CN109247929A - Blood pressure determining apparatus, method, equipment and storage medium - Google Patents
Blood pressure determining apparatus, method, equipment and storage medium Download PDFInfo
- Publication number
- CN109247929A CN109247929A CN201811421288.4A CN201811421288A CN109247929A CN 109247929 A CN109247929 A CN 109247929A CN 201811421288 A CN201811421288 A CN 201811421288A CN 109247929 A CN109247929 A CN 109247929A
- Authority
- CN
- China
- Prior art keywords
- pulse wave
- blood pressure
- characteristic point
- 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
- A61B5/02108—Measuring pressure in heart or blood vessels from analysis of pulse wave characteristics
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Cardiology (AREA)
- Veterinary Medicine (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Vascular Medicine (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The embodiment of the invention discloses a kind of blood pressure determining apparatus, method, equipment and storage medium, which includes: acquisition module, for obtaining the default pulse wave characteristic point of measured；Output module, for default pulse wave characteristic point to be input to the blood pressure for obtaining and exporting measured in the blood pressure model trained.The technical issues of blood pressure measuring method for solving the prior art is not suitable for portable, body-worn medical equipment has reached the technical effect for making portable blood pressure measurement have high accuracy.
Description
Technical field
The present embodiments relate to medical data processing technology field more particularly to a kind of blood pressure determining apparatus, method, set
Standby and storage medium.
Background technique
Blood pressure is important one of vital sign.The measurement of blood pressure is not only clinically diagnosing and treating cardiovascular disease
In important evidence and daily life early prevention, early find cardiovascular disease important means.The measurement method of blood pressure can
A variety of to be divided into invasive measurement and non-invasive measurement, interval measurement and continuous measurement etc., wherein continuous BP measurement is in analysis blood pressure
The sides such as the curative effect of variability, the potential hypertension of diagnosis and white coat hypertension, evaluation target organ damage, evaluation drug for hypertension
Mask is significant.
Currently, common noninvasive continuous BP measurement method has angiosthenia method, volume to clamp down on method and Pulse transit time
Method.Wherein, angiosthenia method and volume clamp down on method the device is complicated, cumbersome, are not suitable for being applied to portable, wearable doctor
Equipment is treated, is also unsuitable in hospital's external pelivimetry.Because it requires to apply blood vessel certain pressure, so being used for a long time can give
Measured brings certain discomfort, is not suitable for the long-term continuous measurement of blood pressure.Pulse transit time method overcomes above two
The shortcomings that person, but it is only preferable to systolic pressure measurement effect, it is larger to the measured deviation of diastolic pressure.
To sum up, the blood pressure measuring method of the prior art is not suitable for portable, body-worn medical equipment.
Summary of the invention
The embodiment of the invention provides a kind of blood pressure determining apparatus, method, equipment and storage mediums, to solve the prior art
The technical issues of needing measurement method to be unsuitable for portable, body-worn medical equipment.
In a first aspect, the embodiment of the invention provides a kind of blood pressure determining apparatus, comprising:
Module is obtained, for obtaining the default pulse wave characteristic point of measured；
Output module, for the default pulse wave characteristic point to be input in the blood pressure model trained, to obtain simultaneously
Export the blood pressure of measured.
Second aspect, the embodiment of the invention also provides a kind of blood pressures to determine method, comprising:
The default pulse wave characteristic point of measured is obtained by obtaining module；
The default pulse wave characteristic point is input in the blood pressure model trained by output module, to obtain and defeated
The blood pressure of measured out.
The third aspect, the embodiment of the invention also provides a kind of equipment, the equipment includes:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes that the blood pressure as described in second aspect determines method.
Fourth aspect, it is described the embodiment of the invention also provides a kind of storage medium comprising computer executable instructions
Computer executable instructions determine method for executing the blood pressure as described in second aspect when being executed as computer processor.
The technical solution of blood pressure determining apparatus provided in an embodiment of the present invention, including module and output module are obtained, it obtains
Module is used to obtain the default pulse wave characteristic point of measured；Output module has been instructed for default pulse wave characteristic point to be input to
In experienced blood pressure model, to obtain the blood pressure of measured.It is determined based on portable device high-precision pulse wave signal obtained
Pressure value, to obtain high-precision pressure value by indirect method, realize blood pressure can portable type measuring.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing does one and simply introduces, it should be apparent that, drawings in the following description are some embodiments of the invention, for this
For the those of ordinary skill of field, without creative efforts, it can also be obtained according to these attached drawings others
Attached drawing.
The structural block diagram for the blood pressure determining apparatus that Fig. 1 embodiment of the present invention one provides；
Fig. 2 is the pulse wave schematic diagram that the embodiment of the present invention one provides；
Fig. 3 is the first pulse signal schematic diagram that the embodiment of the present invention one provides；
Fig. 4 is the second pulse signal schematic diagram that the embodiment of the present invention one provides；
Fig. 5 is the baseline schematic diagram that the embodiment of the present invention one provides；
Fig. 6 is the default pulse characteristics point schematic diagram that the embodiment of the present invention one provides；
Fig. 7 is the another baseline schematic diagram that the embodiment of the present invention one provides；
Fig. 8 is the another default pulse characteristics point schematic diagram that the embodiment of the present invention one provides；
Fig. 9 is the flow chart that blood pressure provided by Embodiment 2 of the present invention determines method；
Figure 10 is the flow chart for the blood pressure model training method that the embodiment of the present invention three provides；
Figure 11 is the estimated value for the systolic pressure that the embodiment of the present invention three provides and the dependency diagram of measured value；
Figure 12 is the estimated value for the diastolic pressure that the embodiment of the present invention three provides and the dependency diagram of measured value；
Figure 13 is the estimated value for the mean pressure that the embodiment of the present invention three provides and the dependency diagram of measured value；
Figure 14 is the structural block diagram for the equipment that the embodiment of the present invention four provides.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, hereinafter with reference to attached in the embodiment of the present invention
Figure, clearly and completely describes technical solution of the present invention by embodiment, it is clear that described embodiment is the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Embodiment one
Fig. 1 is the structural block diagram for the blood pressure determining apparatus that the embodiment of the present invention one provides.The device includes obtaining module 11
With output module 12, the default pulse wave characteristic point that module 11 is used to obtain measured is obtained；Output module 12 will be for that will preset
Pulse wave characteristic point is input in the blood pressure model trained, to obtain and export the blood pressure of measured.
