CN108261192B - Continuous blood pressure estimation method, device and equipment - Google Patents

Abstract

The invention discloses a continuous blood pressure estimation method, a continuous blood pressure estimation device and continuous blood pressure estimation equipment. The method comprises the following steps: 1) and (3) a calibration link: sampling the pulse wave of the tested object to obtain a sample pulse characteristic parameter and acquiring a reference blood pressure value of the tested object, wherein the first pulse characteristic parameter comprises: the slope of the ascending branch of the second order pulse leading wave, the amplitude difference of the ascending branch of the second order pulse leading wave, the coverage area of the ascending branch of the second order pulse leading wave, the slope of the descending branch of the second order pulse leading wave, the amplitude difference of the descending branch of the second order pulse leading wave and the coverage area of the descending branch of the second order pulse leading wave; calculating to obtain a coefficient parameter of the blood pressure estimation model according to the reference blood pressure value and the sample pulse characteristic parameter; measuring the pulse wave of the measured object in real time to obtain a real-time pulse characteristic parameter; and inputting the coefficient parameters and the real-time pulse characteristic parameters into a blood pressure estimation model so as to estimate the real-time pulse continuous blood pressure value of the measured object.

Description

Continuous blood pressure estimation method, device and equipment

Technical Field

The invention relates to the field of medical instruments, in particular to a continuous blood pressure estimation method, a continuous blood pressure estimation device and continuous blood pressure estimation equipment.

Background

The blood pressure is the pressure required to transport the blood of a person to various parts of the body. Blood pressure is the pressure acting on the wall of a blood vessel when blood flows in the blood vessel, and is the driving force for driving the blood to flow in the blood vessel. The ventricles contract and blood flows from the ventricles into the arteries, at which time the pressure of the blood against the arteries is highest, called the Systolic Blood Pressure (SBP). The ventricles relax, the arterial vessels retract elastically, and blood continues to flow forward slowly, but the blood pressure drops, when it drops to a minimum, the pressure at this point is called the Diastolic Blood Pressure (DBP). Blood pressure is an important index of human health state, and in various medical occasions, the blood pressure of a patient needs to be measured in real time. However, the conventional mercury sphygmomanometer has relatively high measurement accuracy, but is not suitable for continuously measuring the blood pressure in real time, and the conventional method for continuously measuring the blood pressure in real time has low measurement accuracy.

Disclosure of Invention

The technical problem to be solved by the embodiments of the present invention is to provide a continuous blood pressure estimation method, device and apparatus, which can effectively and simply realize real-time measurement of continuous blood pressure per stroke.

The invention provides a continuous blood pressure estimation method in a first aspect, which comprises the following steps:

the continuous blood pressure measuring equipment samples the pulse wave of a tested object to obtain a sample pulse characteristic parameter and obtains a reference blood pressure value of the tested object, wherein the pulse characteristic parameter is a characteristic parameter of the pulse wave of the tested object in a heartbeat period, the pulse characteristic parameter comprises a first pulse characteristic parameter, and the first pulse characteristic parameter comprises: at least one of the slope of the ascending branch of the second-order pulse wave, the amplitude difference of the ascending branch of the second-order pulse wave, the coverage area of the ascending branch of the second-order pulse wave, the slope of the descending branch of the second-order pulse wave, the amplitude difference of the descending branch of the second-order pulse wave and the coverage area of the descending branch of the second-order pulse wave, wherein the reference blood pressure value of the measured object is measured by a precision blood pressure measuring instrument, and the second-order pulse wave is obtained by performing twice derivation on an original pulse wave signal;

calculating by the continuous blood pressure measuring equipment according to the reference blood pressure value and the sample pulse characteristic parameter to obtain a coefficient parameter of a blood pressure estimation model;

the continuous blood pressure measuring equipment measures the pulse wave of the measured object in real time so as to obtain real-time pulse characteristic parameters;

and the continuous blood pressure measuring equipment inputs the coefficient parameters and the real-time pulse characteristic parameters into the blood pressure estimation model so as to estimate the real-time pulse-to-pulse continuous blood pressure value of the measured object.

Wherein the content of the first and second substances,

slope of rising branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1Is the initial wave trough of the second order pulse wave in the heartbeat cycleAmplitude of the dot, T_PThe time value T corresponding to the main wave crest point of the second order pulse wave in the heartbeat cycle_V1The time value corresponding to the initial wave trough point of the second-order pulse wave in the heartbeat period is obtained;

the amplitude difference PPG _ AID ═ I of the ascending branch of the second order pulse wave_P-I_V1I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1The amplitude of the initial valley point of the second order pulse wave in the heartbeat period;

the coverage area of the ascending branch of the second order pulse wave

Wherein, P is the main wave peak point of the second order pulse wave in the heartbeat cycle, V1 is the initial wave valley point of the second order pulse wave in the heartbeat cycle, I is the free variable, I_iIs the amplitude of point I, I_V1The amplitude of the starting valley point V1 of the second order pulse leading wave in the heartbeat period;

slope of descending branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude value T of the end point valley point of the second order pulse wave in the heartbeat cycle_PThe time value T corresponding to the main wave crest point of the second order pulse wave in the heartbeat cycle_V2A time value corresponding to a trough point of a terminal point of the second-order pulse wave in the heartbeat period;

the amplitude difference PPG _ DID ═ I of the descending branch of the second order pulse leading wave_P-I_V2I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude of a terminal wave valley point of the second order pulse wave in the heartbeat period;

the coverage area of the descending branch of the second order pulse wave

Wherein P isThe main wave peak point of the second order pulse wave in the heartbeat period, V2 is the end wave valley point of the second order pulse wave in the heartbeat period, I is the free variable, I is_iIs the amplitude of point I, I_V2Is the amplitude of the end-point valley point V2 of the second-order pulse leading wave in the heartbeat cycle.

Wherein the blood pressure estimation model comprises a linear regression model, a non-linear regression model, or a machine learning model.

The linear regression model is y ═ Ax + B, wherein a and B are coefficient parameters of the linear regression model, x is a pulse characteristic parameter, and y is a blood pressure value.

Wherein, the pulse characteristic parameter still includes second pulse characteristic parameter, second pulse characteristic parameter includes: at least one of pulse wave transmission time, pulse wave peak to trough amplitude ratio, dominant wave height, descending isthmus relative height, counterpulsation wave relative height, lowest value of pulse wave data waveform, pulse cycle, duration of diastole, time ratio of systole to diastole, dominant wave rise time, area ratio of systole to diastole, area of pulse wave data waveform, slope of pulse wave peak to descending isthmus, and rising velocity of pulse wave.

Wherein the linear regression model is c ═ k₁a+k₂b+k₃Wherein k is₁、k₂And k₃The parameter values are coefficient parameters of a linear regression model, a is the first pulse characteristic parameter, b is the second pulse characteristic parameter, and c is a blood pressure value.

