限公司 | A kind of blood pressure estimation device and blood pressure estimating system |
| CN108926334A (en) * | 2017-05-26 | 2018-12-04 | 深圳市玉成创新科技有限公司 | Blood pressure acquisition methods and its system and device based on pulse wave |
| CN108937896A (en) * | 2017-05-23 | 2018-12-07 | 深圳先进技术研究院 | A kind of central aortic blood pressure measuring method and equipment |
| CN108992049A (en) * | 2018-06-14 | 2018-12-14 | 深圳鑫想科技有限责任公司 | A kind of smart phone blood pressure test method and system |
| CN109009048A (en) * | 2018-06-12 | 2018-12-18 | 四川斐讯信息技术有限公司 | A kind of PPG peak detection method and system |
| CN109259745A (en) * | 2018-10-25 | 2019-01-25 | 贵州医科大学附属医院 | A kind of wearable cardiovascular and cerebrovascular disease intelligent monitor system and method |
| CN109350031A (en) * | 2018-12-07 | 2019-02-19 | 深圳先进技术研究院 | A kind of photoplethysmographic signal feature point detecting method and device |
| WO2019105105A1 (en) * | 2017-11-28 | 2019-06-06 | 深圳市岩尚科技有限公司 | Classification prediction data processing method for photoplethysmography-based blood pressure measurement device |
| CN109890276A (en) * | 2017-04-01 | 2019-06-14 | 华为技术有限公司 | Monitoring of blood pressure method, apparatus and equipment |
| CN110251105A (en) * | 2019-06-12 | 2019-09-20 | 广州视源电子科技股份有限公司 | A kind of non-invasive blood pressure measuring method, device, equipment and system |
| CN110367957A (en) * | 2018-04-12 | 2019-10-25 | 三星电子株式会社 | Biological information measurement equipment and method for measuring biological information |
| CN110464345A (en) * | 2019-08-22 | 2019-11-19 | 北京航空航天大学 | A kind of separate head bioelectrical power signal interference elimination method and system |
| CN110664386A (en) * | 2019-09-04 | 2020-01-10 | 深圳先进技术研究院 | Acquisition device and method for pulse wave signals |
| CN110974170A (en) * | 2019-12-13 | 2020-04-10 | 中国人民解放军63919部队 | Physiological parameter detection system |
| CN111065321A (en) * | 2017-09-12 | 2020-04-24 | 欧姆龙株式会社 | Pulse wave measuring device, blood pressure measuring apparatus, pulse wave measuring method, and blood pressure measuring method |
| CN111297341A (en) * | 2020-02-20 | 2020-06-19 | 京东方科技集团股份有限公司 | Developments blood pressure check out test set and pulse wave characteristic extraction equipment |
| CN111631733A (en) * | 2020-06-19 | 2020-09-08 | 浙江澍源智能技术有限公司 | Arterial blood spectrum detection method and device |
| CN111904404A (en) * | 2020-08-06 | 2020-11-10 | 苏州国科医工科技发展(集团)有限公司 | Blood pressure regulation and control equipment containing closed-loop monitoring and based on ear vagus nerve stimulation |
| CN111973165A (en) * | 2020-08-14 | 2020-11-24 | 北京航空航天大学 | Linear and nonlinear mixed non-invasive continuous blood pressure measuring system based on PPG |
| CN112656393A (en) * | 2020-12-08 | 2021-04-16 | 山东中科先进技术研究院有限公司 | Heart rate variability detection method and system |
| CN113208573A (en) * | 2021-04-21 | 2021-08-06 | 北京雪扬科技有限公司 | Support wearable equipment of PPG + ECG function |
| CN113520350A (en) * | 2021-07-27 | 2021-10-22 | 香港心脑血管健康工程研究中心有限公司 | Processing method and device for acquiring relevant characteristic parameters and index information of blood pressure map signals |
| CN113854985A (en) * | 2021-08-27 | 2021-12-31 | 联卫医疗科技(上海)有限公司 | Method and device for obtaining machine learning model samples for blood pressure prediction |
| CN113855007A (en) * | 2021-08-27 | 2021-12-31 | 联卫医疗科技(上海)有限公司 | Method and device for obtaining machine learning model samples for blood glucose prediction |
| CN114145724A (en) * | 2021-12-08 | 2022-03-08 | 四川北易信息技术有限公司 | Method for dynamically monitoring blood pressure based on ECG (electrocardiogram) and PPG (photoplethysmography) multiple physiological characteristic parameters |
| CN114305364A (en) * | 2022-01-05 | 2022-04-12 | 北京科技大学 | Blood pressure detection method, system and equipment based on millimeter wave radar |
| CN115670408A (en) * | 2022-12-28 | 2023-02-03 | 可孚医疗科技股份有限公司 | Blood pressure measuring device, linear model coefficient self-correction method and system thereof, and measuring method |