Existing monitoring of blood pressure method be usually blood pressure parameter is directly measured, but these methods be unsuitable for it is portable
Formula measurement.To adapt to portable blood pressure measurement, the present embodiment passes through the pressure value that determining measured is fetched between pulse wave.Therefore
It in blood pressure measurement, needs first to obtain the pulse wave (referring to fig. 2) of measured, then passes through pulse wave estimated blood pressure value.
Since pulse wave is continuous wave, data volume is larger, and in order to improve the speed of blood pressure measurement, the present embodiment uses arteries and veins
Fight wave default pulse characteristics click through promoting circulation of blood pressure estimation.Wherein, the method for determination for presetting pulse wave characteristic point may is that by feature
Point extraction unit 111 obtains pulse wave and extracts the characteristic point of acquired pulse wave, and by Standardisation Cell 112 to feature
Point is standardized to obtain default pulse wave characteristic point.
Wherein, the feature point extraction mode of pulse wave is optional are as follows: first determines that subelement determines the wave crest of pulse wave by position
Position and wave trough position, then by feature point extraction subelement according to the characteristic point of crest location and wave trough position extraction pulse wave.
Wherein, position determines that pulse wave is passed through the first bandpass filter and the second bandpass filter by subelement respectively, to respectively obtain
First pulse signal (referring to Fig. 3) and the second pulse signal (referring to fig. 4), wherein the bandwidth of the first bandpass filter is less than
The bandwidth of two band-pass filter, for example the bandpass range of the first bandpass filter is 0.45-2Hz, the band of the second bandpass filter
Logical range is 0.45-20Hz, since the bandwidth of the first bandpass filter is less than the second bandpass filter, compared to the second arteries and veins
It fights signal, the first pulse signal is thick signal, which is the pulse wave signal of serious distortion, eliminates the dicrotic pulse of pulse wave
The detailed information such as wave, dicrotic notch only remain the substantially waveform of similar sine wave, therefore can be using calculus of finite differences or threshold value point
Cut the position that the methods of method detects the maximum value or minimum value of the first pulse wave, i.e. pulse wave estimates crest location or estimates wave
Paddy position, the rough center then detected in the second pulse signal are to estimate center, then seek this and estimate
Maximum value or minimum value within the scope of the default neighborhood of center can further obtain the crest location or trough of pulse wave
Position, wherein the contiguous range of 0.25-0.4s may be selected in default neighborhood range, if default neighborhood range is 0.3s, to estimate
Centered on center, front and back takes the pulse wave signal of 0.15s.
Wherein, the standardization of characteristic point is within the scope of the amplitude transformation to 0-1 by characteristic point, in order to improve the standard of characteristic point
True property, it usually needs influence of the baseline to pulse wave is considered, for this purpose, obtaining module 11 further includes the first baseline determination unit 1131
With the second baseline determination unit 1132, and two baseline determination units respectively correspond two kinds of baseline methods of determination.
First baseline determination unit 1131 is specifically used for: using wave trough position as cut-point, the second pulse of pulse wave being believed
Number it is divided into many sections, one pulse wave of every section of correspondence (i.e. a heartbeat), and each pulse wave includes a wave crest point and two
A trough point.It will be defined as lifting height from the height of first trough point to wave crest, it will be from second trough point to wave crest
Height is defined as falling head.Each pulse wave is increased from first trough point along time shaft to the data point of 10% lifting height
It is defined as the first basic point (starting point), each pulse wave is increased to the data of 10% falling head from second trough point against time shaft
Point is defined as the second basic point (terminal).Baseline will be defined as (referring specifically in Fig. 5 by the straight line of the first basic point and the second basic point
Dotted line).Corresponding to the first baseline determination unit 1131, Standardisation Cell 112 intercepts the waveform between beginning and end first
Then each pulse wave is resampled to the data point of preset quantity, such as 50,70 or 100 by signal using cubic spline interpolation
A data point makes all pulse waves length all having the same to remove influence of the changes in heart rate to pulse wave length；Then subtract
Go baseline with by the first basic point and the second basic point zero setting；Again divided by the maximum value of waveform at this time so that the amplitude of wave crest is set as 1,
Then the pulse wave characteristic point after just being standardized, i.e., default pulse wave characteristic point, as shown in Figure 6.
It is understood that Standardisation Cell can also be before being standardized pulse wave characteristic point, by the first base
Pulse wave between point and the second basic point subtracts baseline, then extracts the characteristic point of each pulse wave again, then makes pulse wave
Characteristic point obtains default pulse wave characteristic point divided by the maximum value of the waveform.It is understood that default pulse wave characteristic point
Wave crest amplitude be 1.
Second baseline determination unit 1132 is specifically used for: using crest location as cut-point, the smart signal of pulse wave being divided
At many sections, one pulse wave of every section of correspondence (i.e. a heartbeat).Because using wave crest as cut-point, each pulse wave includes
Two wave crest points and a trough point, using first wave crest point as the first basic point, using second wave crest point as the second basic point.
