KR102373092B1 - System and method for estimating blood pressure - Google Patents

Abstract

The present invention relates to a blood pressure estimation system and method.
A blood pressure estimation system according to the present invention includes an input unit for receiving ECG and PPG, a memory storing a program for estimating blood pressure using ECG and PPG, and a processor executing the program, wherein the processor includes a previous RR' value, PPG peak And by considering the peak-to-peak error, the PPG error is reduced and blood pressure is estimated by applying the ratio to the time of successive RR intervals.

Description

Blood pressure estimation system and method {SYSTEM AND METHOD FOR ESTIMATING BLOOD PRESSURE}

The present invention relates to a blood pressure estimation system and method.

According to the prior art, Beats Per Minute (BPM) is obtained using an ECG-based R-R interval and an IBI (Inter-beat interval) that is a PPG-based P-P interval.

However, there is a problem in that the R-R interval does not reflect the characteristics of N-N even if the heart variability at the other end than the heart rate is.

In addition, there is a problem in that the Systolic BP information, which is the Peak P of PPG, is unclear within the interval of BPM and RR, and it is difficult to infer an accurate value for the foot within the interval of PP in PPG, especially as the age increases. There is a problem in that the reliability of blood pressure inference is lowered due to an error according to the gap.
(Patent Document 1) KR 10-2019-0048878 A

The present invention has been proposed to solve the above-mentioned problems, to obtain a highly reliable BPM in a complex sensor system composed of ECG and PPG, to infer the P value and foot of PPG based on the starting point of R Peak of ECG, and to An object of the present invention is to provide a system and method for estimating blood pressure by mutually estimating the blood pressure.

A blood pressure estimation system according to the present invention includes an input unit for receiving ECG and PPG, a memory storing a program for estimating blood pressure using ECG and PPG, and a processor executing the program, wherein the processor includes a previous RR' value, PPG peak And by considering the peak-to-peak error, the PPG error is reduced and blood pressure is estimated by applying the ratio to the time of successive RR intervals.

The blood pressure estimation system according to the present invention reduces the PPG error and increases the reliability of blood pressure estimation by calculating the time and signal values of the PPG peak and the foot based on the R peak of the ECG.

The blood pressure estimation method according to the present invention includes the steps of receiving ECG data and PPG data, synchronizing a sensing scale for ECG data and a sensing scale for PPG data based on a time dependent variable, and using the synchronization result and estimating blood pressure.

According to the present invention, by calculating the BPM based on the ECG RR, calculating the BPM weights of the ECG and PPG using the PP of the PPG, and comparing the individual values and utilizing the proportional information, the blood pressure of the non-invasive based complex sensor method There is a possible effect of inferring and estimating reliable results in a wearable device.

By setting the inaccurate PPG value as a reference point based on the ECG, the accuracy is increased, the PPG peak value is obtained from the ECG R peak signal, and this is calculated by reducing it to a value of time.

By defining the inaccurate PPG value as the reference point (start point) of the signal and time based on the ECG, the signal accuracy is increased, and the PPG peak value is reduced from the ECG R peak signal to a relative time value and calculated.

Effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 illustrates a blood pressure estimation system according to an embodiment of the present invention.
2 is an ECG and PPG graph for explaining a blood pressure estimation process according to an embodiment of the present invention.
3 is a primary systolic and diastolic blood pressure distribution graph according to an embodiment of the present invention.
4 is a secondary systolic and diastolic blood pressure distribution graph according to an embodiment of the present invention.
5 is a two-dimensional systolic and diastolic blood pressure distribution graph according to an embodiment of the present invention.
6 is a result of a development platform according to an embodiment of the present invention.
7 is a flowchart of a method for estimating blood pressure according to an embodiment of the present invention.

The above and other objects, advantages and features of the present invention, and a method for achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings.

However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the following examples are provided to those of ordinary skill in the art to which the present invention pertains. It is only provided to easily inform the composition and effect, and the scope of the present invention is defined by the description of the claims.

On the other hand, the terms used herein are for the purpose of describing the embodiments and are not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, "comprises" and/or "comprising" means that a referenced element, step, operation and/or element is the presence of one or more other elements, steps, operations and/or elements. or added.

