CN111493855B - System and method for non-invasive measurement of individualized cardiac output - Google Patents
System and method for non-invasive measurement of individualized cardiac output Download PDFInfo
- Publication number
- CN111493855B CN111493855B CN202010317299.9A CN202010317299A CN111493855B CN 111493855 B CN111493855 B CN 111493855B CN 202010317299 A CN202010317299 A CN 202010317299A CN 111493855 B CN111493855 B CN 111493855B
- Authority
- CN
- China
- Prior art keywords
- pulse wave
- artery
- module
- vector
- blood 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.)
- Active
Links
Images
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
- A61B5/026—Measuring blood flow
- A61B5/029—Measuring or recording blood output from the heart, e.g. minute volume
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Abstract
The invention discloses a non-invasive measuring system and a method for individualized cardiac output, which comprises a brachial artery blood pressure measuring module, a peripheral superficial layer artery pulse wave measuring module and a pulse wave conduction velocity measuring module; the pulse wave correction module corrects peripheral superficial arterial pulse waves according to brachial artery blood pressure parameters; the pulse wave feature extraction module is used for extracting pulse wave features and outputting the pulse wave features to the individualized pulse feature vector generation module, and the generated individualized pulse wave feature vector comprises the pulse wave features and the individual physiological parameters of the testee; the artificial neural network identifies corresponding stroke volume according to the individualized pulse wave feature vector, and the cardiac output calculating module calculates the cardiac output according to the stroke volume. The invention solves the technical problem that the accuracy of the non-invasive measurement method in the prior art for measuring the cardiac output of an individual is not high, and greatly reduces the difference between the non-invasive measurement and the measurement accuracy of the gold standard method.
Description
Technical Field
The invention belongs to the technical field of cardiac output measurement, and particularly relates to the technical field of noninvasive cardiac output measurement.
Background
The Cardiac Output (CO) is the ejection volume of the left ventricle per minute, is the most important parameter for characterizing the health status of the cardiovascular system, and is an important diagnostic basis for cardiac function and cardiovascular diseases. In addition, many other cardiovascular system parameters can be calculated in an auxiliary manner based on the cardiac output, so that accurate measurement of the cardiac output is very critical in the aspects of cardiovascular disease detection, treatment and the like, and has important clinical significance.
Currently, devices and methods for measuring cardiac output fall into three major categories, invasive, minimally invasive and non-invasive.
The invasive device and method is to insert a catheter from the peripheral artery by using an interventional device, inject a certain amount of physiological saline into the upper part of the right atrium through the catheter, mix the saline with blood, record a temperature change curve at the same time, and obtain CO through calculation of the temperature curve. This method, called thermodilution, is a "gold standard" for measuring cardiac output. The invasive method is mainly used in the fields of first aid, cardiovascular interventional operation, intensive care and the like, has the characteristics of large traumatism, complex operation and the like, and is easy to cause infection or complications after long-time measurement. Therefore, the method has certain clinical limitations.
Minimally invasive devices and methods combine single thermodilution with pulse waves for CO measurement, a technique known as PICCO. The FloTrac/Vigileo system is a typical minimally invasive device, a FloTrac sensor is used for collecting femoral artery or axillary artery pressure waveforms of a patient, the area under an artery pressure waveform curve is analyzed, the relative stroke volume is calculated by combining parameters such as age, sex, height, weight, body surface area and the like of the patient, and the continuous measurement of cardiac output is realized by utilizing a single thermodilution method for calibration. Although the invasive methods are greatly reduced and the risks of infection and complications are greatly reduced, the methods are still invasive and cannot meet the requirements of non-critical patients and healthy people on measuring the cardiac output, and therefore, some noninvasive cardiac output measurement methods are proposed in succession.
The non-invasive device and method mainly comprise an ultrasonic method, a thoracic impedance method, a pulse wave waveform analysis method and the like.
The ultrasonic method measures the blood flow velocity of the aorta or the pulmonary artery through a continuous Doppler ultrasonic technology to obtain the time integral of the blood flow velocity, and then calculates indexes such as the stroke volume and the like by multiplying the area of the cross section of a lumen of the aorta. A representative instrument is the australian USCOM instrument. The CO measuring instrument based on the ultrasonic method has high requirements on operators, the blood flow velocity waveform can be influenced by the strength and the direction of the sensor, so that the calculation result is influenced, and the error of the measurement result of the ultrasonic method and the measurement result of the thermodilution method can reach 40 percent, so the accuracy and the stability of the CO measuring instrument are required to be improved.
The thoracic impedance method is used for measuring the potential change of the body surface electrode of a human body and establishing the relation between the potential and the cardiac output, thereby realizing the measurement of the cardiac output. Typical representatives of this method include the NICOM system in the united states and the ICON system in germany, among others. Impedance method has been widely used and used clinically because of its non-invasive, continuous measurement, simple equipment and safety, but the technology relies on the diffusion of oscillating current through the thorax, and the interference resistance is poor.
Changes in transmitted or reflected light caused by changes in intra-arterial blood flow volume can be obtained by optical techniques based on pulse wave waveform analysis. When the blood flow volume in the artery changes along with the pulsation of the heart, light emitted by the light source passes through the artery and is received by the detector, the received light intensity and the blood flow volume synchronously change in a pulsating mode, and then CO is calculated by using a relation model between the arterial blood flow volume and the CO, so that CO measurement is realized. The cost is lower when the photoplethysmography measures the cardiac output, the signal is stable, but the waveform shape is easily affected by the position of the sensor and background light, and the accuracy needs to be improved.
Based on the peripheral pulse waveform obtained by the pulse wave waveform analysis method through the pressure sensor, a blood vessel mathematical model and a statistical model, such as a Windkessel model, a transmission line model, a regression model and the like, are established, and CO is calculated through the model. The peripheral pulse waveform is easy to obtain, the equipment is cheap, and the relative change of the cardiac output can be well monitored, so the technology has wide application prospect, but the technology has some defects, such as inaccurate mathematical model, especially lack of consideration of individual difference, and the absolute value deviation of the cardiac output is often large.
As described above, the measurement of cardiac output is progressing from invasive and minimally invasive methods to noninvasive methods, and the advantages of the pulse wave-based waveform analysis method are prominent, but there is a problem that the measurement of cardiac output is not accurate enough.
Disclosure of Invention
Aiming at the defects of the technology, the invention provides a noninvasive measuring method for individualized cardiac output, which solves the technical problem that the noninvasive measuring method in the prior art is not high in accuracy of measuring the cardiac output of an individual.
In order to solve the technical problems, the technical scheme of the invention is as follows: a non-invasive measurement system for individualized cardiac output comprises a brachial artery blood pressure measurement module and a peripheral superficial layer artery pulse wave measurement module, wherein the brachial artery blood pressure measurement module is used for acquiring blood pressure parameters of brachial arteries, including systolic pressure and diastolic pressure of the brachial arteries; the peripheral superficial layer arterial pulse wave measuring module is used for collecting peripheral superficial layer arterial pulse waves;
the pulse wave correction module is used for inputting blood pressure parameters of brachial arteries and peripheral superficial artery pulse waves, correcting the peripheral superficial artery pulse waves by using the blood pressure parameters of the brachial arteries, and outputting the corrected peripheral superficial artery pulse waves to the pulse wave feature extraction module;
the pulse wave feature extraction module is used for extracting pulse wave features from the corrected peripheral shallow artery pulse waves and comprises the following time domain features: the blood pressure characteristics, the time characteristics, the area characteristics and the proportion characteristics are output to an individual pulse wave characteristic vector generation module;
the individualized pulse wave characteristic vector generating module is used for generating an individualized pulse wave characteristic vector according to the pulse wave characteristics and the individual physiological parameters of the testee and outputting the individualized pulse wave characteristic vector to the trained artificial neural network;
the artificial neural network is used for calculating corresponding stroke volume according to the input individualized pulse wave feature vector and outputting the corresponding stroke volume to the cardiac output volume calculating module;
the cardiac output calculating module is used for calculating the cardiac output according to the stroke quantity, and the calculation formula is as follows:
CO＝SV*N/Fs*60
wherein, CO represents the cardiac output, SV represents the stroke volume, N represents the sampling point number of the pulse wave in one cardiac cycle, and Fs represents the signal sampling frequency of the system.
Further, the device also comprises a pulse wave velocity measuring module used for measuring the pulse wave velocity from the brachial artery to the peripheral superficial artery; peripheral superficial layer artery pulse ripples is radial artery blood pressure ripples, finger artery blood pressure ripples or low limbs artery blood pressure ripples, and pulse ripples correction module corrects peripheral superficial layer artery pulse ripples according to following formula:
wherein, the first and the second end of the pipe are connected with each other,
is the peripheral superficial arterial pulse wave before correction; w is a group of r Is the corrected peripheral superficial layer arterial pulse wave; SBP b Is brachial artery systolic pressure; DBP b Is brachial artery diastolic pressure; SBP r Is the peripheral superficial arterial pulse wave systolic pressure; DBP r Is peripheral superficial layer movementPulse wave diastolic pressure; alpha is the amplification factor from brachial artery to peripheral superficial artery,
c 1 、c 2 are all regression coefficients, PWV is the pulse wave velocity of the subject, PWV 0 Is a pulse wave velocity reference value.
Further, the range of the amplification factor α is limited to [1,1.5].
Further, the input layer of the artificial neural network normalizes the individualized pulse wave feature vector by adopting the following formula:
wherein the content of the first and second substances,
representing an individualized pulse wave feature vector,
representing the normalized individualized pulse wave feature vector,
which represents a vector of normalized gains, is,
represents a normalized offset vector;
normalized individualized pulse wave feature vector
Obtaining a quasi-output vector after passing through a hidden layer and an output layer
Quasi-output vector
The calculation formula of (a) is as follows:
wherein f represents a binding function in the artificial neural network,
to represent
The transposed vector of (a) is,
a matrix of weights is represented by a matrix of weights,
a vector of the weighted columns is represented,
and
each represents an offset column vector;
the output layer will output the vector quasi
Performing inverse normalization to obtain an output quantity, namely a stroke quantity, and calculating according to the following formula:
wherein SV represents the amount of each stroke,
representing the vector of the anti-normalized gain,
representing inverse normalizationAn offset vector.
Furthermore, sample data for training the artificial neural network is derived from cardiac output, stroke volume and radial artery blood pressure waveform of a thermodilution method, each sample takes a characteristic vector consisting of time-frequency characteristics of the bypass artery blood pressure waveform and individual physiological parameters as an input volume, and takes the stroke volume corresponding to the radial artery blood pressure waveform as a standard output volume; dividing sample data into a training sample set and a test sample set, and training the artificial neural network by adopting the training sample set; testing the trained artificial neural network by adopting a test sample set, if the error of the output quantity and the standard output quantity meets a threshold value, the training is finished, the trained artificial neural network obtains a parameter combination which can enable the error of the output quantity and the standard output quantity to meet the threshold value, and parameters in the parameter combination comprise normalized gain vectors
Normalized offset vector
Weight matrix
Weight column vector
Offset column vector
Offset column vector
Inverse normalized gain vector
And denormalized offset vector
The invention also provides a noninvasive measuring method of individualized cardiac output, which comprises the following steps:
step 1: obtaining blood pressure parameters of brachial artery of a testee, including systolic pressure and diastolic pressure of the brachial artery; acquiring peripheral superficial layer arterial pulse waves of a tested person, wherein the peripheral superficial layer arterial pulse waves are radial arterial blood pressure waves, finger arterial blood pressure waves or lower limb arterial blood pressure waves; acquiring the pulse wave conduction velocity of a testee from a brachial artery to a peripheral superficial artery;
step 2: correcting peripheral superficial artery pulse waves by using blood pressure parameters of brachial arteries according to the following formula:
wherein the content of the first and second substances,
is the peripheral superficial arterial pulse wave before correction; w is a group of r Is the corrected peripheral superficial layer arterial pulse wave; SBP b Is brachial artery systolic pressure; DBP b Is brachial artery diastolic pressure; SBP r Peripheral superficial arterial pulse wave systolic pressure; DBP r Peripheral superficial arterial pulse wave diastolic pressure; alpha is the amplification factor from the brachial artery to the peripheral superficial artery,
c 1 、c 2 are all regression coefficients, PWV is the pulse wave velocity of the subject, PWV 0 Is a pulse wave velocity reference value;
and step 3: extracting pulse wave characteristics including time domain characteristics and frequency domain characteristics from the corrected peripheral shallow artery pulse waves; the time domain features comprise blood pressure features, time features, area features and proportion features, and the frequency domain features comprise harmonic amplitudes of multiple frequencies; the time domain characteristic and the frequency domain characteristic are combined to form a pulse wave characteristic;
and 4, step 4: generating an individualized pulse wave feature vector according to the pulse wave feature and the individual physiological parameters of the testee;
and 5: outputting the individualized pulse wave feature vector to a trained artificial neural network, and calculating the corresponding stroke volume by the artificial neural network according to the individualized pulse wave feature vector;
step 6: calculating cardiac output from stroke volume according to the following formula:
CO＝SV*N/Fs*60
wherein, CO represents the cardiac output, SV represents the stroke volume, N represents the sampling point number of the pulse wave in one cardiac cycle, and Fs represents the signal sampling frequency of the system.
Compared with the prior art, the invention has the advantages that:
1. the pulse wave is weak and is easy to be interfered, the peripheral superficial layer artery pulse wave is corrected through brachial artery blood pressure parameters to reduce the distortion degree, and the method is the basis for accurately extracting the pulse wave characteristics. Different from the prior art which adopts a fixed scale factor for correction, the pulse wave correction method firstly utilizes the fact that the pulse wave is corrected based on the fact that the arteriosclerosis and the pulse wave amplification have a direct proportional relation
The systolic pressure and diastolic pressure of the peripheral superficial artery are mapped to the systolic pressure and diastolic pressure of the brachial artery, and then multiplied by an amplification factor alpha from the brachial artery to the peripheral superficial artery, so that an amplification effect is embodied.
2. The amplification factor alpha of the invention is calculated based on the pulse wave conduction velocity of the individual, so that the corrected pulse wave shows the individual difference. The value range of the amplification factor alpha is limited to [1,1.5], so that the condition that the alpha is too large due to inaccurate measurement of the pulse wave conduction velocity is prevented. Meanwhile, the influence degree of individual physiological difference on the pulse wave conduction process is different, individual physiological parameters (such as height, age, weight, sex, medical history and the like) are introduced when the pulse wave characteristic vector is established, one-sided attention to waveform characteristics is avoided, and therefore the multi-parameter fused individualized pulse wave characteristic vector is formed.
3. The invention combines the artificial neural network to identify the stroke quantity of the individualized pulse wave characteristic vector, avoids complex mathematical modeling and overcomes the defect of insufficient expression capability of a mathematical model. The training sample is derived from the measurement data of the thermodilution method, so that the accuracy of the artificial neural network is ensured, and the trained artificial neural network can output a measurement result which is closer to the measurement result of the thermodilution method.
4. The magnitude orders of various parameters in the vectors are adjusted to be consistent by normalizing the input vectors, so that the training of the artificial neural network is facilitated. The de-normalization adjusts the quasi-output vector to the actual range.
Drawings
Fig. 1 is a block diagram of a non-invasive measurement system for individualized cardiac output;
FIG. 2 is a graph comparing cardiac output measured using a prior art measurement model with measurements made using the "gold standard" method;
FIG. 3 is a graph comparing cardiac output measured by the non-invasive system for measuring individualized cardiac output according to the present embodiment with the "gold standard" method;
fig. 4 is a waveform diagram of the radial pulse wave before correction.
Detailed Description
A) System architecture
Referring to fig. 1, a non-invasive measurement system for individualized cardiac output includes a brachial artery blood pressure measurement module, a peripheral superficial artery pulse wave measurement module, and a pulse wave velocity measurement module, wherein the brachial artery blood pressure measurement module is used for acquiring blood pressure parameters of brachial artery, including systolic pressure and diastolic pressure of brachial artery; the peripheral superficial layer arterial pulse wave measuring module is used for collecting peripheral superficial layer arterial pulse waves; the pulse wave velocity measuring module is used for measuring the pulse wave velocity from the brachial artery to the peripheral superficial artery;
the pulse wave correction module is used for inputting blood pressure parameters of brachial arteries and peripheral superficial artery pulse waves, correcting the peripheral superficial artery pulse waves by using the blood pressure parameters of the brachial arteries, and outputting the corrected peripheral superficial artery pulse waves to the pulse wave feature extraction module;
the pulse wave feature extraction module is used for extracting pulse wave features from the corrected peripheral shallow artery pulse waves and comprises the following time domain features: the blood pressure characteristics, the time characteristics, the area characteristics and the proportion characteristics are output to an individual pulse wave characteristic vector generation module;
the individualized pulse wave characteristic vector generating module is used for generating an individualized pulse wave characteristic vector according to the pulse wave characteristics and the individual physiological parameters of the testee and outputting the individualized pulse wave characteristic vector to the trained artificial neural network;
the artificial neural network is used for calculating corresponding stroke volume according to the input individualized pulse wave feature vector and outputting the corresponding stroke volume to the cardiac output volume calculating module;
the cardiac output calculating module is used for calculating cardiac output according to the stroke volume, and the calculation formula is as follows:
CO＝SV*N/Fs* 60
wherein, CO represents the cardiac output, SV represents the stroke volume, N represents the sampling point number of the pulse wave in one cardiac cycle, and Fs represents the signal sampling frequency of the system.
Peripheral superficial layer artery pulse ripples is radial artery blood pressure ripples, finger artery blood pressure ripples or low limbs artery blood pressure ripples, and pulse ripples correction module corrects peripheral superficial layer artery pulse ripples according to following formula:
wherein the content of the first and second substances,
is the peripheral superficial arterial pulse wave before correction; w is a group of r Is the corrected peripheral superficial arterial pulse wave; SBP b Is brachial arterial systolic pressure; DBP b Is brachial artery diastolic pressure; SBP r Is the peripheral superficial arterial pulse wave systolic pressure; DBP r Peripheral superficial arterial pulse wave diastolic pressure; alpha is the amplification factor from brachial artery to peripheral superficial artery,
c 1 、c 2 all are regression coefficients (obtained by measuring the amplification factor of PWV and radial artery relative to brachial artery blood pressure of multiple persons and adopting regression analysis), PWV is the pulse wave conduction velocity of the testee, PWV is 0 Is a pulse wave velocity reference value.
The range of values of the amplification factor alpha is limited to [1,1.5].
In order to establish a characteristic vector capable of reflecting the pulse wave more accurately, the pulse wave characteristic extraction module also extracts frequency domain characteristics including harmonic amplitudes of multiple frequencies from the corrected peripheral shallow arterial pulse wave, and the time domain characteristics and the frequency domain characteristics are combined to form the pulse wave characteristics and then output to the individualized pulse wave characteristic vector generation module.
The input layer of the artificial neural network normalizes the individualized pulse wave characteristic vector by adopting the following formula:
wherein the content of the first and second substances,
representing an individualized pulse wave feature vector,
representing the normalized individualized pulse wave feature vector,
which represents a vector of normalized gains, is,
representing a normalized offset vector;
normalized individualized pulse wave feature vector
Obtaining a quasi-output vector after passing through a hidden layer and an output layer
Quasi-output vector
The calculation formula of (a) is as follows:
wherein f represents a binding function in the artificial neural network,
represent
The transposed vector of (a) is,
a matrix of weights is represented by a matrix of weights,
a vector of the weighted columns is represented,
and with
Each represents an offset column vector;
the output layer will output the vector quasi
Performing inverse normalization to obtain an output quantity, namely a stroke quantity, and calculating according to the following formula:
wherein SV represents the amount of each stroke,
which represents the vector of the anti-normalized gain,
representing the denormalized offset vector.
The brachial artery blood pressure measuring device further comprises a data display module and a data acquisition control module, wherein the data acquisition control module is used for controlling the data acquisition process of the brachial artery blood pressure measuring module, the peripheral superficial artery pulse wave measuring module and the pulse wave conduction velocity measuring module; the data display module is used for displaying relevant data in the measuring process of the cardiac output quantity, including brachial artery blood pressure parameters, peripheral superficial artery pulse waves after correction, stroke volume, cardiac output quantity and individual physiological parameters of a tested person.
The brachial artery blood pressure measuring module comprises a cuff, an air channel catheter, an air pressure sensor, an air inflation and deflation motor and a blood pressure data processing module; the motor charges and discharges air to the cuff through the air channel catheter, the air pressure sensor monitors the air pressure change in the cuff or the air channel, and transmits the measured air pressure signal to the blood pressure data processing module; the blood pressure data processing module calculates brachial artery blood pressure parameters according to the following programs: decomposing the air pressure signal to obtain an oscillation signal and a linear ascending or descending signal; detecting the peak value of the oscillation signal, and obtaining the pressures of the rising or falling signals corresponding to two time points, namely the systolic pressure and the diastolic pressure, at the left and right of the peak value according to a certain proportion (such as 60% or 80%) of the amplitude of the peak value;
the peripheral superficial layer artery pulse wave measuring module is a radial artery measuring device, a finger artery measuring device or a lower limb artery measuring device. The specific embodiment adopts a radial artery blood pressure measuring module: the blood pressure signal processing circuit comprises a piezoelectric sensor, a wire and a blood pressure signal processing circuit, wherein the piezoelectric sensor obtains a pulse signal of a radial artery and transmits the signal to the blood pressure signal processing circuit through the wire, the circuit completes the processing of filtering, amplifying and the like of the blood pressure signal and transmits the processed signal to a blood pressure data processing module through a data acquisition control module.
The pulse wave velocity measuring module adopts a brachial artery blood pressure measuring module and a peripheral superficial layer artery pulse wave measuring module to synchronously measure brachial artery pulse waves and peripheral superficial layer artery pulse waves, calculates the wave foot point time difference PTT (pulse wave conduction time) of two wave forms, then adopts a measuring tape to measure the human body surface distance L between the two measuring points, and finally divides the PTT by the L to obtain the pulse wave velocity. The cuff pressure is generally raised to the brachial artery mean pressure, which cannot be raised too high, and this may cause the distal peripheral arterial pulse wave to disappear, thereby failing the measurement.
Two), training artificial neural network
And training the artificial neural network by adopting an error back propagation method and combining a gradient descent method. The sample data used for training the artificial neural network is derived from cardiac output, stroke volume and radial artery blood pressure waveform of thermodilution method, and can be inquired through public data. Each sample takes a characteristic vector consisting of time-frequency characteristics of the arteria crura blood pressure waveform and individual physiological parameters as an input quantity, and takes a stroke quantity corresponding to the radial artery blood pressure waveform as a standard output quantity; dividing the sample data into a training sample set and a testing sample set, and training the artificial neural network by adopting the training sample set; testing the trained artificial neural network by adopting a test sample set, if the error of the output quantity and the standard output quantity meets a threshold value, the training is finished, the trained artificial neural network obtains a parameter combination which can enable the error of the output quantity and the standard output quantity to meet the threshold value, and parameters in the parameter combination comprise normalized gain vectors
Normalized offset vector
Weight matrix
Weight column vector
Offset column vector
Offset column vector
Inverse normalized gain vector
And denormalized offset vector
The partial waveform characteristic parameters of the testee are shown in the following table 1:
TABLE 1 statistics of partial waveform characteristics of patients
FIG. 2 Model of the prior art Rcdecay Comparing the result with that of the 'gold standard' method, wherein the abscissa is SV of the gold standard measurement, and the ordinate is Model of the existing Model RCdecay The calculated SV, straight lines in the figure represent linear regression lines.
FIG. 3 is a graph comparing the results of the Artificial Neural Network (ANN) of the present invention with those of the "gold standard" method, in which the abscissa is the SV measured in the gold standard and the SV calculated in the artificial neural network of the present invention, and the straight line represents a linear regression line.
The present invention provides a comparison of the results of an Artificial Neural Network (ANN) with other existing models, as shown in Table 2 below, the slope and intercept are the linear regression equation parameters of the model and the measured SV, and the correlation coefficient is the Pearson correlation coefficient.
TABLE 2
As can be seen from the table above, the standard deviation of the measurement results of the invention and the gold standard method is far smaller than the standard deviation of the measurement results of the existing model and the gold standard method, and the accuracy of non-invasive measurement is greatly improved by the artificial neural network model of the invention.
Third), measuring process
The non-invasive measurement system for individualized cardiac output according to the present embodiment is used to measure the cardiac output of a subject, and the specific procedure is as follows.
After the testee lies and has a rest for 3-5 minutes, the data acquisition control module starts and controls the inflation and deflation speed of the air pump in the brachial artery blood pressure measurement module and the air pressure in the cuff to complete the measurement of the brachial artery blood pressure.
The radial artery blood pressure measuring module is started and controlled through the data acquisition control module, the measurement of the radial artery blood pressure signals is completed, the signals are filtered and amplified through the analog circuit, and the processed signals are transmitted to the data processing module through the data acquisition control module.
Starting a data processing module through a data acquisition control module, and processing the brachial artery air pressure signal input by the data processing module to obtain systolic pressure, average pressure and diastolic pressure; denoising, drifting removal, normalization, calibration and other processing are carried out on the radial artery blood pressure signal data; and then, the three blood pressures are used for correcting the radial artery blood pressure waveform and amplifying the radial artery blood pressure waveform with certain gain, and the corrected and amplified radial artery pulse wave signals are respectively sent to the pulse wave characteristic extraction module and the display module.
In the pulse wave feature extraction module, first, the minimum value and the maximum value of the difference sequence are detected through the second order or higher order numerical difference of the pulse wave, so as to obtain the central isthmus and the peak of the double wave in the pulse wave falling period, and the feature points refer to fig. 4. Based on the two feature points and the systolic peak feature point, other relevant time domain features are calculated.
The frequency domain characteristics are subjected to Fourier transform of the pulse waves to obtain multiple frequency harmonic amplitudes, and then the time domain characteristics and the frequency domain characteristics are combined to construct pulse wave characteristic vectors. Starting a pulse wave characteristic calculation module, finishing the processing and calculation of the wave time domain and the frequency domain characteristics of the pulse wave, constructing a pulse wave characteristic vector, inputting the pulse wave characteristic vector and the individual physiological parameters of the testee into an individualized pulse wave characteristic vector generation module, generating an individualized pulse wave characteristic vector, inputting the individualized pulse wave characteristic vector into an artificial neural network, and sending part of the parameters to a data display module for display.
The artificial neural network carries out a series of operations such as input normalization, transformation and output inverse normalization on the input individualized pulse wave characteristic vector, calculates the stroke volume and outputs the stroke volume to the cardiac output volume calculating module, and the cardiac output volume calculating module calculates the cardiac output volume according to the stroke volume.
The data display module displays the pulse wave waveform, the stroke volume, the cardiac output and relevant cardiovascular system parameters on a display screen, and simultaneously generates a measurement report.
Claims (9)
1. A non-invasive measurement system for individualized cardiac output is characterized by comprising a brachial artery blood pressure measurement module and a peripheral superficial layer arterial pulse wave measurement module, wherein the brachial artery blood pressure measurement module is used for acquiring blood pressure parameters of brachial arteries, including brachial artery systolic pressure and brachial artery diastolic pressure; the peripheral superficial layer arterial pulse wave measuring module is used for collecting peripheral superficial layer arterial pulse waves;
the pulse wave correction module is used for inputting blood pressure parameters of brachial arteries and peripheral superficial artery pulse waves, correcting the peripheral superficial artery pulse waves by using the blood pressure parameters of the brachial arteries, and outputting the corrected peripheral superficial artery pulse waves to the pulse wave feature extraction module;
the pulse wave feature extraction module is used for extracting pulse wave features from the corrected peripheral shallow artery pulse waves and comprises the following time domain features: the blood pressure characteristics, the time characteristics, the area characteristics and the proportion characteristics are output to an individual pulse wave characteristic vector generation module;
the individualized pulse wave characteristic vector generating module is used for generating an individualized pulse wave characteristic vector according to the pulse wave characteristics and the individual physiological parameters of the testee and outputting the individualized pulse wave characteristic vector to the trained artificial neural network;
the artificial neural network is used for calculating corresponding stroke volume according to the input individualized pulse wave feature vector and outputting the corresponding stroke volume to the cardiac output volume calculating module;
the cardiac output calculating module is used for calculating cardiac output according to the stroke volume, and the calculation formula is as follows:
CO＝SV*N/Fs*60
wherein, CO represents the cardiac output, SV represents the stroke volume, N represents the sampling point number of the pulse wave in one cardiac cycle, and Fs represents the signal sampling frequency of the system.
2. The system for noninvasive measurement of individualized cardiac output according to claim 1, further comprising a pulse wave velocity measurement module for measuring pulse wave velocity of the brachial artery to the peripheral superficial artery; peripheral superficial layer artery pulse ripples is radial artery blood pressure ripples, finger artery blood pressure ripples or low limbs artery blood pressure ripples, and pulse ripples correction module corrects peripheral superficial layer artery pulse ripples according to following formula:
wherein the content of the first and second substances,
is the peripheral superficial arterial pulse wave before correction; w r Is the corrected peripheral superficial layer arterial pulse wave; SBP b Is brachial artery systolic pressure; DBP b Is brachial artery diastolic pressure; SBP r Is the peripheral superficial arterial pulse wave systolic pressure; DBP r Peripheral superficial arterial pulse wave diastolic pressure; alpha is the amplification factor from the brachial artery to the peripheral superficial artery,
c 1 、c 2 are regression coefficients, PWV is the pulse wave velocity of the subject, PWV 0 Is a pulse wave velocity reference value.
3. The system for noninvasive measurement of individualized cardiac output according to claim 2, wherein the range of values of the amplification factor α is limited to [1,1.5].
4. The system of claim 1, wherein the pulse wave feature extraction module further extracts frequency domain features including harmonic amplitudes of multiple frequencies from the corrected peripheral superficial arterial pulse wave, and the time domain features and the frequency domain features are combined to form pulse wave features which are then output to the personalized pulse wave feature vector generation module.
5. The system of claim 1, wherein the input layer of the artificial neural network normalizes the individualized pulse wave feature vector using the formula:
wherein the content of the first and second substances,
representing an individualized pulse wave feature vector,
representing the normalized individualized pulse wave feature vector,
which represents a vector of normalized gains, and,
represents a normalized offset vector;
normalized individualized pulse wave feature vector
Obtaining a quasi-output vector after passing through a hidden layer and an output layer
Quasi-output vector
The calculation formula of (a) is as follows:
wherein f represents a binding function in the artificial neural network,
to represent
The transposed vector of (a) is provided,
a matrix of weights is represented by a matrix of weights,
a vector of weight columns is represented and,
and
each represents an offset column vector;
the output layer will output the vector quasi
Performing inverse normalization to obtain an output quantity, namely a stroke quantity, and calculating according to the following formula:
wherein SV represents the amount of each stroke,
representing the vector of the anti-normalized gain,
representing the denormalized offset vector.
6. The system of claim 1, wherein the sample data for training the artificial neural network is derived from cardiac output, stroke volume and radial artery blood pressure waveform of thermodilution, and each sample has a feature vector composed of time-frequency features of the arteria-rich blood pressure waveform and individual physiological parameters as input and a stroke volume corresponding to the radial artery blood pressure waveform as standard output; dividing the sample data into a training sample set and a testing sample set, and training the artificial neural network by adopting the training sample set; testing the trained artificial neural network by adopting a test sample set, if the error of the output quantity and the standard output quantity meets a threshold value, the training is finished, the trained artificial neural network obtains a parameter combination which can enable the error of the output quantity and the standard output quantity to meet the threshold value, and parameters in the parameter combination comprise normalized gain vectors
Normalized offset vector
Weight matrix
Weight column vector
Offset column vector
Offset column vector
Inverse normalized gain vector
And denormalized offset vector
7. The system of claim 6, wherein the artificial neural network is trained using error back-propagation in combination with gradient descent.
8. The system of claim 1, wherein the brachial artery blood pressure measurement module comprises a cuff, an airway tube, an air pressure sensor, a gas charging and discharging motor, and a blood pressure data processing module; the motor charges and discharges air to the cuff through the air channel catheter, the air pressure sensor monitors the air pressure change in the cuff or the air channel, and transmits the measured air pressure signal to the blood pressure data processing module; the blood pressure data processing module calculates brachial artery blood pressure parameters according to the following programs: decomposing the air pressure signal to obtain an oscillation signal and a linear ascending or descending signal; detecting the peak value of the oscillation signal, obtaining the pressures of the rising or falling signals corresponding to two time points, namely the systolic pressure and the diastolic pressure, at the left and right of the peak value according to a certain proportion of the amplitude of the peak value;
the peripheral superficial layer artery pulse wave measuring module is a radial artery measuring device, a finger artery measuring device or a lower limb artery measuring device.
9. The system of claim 1, further comprising a data display module and a data acquisition control module for controlling the data acquisition process of the brachial artery blood pressure measurement module and the peripheral superficial artery pulse wave measurement module; the data display module is used for displaying relevant data in the measuring process of the cardiac output quantity, and the relevant data comprises brachial artery blood pressure parameters, peripheral superficial layer artery pulse waves, corrected peripheral superficial layer artery pulse waves, stroke volume, cardiac output quantity and individual physiological parameters of a tested person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010317299.9A CN111493855B (en) | 2020-04-21 | 2020-04-21 | System and method for non-invasive measurement of individualized cardiac output |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010317299.9A CN111493855B (en) | 2020-04-21 | 2020-04-21 | System and method for non-invasive measurement of individualized cardiac output |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111493855A CN111493855A (en) | 2020-08-07 |
| CN111493855B true CN111493855B (en) | 2023-01-06 |
Family
ID=71865898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010317299.9A Active CN111493855B (en) | 2020-04-21 | 2020-04-21 | System and method for non-invasive measurement of individualized cardiac output |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111493855B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112790748A (en) * | 2020-12-30 | 2021-05-14 | 重庆理工大学 | Central arterial pressure waveform reconstruction system and method |
| CN113080907B (en) * | 2021-04-14 | 2022-10-25 | 贵州省人民医院 | Pulse wave signal processing method and device |
| CN113057617B (en) * | 2021-04-30 | 2022-08-26 | 重庆理工大学 | Non-invasive monitoring system for cardiac output |
| CN113143230B (en) * | 2021-05-11 | 2022-05-20 | 重庆理工大学 | Peripheral arterial blood pressure waveform reconstruction system |
| CN113499048B (en) * | 2021-07-22 | 2022-07-08 | 重庆理工大学 | Central arterial pressure waveform reconstruction system and method based on CNN-BilSTM |
| CN114027804A (en) * | 2021-12-03 | 2022-02-11 | 科思技术(温州)研究院 | Pulse condition diagnosis method, device and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5400793A (en) * | 1991-01-29 | 1995-03-28 | Nederlandse Organisatie Voor Toegepast-Natuurwetenschappelijk Onderzoek Tno | Method of determining the stroke volume and the cardiac output of the human heart |
| CN103892818A (en) * | 2012-12-28 | 2014-07-02 | 吴健康 | Non-invasive central aortic blood pressure measuring method and device |
| CN104244814A (en) * | 2012-05-15 | 2014-12-24 | 皇家飞利浦有限公司 | Monitoring of cardiac output |
| CN104323768A (en) * | 2012-11-20 | 2015-02-04 | 深圳市理邦精密仪器股份有限公司 | Parameter calibration method for continuously monitoring cardiac output |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5913826A (en) * | 1996-06-12 | 1999-06-22 | K-One Technologies | Wideband external pulse cardiac monitor |
| US7822470B2 (en) * | 2001-10-11 | 2010-10-26 | Osypka Medical Gmbh | Method for determining the left-ventricular ejection time TLVE of a heart of a subject |
| US7815578B2 (en) * | 2003-02-10 | 2010-10-19 | Massachusetts Institute Of Technology | Methods and apparatus for determining cardiac output |
| WO2005084536A1 (en) * | 2004-03-05 | 2005-09-15 | Atcor Medical Pty Limited | Method and apparatus for determination of cardiac output from the arterial pressure pulse waveform |
| CN101006919A (en) * | 2007-01-26 | 2007-08-01 | 北京工业大学 | Detection method of cardiac output under the high differential pressure and device thereof |
| CN101176663B (en) * | 2007-12-06 | 2010-10-27 | 山东大学 | Non-invasive cardiac output detecting methods and apparatus based on sphygmus wave |
| US10405762B2 (en) * | 2009-04-22 | 2019-09-10 | Vital Metrix, Inc. | System and method for noninvasively measuring ventricular stroke volume and cardiac output |
| CN102499669B (en) * | 2011-10-26 | 2014-12-24 | 中国科学院深圳先进技术研究院 | Heart parameter measuring method and device |
| JP5985355B2 (en) * | 2012-10-30 | 2016-09-06 | 日本光電工業株式会社 | Blood volume measuring method and measuring apparatus |
| US9949696B2 (en) * | 2013-03-14 | 2018-04-24 | Tensys Medical, Inc. | Apparatus and methods for computing cardiac output of a living subject via applanation tonometry |
| US10542961B2 (en) * | 2015-06-15 | 2020-01-28 | The Research Foundation For The State University Of New York | System and method for infrasonic cardiac monitoring |
| CN105726000B (en) * | 2016-01-29 | 2019-03-22 | 北京工业大学 | A kind of device of the cardiovascular functional parameter based on blood pressure of four limbs pulse |
| WO2018017542A1 (en) * | 2016-07-19 | 2018-01-25 | Mayo Foundation For Medical Education And Research | Non-invasive cardiac output assessment |
| CN109512412B (en) * | 2018-11-21 | 2021-10-08 | 重庆理工大学 | Central artery blood pressure measuring device |
-
2020
- 2020-04-21 CN CN202010317299.9A patent/CN111493855B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5400793A (en) * | 1991-01-29 | 1995-03-28 | Nederlandse Organisatie Voor Toegepast-Natuurwetenschappelijk Onderzoek Tno | Method of determining the stroke volume and the cardiac output of the human heart |
| CN104244814A (en) * | 2012-05-15 | 2014-12-24 | 皇家飞利浦有限公司 | Monitoring of cardiac output |
| CN104323768A (en) * | 2012-11-20 | 2015-02-04 | 深圳市理邦精密仪器股份有限公司 | Parameter calibration method for continuously monitoring cardiac output |
| CN103892818A (en) * | 2012-12-28 | 2014-07-02 | 吴健康 | Non-invasive central aortic blood pressure measuring method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111493855A (en) | 2020-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111493855B (en) | System and method for non-invasive measurement of individualized cardiac output | |
| US5265615A (en) | Method and apparatus for continuous measurement of cardiac output and SVR | |
| US7220230B2 (en) | Pressure-based system and method for determining cardiac stroke volume | |
| AU704699B2 (en) | Method and device for determining brachial arterial pressure wave on the basis of noninvasively measured finger blood pressure wave | |
| US4873987A (en) | Noninvasive continuous monitor of arterial blood pressure waveform | |
| US7361148B2 (en) | Cuff volumetric pulse wave obtaining apparatus, cuff volumetric pulse wave analyzing apparatus, pressure pulse wave obtaining apparatus, and pressure pulse wave analyzing apparatus | |
| US6120459A (en) | Method and device for arterial blood pressure measurement | |
| CN109512412B (en) | Central artery blood pressure measuring device | |
| CN101765398B (en) | Assessment of preload dependence and fluid responsiveness | |
| US20020028998A1 (en) | Method and instrument to measure vascular impedance | |
| EP0651970A1 (en) | Method and apparatus for assessing cardiovascular performance | |
| EP0818175A1 (en) | Living body condition measuring apparatus | |
| JP2014000105A (en) | Non-invasive, continuous blood pressure monitoring method and apparatus | |
| CN114145724A (en) | Method for dynamically monitoring blood pressure based on ECG (electrocardiogram) and PPG (photoplethysmography) multiple physiological characteristic parameters | |
| WO1992006633A1 (en) | Method and apparatus for measuring cardiac output | |
| EP1150604B1 (en) | Method and device for continuous analysis of cardiovascular activity of a subject | |
| WO2008156377A1 (en) | Method and apparatus for obtaining electronic oscillotory pressure signals from an inflatable blood pressure cuff | |
| Zhang et al. | A LabVIEW based measure system for pulse wave transit time | |
| CN114587307A (en) | Non-contact blood pressure detector and method based on capacitive coupling electrode | |
| Wang et al. | An improved algorithm for noninvasive blood pressure measurement | |
| CN210095711U (en) | Noninvasive continuous blood pressure measuring equipment | |
| Vajanarat et al. | A comparison of cuff-less blood pressure estimation between pulse arrival time and pulse transit time using photoplethysmography | |
| RU2107456C1 (en) | Method and system for measuring blood pressure in deep brachial vein | |
| RU2327414C1 (en) | Method of blood pressure measurement based on three-dimensional compression oscillogram | |
| Sidhu et al. | Comparison of artificial intelligence based oscillometric blood pressure estimation techniques: a review paper |
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 |