| CN113520350B (en) * | 2021-07-27 | 2024-05-17 | 香港心脑血管健康工程研究中心有限公司 | Processing method and device for acquiring relevant characteristic parameters and index information of blood pressure chart signals |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106343976B (en) * | 2016-09-14 | 2018-09-07 | 京东方科技集团股份有限公司 | The method and apparatus established the method and apparatus of blood pressure model and determine blood pressure |
| CN107184194B (en) * | 2017-07-06 | 2023-03-10 | 中国科学院合肥物质科学研究院 | Automatic blood pressure measuring device and method based on digital control |
| TWI729387B (en) | 2019-05-03 | 2021-06-01 | 華碩電腦股份有限公司 | Wearable device for physiological data detection |
| CN111248881B (en) * | 2020-02-21 | 2022-08-02 | 乐普（北京）医疗器械股份有限公司 | Method and device for predicting blood pressure |
| CN111419205A (en) * | 2020-03-12 | 2020-07-17 | 天津大学 | Three-element cuff-free continuous blood pressure detection system based on artificial neural network |
| CN112932429B (en) * | 2021-02-02 | 2022-08-26 | 成都泰盟软件有限公司 | Automatic real-time calibration method for continuous blood pressure measurement |
| CN113288090B (en) * | 2021-05-06 | 2022-04-22 | 广东工业大学 | Blood pressure prediction method, system, device and storage medium |
| CN113303776B (en) * | 2021-05-28 | 2024-02-09 | 西安理工大学 | Non-contact blood pressure measurement method based on circulating neural network |
| CN113647924A (en) * | 2021-08-20 | 2021-11-16 | 刘明 | Arm-wearing type blood pressure meter based on hongmeng operating system |
| CN114515147B (en) * | 2021-12-20 | 2023-10-03 | 之江实验室 | Physiological monitoring system based on BCG signal and PPG signal fusion |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101193588A (en) * | 2005-03-21 | 2008-06-04 | 海尔思-斯玛特有限公司 | System for continuous blood pressure monitoring |
| CN102008296A (en) * | 2010-12-24 | 2011-04-13 | 吉林大学 | Device and method for measuring arterial blood pressures based on pulse wave signals and electrocardiosignals |
| CN102397064A (en) * | 2011-12-14 | 2012-04-04 | 中国航天员科研训练中心 | Continuous blood pressure measuring device |
| CN103519794A (en) * | 2012-07-04 | 2014-01-22 | 索尼公司 | Measurement apparatus, measurement method, program, storage medium, and measurement system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4869262A (en) * | 1987-02-02 | 1989-09-26 | Pulse Time Products Limited | Device for displaying blood pressure |
| JP3318727B2 (en) * | 1994-06-06 | 2002-08-26 | 日本光電工業株式会社 | Pulse wave transit time sphygmomanometer |
| CN103385702B (en) * | 2013-07-26 | 2015-08-26 | 中国科学院深圳先进技术研究院 | A kind of non-invasive blood pressure continuous detection apparatus and method |
| JP6435128B2 (en) * | 2013-07-26 | 2018-12-05 | タタ・コンサルタンシー・サーヴィシズ・リミテッド | Physiological parameter monitoring |
-
2015
- 2015-08-08 WO PCT/CN2015/086429 patent/WO2017024457A1/en active Application Filing
- 2015-08-08 CN CN201580000417.0A patent/CN106413534B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101193588A (en) * | 2005-03-21 | 2008-06-04 | 海尔思-斯玛特有限公司 | System for continuous blood pressure monitoring |
| CN102008296A (en) * | 2010-12-24 | 2011-04-13 | 吉林大学 | Device and method for measuring arterial blood pressures based on pulse wave signals and electrocardiosignals |
| CN102397064A (en) * | 2011-12-14 | 2012-04-04 | 中国航天员科研训练中心 | Continuous blood pressure measuring device |
| CN103519794A (en) * | 2012-07-04 | 2014-01-22 | 索尼公司 | Measurement apparatus, measurement method, program, storage medium, and measurement system |
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018152713A1 (en) * | 2017-02-22 | 2018-08-30 | 清华大学深圳研究生院 | Data processing method for use with blood pressure measuring devices |
| CN106974631B (en) * | 2017-03-17 | 2020-01-07 | 深圳大学 | Blood pressure measuring method and device based on pulse wave waveform and electrocardiosignal |
| CN106974631A (en) * | 2017-03-17 | 2017-07-25 | 深圳大学 | A kind of blood pressure measuring method and device based on pulse waveform and electrocardiosignal |
| CN109890276A (en) * | 2017-04-01 | 2019-06-14 | 华为技术有限公司 | Monitoring of blood pressure method, apparatus and equipment |
| CN109890276B (en) * | 2017-04-01 | 2021-05-18 | 华为技术有限公司 | Blood pressure monitoring method, device and equipment |