The straight line for connecting the first basic point and the second basic point is defined as baseline, referring to Fig. 7.Corresponding to the second baseline determination unit 1132,
Standardisation Cell 112 intercepts the waveform signal between first wave crest point and second wave crest point first, is inserted using cubic spline
Value is resampled to the data point of preset quantity, such as 50,70 or 100 data points, so that all pulse waves all have phase
Same sampling number；Then baseline is subtracted, so that first wave crest point and the second equal zero setting of wave crest point；Again divided by waveform at this time
Minimum value (because baseline is the line of wave crest, waveform is negative after subtracting baseline, so minimum value at this time is negative and absolutely
Value is maximum), it is flipped up the pulse waveform, and the amplitude at original waveform minimum value is 1, has then just obtained default pulse
Wave characteristic point, referring to Fig. 8.
Using wave crest as cut-point, trough is located at centre, is equally avoided that the flat waveform near trough causes segmentation inaccurate
The problem of, it can also obtain better effects.But because being anti-convention way, the single pulse wave intercepted actually spans front and back
Two successive pulse waves, the rising part of sloping portion and the latter pulse wave including previous pulse wave, so it is simultaneously
A not cardiac cycle in matching convention meaning, but same blood pressure precision of prediction with higher.
It is understood that before carrying out feature point extraction to pulse wave, it usually needs first to pulse wave collected
It is pre-processed, therefore the acquisition module of the present embodiment further includes pretreatment unit 114, but the present embodiment is not herein to pretreatment
The specific implementation form of unit is defined, using the prior art.
Since blood pressure parameter includes at least diastolic pressure and systolic pressure, in order to improve the accuracy of each blood pressure parameter, this reality
The blood pressure model trained for applying example includes the regression model for estimating each blood pressure parameter, for example, if blood pressure parameter includes relaxing
When opening pressure and systolic pressure, the blood pressure model trained includes diastolic pressure regression model and systolic pressure regression model.Correspondingly, output
Default pulse wave characteristic point is input to the blood pressure model trained by module 12, is referred to and is inputted default pulse wave characteristic point respectively
The diastolic pressure regression model and systolic pressure regression model trained, to obtain the diastolic pressure and systolic pressure of measured；If blood pressure
Parameter is diastolic pressure, systolic pressure and mean pressure, then the blood pressure model trained includes diastolic pressure regression model, systolic pressure recurrence
It model and averagely pushes back and returns model, correspondingly, default pulse wave characteristic point is input to the blood pressure mould trained by output module 12
Type refers to and default pulse wave characteristic point is inputted the diastolic pressure regression model trained, systolic pressure regression model respectively and is averaged
Regression model is pressed, to obtain diastolic pressure, systolic pressure and the mean pressure of measured.
It is understood that the blood pressure model trained can estimate blood pressure by pulse wave, it is normally based on pulse wave
Contacting between blood pressure data or relationship, and to establish this connection or relationship, then need first to determine blood pressure model, then together
When obtain measured pulse wave and blood pressure data, and based on simultaneously obtain pulse wave and blood pressure data to blood pressure model carry out
Training, therefore the blood pressure determining apparatus of the present embodiment further includes blood pressure model determining module 13.
The blood pressure model determining module 13 is used for while obtaining the pulse wave and blood pressure data of measured；And determine pulse
The diastolic pressure of the default pulse wave characteristic point and default pulse wave characteristic point of wave and blood pressure data, systolic pressure and mean pressure
Corresponding relationship；And it is based on support vector machines, diastolic pressure is established according to the corresponding relationship of default pulse wave characteristic point and diastolic pressure
Regression model establishes systolic pressure regression model according to the corresponding relationship of default pulse wave characteristic point and diastolic pressure, according to default arteries and veins
Wave characteristic of fighting point and the corresponding relationship of mean pressure establish mean pressure regression model.
Wherein, the pulse wave of the present embodiment is obtained is obtained using the prior art, for example, being acquired using optical sensor
The photoplethysmographic signal of finger, or using the pressure pulse signal of pressure sensor acquisition wrist, sample rate should be big
In 50Hz.Invasive blood pressure measuring device can be used in blood pressure instrument, angiosthenia method also can be used, volume clamps down on method or pulse passes
The equipment that the principles such as Time Method carry out continuous BP measurement is led, should ensure that can at least provide systolic pressure value to each heartbeat
And diastolic blood pressure values.In order to propose the stability of hypertension model and the accuracy of blood pressure estimation, the present embodiment is in blood pressure and pulse wave
In collection process, cold water, the stimulating methods such as movement or audio and video of clenching fist can be used, blood pressure is made to have certain fluctuation.
Wherein, the corresponding relationship between pulse wave and blood pressure data is represented by, and presetting pulse wave characteristic point is independent variable,
Blood pressure data is dependent variable.Blood pressure model typically at least includes the diastolic pressure regression model established based on support vector machines and contraction
Regression model is pressed, can also again include the combination of mean pressure regression model.And support vector machines preferably uses Taiwan woods intelligence benevolence to teach
The open source LIBSVM kit awarded, kernel function is preferably Radial basis kernel function.
After blood pressure model determines, when using blood pressure model according to pulse wave estimated blood pressure, it is also necessary to it is trained,
By blood pressure model include diastolic pressure regression model, systolic pressure regression model and averagely push back and return model for.User or factory
Quotient needs first to determine default training samples number, and combines the default pulse wave characteristic point and blood pressure data of default sample size
Inputting diastolic pressure regression model, systolic pressure regression model and averagely pushing back returns model to carry out model training, has been trained with generation
Diastolic pressure regression model, the systolic pressure regression model trained and the mean pressure regression model trained.
To sum up, blood pressure provided in an embodiment of the present invention determines the technical solution of method, obtains measured by obtaining module
Default pulse wave characteristic point；Default pulse wave characteristic point is input in the blood pressure model trained by output module, with
Obtain the blood pressure of measured.Pressure value is determined based on portable device high-precision pulse wave signal obtained, thus between passing through
It connects method and obtains high-precision pressure value, realize blood pressure can portable type measuring.
Embodiment two
Fig. 9 is the flow chart that blood pressure provided by Embodiment 2 of the present invention determines method.The technical solution of the present embodiment is applicable in
In portable type measuring examinee's blood pressure the case where.This method can be held by blood pressure determining apparatus provided in an embodiment of the present invention
Row, the device can be realized by the way of software and/or hardware, and configure and apply in the processor.This method specifically includes
Following steps:
S101, the default pulse wave characteristic point that measured is obtained by obtaining module.
Existing monitoring of blood pressure method be usually blood pressure parameter is directly measured, but these methods be unsuitable for it is portable
Formula measurement.To adapt to portable blood pressure measurement, the present embodiment passes through the pressure value that determining measured is fetched between pulse wave.Therefore
It in blood pressure measurement, needs first to obtain the pulse wave (referring to fig. 2) of measured, then passes through pulse wave estimated blood pressure value.
Since pulse wave is continuous wave, data volume is larger, and in order to improve the speed of blood pressure measurement, the present embodiment use is obtained
Default pulse characteristics acquired in modulus block 11 click through promoting circulation of blood pressure estimation.Wherein, the determination method packet of pulse wave characteristic point is preset
It includes: pulse wave is obtained by feature point extraction unit 111 and extract the characteristic point of acquired pulse wave, and by Standardisation Cell
112 pairs of characteristic points are standardized to obtain default pulse wave characteristic point.
Wherein, the Feature Points Extraction of pulse wave specifically: first determine that subelement determines the wave crest of pulse wave by position
Position and wave trough position, then by feature point extraction subelement according to the characteristic point of crest location and wave trough position extraction pulse wave.
Wherein, the determination method of wave crest and wave trough position are as follows: determine that pulse wave will be passed through respectively the filter of the first band logical by subelement by position
Wave device and the second bandpass filter, to respectively obtain the first pulse signal (referring to Fig. 3) and the second pulse signal (referring to fig. 4),
Wherein, bandwidth of the bandwidth of the first bandpass filter less than the second bandpass filter, such as the band logical model of the first bandpass filter
It encloses for 0.45-2Hz, the bandpass range of the second bandpass filter is 0.45-20Hz, since the bandwidth of the first bandpass filter is less than
Second bandpass filter, therefore compared to the second pulse signal, the first pulse signal is thick signal, which is serious distortion
Pulse wave signal, eliminates the detailed information such as dicrotic wave, the dicrotic notch of pulse wave, only remains the substantially wave of similar sine wave
Shape, therefore the position of the maximum value or minimum value of the first pulse wave can be detected using the methods of calculus of finite differences or thresholding method,
That is pulse wave estimates crest location or estimates wave trough position, the rough center then detected in the second pulse signal
To estimate center, then seeks this and estimate the maximum value or minimum value within the scope of the default neighborhood of center, Ji Kejin
One step obtains the crest location or wave trough position of pulse wave, wherein the neighborhood model of 0.25-0.4s may be selected in default neighborhood range
It encloses, if default neighborhood range is 0.3s, centered on estimating center, front and back takes the pulse wave signal of 0.15s.
Wherein, the standardization of characteristic point is within the scope of the amplitude transformation to 0-1 by characteristic point, in order to improve the standard of characteristic point
True property, it usually needs influence of the baseline to pulse wave is considered, for this purpose, obtaining module 11 further includes the first baseline determination unit 1131
With the second baseline determination unit 1132, two baseline determination units respectively correspond different baseline methods of determination.
First baseline determination unit 1131 is specifically used for: using wave trough position as cut-point, the second pulse of pulse wave being believed
Number it is divided into many sections, one pulse wave of every section of correspondence (i.e. a heartbeat), and each pulse wave includes a wave crest point and two
A trough point.It will be defined as lifting height from the height of first trough point to wave crest, it will be from second trough point to wave crest
Height is defined as falling head.Each pulse wave is increased from first trough point along time shaft to the data point of 10% lifting height
It is defined as the first basic point (starting point), each pulse wave is increased to the data of 10% falling head from second trough point against time shaft
Point is defined as the second basic point (terminal).Baseline will be defined as (referring specifically in Fig. 5 by the straight line of the first basic point and the second basic point
Dotted line).Corresponding to the first baseline determination unit 1131, Standardisation Cell 112 intercepts the waveform between beginning and end first
Then each pulse wave is resampled to the data point of preset quantity, such as 50,70 or 100 by signal using cubic spline interpolation
A data point makes all pulse waves length all having the same to remove influence of the changes in heart rate to pulse wave length；Then subtract
Go baseline with by the first basic point and the second basic point zero setting；Again divided by the maximum value of waveform at this time so that the amplitude of wave crest is set as 1,
Then the pulse wave characteristic point after just being standardized, i.e., default pulse wave characteristic point.
As shown in Figure 6.It is understood that Standardisation Cell can also be standardized it to pulse wave characteristic point
Before, the pulse wave between the first basic point and the second basic point is subtracted into baseline, then extracts the characteristic point of each pulse wave again, then
Make the characteristic point of pulse wave divided by the maximum value of the waveform to obtain default pulse wave characteristic point.It is understood that default arteries and veins
The wave crest amplitude of wave characteristic of fighting point is 1.
Second baseline determination unit 1132 is specifically used for: using crest location as cut-point, the smart signal of pulse wave being divided
At many sections, one pulse wave of every section of correspondence (i.e. a heartbeat).Because using wave crest as cut-point, each pulse wave includes
Two wave crest points and a trough point, using first wave crest point as the first basic point, using second wave crest point as the second basic point.
The straight line for connecting the first basic point and the second basic point is defined as baseline, referring to Fig. 7.Corresponding to the second baseline determination unit 1132,
Standardisation Cell 112 intercepts the waveform signal between first wave crest point and second wave crest point first, is inserted using cubic spline
Value is resampled to the data point of preset quantity, such as 50,70 or 100 data points, so that all pulse waves all have phase
Same sampling number；Then baseline is subtracted, so that first wave crest point and the second equal zero setting of wave crest point；Again divided by waveform at this time
Minimum value (because baseline is the line of wave crest, waveform is negative after subtracting baseline, so minimum value at this time is negative and absolutely
Value is maximum), it is flipped up the pulse waveform, and the amplitude at original waveform minimum value is 1, has then just obtained default pulse
Wave characteristic point, referring to Fig. 8.