The invention provides a continuous blood pressure measuring device, which comprises an acquisition module, a calculation module, an actual measurement module and an estimation module,

the acquisition module is used for sampling the pulse wave of the measured object to obtain a sample pulse characteristic parameter and acquiring a reference blood pressure value of the measured object, wherein the pulse characteristic parameter is a characteristic parameter of the pulse wave of the measured object in a heartbeat period, the pulse characteristic parameter comprises a first pulse characteristic parameter, and the first pulse characteristic parameter comprises: at least one of the slope of the ascending branch of the second-order pulse wave, the amplitude difference of the ascending branch of the second-order pulse wave, the coverage area of the ascending branch of the second-order pulse wave, the slope of the descending branch of the second-order pulse wave, the amplitude difference of the descending branch of the second-order pulse wave and the coverage area of the descending branch of the second-order pulse wave, wherein the reference blood pressure value of the measured object is measured by a precision blood pressure measuring instrument, and the second-order pulse wave is obtained by performing twice derivation on an original pulse wave signal;

the calculation module is used for calculating to obtain a coefficient parameter of a blood pressure estimation model according to the reference blood pressure value and the sample pulse characteristic parameter;

the actual measurement module is used for measuring the pulse wave of the measured object in real time so as to obtain real-time pulse characteristic parameters;

the estimation module is used for inputting the coefficient parameters and the real-time pulse characteristic parameters into the blood pressure estimation model so as to estimate the real-time pulse-to-pulse continuous blood pressure value of the measured object.

Wherein the content of the first and second substances,

slope of rising branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1The amplitude value T of the initial valley point of the second order pulse wave in the heartbeat cycle_PThe time value T corresponding to the main wave crest point of the second order pulse wave in the heartbeat cycle_V1The time value corresponding to the initial wave trough point of the second-order pulse wave in the heartbeat period is obtained;

the amplitude difference PPG _ AID ═ I of the ascending branch of the second order pulse wave_P-I_V1I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1The amplitude of the initial valley point of the second order pulse wave in the heartbeat period;

the coverage area of the ascending branch of the second order pulse wave

Wherein, P is the main wave peak point of the second order pulse wave in the heartbeat cycle, V1 is the initial wave valley point of the second order pulse wave in the heartbeat cycle, I is the free variable, I_iIs the amplitude of point I, I_V1The amplitude of the starting valley point V1 of the second order pulse leading wave in the heartbeat period;

slope of descending branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude value T of the end point valley point of the second order pulse wave in the heartbeat cycle_PThe time value T corresponding to the main wave crest point of the second order pulse wave in the heartbeat cycle_V2A time value corresponding to a trough point of a terminal point of the second-order pulse wave in the heartbeat period;

the amplitude difference PPG _ DID ═ I of the descending branch of the second order pulse leading wave_P-I_V2I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude of a terminal wave valley point of the second order pulse wave in the heartbeat period;

the coverage area of the descending branch of the second order pulse wave

Wherein, P is the main wave peak point of the second order pulse wave in the heartbeat cycle, V2 is the terminal wave valley point of the second order pulse wave in the heartbeat cycle, I is the free variable, I_iIs the amplitude of point I, I_V2Is the amplitude of the end-point valley point V2 of the second-order pulse leading wave in the heartbeat cycle.

Wherein the blood pressure estimation model comprises a linear regression model, a non-linear regression model, or a machine learning model.

The linear regression model is y ═ Ax + B, wherein a and B are coefficient parameters of the linear regression model, x is a pulse characteristic parameter, and y is a blood pressure value.

Wherein, the pulse characteristic parameter still includes second pulse characteristic parameter, second pulse characteristic parameter includes: at least one of pulse wave transmission time, pulse wave peak to trough amplitude ratio, dominant wave height, descending isthmus relative height, counterpulsation wave relative height, lowest value of pulse wave data waveform, pulse cycle, duration of diastole, time ratio of systole to diastole, dominant wave rise time, area ratio of systole to diastole, area of pulse wave data waveform, slope of pulse wave peak to descending isthmus, and rising velocity of pulse wave.

Wherein the linear regression model is c ═ k₁a+k₂b+k₃Wherein k is₁、k₂And k₃The parameter values are coefficient parameters of a linear regression model, a is the first pulse characteristic parameter, b is the second pulse characteristic parameter, and c is a blood pressure value.

A third aspect of the invention provides a continuous blood pressure measurement device comprising an interface circuit, a memory, and a processor, wherein the memory stores a set of program code therein, and the processor is configured to invoke the program code stored in the memory for performing the following operations:

sampling a pulse wave of a tested object to obtain a sample pulse characteristic parameter, and acquiring a reference blood pressure value of the tested object, wherein the pulse characteristic parameter is a characteristic parameter of the pulse wave of the tested object in a heartbeat period, the pulse characteristic parameter comprises a first pulse characteristic parameter, and the first pulse characteristic parameter comprises: at least one of a slope of an ascending branch of the second-order pulse wave, an amplitude difference of the ascending branch of the second-order pulse wave, a coverage area of the ascending branch of the second-order pulse wave, a slope of a descending branch of the second-order pulse wave, an amplitude difference of the descending branch of the second-order pulse wave and a coverage area of the descending branch of the second-order pulse wave, wherein the reference blood pressure value of the measured object is measured by a precision blood pressure measuring instrument, and the second-order pulse wave is obtained by carrying out secondary derivation on the pulse wave;

calculating to obtain a coefficient parameter of a blood pressure estimation model according to the reference blood pressure value and the sample pulse characteristic parameter;

measuring the pulse wave of the measured object in real time to obtain a real-time pulse characteristic parameter;

and inputting the coefficient parameters and the real-time pulse characteristic parameters into the blood pressure estimation model so as to estimate the real-time pulse-to-pulse continuous blood pressure value of the measured object.

In the above embodiment, the real-time pulse-per-beat continuous blood pressure value of the measured object is calculated by using at least one pulse characteristic parameter selected from the slope of the ascending branch of the second order lead pulse wave, the amplitude difference of the ascending branch of the second order lead pulse wave, the coverage area of the ascending branch of the second order lead pulse wave, the slope of the descending branch of the second order lead pulse wave, the amplitude difference of the descending branch of the second order lead pulse wave, and the coverage area of the descending branch of the second order lead pulse wave, the continuous blood pressure measurement can be realized without a cuff, the electrocardio measurement is also not required, the miniaturized and comfortable wearable design is convenient to realize, and the experimental data proves that the precision of calculating the blood pressure by adopting the pulse characteristic parameters is higher, so that the use requirements of various medical occasions can be met.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a schematic diagram of one embodiment of a pulse wave of a heartbeat cycle in accordance with the present disclosure;

FIG. 2 is a schematic diagram of an embodiment of a second order derivative pulse wave of a heartbeat cycle according to the disclosure;

FIG. 3 is a flow chart of a continuous blood pressure estimation method disclosed in the practice of the present invention;

FIG. 4 is a flow chart of a first embodiment of a continuous blood pressure estimation method disclosed in the present application;

FIG. 5 is a flowchart of a second embodiment of a continuous blood pressure estimation method disclosed in the present application;

FIG. 6 is a flowchart of a third embodiment of a continuous blood pressure estimation method disclosed in the present application;

FIGS. 7a to d are graphs of experimental results obtained by a continuous blood pressure estimation method disclosed in the practice of the present invention;

FIG. 8 is a schematic structural diagram of a continuous blood pressure measuring device according to the present disclosure;

fig. 9 is a schematic structural diagram of a continuous blood pressure measuring device disclosed in the implementation of the invention.

Detailed Description

It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element may be termed a second element, and, similarly, a second element may be termed a first element, without departing from the scope of example embodiments. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

The pulse wave form of each heartbeat cycle is substantially similar in a plurality of heartbeat cycles, so the pulse wave form of one heartbeat cycle is described below. As shown in FIG. 1, when the x-axis is time and the y-axis is the amplitude value of the pulse wave, the pulse wave of one heart cycle is shown in FIG. 1. In fig. 1, point a is the main peak point of the pulse wave, point b is the start valley point of the pulse wave, and point c is the end valley point of the pulse wave. The ascending branch is called from point b to point a, and the descending branch is called from point a to point c. The pulse wave shown in fig. 1 is merely an example, and is not particularly limited, and the shape of the pulse wave is generally different from one human body to another, but the pulse wave has features of a main peak point, a start valley point, and an end valley point.

The second order derivation is performed on the pulse wave of one heart cycle to obtain a second order derived pulse wave of one heart cycle as shown in fig. 2. In fig. 2, point a is a main peak point of the second order lead pulse wave, point B is a start valley point of the second order lead pulse wave, and point C is an end valley point of the second order lead pulse wave. The ascending branch is called from the point B to the point A, and the descending branch is called from the point A to the point C.

The pulse characteristic parameters are parameters capable of reflecting the characteristics of the pulse waves, and include both the characteristic parameters of the pulse waves and the characteristic parameters of the second-order pulse waves, for example, the amplitude of the main wave peak of the pulse waves is a pulse characteristic parameter of the pulse waves, which can reflect the maximum value of the pulse waves; the amplitude of the initial valley point of the pulse wave is a pulse characteristic parameter of the pulse wave, which can reflect the minimum value of the pulse wave at the ascending branch, the amplitude of the end valley point of the pulse wave is a pulse characteristic parameter of the pulse wave, which can reflect the minimum value of the pulse wave at the descending branch, and so on. In the embodiment of the present invention, the pulse characteristic parameters are artificially divided into a first pulse characteristic parameter and a second pulse characteristic parameter. The first pulse characteristic parameter is a newly discovered and applied pulse characteristic parameter in the invention, and the second pulse characteristic parameter is a more common pulse characteristic parameter. The first pulse characteristic parameter is one or more combination of the slope of the ascending branch of the second order pulse leading wave, the amplitude difference of the ascending branch of the second order pulse leading wave, the coverage area of the ascending branch of the second order pulse leading wave, the slope of the descending branch of the second order pulse leading wave, the amplitude difference of the descending branch of the second order pulse leading wave and the coverage area of the descending branch of the second order pulse leading wave. The second pulse characteristic parameter is one or more of a combination of pulse wave transmission time, pulse wave peak-to-trough amplitude ratio, main wave height, isthmus relative height, dicrotic wave relative height, minimum value of pulse wave data waveform, pulse period, duration of diastolic period, time ratio of systolic period to diastolic period, main wave rise time, area ratio of systolic period to diastolic period, area of pulse wave data waveform, slope of pulse wave peak to isthmus, and rise speed of pulse wave, etc. It is understood that, for reasons of space, only some of the second pulse characteristic parameters are listed here, and that more of the second pulse characteristic parameters are not listed here.

Since the first pulse characteristic parameters are found and applied first in the present invention, six first pulse characteristic parameters (the slope of the ascending branch of the second order pulse leading wave, the amplitude difference of the ascending branch of the second order pulse leading wave, the coverage area of the ascending branch of the second order pulse leading wave, the slope of the descending branch of the second order pulse leading wave, the amplitude difference of the descending branch of the second order pulse leading wave, and the coverage area of the descending branch of the second order pulse leading wave) will be described below with reference to fig. 2, while the second pulse characteristic parameters existing in the prior art will not be specifically described herein, and refer to the existing documents.

Slope of rising branch of the second order lead pulse wave

Wherein, I_PIs the amplitude, I, of the main wave peak point A of the second order pulse wave in the heartbeat cycle of FIG. 2_V1Is the amplitude, T, of the initial valley point B of the second order derivative pulse wave in the heartbeat cycle of FIG. 2_PIs two in the heartbeat cycle of fig. 2The time value T corresponding to the main wave peak point A of the order leading pulse wave_V1The time value corresponding to the start valley point B of the second-order pulse wave in the heartbeat cycle of fig. 2;

the amplitude difference PPG _ AID ═ I of the ascending branch of the second order pulse wave_P-I_V1I, wherein I_PIs the amplitude, I, of the main wave peak point A of the second order pulse wave in the heartbeat cycle of FIG. 2_V1The amplitude of the initial valley point B of the second-order pulse wave in the heartbeat cycle of FIG. 2;

the coverage area of the ascending branch of the second order pulse wave

Wherein, P is the main wave peak point a of the second order pulse leading wave in the heartbeat cycle of fig. 2, V1 is the initial wave valley point B of the second order pulse leading wave in the heartbeat cycle of fig. 2, I is the free variable, I is the peak point of the second order pulse leading wave in the heartbeat cycle of fig. 2_iIs the amplitude of point I, I_V1The amplitude of the start valley point V1 of the second order derivative pulse wave in the heartbeat cycle of fig. 2, and the end valley point is point C in fig. 2; it can be understood that the coverage area of the ascending branch of the second order derivative pulse wave is the "1" area shown in fig. 2;

slope of descending branch of the second order lead pulse wave

Wherein, I_PIs the amplitude, I, of the main wave peak point A of the second order pulse wave in the heartbeat cycle of FIG. 2_V2Is the amplitude, T, of the end-point valley point C of the second order lead pulse wave in the heartbeat cycle of FIG. 2_PIs the time value, T, corresponding to the main wave peak point A of the second order pulse wave in the heartbeat cycle of FIG. 2_V2The time value corresponding to the end point valley point C of the second-order pulse wave in the heartbeat cycle of fig. 2;

the amplitude difference PPG _ DID ═ I of the descending branch of the second order pulse leading wave_P-I_V2I, wherein I_PIs the amplitude, I, of the main wave peak point A of the second order pulse wave in the heartbeat cycle of FIG. 2_V2The amplitude of the end-point valley point C of the second-order derived pulse wave in the heartbeat cycle of fig. 2;

the second mentionedCoverage area of descending branch of order guide pulse wave

Wherein, P is the main wave peak point a of the second order pulse leading wave in the heartbeat cycle of fig. 2, V2 is the end wave valley point C of the second order pulse leading wave in the heartbeat cycle, I is the free variable, I is_iIs the amplitude of point I, I_V2The amplitude of the end point valley point V2 of the second order pulse wave in the heartbeat cycle₂Point C in fig. 2. It can be understood that the coverage area of the descending branch of the second order derivative pulse wave is the "2" area shown in fig. 2.

In order to continuously measure the blood pressure in real time, the invention provides a continuous blood pressure measuring device, which can execute a continuous blood pressure estimation method disclosed by the embodiment of the invention, and the specific steps of the continuous blood pressure measuring method are referred to below and are not described at first. The principle that the continuous blood pressure measuring device can continuously measure the blood pressure in real time is as follows: a blood pressure estimation model is established in the continuous blood pressure measuring equipment, and the blood pressure estimation model can reflect the relation between a first pulse characteristic parameter of a pulse wave of a measured object and a blood pressure value. The continuous blood pressure measuring equipment can continuously estimate the real-time pulse continuous blood pressure value of the measured object in real time by continuously measuring the first pulse characteristic parameter of the pulse wave in real time to obtain the real-time pulse characteristic parameter and inputting the real-time pulse characteristic parameter into the blood pressure estimation model. The blood pressure value may be any one of diastolic pressure and systolic pressure or a combination of both. The reason why the continuous blood pressure measuring device can continuously measure the first pulse characteristic parameter of the pulse wave in real time is that the continuous blood pressure measuring device measures the pulse wave through a photoelectric sensor placed at a measuring part outside the measured object, and the photoelectric sensor sends the measured pulse wave to a processor for calculation and analysis so as to obtain the pulse wave characteristic parameter. The measurement site may be any superficial artery capable of measuring pulse wave, such as fingertip artery, earlobe artery, and wrist artery. The pulse wave can be measured by the photoelectric sensor arranged outside the measured object, so the continuous blood pressure measuring device of the invention is non-invasive (i.e. does not cause wound to human body), and the photoelectric sensor can continuously collect the pulse wave of the measured object in real time, therefore, the continuous blood pressure measuring device can naturally and continuously estimate the blood pressure value of the measured object in real time. More specific process is described in the following text for a continuous blood pressure estimation method.

In the embodiment of the present invention, the six first pulse characteristic parameters may be used individually, or may be used partially or wholly in combination. Moreover, the effect of using the six first pulse feature parameters in combination, in part or in whole, by a linear regression model, a non-linear regression model, or a machine learning model is higher than the estimation accuracy of using any one of the six first pulse feature parameters alone. It is understood that, for purposes of space, only a portion of the models are illustrated, and that more regression prediction models are not illustrated.

As shown in fig. 3, the embodiment of the present invention provides a continuous blood pressure estimation method. The continuous blood pressure measuring method provided by the embodiment of the invention comprises the following steps:

310: the continuous blood pressure measuring equipment samples the pulse wave of the measured object to obtain a sample pulse characteristic parameter and obtains a reference blood pressure value of the measured object.

In an embodiment of the present invention, the pulse characteristic parameter is a characteristic parameter of a pulse wave of the measured object in a heartbeat cycle, and the pulse characteristic parameter includes a first pulse characteristic parameter, and the first pulse characteristic parameter includes: the slope of the ascending branch of the second order pulse leading wave, the amplitude difference of the ascending branch of the second order pulse leading wave, the coverage area of the ascending branch of the second order pulse leading wave, the slope of the descending branch of the second order pulse leading wave, the amplitude difference of the descending branch of the second order pulse leading wave and the coverage area of the descending branch of the second order pulse leading wave. In an optional embodiment, the pulse characteristic parameters further include a second pulse characteristic parameter, and the second pulse characteristic parameter includes at least one of pulse wave transmission time, pulse wave peak to trough amplitude ratio, dominant wave height, isthmus relative height, dicrotic wave relative height, lowest value of pulse wave data waveform, pulse period, duration of diastole, time ratio of systole to diastole, dominant wave rise time, area ratio of systole to diastole, area of pulse wave data waveform, slope of pulse wave peak to isthmus, and rise speed of pulse wave.

In the embodiment of the invention, the sampling pulse characteristic parameters of the tested object are obtained by sampling through a continuous blood pressure measuring device. Wherein the continuous blood pressure measuring apparatus is a non-invasive continuous blood pressure measuring apparatus and is a sleeveless measuring apparatus. The continuous blood pressure measuring device is designed to be wearable so that a user can perform continuous blood pressure measurement anytime and anywhere, and the continuous blood pressure measuring device is not separated from a measured object due to movement or movement of the measured object.

In the embodiment of the invention, the reference blood pressure value of the measured object is obtained by measuring through a precision blood pressure measuring instrument and is sent to the continuous blood pressure measuring equipment in a wireless or wired mode. In another embodiment, the reference blood pressure value of the measured object may be manually input to the continuous blood pressure measuring apparatus by medical staff or the like. The precise blood pressure measuring instrument can be an invasive instrument or a non-invasive instrument. For example, when the precision blood pressure measuring instrument is an invasive instrument, the precision blood pressure measuring instrument may be a measuring instrument that measures blood pressure by directly inserting a catheter of a pressure sensor into a blood vessel of a patient, or the like; when The precision blood pressure measuring instrument is a non-invasive instrument, The precision blood pressure measuring instrument may be a mercury sphygmomanometer or a mature commercial device certified by The Medical instrument certification authority such as The american society for The Advancement of Medical Instrumentation (AAMI), and The like. The precise blood pressure measuring instrument may be a cuff-type measuring instrument or a cuff-less measuring instrument.

It can be understood that the blood pressure value of the human body may change with time, and in order to ensure the accuracy of the coefficient parameter of the blood pressure estimation model calculated in step 320, it is required to ensure that the sampling pulse characteristic parameter of the measured object sampled by the continuous blood pressure measuring device and the sampling blood pressure of the measured object measured by the precise blood pressure measuring device are performed simultaneously. For example, at the same time, the blood pressure measuring device samples the sampled pulse characteristic parameters of the measured object at the finger tip of the index finger of the left hand of the measured object, and the precision blood pressure measuring device measures the reference blood pressure of the measured object at the left arm of the measured object. Or, at the same time, the blood pressure measuring device samples the sampling pulse characteristic parameters of the measured object at the left wrist of the measured object, and the precision blood pressure measuring device measures the reference blood pressure of the measured object at the left arm of the measured object.

320: and calculating to obtain a coefficient parameter of the blood pressure estimation model by the continuous blood pressure measuring equipment according to the reference blood pressure value and the sample pulse characteristic parameter.

In the embodiment of the present invention, the coefficient parameters of the blood pressure estimation models of different subjects are usually different for different subjects, so before formally using the continuous blood pressure measurement device to measure the real-time pulse-to-pulse continuous blood pressure value of the subject, the coefficient parameters of the blood pressure estimation models need to be calculated by using the reference blood pressure value obtained in step 310 and the sample pulse characteristic parameters. Wherein the model is derived from a linear regression model, a non-linear regression model, or a machine learning model. It is understood that, for purposes of space, only a portion of the models are illustrated, and that more regression prediction models are not illustrated.

330: and the continuous blood pressure measuring equipment measures the pulse wave of the measured object in real time so as to obtain real-time pulse characteristic parameters.

340: and the continuous blood pressure measuring equipment inputs the coefficient parameters and the real-time pulse characteristic parameters into the blood pressure estimation model so as to estimate the real-time pulse-to-pulse continuous blood pressure value of the measured object.

The continuous blood pressure measuring method of the present invention is described below by way of several specific examples, and it is to be understood that the following examples are for illustrative clarity only and are not to be construed as limiting.

The first embodiment is as follows: the pulse characteristic parameter of the measured object only takes one first pulse characteristic parameter (for example, the slope of the ascending branch of the second-order leading pulse wave), and at this time, the blood pressure estimation model is a linear regression model y ═ Ax + B, where a and B are both coefficient parameters of the linear regression model, x is the slope of the ascending branch, and y is the blood pressure value. As shown in figure 4 of the drawings,

410: the continuous blood pressure measuring equipment samples the slope of the ascending branch of the second-order pulse wave of the tested object to obtain the slope x of the ascending branch of the second-order pulse wave of two samples₁，x₂Simultaneously, two reference blood pressure values y of the measured object are obtained₁，y₂。

420: the continuous blood pressure measuring equipment is used for measuring the blood pressure according to the reference blood pressure value y₁，y₂And the slope x of the rising branch of the sample second derivative pulse wave₁，x₂And calculating to obtain coefficient parameters A and B of the blood pressure estimation model. In particular, the reference blood pressure value y may be₁，y₂And the slope x of the rising branch of the sample second derivative pulse wave₁，x₂And respectively substituting the linear regression model into y ═ Ax + B to obtain an equation system (1):

the solution of the equation set (1) can be obtained,

therefore, the linear regression model can be expressed as

It can be understood that, in the above-mentioned two sampling calculations, the values of one coefficient parameter a and one coefficient parameter B are obtained, and in practical application, the values of the coefficient parameter a and the coefficient parameter B can be obtained through multiple sampling calculations by using a rule such as least square fitting, so as to improve the accuracy of the coefficient parameters a and B.

430: the continuous blood pressure measuring equipment measures the pulse wave of the measured object in real time so as to obtain the slope x of the ascending branch of the real-time second-order pulse wave_i。

440: the continuous blood pressure measuring equipment uses the coefficient parameter

And the slope x of the ascending branch of the real-time second order pulse wave_iInputting the blood pressure estimation model to estimate real-time stroke continuous blood pressure value of the measured object

Example two: the pulse characteristic parameters of the object to be measured are two first pulse characteristic parameters (for example, the slope of the ascending branch of the second-order pulse wave and the slope of the descending branch of the second-order pulse wave), and at this time, the blood pressure estimation model is a linear regression model with y ═ A₁x_i1+A₂x_i2+ B, wherein, A₁、A₂And B are both coefficient parameters of the linear regression model, x_i1Is the slope of the ascending branch of the second order leading pulse wave, x_i2The slope of the descending branch of the second-order pulse leading wave, y is the blood pressure value, and i is the sampling time. As shown in figure 5 of the drawings,

510: the continuous blood pressure measuring equipment respectively samples the slope of the ascending branch of the second order pulse wave and the slope of the descending branch of the second order pulse wave of the tested object to obtain the slope of the ascending branch of the second order pulse wave and the slope (x) of the descending branch of the second order pulse wave of 3 groups of samples₁₁，x₁₂)，(x₂₁，x₂₂) And (x)₃₁，x₃₂) And obtaining 3 reference blood pressure values (y) of the measured object₁，y₂，y₃). Wherein x is₁₁，x₂₁，x₃₁Is the sample value of the slope of the rising branch of the second derivative pulse wave of the sample, x₁₂，x₂₂，x₃₂Is the sample value of the slope of the descending branch of the sample second order lead pulse wave.

520: continuous blood pressureThe measuring equipment is used for measuring the slope (x) of the ascending branch of the sample second-order lead pulse wave and the slope (x) of the descending branch of the sample second-order lead pulse wave according to 3 groups of the ascending branches of the sample second-order lead pulse wave₁₁，x₁₂)，(x₂₁，x₂₂)，(x₃₁，x₃₂) And 3 reference blood pressure values (y)₁，y₂，y₃) Calculating to obtain a coefficient parameter A of the blood pressure estimation model₁、A₂And B. Specifically, the slopes of the ascending branches of the sample second-order lead pulse wave and the slopes of the descending branches of the sample second-order lead pulse wave (x) may be divided into 3 groups₁₁，x₁₂)，(x₂₁，x₂₂)，(x₃₁，x₃₂) And 3 of said reference blood pressure values (y)₁，y₂，y₃) Respectively substituting the linear regression model into y ═ A₁x_i1+A₂x_i2+ B, thereby obtaining equation set (2):

solving equation set (2) to obtain A₁、A₂And the value of B.

It will be appreciated that the above calculation of a coefficient parameter a by three samples results in₁A coefficient parameter A₂And a value of a coefficient parameter B, and in practical application, the coefficient parameter A can be obtained by multiple sampling and calculation by adopting a least square fitting rule and other rules₁、A₂And the value of the coefficient parameter B to increase the coefficient parameter A₁、A₂And the accuracy of B.

530: the continuous blood pressure measuring equipment measures the pulse wave of the measured object in real time so as to obtain the slope x of the ascending branch of the real-time second-order pulse wave_k1And the slope x of the descending branch of the real-time second-order pulse leading wave_k2。

540: the continuous blood pressure measuring equipment uses the coefficient parameter A₁、A₂And B and the slope x of the ascending branch of the real-time second order pulse wave_i1And the slope x of the descending branch of the real-time second-order pulse leading wave_i2Inputting the blood pressure estimation model to estimate the real-time pulse continuous blood pressure value y of the measured object_k＝A₁x_k1+A₂x_k2+B。

Example three: the pulse characteristic parameters of the subject are 1 first pulse characteristic parameter (for example, the slope of the ascending branch of the second-order pulse wave) and 1 second pulse characteristic parameter (for example, the pulse wave transmission time), and the blood pressure estimation model is a linear regression model c ═ k at this time₁a+k₂b+k₃Wherein k is₁、k₂And k₃All the parameters are coefficient parameters of a linear regression model, wherein a is the slope of the ascending branch, b is the pulse wave transmission time, and c is the blood pressure value. As shown in figure 6 of the drawings,

610: the continuous blood pressure measuring equipment samples the slope of the rising branch of the second order pulse wave of the measured object and the pulse wave transmission time respectively to obtain the slope of the rising branch of 3 groups of samples and the sample pulse wave transmission time (a)₁，b₁)，(a₂，b₂) And (a)₃，b₃) And obtaining 3 reference blood pressure values (c) of the measured object₁，c₂，c₃). Wherein, a₁，a₂，a₃Is the sample value of the slope of the rising branch of the second derivative pulse wave of the sample, b₁，b₂，b₃Is the sampled value of the transmission time of the sample pulse wave.

620: the continuous blood pressure measuring equipment is based on the slope of the rising branch of the 3 groups of the sample second order derivative pulse waves and the sample pulse wave transmission time (a)₁，b₁)，(a₂，b₂) And (a)₃，b₃) And 3 reference blood pressure values (c)₁，c₂，c₃) Calculating to obtain a coefficient parameter k of the blood pressure estimation model₁，k₂And k₃. Specifically, the slope of the rising branch of the second-order derivative pulse wave of 3 sets of the sample and the sample pulse wave transmission time (a) may be set₁，b₁)，(a₂，b₂) And (a)₃，b₃) And 3 of said reference blood pressure values (c)₁，c₂，c₃) Respectively substituting the linear regression model into c ═ k₁a+k₂b+k₃Thereby obtaining equation set (3):

k can be obtained by solving equation set (3)₁，k₂，k₃The value of (c).

It will be appreciated that the above calculation of a coefficient parameter k by three samples yields₁A coefficient parameter k₂And a coefficient parameter k₃In practical application, the coefficient parameter k can be obtained by multiple sampling and calculation by adopting principles such as least square fitting and the like₁、k₂And k₃To increase the coefficient parameter k₁，k₂，k₃To the accuracy of (2).

630: the continuous blood pressure measuring equipment measures the pulse wave of the measured object in real time so as to obtain the slope a of the ascending branch of the real-time second-order pulse wave_iAnd real time pulse wave transmission time b_i。

640: the continuous blood pressure measuring equipment measures the coefficient parameter k₁，k₂，k₃And the slope a of the ascending branch of the real-time second order pulse leading wave_iAnd real time pulse wave transmission time b_iInputting the blood pressure estimation model to estimate the real-time stroke continuous blood pressure value c of the measured object_i＝k₁a_i+k₂b_i+k₃。

In order to prove that the accuracy of the real-time continuous blood pressure value measurement by using the first pulse wave characteristic parameter provided by the invention is higher than the accuracy of the real-time continuous blood pressure value measurement by using the second pulse wave characteristic parameter used in the prior art, an experimenter collects the continuous blood pressure data of 22 volunteers for experiment, thereby obtaining the experiment result shown in fig. 7.

As shown in fig. 7a, the area (a) in the figure shows the experimental results of the mean systolic blood pressure error values obtained by real-time continuous blood pressure value measurement respectively using the single first pulse wave feature parameter proposed by the present invention; the area (b) in the figure shows the experimental result of the mean value of systolic blood pressure errors obtained by respectively measuring the real-time continuous blood pressure values by using a single second pulse characteristic parameter used in the prior art; the area (c) in the figure shows the experimental result of the mean systolic blood pressure error value obtained by respectively carrying out real-time continuous blood pressure value measurement by adopting the single first pulse wave characteristic parameter provided by the invention and the pulse wave transmission time in the second pulse wave characteristic parameter used by the prior art. The larger the dark area in the figure, the larger the error and the worse the effect. As can be seen from the figure, the dark region of the region (b) is the most, the dark region of the region (a) is the next to the dark region, and the dark region of the region (c) is the least. The vertical axis represents the number of sampling samples for calibration, from small to large, the larger the number of sampling samples for calibration, the smaller the estimation error, and the better the effect.

As shown in fig. 7b, the area (a) in the figure represents the experimental result of the mean diastolic blood pressure error obtained by real-time continuous blood pressure value measurement respectively using the single first pulse wave feature parameter proposed by the present invention; the area (b) in the figure shows the experimental result of the mean value of diastolic pressure errors obtained by respectively carrying out real-time continuous blood pressure value measurement by using a single second pulse wave characteristic parameter used in the prior art; the area (c) in the figure shows the experimental result of the mean diastolic pressure error value obtained by real-time continuous blood pressure value measurement respectively by using the single first pulse wave characteristic parameter provided by the invention and the pulse wave transmission time in the second pulse wave characteristic parameter used in the prior art. The larger the dark area in the figure, the larger the error and the worse the effect. As can be seen from the figure, the dark region of the region (b) is the most, the dark region of the region (a) is the next to the dark region, and the dark region of the region (c) is the least. The vertical axis represents the number of sampling samples for calibration, from small to large, the larger the number of sampling samples for calibration, the smaller the estimation error, and the better the effect.

As shown in fig. 7c, the area (a) in the figure shows the experimental results of the standard deviation of systolic blood pressure error obtained by real-time continuous blood pressure value measurement respectively using the single first pulse wave feature parameter proposed by the present invention; the area (b) in the figure shows the experimental result of the standard deviation of systolic blood pressure error obtained by real-time continuous blood pressure value measurement by using a single second pulse characteristic parameter used in the prior art; the area (c) in the figure shows the experimental result of the systolic blood pressure error standard deviation obtained by respectively carrying out real-time continuous blood pressure value measurement by adopting the single first pulse wave characteristic parameter provided by the invention and the pulse wave transmission time in the second pulse wave characteristic parameter used by the prior art. The larger the dark area in the figure, the larger the error and the worse the effect. As can be seen from the figure, the dark region of the region (b) is the most, the dark region of the region (a) is the next to the dark region, and the dark region of the region (c) is the least. The vertical axis represents the number of sampling samples for calibration, from small to large, the larger the number of sampling samples for calibration, the smaller the estimation error, and the better the effect.

As shown in fig. 7d, the area (a) in the figure represents the experimental result of the diastolic pressure error standard deviation obtained by respectively performing real-time continuous blood pressure value measurement by using the single first pulse wave feature parameter proposed by the present invention; the area (b) in the figure shows the experimental result of the diastolic pressure error standard deviation obtained by respectively carrying out real-time continuous blood pressure value measurement by using a single second pulse characteristic parameter used in the prior art; the area (c) in the figure shows the experimental result of the diastolic pressure error standard deviation obtained by respectively carrying out real-time continuous blood pressure value measurement by adopting the single first pulse wave characteristic parameter provided by the invention and the pulse wave transmission time in the second pulse wave characteristic parameter used in the prior art. The larger the dark area in the figure, the larger the error and the worse the effect. As can be seen from the figure, the dark region of the region (b) is the most, the dark region of the region (a) is the next to the dark region, and the dark region of the region (c) is the least. The vertical axis represents the number of sampling samples for calibration, from small to large, the larger the number of sampling samples for calibration, the smaller the estimation error, and the better the effect.

While the method of the embodiments of the present invention has been described in detail, in order to better implement the above-described aspects of the embodiments of the present invention, the following also provides the related apparatus for implementing the aspects.

Referring to fig. 8, fig. 8 is a schematic structural diagram of a continuous blood pressure measuring device according to the present invention. The continuous blood pressure measuring apparatus of the present embodiment includes: an acquisition module 810, a calculation module 820, an actual measurement module 830, and an estimation module 840.

The obtaining module 810 is configured to sample a pulse wave of a measured object to obtain a sample pulse characteristic parameter, and obtain a reference blood pressure value of the measured object, where the pulse characteristic parameter is a characteristic parameter of the pulse wave of the measured object in a heartbeat cycle, the pulse characteristic parameter includes a first pulse characteristic parameter, and the first pulse characteristic parameter includes: at least one of a slope of an ascending branch of the second-order pulse wave, an amplitude difference of the ascending branch of the second-order pulse wave, a coverage area of the ascending branch of the second-order pulse wave, a slope of a descending branch of the second-order pulse wave, an amplitude difference of the descending branch of the second-order pulse wave and a coverage area of the descending branch of the second-order pulse wave, wherein the reference blood pressure value of the measured object is measured by a precision blood pressure measuring instrument, and the second-order pulse wave is obtained by carrying out secondary derivation on the pulse wave;

the calculation module 820 is configured to calculate a coefficient parameter of a blood pressure estimation model according to the reference blood pressure value and the sample pulse characteristic parameter;

the actual measurement module 830 is configured to measure the pulse wave of the measured object in real time to obtain a real-time pulse characteristic parameter;

the estimation module 840 is configured to input the coefficient parameter and the real-time pulse feature parameter into the blood pressure estimation model, so as to estimate a real-time pulse-to-pulse continuous blood pressure value of the measured object.

Alternatively,

slope of rising branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1The amplitude value T of the initial valley point of the second order pulse wave in the heartbeat cycle_PThe time value T corresponding to the main wave crest point of the second order pulse wave in the heartbeat cycle_V1The time value corresponding to the initial wave trough point of the second-order pulse wave in the heartbeat period is obtained;

the amplitude difference PPG _ AID ═ I of the ascending branch of the second order pulse wave_P-I_V1I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1The amplitude of the initial valley point of the second order pulse wave in the heartbeat period;

coverage area of ascending branch of second order lead pulse wave

Wherein, P is the main wave peak point of the second order pulse wave in the heartbeat cycle, V1 is the initial wave valley point of the second order pulse wave in the heartbeat cycle, I is the free variable, I_iIs the amplitude of point I, I_V1The amplitude of the starting valley point V1 of the second order pulse leading wave in the heartbeat period;

slope of descending branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude value T of the end point valley point of the second order pulse wave in the heartbeat cycle_PThe time value T corresponding to the main wave crest point of the second order pulse wave in the heartbeat cycle_V2A time value corresponding to a trough point of a terminal point of the second-order pulse wave in the heartbeat period;

the amplitude difference PPG _ DID ═ I of the descending branch of the second order pulse leading wave_P-I_V2I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude of a terminal wave valley point of the second order pulse wave in the heartbeat period;

the coverage area of the descending branch of the second order pulse wave

Wherein P is the second order pulse leading in the heartbeat periodThe main wave peak point of the wave, V2 the end point of the second order pulse wave in the heart cycle, I the free variable, I_iIs the amplitude of point I, I_V2Is the amplitude of the end-point valley point V2 of the second-order pulse leading wave in the heartbeat cycle.

Optionally, the blood pressure estimation model comprises a linear regression model, a non-linear regression model, or a machine learning model.

Optionally, the linear regression model is y ═ Ax + B, where a and B are both coefficient parameters of the linear regression model, x is a pulse characteristic parameter, and y is a blood pressure value.

Optionally, the pulse characteristic parameters further include a second pulse characteristic parameter, which includes: at least one of pulse wave transmission time, pulse wave peak to trough amplitude ratio, dominant wave height, descending isthmus relative height, counterpulsation wave relative height, lowest value of pulse wave data waveform, pulse cycle, duration of diastole, time ratio of systole to diastole, dominant wave rise time, area ratio of systole to diastole, area of pulse wave data waveform, slope of pulse wave peak to descending isthmus, and rising velocity of pulse wave.

Optionally, the linear regression model is c ═ k₁a+k₂b+k₃Wherein k is₁、k₂And k₃The parameter values are coefficient parameters of a linear regression model, a is the first pulse characteristic parameter, b is the second pulse characteristic parameter, and c is a blood pressure value.

The continuous blood pressure measuring device according to the embodiment of the present invention can implement the continuous blood pressure measuring method shown in fig. 3 to 6, and please refer to fig. 3 to 6 and related embodiments specifically, which will not be repeated herein.

Referring to fig. 9, a continuous blood pressure measuring device provided by an embodiment of the present application includes: a storage unit 910, a communication interface 920, and a processor 930 coupled to the storage unit 910 and the communication interface 920. The storage unit 910 is configured to store instructions, the processor 920 is configured to execute the instructions, and the communication interface 920 is configured to communicate with other devices under the control of the processor 930. The processor 930 when executing the instructions may perform any one of the continuous blood pressure estimation methods in the above embodiments of the present application according to the instructions.

Processor 930 may also be referred to as a Central Processing Unit (CPU). The memory unit 910 may include a read-only memory and a random access memory, and provides instructions and data, etc. to the processor 930. A portion of the storage unit 910 may also include a non-volatile random access memory. The components of the wallpaper changing apparatus in a particular application are coupled together, for example, by a bus system. The bus system may include a power bus, a control bus, a status signal bus, and the like, in addition to the data bus. For clarity of illustration, however, the various buses are identified in the figure as the bus system 940. The method disclosed in the above embodiments of the present invention can be applied to the processor 930 or implemented by the processor 930. Processor 930 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 90. The processor 930 may be a general-purpose processor, a digital signal processor, an application specific integrated circuit, an off-the-shelf programmable gate array or other programmable logic device, discrete gate or transistor logic, or discrete hardware components, among others. Processor 930 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the storage unit 910, and the processor 930 may read information in the storage unit 910, and implement the steps of the above method in combination with hardware thereof.

Sampling a pulse wave of a tested object to obtain a sample pulse characteristic parameter, and acquiring a reference blood pressure value of the tested object, wherein the pulse characteristic parameter is a characteristic parameter of the pulse wave of the tested object in a heartbeat period, the pulse characteristic parameter comprises a first pulse characteristic parameter, and the first pulse characteristic parameter comprises: at least one of a slope of an ascending branch of the second-order pulse wave, an amplitude difference of the ascending branch of the second-order pulse wave, a coverage area of the ascending branch of the second-order pulse wave, a slope of a descending branch of the second-order pulse wave, an amplitude difference of the descending branch of the second-order pulse wave and a coverage area of the descending branch of the second-order pulse wave, wherein the reference blood pressure value of the measured object is measured by a precision blood pressure measuring instrument, and the second-order pulse wave is obtained by carrying out secondary derivation on the pulse wave;

calculating to obtain a coefficient parameter of a blood pressure estimation model according to the reference blood pressure value and the sample pulse characteristic parameter;

measuring the pulse wave of the measured object in real time to obtain a real-time pulse characteristic parameter;

and inputting the coefficient parameters and the real-time pulse characteristic parameters into the blood pressure estimation model so as to estimate the real-time pulse-to-pulse continuous blood pressure value of the measured object.

Alternatively,

slope of rising branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1The amplitude value T of the initial valley point of the second order pulse wave in the heartbeat cycle_PThe time value T corresponding to the main wave crest point of the second order pulse wave in the heartbeat cycle_V1The time value corresponding to the initial wave trough point of the second-order pulse wave in the heartbeat period is obtained;

the amplitude difference PPG _ AID ═ I of the ascending branch of the second order pulse wave_P-I_V1I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1Is the heart beatThe amplitude of the initial valley point of the second order lead pulse wave in the period;

the coverage area of the ascending branch of the second order pulse wave

Wherein, P is the main wave peak point of the second order pulse wave in the heartbeat cycle, V1 is the initial wave valley point of the second order pulse wave in the heartbeat cycle, I is the free variable, I_iIs the amplitude of point I, I_V1The amplitude of the starting valley point V1 of the second order pulse leading wave in the heartbeat period;

slope of descending branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude value T of the end point valley point of the second order pulse wave in the heartbeat cycle_PThe time value T corresponding to the main wave crest point of the second order pulse wave in the heartbeat cycle_V2A time value corresponding to a trough point of a terminal point of the second-order pulse wave in the heartbeat period;

the amplitude difference PPG _ DID ═ I of the descending branch of the second order pulse leading wave_P-I_V2I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude of a terminal wave valley point of the second order pulse wave in the heartbeat period;

the coverage area of the descending branch of the second order pulse wave

Wherein, P is the main wave peak point of the second order pulse wave in the heartbeat cycle, V2 is the terminal wave valley point of the second order pulse wave in the heartbeat cycle, I is the free variable, I_iIs the amplitude of point I, I_V2Is the amplitude of the end-point valley point V2 of the second-order pulse leading wave in the heartbeat cycle.

Optionally, the blood pressure estimation model comprises a linear regression model, a non-linear regression model, or a machine learning model.

Optionally, the linear regression model is y ═ Ax + B, where a and B are both coefficient parameters of the linear regression model, x is a pulse characteristic parameter, and y is a blood pressure value.

Optionally, the pulse characteristic parameters further include a second pulse characteristic parameter, which includes: at least one of pulse wave transmission time, pulse wave peak to trough amplitude ratio, dominant wave height, descending isthmus relative height, counterpulsation wave relative height, lowest value of pulse wave data waveform, pulse cycle, duration of diastole, time ratio of systole to diastole, dominant wave rise time, area ratio of systole to diastole, area of pulse wave data waveform, slope of pulse wave peak to descending isthmus, and rising velocity of pulse wave.

Optionally, the linear regression model is c ═ k₁a+k₂b+k₃Wherein k is₁、k₂And k₃The parameter values are coefficient parameters of a linear regression model, a is the first pulse characteristic parameter, b is the second pulse characteristic parameter, and c is a blood pressure value.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (7)

1. A continuous blood pressure measuring device is characterized by comprising an acquisition module, a calculation module, an actual measurement module and an estimation module,

the acquisition module is used for sampling the pulse wave of the measured object to obtain a sample pulse characteristic parameter and acquiring a reference blood pressure value of the measured object, wherein the pulse characteristic parameter is a characteristic parameter of the pulse wave of the measured object in a heartbeat period, the pulse characteristic parameter comprises a first pulse characteristic parameter, and the first pulse characteristic parameter comprises: at least one of the slope of the ascending branch of the second-order pulse wave, the amplitude difference of the ascending branch of the second-order pulse wave, the coverage area of the ascending branch of the second-order pulse wave, the slope of the descending branch of the second-order pulse wave, the amplitude difference of the descending branch of the second-order pulse wave and the coverage area of the descending branch of the second-order pulse wave, wherein the reference blood pressure value of the measured object is measured by a precision blood pressure measuring instrument, and the second-order pulse wave is obtained by performing twice derivation on an original pulse wave signal;

the calculation module is used for calculating to obtain a coefficient parameter of a blood pressure estimation model according to the reference blood pressure value and the sample pulse characteristic parameter;

the actual measurement module is used for measuring the pulse wave of the measured object in real time so as to obtain real-time pulse characteristic parameters;

the estimation module is used for inputting the coefficient parameters and the real-time pulse characteristic parameters into the blood pressure estimation model so as to estimate the real-time pulse-to-pulse continuous blood pressure value of the measured object.

2. The apparatus of claim 1,

slope of rising branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1The amplitude value T of the initial valley point of the second order pulse wave in the heartbeat cycle_PIs the time value corresponding to the main wave crest point of the second order pulse wave in the heartbeat period,T_V1the time value corresponding to the initial wave trough point of the second-order pulse wave in the heartbeat period is obtained;

the amplitude difference PPG _ AID ═ I of the ascending branch of the second order pulse wave_P-I_V1I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V1The amplitude of the initial valley point of the second order pulse wave in the heartbeat period;

the coverage area of the ascending branch of the second order pulse wave

Wherein, P is the main wave peak point of the second order pulse wave in the heartbeat cycle, V1 is the initial wave valley point of the second order pulse wave in the heartbeat cycle, I is the free variable, I_iIs the amplitude of point I, I_V1The amplitude of the starting valley point V1 of the second order pulse leading wave in the heartbeat period;

slope of descending branch of the second order lead pulse wave

Wherein, I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude value T of the end point valley point of the second order pulse wave in the heartbeat cycle_PThe time value T corresponding to the main wave crest point of the second order pulse wave in the heartbeat cycle_V2A time value corresponding to a trough point of a terminal point of the second-order pulse wave in the heartbeat period;

the amplitude difference PPG _ DID ═ I of the descending branch of the second order pulse leading wave_P-I_V2I, wherein I_PIs the amplitude of the main wave peak point of the second order pulse wave in the heartbeat cycle, I_V2The amplitude of a terminal wave valley point of the second order pulse wave in the heartbeat period;

the coverage area of the descending branch of the second order pulse wave

Wherein, P is the main wave peak point of the second order pulse wave in the heartbeat cycle, and V2 is the main wave peak point in the heartbeat cycleThe second order lead pulse wave has the end point valley point, I is free variable, I_iIs the amplitude of point I, I_V2Is the amplitude of the end-point valley point V2 of the second-order pulse leading wave in the heartbeat cycle.

3. The apparatus of claim 1, wherein the blood pressure estimation model comprises a linear regression model, a non-linear regression model, or a machine learning model.

4. The apparatus according to claim 3, wherein the linear regression model is y-Ax + B, where A and B are both coefficient parameters of the linear regression model, x is a pulse feature parameter, and y is a blood pressure value.

5. The apparatus of claim 3, wherein the pulse feature parameters further comprise a second pulse feature parameter, the second pulse feature parameter comprising: at least one of pulse wave transmission time, pulse wave peak to trough amplitude ratio, dominant wave height, descending isthmus relative height, counterpulsation wave relative height, lowest value of pulse wave data waveform, pulse cycle, duration of diastole, time ratio of systole to diastole, dominant wave rise time, area ratio of systole to diastole, area of pulse wave data waveform, slope of pulse wave peak to descending isthmus, and rising velocity of pulse wave.

6. The apparatus of claim 5, wherein the linear regression model is c-k₁a+k₂b+k₃Wherein k is₁、k₂And k₃The parameter values are coefficient parameters of a linear regression model, a is the first pulse characteristic parameter, b is the second pulse characteristic parameter, and c is a blood pressure value.

7. A continuous blood pressure measurement device comprising an interface circuit, a memory, and a processor, wherein the memory stores a set of program code therein, and wherein the processor is configured to invoke the program code stored in the memory for performing the following operations:

sampling a pulse wave of a tested object to obtain a sample pulse characteristic parameter, and acquiring a reference blood pressure value of the tested object, wherein the pulse characteristic parameter is a characteristic parameter of the pulse wave of the tested object in a heartbeat period, the pulse characteristic parameter comprises a first pulse characteristic parameter, and the first pulse characteristic parameter comprises: at least one of the slope of the ascending branch of the second-order pulse wave, the amplitude difference of the ascending branch of the second-order pulse wave, the coverage area of the ascending branch of the second-order pulse wave, the slope of the descending branch of the second-order pulse wave, the amplitude difference of the descending branch of the second-order pulse wave and the coverage area of the descending branch of the second-order pulse wave, wherein the reference blood pressure value of the measured object is measured by a precision blood pressure measuring instrument, and the second-order pulse wave is obtained by performing twice derivation on an original pulse wave signal;

calculating to obtain a coefficient parameter of a blood pressure estimation model according to the reference blood pressure value and the sample pulse characteristic parameter;

measuring the pulse wave of the measured object in real time to obtain a real-time pulse characteristic parameter;

and inputting the coefficient parameters and the real-time pulse characteristic parameters into the blood pressure estimation model so as to estimate the real-time pulse-to-pulse continuous blood pressure value of the measured object.

Images