| CN108937896A (en) * | 2017-05-23 | 2018-12-07 | 深圳先进技术研究院 | A kind of central aortic blood pressure measuring method and equipment |
| CN108926334A (en) * | 2017-05-26 | 2018-12-04 | 深圳市玉成创新科技有限公司 | Blood pressure acquisition methods and its system and device based on pulse wave |
| CN107550481A (en) * | 2017-08-24 | 2018-01-09 | 京东方科技集团股份有限公司 | A kind of portable equipment and blood pressure measuring method |
| CN107361753A (en) * | 2017-08-29 | 2017-11-21 | 哈尔滨理工大学 | Health state monitoring method based on pulse wave characteristic point |
| CN111065321A (en) * | 2017-09-12 | 2020-04-24 | 欧姆龙株式会社 | Pulse wave measuring device, blood pressure measuring apparatus, pulse wave measuring method, and blood pressure measuring method |
| CN107692993A (en) * | 2017-11-08 | 2018-02-16 | 深圳市玉成创新科技有限公司 | A kind of blood pressure instrument |
| WO2019105105A1 (en) * | 2017-11-28 | 2019-06-06 | 深圳市岩尚科技有限公司 | Classification prediction data processing method for photoplethysmography-based blood pressure measurement device |
| CN107854123A (en) * | 2017-12-13 | 2018-03-30 | 清华大学深圳研究生院 | One kind is without oversleeve continuous blood pressure monitoring method and apparatus |
| CN107854123B (en) * | 2017-12-13 | 2021-02-02 | 清华大学深圳研究生院 | Sleeveless continuous blood pressure monitoring method and device |
| CN108670231A (en) * | 2018-03-14 | 2018-10-19 | 深圳竹信科技有限公司 | Blood pressure measuring method, terminal and computer readable storage medium |
| CN110367957A (en) * | 2018-04-12 | 2019-10-25 | 三星电子株式会社 | Biological information measurement equipment and method for measuring biological information |
| CN108720821A (en) * | 2018-05-28 | 2018-11-02 | 京东方科技集团股份有限公司 | A kind of blood pressure estimation device and blood pressure estimating system |
| CN109009048A (en) * | 2018-06-12 | 2018-12-18 | 四川斐讯信息技术有限公司 | A kind of PPG peak detection method and system |
| CN108992049A (en) * | 2018-06-14 | 2018-12-14 | 深圳鑫想科技有限责任公司 | A kind of smart phone blood pressure test method and system |
| CN109259745A (en) * | 2018-10-25 | 2019-01-25 | 贵州医科大学附属医院 | A kind of wearable cardiovascular and cerebrovascular disease intelligent monitor system and method |
| CN109350031A (en) * | 2018-12-07 | 2019-02-19 | 深圳先进技术研究院 | A kind of photoplethysmographic signal feature point detecting method and device |
| WO2020114448A1 (en) * | 2018-12-07 | 2020-06-11 | 深圳先进技术研究院 | Photoplethysmography signal feature point detecting method and device |
| CN110251105A (en) * | 2019-06-12 | 2019-09-20 | 广州视源电子科技股份有限公司 | A kind of non-invasive blood pressure measuring method, device, equipment and system |
| CN110251105B (en) * | 2019-06-12 | 2022-06-21 | 广州视源电子科技股份有限公司 | Noninvasive blood pressure measuring method, device, equipment and system |
| CN110464345A (en) * | 2019-08-22 | 2019-11-19 | 北京航空航天大学 | A kind of separate head bioelectrical power signal interference elimination method and system |
| CN110664386A (en) * | 2019-09-04 | 2020-01-10 | 深圳先进技术研究院 | Acquisition device and method for pulse wave signals |
| CN110974170A (en) * | 2019-12-13 | 2020-04-10 | 中国人民解放军63919部队 | Physiological parameter detection system |
| CN111297341A (en) * | 2020-02-20 | 2020-06-19 | 京东方科技集团股份有限公司 | Developments blood pressure check out test set and pulse wave characteristic extraction equipment |
| CN111631733A (en) * | 2020-06-19 | 2020-09-08 | 浙江澍源智能技术有限公司 | Arterial blood spectrum detection method and device |
| CN111631733B (en) * | 2020-06-19 | 2024-01-26 | 浙江澍源智能技术有限公司 | Arterial blood spectrum detection method and device |
| CN111904404A (en) * | 2020-08-06 | 2020-11-10 | 苏州国科医工科技发展(集团)有限公司 | Blood pressure regulation and control equipment containing closed-loop monitoring and based on ear vagus nerve stimulation |
| CN111973165A (en) * | 2020-08-14 | 2020-11-24 | 北京航空航天大学 | Linear and nonlinear mixed non-invasive continuous blood pressure measuring system based on PPG |
| CN112656393A (en) * | 2020-12-08 | 2021-04-16 | 山东中科先进技术研究院有限公司 | Heart rate variability detection method and system |
| CN112656393B (en) * | 2020-12-08 | 2023-06-27 | 山东中科先进技术有限公司 | Method and system for detecting heart rate variability |