Using wave crest as cut-point, trough is located at centre, is equally avoided that the flat waveform near trough causes segmentation inaccurate
The problem of, it can also obtain better effects.But because being anti-convention way, the single pulse wave intercepted actually spans front and back
Two successive pulse waves, the rising part of sloping portion and the latter pulse wave including previous pulse wave, so it is simultaneously
A not cardiac cycle in matching convention meaning, but same blood pressure precision of prediction with higher.
It is understood that before carrying out feature point extraction to pulse wave, it usually needs first to pulse wave collected
It is pre-processed, the present embodiment is not defined pretreated specific method.
S102, default pulse wave characteristic point is input in the blood pressure model trained by output module, to obtain simultaneously
Export the blood pressure of measured.
Blood pressure parameter includes at least diastolic pressure and systolic pressure, in order to improve the accuracy of each blood pressure parameter, the present embodiment
The blood pressure model trained include the regression model for estimating each blood pressure parameter, for example, if blood pressure parameter includes diastolic pressure
When with systolic pressure, the blood pressure model trained includes diastolic pressure regression model and systolic pressure regression model.Correspondingly, output module
Default pulse wave characteristic point is input to the blood pressure model trained by 12, is referred to respectively to input default pulse wave characteristic point and instructed
Experienced diastolic pressure regression model and systolic pressure regression model, to obtain the diastolic pressure and systolic pressure of measured；If blood pressure parameter
For diastolic pressure, systolic pressure and mean pressure, then the blood pressure model trained includes diastolic pressure regression model, systolic pressure regression model
It averagely pushes back and returns model, correspondingly, default pulse wave characteristic point is input to the blood pressure model trained by output module 12, be
Default pulse wave characteristic point is inputted the diastolic pressure regression model trained, systolic pressure regression model respectively and averagely pushed back by finger returns
Model, to obtain diastolic pressure, systolic pressure and the mean pressure of measured.
Blood pressure provided in an embodiment of the present invention determines the technical solution of method, comprising: obtains the default pulse wave of measured
Characteristic point；Default pulse wave characteristic point is input in the blood pressure model trained, to obtain the blood pressure of measured.Based on portable
Formula equipment high-precision pulse wave signal obtained determines pressure value, so that high-precision pressure value is obtained by indirect method,
Realize blood pressure can portable type measuring.
Embodiment three
Figure 10 is the flow chart for the blood pressure model training method that the embodiment of the present invention three provides.The embodiment of the present invention is above-mentioned
On the basis of embodiment, the step of increasing blood pressure model training method, this method comprises:
S1001, the pulse wave and blood pressure data for obtaining measured simultaneously.
The blood pressure model trained can estimate blood pressure by pulse wave, be normally based between pulse wave and blood pressure data
Connection or relationship, and to establish this connection or relationship, then need to obtain the pulse wave and blood pressure data of measured simultaneously.
Wherein, the pulse wave of the present embodiment is obtained is obtained using the prior art, for example, being acquired using optical sensor
The photoplethysmographic signal of finger, or using the pressure pulse signal of pressure sensor acquisition wrist, sample rate should be big
In 50Hz.Invasive blood pressure measuring device can be used in blood pressure instrument, angiosthenia method also can be used, volume clamps down on method or pulse passes
The equipment that the principles such as Time Method carry out continuous BP measurement is led, should ensure that can at least provide systolic pressure value to each heartbeat
And diastolic blood pressure values.In order to propose the stability of hypertension model and the accuracy of blood pressure estimation, the present embodiment is in blood pressure and pulse wave
In collection process, cold water, the stimulating methods such as movement or audio and video of clenching fist can be used, blood pressure is made to have certain fluctuation.
S1002, the default pulse wave characteristic point for determining pulse wave and default pulse wave characteristic point and blood pressure data relax
Open the corresponding relationship of pressure, systolic pressure and mean pressure.
Using the default pulse wave characteristic point of measured as independent variable, pair of the two is established using blood pressure data as dependent variable
It should be related to.
S1003, it is based on support vector machines, diastolic pressure is established according to the corresponding relationship of default pulse wave characteristic point and diastolic pressure
Regression model establishes systolic pressure regression model according to the corresponding relationship of default pulse wave characteristic point and diastolic pressure, according to default arteries and veins
Wave characteristic of fighting point and the corresponding relationship of mean pressure establish mean pressure regression model.
Wherein, blood pressure model typically at least includes that the diastolic pressure regression model established based on support vector machines and contraction are pushed back
Return model, can also again include the combination of mean pressure regression model.With blood pressure model include diastolic pressure regression model, shrink push back
Return model and averagely push back return model for illustrate.Determine default training samples number first, and by the pre- of default sample size
If pulse wave characteristic point and blood pressure data combination, which input diastolic pressure regression model, systolic pressure regression model and averagely push back, returns model
Model training is carried out, to generate the diastolic pressure regression model trained, the systolic pressure regression model trained and train flat
Press regression model.Wherein, the open source LIBSVM kit that support vector machines preferably uses Taiwan Lin Zhiren to teach, kernel function are excellent
It is selected as Radial basis kernel function.
Illustratively, the pulse wave pulse wave of 70 healthy measured is acquired using medical pulse blood oxygen instrument, while with company
Each heart of continuous survey meter of blood pressure Finapres (Finapres Medical Systems B.V, Holland) measurement measured is fought
Dynamic systolic pressure, diastolic pressure and mean pressure makes blood pressure generate certain fluctuation in experiment by cold water stimulating.
The accuracy of regression model is verified using 10 folding cross validation methods.Firstly, by the pulse wave of each measured
Being divided into 10 equal-sized subsample collection with blood pressure data, (input vector is default pulse wave characteristic point, and target value is to shrink
Pressure, diastolic pressure and mean pressure), wherein 9 subsets are used to Training Support Vector Machines regression model, leave an individual subset and make
The precision of model is verified for test data.Then, it still further selects 9 subsets to be used to train blood pressure model, leaves one individually
Subset as test data verifying blood pressure model precision.So analogize, is repeated 10 times altogether, each subset verifying one
It is secondary,
The exemplary verification result for providing wherein one-time authentication of the present embodiment, such as Figure 11, such as 12 and Figure 13, wherein Figure 11
The relationship between the estimated value of diastolic pressure and measured value is shown, Figure 12 is shown between the estimated value of systolic pressure and measured value
Relationship, Figure 13 show the relationship between the estimated value of mean pressure and measured value.In order to better describe the blood pressure mould trained
The blood pressure estimated accuracy of type calculates related coefficient (CC), the mean square error (RMSE), mean error of the blood pressure of each measured
(ME) and the statistics such as the standard deviation of error (SD), calculation formula are as follows:
Wherein, y indicates the estimated value of blood pressure model, specifically: if blood pressure model is diastolic pressure regression model, y table
Show diastolic pressure estimated value, if blood pressure model is systolic pressure regression model, y indicates systolic pressure estimated value, if blood pressure model
For mean pressure regression model, then y indicates mean pressure estimated value；X indicates the measured value of continuous BP measurement instrument, specifically: if
Blood pressure model is diastolic pressure regression model, then x indicates the measured value of diastolic pressure, if blood pressure model is systolic pressure regression model,
Then x indicates the measured value of systolic pressure, if blood pressure model is mean pressure regression model, x indicates the measured value of mean pressure；N table
Show sample size, i.e., each subject can be used for the effective beats calculated.
Calculated result is summarized in table one, specific as follows:
The blood pressure that one blood pressure model of table estimates is compared with surveying blood pressure
Wherein, SBP is systolic pressure, and DBP is diastolic pressure, and MBP is mean pressure.
Table one is shown, using the obtained blood pressure data of the blood pressure model standard with higher trained of the present embodiment
True property, therefore it is contemplated that it in portable blood pressure fields of measurement practicability with higher.
Example IV
Figure 14 is the structural schematic diagram for the equipment that the embodiment of the present invention four provides, and as shown in figure 14, which includes processing
Device 201, memory 202, input unit 203 and output device 204；In equipment the quantity of processor 201 can be one or
It is multiple, in Figure 14 by taking a processor 201 as an example；Processor 201, memory 202, input unit 203 in equipment and defeated
Device 204 can be connected by bus or other modes out, in Figure 14 for being connected by bus.
Memory 202 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, as the blood pressure in the embodiment of the present invention determines the corresponding program instruction/module of method (for example, obtaining module 11
With output module 12).Software program, instruction and the module that processor 201 is stored in memory 202 by operation, thus
The various function application and data processing for executing equipment, that is, realize that above-mentioned blood pressure determines method.
Memory 202 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function；Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 202 may include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 202 can be into one
Step includes the memory remotely located relative to processor 201, these remote memories can pass through network connection to equipment.On
The example for stating network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 203 can be used for receiving the number or character information of input, and generate with the user setting of equipment with
And the related key signals input of function control.
Output device 204 may include that display screen etc. shows equipment, for example, the display screen of user terminal.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium comprising computer executable instructions, and the computer can be held
Row instruction determines method for executing a kind of blood pressure when being executed by computer processor, this method comprises:
The default pulse wave characteristic point of measured is obtained by obtaining module；
The default pulse wave characteristic point is input in the blood pressure model trained by output module, to obtain and defeated
The blood pressure of measured out.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed blood pressure provided by any embodiment of the invention and determines
Relevant operation in method.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, abbreviation ROM), random access memory (Random such as computer
Access Memory, abbreviation RAM), flash memory (FLASH), hard disk or CD etc., including some instructions use so that an equipment
(can be personal computer, server or the network equipment etc.) executes blood pressure determination side described in each embodiment of the present invention
Method.
It is worth noting that, included each unit and module are only pressed in the embodiment of above-mentioned blood pressure determining apparatus
It is divided, but is not limited to the above division according to function logic, as long as corresponding functions can be realized；In addition,
The specific name of each functional unit is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of blood pressure determining apparatus characterized by comprising
Module is obtained, for obtaining the default pulse wave characteristic point of measured；
Output module, for the default pulse wave characteristic point to be input in the blood pressure model trained, to obtain and export
The blood pressure of measured.
2. the apparatus according to claim 1, which is characterized in that the acquisition module includes:
Feature point extraction unit for obtaining the pulse wave of measured, and extracts the characteristic point of the pulse wave；
Standardisation Cell, for being standardized to the characteristic point, to obtain default pulse wave characteristic point.
3. the apparatus of claim 2, which is characterized in that the feature point extraction unit includes:
Position determines subelement, for obtaining the pulse wave of measured, and determines crest location and the trough position of the pulse wave
It sets；
Feature point extraction subelement, for extracting the feature of the pulse wave according to the crest location and the wave trough position
Point.
4. device according to claim 3, which is characterized in that the position determines that subelement is specifically used for obtaining measured
Pulse wave, and the pulse wave is passed through into the first bandpass filter and the second bandpass filter respectively, to respectively obtain first
Pulse signal and the second pulse signal；Determine that estimating for pulse wave and estimates trough at crest location according to first pulse signal
Position；Center position is estimated according to what second pulse wave signal determined pulse wave；According to it is described estimate center position,
It is described to estimate crest location and the crest location and wave trough position estimated wave trough position and determine the pulse wave, wherein institute
State bandwidth of the bandwidth less than the second bandpass filter of the first bandpass filter.
5. the apparatus of claim 2, which is characterized in that the acquisition module further include:
First baseline determination unit, for when the pulse wave includes two troughs, respectively higher than two troughs first to be preset
Height and the second preset height o'clock as two basic points, using the line of two basic points as baseline；
Correspondingly, Standardisation Cell is specifically used for: using the characteristic point and the difference of the baseline as the feature after removing baseline
Point, and by the characteristic point gone after baseline divided by the maximum value of current pulse wave, to obtain default pulse wave characteristic point.
6. -5 any device according to claim 1, which is characterized in that the acquisition module further include:
Second baseline determines subelement, is used for when the pulse wave includes two wave crests, by the company of two wave crests of pulse wave
Line is as baseline；
Correspondingly, Standardisation Cell is specifically used for: using the characteristic point and the difference of the baseline as the feature after removing baseline
Point, and by the characteristic point gone after baseline divided by the minimum value of current pulse wave, to obtain default pulse wave characteristic point.
7. device according to claim 6, which is characterized in that further include blood pressure model determining module, the blood pressure model
Determining module is used for while obtaining the pulse wave and blood pressure data of measured；Determine the default pulse wave characteristic of the pulse wave
Point, and determine that the default pulse wave characteristic point is corresponding with the diastolic pressure of the blood pressure data, systolic pressure and mean pressure and close
System；And it is based on support vector machines, diastole is established according to the corresponding relationship of the default pulse wave characteristic point and the diastolic pressure
Regression model is pressed, systolic pressure regression model is established according to the corresponding relationship of default pulse wave characteristic point and the diastolic pressure, according to
The default pulse wave characteristic point and the corresponding relationship of the mean pressure establish mean pressure regression model.
8. a kind of blood pressure determines method characterized by comprising
The default pulse wave characteristic point of measured is obtained by obtaining module；
The default pulse wave characteristic point is input in the blood pressure model trained by output module, to obtain and export quilt
The blood pressure of survey person.
9. a kind of equipment, which is characterized in that the equipment includes:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now blood pressure as claimed in claim 8 determines method.
10. a kind of storage medium comprising computer executable instructions, which is characterized in that the computer executable instructions by
Method is determined for executing blood pressure as claimed in claim 8 when computer processor executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811421288.4A CN109247929B (en) | 2018-11-26 | 2018-11-26 | Blood pressure determination device, method, apparatus, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811421288.4A CN109247929B (en) | 2018-11-26 | 2018-11-26 | Blood pressure determination device, method, apparatus, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109247929A true CN109247929A (en) | 2019-01-22 |
| CN109247929B CN109247929B (en) | 2021-04-27 |
Family
ID=65042154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811421288.4A Expired - Fee Related CN109247929B (en) | 2018-11-26 | 2018-11-26 | Blood pressure determination device, method, apparatus, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109247929B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021068193A1 (en) * | 2019-10-11 | 2021-04-15 | 中国科学院深圳先进技术研究院 | Method and apparatus for monitoring blood pressure waveform |
| CN113229788A (en) * | 2021-03-26 | 2021-08-10 | 中科院长春应化所黄埔先进材料研究院 | Pulse wave denoising method and device based on film pressure sensor |
| CN116942102A (en) * | 2023-09-19 | 2023-10-27 | 北京清雷科技有限公司 | Sleep stage method and device based on pulse wave |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040087863A1 (en) * | 2002-10-30 | 2004-05-06 | Eide Per Kristian | Method for analysis of single pulse pressure waves |
| JP2012170721A (en) * | 2011-02-23 | 2012-09-10 | Fukuda Denshi Co Ltd | Bioinformation analysis device, bioinformation analysis method and bioinformation analysis program |
| CN103908236A (en) * | 2013-05-13 | 2014-07-09 | 天津点康科技有限公司 | Automatic blood pressure measuring system |
| CN105286815A (en) * | 2015-11-02 | 2016-02-03 | 重庆大学 | Pulse wave signal feature point detection method based on waveform time domain features |
| US20160158431A1 (en) * | 2012-07-13 | 2016-06-09 | Gambro Lundia Ab | Filtering of pressure signals for suppression of periodic tables |
| CN105726006A (en) * | 2005-04-13 | 2016-07-06 | 爱德华兹生命科学公司 | Pulse contour method and apparatus for continuous assessment of a cardiovascular parameter |
| CN106037694A (en) * | 2016-05-13 | 2016-10-26 | 吉林大学 | Continuous blood pressure measuring device based on pulse waves |
| US20170105634A1 (en) * | 2015-10-20 | 2017-04-20 | Denso Corporation | Pulse Wave Signal Processor |
| CN107530005A (en) * | 2015-02-09 | 2018-01-02 | 日东电工株式会社 | Method and apparatus for the mean arterial pressure of derived object |
| CN107669256A (en) * | 2017-11-13 | 2018-02-09 | 深圳先进技术研究院 | Measuring method, the device and system of continuous blood pressure |
| US20180177420A1 (en) * | 2016-12-26 | 2018-06-28 | Nihon Kohden Corporation | Atrial fibrillation detector, atrial fibrillation detecting method, and computer readable medium |
| CN108261191A (en) * | 2016-12-30 | 2018-07-10 | 深圳先进技术研究院 | Continuous BP measurement method, apparatus and equipment |
| CN108403100A (en) * | 2018-02-09 | 2018-08-17 | 重庆东渝中能实业有限公司 | Blood pressure computational methods based on oscillation wave waveform envelope feature |
| CN108652605A (en) * | 2018-03-27 | 2018-10-16 | 上海交通大学 | Real-time blood pressure monitoring device based on single channel PPG signals |
| 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 |
-
2018
- 2018-11-26 CN CN201811421288.4A patent/CN109247929B/en not_active Expired - Fee Related
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040087863A1 (en) * | 2002-10-30 | 2004-05-06 | Eide Per Kristian | Method for analysis of single pulse pressure waves |
| CN105726006A (en) * | 2005-04-13 | 2016-07-06 | 爱德华兹生命科学公司 | Pulse contour method and apparatus for continuous assessment of a cardiovascular parameter |
| JP2012170721A (en) * | 2011-02-23 | 2012-09-10 | Fukuda Denshi Co Ltd | Bioinformation analysis device, bioinformation analysis method and bioinformation analysis program |
| US20160158431A1 (en) * | 2012-07-13 | 2016-06-09 | Gambro Lundia Ab | Filtering of pressure signals for suppression of periodic tables |
| CN103908236A (en) * | 2013-05-13 | 2014-07-09 | 天津点康科技有限公司 | Automatic blood pressure measuring system |
| CN107530005A (en) * | 2015-02-09 | 2018-01-02 | 日东电工株式会社 | Method and apparatus for the mean arterial pressure of derived object |
| US20170105634A1 (en) * | 2015-10-20 | 2017-04-20 | Denso Corporation | Pulse Wave Signal Processor |
| CN105286815A (en) * | 2015-11-02 | 2016-02-03 | 重庆大学 | Pulse wave signal feature point detection method based on waveform time domain features |
| CN106037694A (en) * | 2016-05-13 | 2016-10-26 | 吉林大学 | Continuous blood pressure measuring device based on pulse waves |
| US20180177420A1 (en) * | 2016-12-26 | 2018-06-28 | Nihon Kohden Corporation | Atrial fibrillation detector, atrial fibrillation detecting method, and computer readable medium |
| CN108261191A (en) * | 2016-12-30 | 2018-07-10 | 深圳先进技术研究院 | Continuous BP measurement method, apparatus and equipment |
| CN107669256A (en) * | 2017-11-13 | 2018-02-09 | 深圳先进技术研究院 | Measuring method, the device and system of continuous blood pressure |
| CN108403100A (en) * | 2018-02-09 | 2018-08-17 | 重庆东渝中能实业有限公司 | Blood pressure computational methods based on oscillation wave waveform envelope feature |
| CN108652605A (en) * | 2018-03-27 | 2018-10-16 | 上海交通大学 | Real-time blood pressure monitoring device based on single channel PPG signals |
| 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 |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021068193A1 (en) * | 2019-10-11 | 2021-04-15 | 中国科学院深圳先进技术研究院 | Method and apparatus for monitoring blood pressure waveform |
| CN113229788A (en) * | 2021-03-26 | 2021-08-10 | 中科院长春应化所黄埔先进材料研究院 | Pulse wave denoising method and device based on film pressure sensor |
| CN113229788B (en) * | 2021-03-26 | 2022-07-19 | 广东粤港澳大湾区黄埔材料研究院 | Pulse wave denoising method and device based on film pressure sensor |
| CN116942102A (en) * | 2023-09-19 | 2023-10-27 | 北京清雷科技有限公司 | Sleep stage method and device based on pulse wave |
| CN116942102B (en) * | 2023-09-19 | 2023-12-22 | 北京清雷科技有限公司 | Sleep stage method and device based on pulse wave |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109247929B (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gaurav et al. | Cuff-less PPG based continuous blood pressure monitoring—A smartphone based approach | |
| Liu et al. | Modeling carotid and radial artery pulse pressure waveforms by curve fitting with Gaussian functions | |
| Yan et al. | Novel deep convolutional neural network for cuff-less blood pressure measurement using ECG and PPG signals | |
| CN108498089A (en) | A kind of noninvasive continuous BP measurement method based on deep neural network | |
| Wang et al. | Photoplethysmography-based blood pressure estimation combining filter-wrapper collaborated feature selection with LASSO-LSTM model | |
| WO2019127623A1 (en) | Method and device for constructing model for estimating arterial blood vessel age | |
| CN109247929A (en) | Blood pressure determining apparatus, method, equipment and storage medium | |
| Yang et al. | Estimation and validation of arterial blood pressure using photoplethysmogram morphology features in conjunction with pulse arrival time in large open databases | |
| Mehrabadi et al. | Novel blood pressure waveform reconstruction from photoplethysmography using cycle generative adversarial networks | |
| Chen et al. | Assessment of algorithms for oscillometric blood pressure measurement | |
| Karamanoglu | A system for analysis of arterial blood pressure waveforms in humans | |
| CN115003215A (en) | System and method for pulse transit time measurement from optical data | |
| Jean Effil et al. | Wavelet scattering transform and long short-term memory network-based noninvasive blood pressure estimation from photoplethysmograph signals | |
| CN114929101A (en) | System and method for physiological measurement based on optical data | |
| CN111839488A (en) | Non-invasive continuous blood pressure measuring device and method based on pulse wave | |
| Mejía-Mejía et al. | Comparison of pulse rate variability and morphological features of photoplethysmograms in estimation of blood pressure | |
| Kanoga et al. | Comparison of seven shallow and deep regressors in continuous blood pressure and heart rate estimation using single-channel photoplethysmograms under three evaluation cases | |
| JP2002253521A (en) | Analysis method and device for biological reaction waveform information, and diagnostic device | |
| US20220323023A1 (en) | Method for determining respiratory rate | |
| Zhuang et al. | Remote blood pressure measurement via spatiotemporal mapping of a short-time facial video | |
| Alam et al. | UbiHeart: A novel approach for non-invasive blood pressure monitoring through real-time facial video | |
| Sun et al. | Noninvasive Blood Pressure Prediction Based on Dual Encoder U-Net | |
| Ma et al. | Continuous non-invasive arterial blood pressure monitoring with photoplethysmography via SE-MSResUNet network | |
| Kumar et al. | Long Short Term Memory (LSTM)-based Cuffless Continuous Blood Pressure Monitoring | |
| Kanoga et al. | Comparison of six shallow and deep regressors in continuous blood pressure and heart rate estimation using single-channel photoplethysmograms |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210427 Termination date: 20211126 |