According to the prior art, the interval between the minimum value (Foot of PPG, DBP) and the maximum value (SBP, systolic) of PPG based on individual values in the RR interval is calculated assuming that PP (pulse pressure), or PTTp ( Based on the interval between the pulse transit time peak) and the pulse transit time foot (PTTf), the second difference, AMP, is calculated.

However, according to the prior art, it is possible to infer an accurate value in the case of a person having a standard heartbeat characteristic. Otherwise, there is a problem in that the reliability of the inference is lowered.

As an inference technique in which the highest point PPT is subdivided into the PPG signal according to the prior art, the SBP and DBP mixed estimation technique has accuracy enough to fit into the range of living medical devices in a customized method, but the intersection equation is not constant for universal use. , diabetes, hyperlipidemia, heart disease, etc., there is a problem that it is difficult to reflect the characteristics of patients with lesions.

In addition, an inference technique that mixes pulse variability (PRV) and heart rate variability (HRV) is presented. The indirect relationship between SBP, DBP, and blood pressure is identified, but there are various medical opinions about the direct relationship, which limits its practical application. , although systolic in PPG is clear, there is a limit to continuous diastolic estimation due to indeterminate values of PPG.

The arterial blood pressure (APG) technique according to the prior art is a method of classifying the maximum and minimum values of PPG into values identified through primary and secondary differentiation. , there is a problem in that it is difficult to catch a deviation because one cycle error is periodically generated for 10 ms or more, and there is a problem in that it is difficult to optimize dependent optimization for each PPG sensor manufacturer.

The present invention has been proposed to solve the above problems, and provides a blood pressure estimation system and method capable of obtaining a reliable BPM through BPM correction and inferring blood pressure between individual intervals based on the BPM correction.

According to an embodiment of the present invention, it is possible to expand the universality of use by reducing the deviation of the error and lowering the reflection rate for the characteristics of the sensor.

According to the present invention, blood pressure is inferred by using the pulse wave transit time (PTT) and the pulse wave velocity (PWV) that occur in the ECG and PPG relationship, thereby enabling stable extraction of sensing signal errors compared to HPF using signal peaks.

1 illustrates a blood pressure estimation system according to an embodiment of the present invention.

The blood pressure estimation system according to an embodiment of the present invention includes an input unit 110 for receiving ECG data and PPG data, and a memory 120 storing a program for estimating blood pressure using the ECG data and PPG data. ) and a processor 130 for executing a program, wherein the processor 130 synchronizes a sensing scale for ECG data and a sensing scale for PPG data based on a time dependent variable, and using the synchronization result to synchronize blood pressure to estimate

The memory 120 stores a preset number (eg, 200) of continuous data of ECG and PPG.

delete

The processor 130 synchronizes the ECG sensing scale and the PPG sensing scale based on a time dependent variable.

The processor 130 increases the accuracy of the inaccurate PPG value by setting a reference point based on the ECG, obtains the peak value of the PPG from the peak signal of R, and calculates it by reducing it to a value of time.

In the case of estimating blood pressure using voltage values expressed differently for each ECG and PPG sensor, a new algorithm is required every time the sensor is changed. By calculating, since it can be independent from the types of various sensors, there is an effect that high-reliability estimation of blood pressure is possible even by different types of sensors without being affected by the sensing scale.

The processor 130 defines a first disparity between the ECG R maximum value and the PPG minimum value and a second disparity between the ECG R maximum value and the PPG maximum value, wherein the interval between the previous minimum value and the next minimum value of PPG is different from the aforementioned ratio In this case, it is excluded from the data for inference,

The processor 130 calculates the BP ratio through the ratio of the first and second disparities, and reflects the normalized value using the diastolic and systolic standard deviation for the BP ratio with the correction factor in the systolic and diastolic blood pressure inference. .

In general, the BPM of the ECG signal may be expressed as an R-R interval interval according to time, and the more the number of R-R interval values is averaged, the more the error decreases.

According to the present invention, it is possible to reduce the error by applying the ratio of the time of the continuous R-R interval to before and after considering the previous R-R' value and the mutual difference according to the interval between the PPG peak and the next peak.

Assuming that the peaks and currents of the PPG peaks are p _t (n), the values of the previous peaks and peaks can be expressed as p _t (n-1).

At this time, assuming that the current RR' interval of the same ECG is e _t (n) and that the R'-R'' time in the previous maximum interval is e _t (n-1), the ECG and PPG according to each signal The time ratio of the maximum signal is as [Equation 1].

[Equation 1]

delete

A method for estimating blood pressure using ECG and PPG according to another embodiment of the present invention will be described with reference to FIG. 2 , it may be defined by [Equation 2] to [Equation 5] below.

R is the maximum value of ECG, and as in [Equation 2], the difference between the interval between R' and R and the interval between R'' and R' can be defined as R1(n).

[Equation 2]

R1(n _t ) = (R'-R Interval)-(R''-R' Interval)

Since the general interval of ECG has a continuous value, it has a value less than the error distribution unless a large human motion occurs.

As shown in [Equation 3] and [Equation 4] below, P _f (n), which is the time difference between the maximum ECG R value and PPG foot, which is the minimum value of PPG, is defined at the same time, and the time difference with PPG Peak, which is the maximum value of PPG is defined as P _p (n).

[Equation 3]

P _f 1(n _ft ) = R time - PPG foot time

[Equation 4]

P _p 1(n _pt )= R time - PPG Peak time

The interval between the current PPG foot and the next PPG foot' has the same ratio as in [Equation 1].

If the ratio is not the same, since it is an incorrect measurement value, all current values are ignored and calculated using the next duration.

For the foot of PPG and the peak of PPG, the reciprocal ratio of P _ft (n _v ) and P _pt (n _v ) is calculated as in [Equation 5] below based on 0V, which is the baseline.

[Equation 5]

BP _ratio = P _pt (n _v )/P _ft (n _v )

The BP ratio has a correction factor in the inference of final systolic blood pressure and diastolic blood pressure.

4-5 equations can be calculated, and it has the characteristics of [Equation 6].

[Equation 6]

BP _n =a PTT + b BPM + c BP _n-1 + d BP _ratio + e

At this time, a, b, c, d, and e define the corresponding values through the least square method by mixing the PPG with the APG that vomited the first and second derivatives.

At this time, when the value of [Equation 3] is reflected in the PTT, it can be expressed as DBP (diastolic phase), and when the value of [Equation 4] is reflected, it can be expressed as SBP (systolic phase).

For correction, an e value is added, and the e value is as in [Equation 7].

[Equation 7]

eDBP= (BPM(n)-BPM(arg)) / std(n _ft )

eSBP= (BPM(n)-BPM(arg))/ std(n _pt )

[Equation 7] is normalized to a constant value using the standard deviation of diastole and systole, and the reflection of the mutual ratio of [Equation 5] is shown on the same line as the feature quantity that is not compared with each other through the final [Equation 8] to bet

[Equation 8]

BP _n =a PTT + b BPM + c BP _n-1 + d BP _ratio + e (eDBP·BP _ratio or eSBP·BP _ratio )

Using this quaternary equation, the diastolic and systolic of blood pressure can be estimated.

For the blood pressure estimation algorithm according to the embodiment of the present invention, the accuracy of the algorithm was compared and analyzed by verifying it twice by about 250,000 times.

3 and 4, ABP is actual blood pressure, Estimated BP is inferred blood pressure, and the accuracy distribution was verified within ±30% based on the central point of 0.0%.

As shown in FIGS. 3 and 4 , it can be seen that the inferred values of systolic and diastolic blood pressure are distributed as 28.5% and 27.9% of the plurality of verification contents.

5 is a two-dimensional comparison graph of systolic and diastolic verification. Red is an actual SBP (systolic) and DBP (diastolic) graph, and blue is an eSBP (systolic) and DBP (diastolic) comparative verification graph from which actual data is estimated (Estimated). , it can be seen that they are in almost the same range.

When the SBP/DBP was 129/71 on the blood pressure monitor, and the BPM of the heart was 70, the Heart Rate (BPM) on the development platform shown in FIG. SBP/DBP was 130/72.

Accordingly, the BPM satisfies the wearable health device's ±5 BPM, and the blood pressure error also satisfies the performance within ±15% of the error of the home blood pressure monitor.

According to an embodiment of the present invention, blood pressure inference is performed using PPG and ECG, which can be used for wearable devices and portable blood pressure monitors, and satisfies the licensing review regulations of the 'U-Healthcare' medical device system.

7 is a flowchart of a method for estimating blood pressure according to an embodiment of the present invention.

The blood pressure estimation method according to the present invention includes the steps of receiving ECG data and PPG data (S710), and synchronizing a sensing scale for ECG data and a sensing scale for PPG data based on a time dependent variable (S720) and estimating the blood pressure using the synchronization result (S730).

In step S710, a preset number (eg, 200 or more) of continuous data of ECG and PPG is received.

In step S730, the ratio of the PPG time interval and the ECG time interval is used as a correction value for estimating the lowest and highest blood pressure.

Step S730 defines a first lag between the ECG R maximum value and the PPG minimum value, and a second lag between the ECG R maximum value and the PPG maximum value, and if the interval between the previous minimum value and the next minimum value of PPG is different from the ratio, inference is performed excluded from the data for

In step S730, the BP ratio is calculated through the ratio of the first and second lags, and the normalized value using the diastolic and systolic standard deviations is reflected for the BP ratio having a correction factor in systolic and diastolic blood pressure inference.

Meanwhile, the blood pressure estimation method according to an embodiment of the present invention may be implemented in a computer system or recorded in a recording medium. A computer system may include at least one processor, memory, a user input device, a data communication bus, a user output device, and storage. Each of the above-described components performs data communication through a data communication bus.

The computer system may further include a network interface coupled to the network. The processor may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in a memory and/or storage.

The memory and storage may include various types of volatile or non-volatile storage media. For example, memory may include ROM and RAM.

Accordingly, the blood pressure estimation method according to an embodiment of the present invention may be implemented as a computer-executable method. When the method for estimating blood pressure according to an embodiment of the present invention is performed in a computer device, computer readable instructions may perform the method for estimating blood pressure according to the present invention.

Meanwhile, the method for estimating blood pressure according to the present invention described above may be implemented as computer-readable codes on a computer-readable recording medium. The computer-readable recording medium includes any type of recording medium in which data that can be read by a computer system is stored. For example, there may be a read only memory (ROM), a random access memory (RAM), a magnetic tape, a magnetic disk, a flash memory, an optical data storage device, and the like. In addition, the computer-readable recording medium may be distributed in computer systems connected through a computer communication network, and stored and executed as readable codes in a distributed manner.

So far, the embodiments of the present invention have been mainly looked at. Those of ordinary skill in the art to which the present invention pertains will understand that the present invention can be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments are to be considered in an illustrative rather than a restrictive sense. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the scope equivalent thereto should be construed as being included in the present invention.

Claims (11)

an input unit for receiving ECG data and PPG data;
a memory storing a program for estimating blood pressure using the ECG data and the PPG data; and
A processor for executing the program,
The processor synchronizes the sensing scale for the ECG data and the sensing scale for the PPG data based on a time dependent variable, and estimates blood pressure using the synchronization result,
the processor defines a first disparity between the maximum ECG R value and the minimum value of PPG, a second disparity between the maximum ECG R value and the maximum value of PPG, and calculates a BP ratio through the ratio of the first and second disparities; Reflecting a normalized value using the standard deviation of diastolic and systolic for the BP ratio with a correction factor in systolic and diastolic blood pressure inference
Phosphorus blood pressure estimation system.
The method of claim 1,
The memory stores continuous data of a preset number of ECG and PPG
Phosphorus blood pressure estimation system.
delete delete delete delete (a) receiving ECG data and PPG data;
(b) synchronizing the sensing scale for the ECG data and the sensing scale for the PPG data based on a time dependent variable; and
(c) estimating blood pressure using the synchronization result;
The step (c) defines a first lag between the maximum ECG R value and the minimum value of PPG, and a second lag between the maximum ECG R value and the maximum value of PPG, and determines the BP ratio through the ratio of the first and second lags Calculating and reflecting the normalized values using the diastolic and systolic standard deviations for the BP ratio with a correction factor in the systolic and diastolic blood pressure inferences
Phosphorus blood pressure estimation method.
8. The method of claim 7,
The step (a) is to receive a preset number of consecutive data of ECG and PPG
Phosphorus blood pressure estimation method.
delete delete delete

Images