| CN113208573A (en) * | 2021-04-21 | 2021-08-06 | 北京雪扬科技有限公司 | Support wearable equipment of PPG + ECG function |
| CN113208573B (en) * | 2021-04-21 | 2022-07-12 | 北京雪扬科技有限公司 | Support wearable equipment of PPG + ECG function |
| CN113520350A (en) * | 2021-07-27 | 2021-10-22 | 香港心脑血管健康工程研究中心有限公司 | Processing method and device for acquiring relevant characteristic parameters and index information of blood pressure map signals |
| CN113520350B (en) * | 2021-07-27 | 2024-05-17 | 香港心脑血管健康工程研究中心有限公司 | Processing method and device for acquiring relevant characteristic parameters and index information of blood pressure chart signals |
| CN113855007A (en) * | 2021-08-27 | 2021-12-31 | 联卫医疗科技(上海)有限公司 | Method and device for obtaining machine learning model samples for blood glucose prediction |
| CN113854985A (en) * | 2021-08-27 | 2021-12-31 | 联卫医疗科技(上海)有限公司 | Method and device for obtaining machine learning model samples for blood pressure prediction |
| CN114145724A (en) * | 2021-12-08 | 2022-03-08 | 四川北易信息技术有限公司 | Method for dynamically monitoring blood pressure based on ECG (electrocardiogram) and PPG (photoplethysmography) multiple physiological characteristic parameters |
| CN114305364A (en) * | 2022-01-05 | 2022-04-12 | 北京科技大学 | Blood pressure detection method, system and equipment based on millimeter wave radar |
| CN114305364B (en) * | 2022-01-05 | 2023-08-11 | 北京科技大学 | Blood pressure detection method, system and equipment based on millimeter wave radar |
| CN115670408A (en) * | 2022-12-28 | 2023-02-03 | 可孚医疗科技股份有限公司 | Blood pressure measuring device, linear model coefficient self-correction method and system thereof, and measuring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106413534B (en) | 2020-06-30 |
| WO2017024457A1 (en) | 2017-02-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106413534A (en) | Blood-pressure continuous-measurement device, measurement model establishment method, and system | |
| CN102429649B (en) | Continuous blood pressure measuring device | |
| JP6721153B2 (en) | Biological information analysis device, system, and program | |
| CN104873186B (en) | A kind of wearable artery detection device and its data processing method | |
| CN102397064B (en) | Continuous blood pressure measuring device | |
| CN102488503B (en) | Continuous blood pressure measurer | |
| WO2019161609A1 (en) | Method for analyzing multi-parameter monitoring data and multi-parameter monitor | |
| CN108577830B (en) | User-oriented physical sign information dynamic monitoring method and system | |
| US8755871B2 (en) | Systems and methods for detecting arrhythmia from a physiological signal | |
| WO2019161608A1 (en) | Multi-parameter monitoring data analysis method and multi-parameter monitoring system | |
| WO2020007041A1 (en) | Blood pressure measurement apparatus and method, electronic device, and computer readable storage medium | |
| CN110251105A (en) | A kind of non-invasive blood pressure measuring method, device, equipment and system | |
| US20150088003A1 (en) | Data integrity | |
| JP2018508273A (en) | Method and apparatus for deriving mean arterial pressure in a subject | |
| US11517223B2 (en) | Apparatus and method for estimating blood glucose | |
| CN204708828U (en) | A kind of wearable noinvasive arterial health checkout gear | |
| CN110236508A (en) | A kind of non-invasive blood pressure continuous monitoring method | |
| KR20200021208A (en) | Apparatus and method for estimating blood pressure | |
| WO2021184803A1 (en) | Blood pressure classification method and apparatus | |
| CN111248881B (en) | Method and device for predicting blood pressure | |
| CN104739394A (en) | Portable human body physiological signal monitoring and alarming system | |
| CN108124419B (en) | Blood pressure measuring method, intelligent heart rate earphone and system | |
| WO2020160058A1 (en) | Systems and methods for computationally efficient non-invasive blood quality measurement | |
| CN113040738B (en) | Blood pressure detecting device | |
| KR20220053439A (en) | Continuous blood pressure monitoring system based on photoplethysmography by using convolutionalbidirectional long short-term memory neural networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |