Blood pressure measuring device, pressurization control method for blood pressure measuring device, program

Abstract

This reduces the computational complexity required to stop pressurizing the cuff at the desired position. [Solution] The blood pressure measuring device includes a cuff, a sensor for detecting cuff pressure, a pulse wave acquisition unit for acquiring pulse wave data, an index estimation unit for estimating an index representing the current position relative to the expected envelope that is expected to be obtained if the cuff pressure is continued, based on the pulse wave data acquired up to the present while the cuff is being pressurized, a basic information storage unit for accumulating basic information including the estimated index value and the cuff pressure at the time of index estimation, a relationship estimation unit for estimating the relationship between the index and the cuff pressure based on the basic information accumulated up to the present, a target cuff pressure determination unit for determining the target cuff pressure, which is the cuff pressure at which the pressurization of the cuff should be stopped, based on the estimated relationship, and a pressurization control unit for stopping pressurization when the cuff pressure reaches the determined target cuff pressure. The index estimation process is performed at predetermined intervals until the target cuff pressure is determined by the target cuff pressure determination unit.

Description

[Technical Field]

[0001] This invention relates to a blood pressure measuring device, and more particularly to cuff pressurization control. [Background technology]

[0002] In recent years, technologies for managing health by measuring personal physical information such as blood pressure values ​​using measuring devices, recording the measurement results, and analyzing them have become widespread. One example of a measuring device is a blood pressure monitor, which is configured to measure blood pressure, including systolic blood pressure (SBP), by attaching a cuff to the part of the subject to be measured, such as the upper arm or wrist, measuring the pressure pulse wave during the process of pressurizing the attached cuff, and then measuring the blood pressure according to the measured pressure pulse wave. For example, Patent Document 1 proposes a method to complete blood pressure measurement before the blood vessel is completely blocked by the cuff by determining a pulse score from the pressure pulse wave profiles of multiple heartbeats measured most recently, and generating a pressure pulse wave envelope and estimating blood pressure when the pulse score exceeds a threshold. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] U.S. Patent No. 9750419 [Overview of the project] [Problems that the invention aims to solve]

[0004] The pulse score proposed in Patent Document 1 is designed to numerically represent the likelihood that the current cuff pressure is above the cuff pressure corresponding to the envelope peak. Specifically, a pulse score of 3 indicates a 100% probability that the current cuff pressure is above the cuff pressure corresponding to the envelope peak, while a pulse score of 2 indicates a 90% probability. The method in Patent Document 1 can be described as an approach that sets "collection of pressure pulse waves until the envelope peak is exceeded" as a necessary condition for accurate blood pressure estimation, and attempts to determine whether this necessary condition has been met using the pulse score.

[0005] However, while the inventors were examining blood pressure estimation algorithms, they found that to improve estimation accuracy, it is more important to "clearly determine the position on the envelope to which the collected pressure pulse wave represents" than to "have the pressure pulse wave collected up to the peak of the envelope." When attempting to estimate blood pressure from an incomplete envelope, if prior knowledge is given as to whether the given envelope is in the process of approaching the peak, near the peak, or past the peak, then the estimation accuracy can be improved by, for example, switching the blood pressure estimation algorithm or tuning the parameters according to the stage of the envelope. In other words, even if only a pressure pulse wave up to just before the peak of the envelope is obtained, accurate blood pressure estimation can be expected if it is guaranteed that the data represents "data up to a position before the peak of the envelope."

[0006] From this perspective, the pulse score in Patent Document 1 has the following problems.

[0007] Firstly, even with the pulse score, it is not possible to clearly determine the exact position of the collected pressure pulse wave on the envelope. Even if the pulse score threshold is set to 3, this only guarantees that "the pressure pulse wave will be collected up to the peak of the envelope." For example, in one subject, the pulse score will be 3 at a cuff pressure slightly above the peak, but in another subject, it will be 3 at a pressure significantly above the peak, close to the maximum blood pressure. The resulting envelope can vary significantly from subject to subject, as a pulse score of 3 is possible. Furthermore, while setting the pulse score threshold to 2 guarantees a 90% probability of exceeding the envelope peak, conversely, there is a 10% probability (i.e., once every 10 measurements) of only obtaining a pressure pulse wave up to a position before the peak. Thus, because the interval of the collected pressure pulse wave (especially the position on the envelope to which the pressure pulse wave was measured) is unpredictable, there are limitations in improving the accuracy and reliability of subsequent blood pressure estimations when using pulse score-based determination.

[0008] Secondly, when using pulse scoring, it is not possible to control the measurement or pressurization to end before the envelope peak. This is because, basically, the measurement of the pressure pulse wave continues until it exceeds the envelope peak (as mentioned above, there is a probability that the measurement may end before the peak, but this is an exception and cannot be actively controlled in that way). Therefore, there are limitations to speeding up the measurement or reducing the cuff pressure when using pulse scoring for determination.

[0009] Thirdly, although examples have been disclosed in which pressurization is stopped based on whether or not the cuff pressure has reached the target pressure, it remains unclear how the timing of pressurization stoppage is determined in relation to the pulse score without occluding the blood vessel.

[0010] The present invention aims to provide a technique that enables the reduction of computational complexity when measuring pressure pulse waves or stopping cuff pressurization at a desired position on the envelope. [Means for solving the problem]

[0011] This disclosure relates to a blood pressure measuring device having a blood pressure estimation unit that performs a blood pressure estimation process to estimate a blood pressure value using pulse wave data, the device comprising: a cuff for compressing the part to be measured; a sensor for detecting the pressure of the cuff; a pulse wave acquisition unit for acquiring pulse wave data from the output signal of the sensor; an index estimation unit that performs an index estimation process to estimate an index representing the current position relative to a predicted envelope that is expected to be obtained if the pressure of the cuff is continued, based on the pulse wave data acquired up to the present while gradually pressurizing the cuff; a basic information storage unit that stores basic information including the value of the index estimated by the index estimation process and the pressure of the cuff at the time of the index estimation; and gradually pressurizing the cuff The system includes: a relationship estimation unit that performs a relationship estimation process to estimate the relationship between the index and the cuff pressure based on the basic information accumulated up to the present while applying pressure; a target cuff pressure determination unit that performs a target cuff pressure determination process to determine the target cuff pressure, which is the cuff pressure corresponding to the target value of the index at which the pressure of the cuff should be stopped, based on the relationship estimated by the relationship estimation unit; and a pressure control unit that stops the pressure of the cuff when the pressure of the cuff reaches the target cuff pressure determined by the target cuff pressure determination process. The index estimation unit performs the index estimation process at predetermined intervals until the target cuff pressure is determined by the target cuff pressure determination unit.

[0012] The relationship estimation unit may estimate the relationship based on the basic information and the variability when the values ​​of the indicators included in the basic information are estimated by the indicator estimation process.

[0013] The relationship estimation unit may estimate the relationship by curve approximation.

[0014] The target cuff pressure determination unit may include a target cuff pressure estimation unit that performs a target cuff pressure estimation process to estimate the target cuff pressure based on the relationship estimated by the relationship estimation unit, and an accuracy determination unit that determines the target cuff pressure based on the accuracy of the estimated value of the target cuff pressure estimated by the target cuff pressure estimation process.

[0015] Said blood pressure estimation unit may be configured to execute said blood pressure estimation processing that estimates a blood pressure value using an envelope obtained from pulse wave data acquired before pressurization of said cuff is stopped.

[0016] Said index may be an index designed to take a first value at a position where the amplitude of said predicted envelope reaches a maximum value, and take a second value at a position where the amplitude of said predicted envelope is a predetermined ratio relative to said maximum value.

[0017] Said predetermined ratio may be 1 / 2 of said maximum value.

[0018] Said index may be an index designed to take a first value at a position corresponding to diastolic blood pressure in said predicted envelope, and take a second value at a position corresponding to systolic blood pressure in said predicted envelope.

[0019] Said index estimation unit may acquire, from pulse wave data acquired up to the current time point, an envelope up to the current time point and a pulse wave for the most recent one heartbeat, and estimate the value of said index based on feature quantities of the envelope up to the current time point and feature quantities of the pulse wave for the most recent one heartbeat.

[0020] Said index estimation unit may execute said index estimation processing using a trained model that has been machine-learned to output the value of said index when the feature quantities of the envelope up to the current time point and the feature quantities of the pulse wave for the most recent one heartbeat are input thereto.

[0021] Said index estimation unit may acquire, from pulse wave data acquired up to the current time point, an envelope up to the current time point and pulse waves for a plurality of most recent heartbeats, and estimate the value of said index based on feature quantities of the envelope up to the current time point and feature quantities of the pulse waves for the plurality of most recent heartbeats.

[0022] Said index estimation unit may execute said index estimation processing using a trained model that has been machine-learned to output the value of said index when the feature quantities of the envelope up to the current time point and the feature quantities of the pulse waves for the plurality of most recent heartbeats are input thereto.

[0023] This disclosure provides a pressurization control method for a blood pressure measuring device that estimates blood pressure values ​​using pulse wave data, comprising: performing an index estimation process to estimate an index representing the current position relative to a predicted envelope expected to be obtained if the pressurization of the cuff is continued, based on pulse wave data acquired up to the present while gradually pressurizing the cuff; accumulating basic information including the value of the index estimated by the index estimation process and the pressure of the cuff at the time of the index estimation; performing a relationship estimation process to estimate the relationship between the index and the pressure of the cuff based on the basic information accumulated up to the present while gradually pressurizing the cuff; performing a target cuff pressure determination process to determine a target cuff pressure, which is the pressure of the cuff corresponding to a target value of the index at which the pressurization of the cuff should be stopped, based on the relationship estimated by the relationship estimation unit; and stopping the pressurization of the cuff when the pressure of the cuff reaches the target cuff pressure determined by the target cuff pressure determination process, wherein the index estimation process is performed at a predetermined interval until the target cuff pressure is determined by the target cuff pressure determination process.

[0024] This disclosure provides a processor for a blood pressure measuring device that estimates blood pressure values ​​using pulse wave data, which performs an index estimation process to estimate an index representing the current position relative to a predicted envelope expected to be obtained if the cuff is continuously pressurized, based on the pulse wave data acquired up to the present while gradually pressurizing the cuff; stores basic information including the value of the index estimated by the index estimation process and the cuff pressure at the time of the index estimation; performs a relationship estimation process to estimate the relationship between the index and the cuff pressure based on the basic information accumulated up to the present while gradually pressurizing the cuff; and performs a target cuff pressure determination process to determine the target cuff pressure, which is the cuff pressure corresponding to the target value of the index at which the cuff pressurization should be stopped, based on the relationship estimated by the relationship estimation process. The program includes a method for performing pressurization control, which involves stopping pressurization of the cuff when the pressure of the cuff reaches the target cuff pressure determined by the target cuff pressure determination process, and performing the index estimation process at predetermined intervals until the target cuff pressure is determined by the target cuff pressure determination process.

[0025] The present invention may be understood as a blood pressure measuring device, blood pressure monitor, biological information acquisition device, etc., having at least a part of the above configuration. Furthermore, the present invention may be understood as a pressurization control method, a blood pressure measuring method, or a program for implementing such a method, or a recording medium on which such a program is stored, including at least a part of the above processing. Note that each of the above means and processing can be combined with each other as much as possible to constitute the present invention. [Effects of the Invention]

[0026] According to the present invention, it is possible to provide a technique that reduces the amount of computation required when measuring the pressure pulse wave or stopping the pressurization of the cuff at a desired position on the envelope. [Brief explanation of the drawing]

[0027] [Figure 1] Figure 1 is a diagram illustrating the pressure level index P. [Figure 2] Figure 2 is a diagram that conceptually explains the technical meaning and effect of the pressure level index P. [Figure 3] Figure 3 is a schematic diagram showing an example of the hardware configuration of a blood pressure measuring device according to an embodiment. [Figure 4] Figure 4 is a block diagram showing an example of the functional configuration of the blood pressure measuring device 1 according to an embodiment. [Figure 5] Figure 5 is a flowchart showing the overall procedure for blood pressure measurement. [Figure 6] Figure 6 is a flowchart showing the procedure for the indicator estimation process performed by the indicator estimation unit. [Figure 7] Figure 7 is a schematic diagram illustrating the flow of the indicator estimation process performed by the indicator estimation unit. [Figure 8]Figures 8A and 8B illustrate design example 1 of the pressure level index P. [Figure 9] Figure 9 illustrates design example 2 of the pressure level index P. [Figure 10] Figure 10 illustrates the target cuff pressure estimation process performed by the target cuff pressure determination unit. [Figure 11] Figure 11 is a flowchart showing the procedure for estimating the target cuff pressure by the target cuff pressure determination unit. [Figure 12] Figure 12 illustrates a modified example of the target cuff pressure estimation process performed by the target cuff pressure determination unit. [Figure 13] Figure 13 is a flowchart showing the procedure for estimating the target cuff pressure in a modified example using the target cuff pressure determination unit. [Figure 14] Figure 14 is a schematic diagram illustrating the training process of the machine learning model used for metric estimation. [Modes for carrying out the invention]

[0028] First, I will explain the outline of the proposed method. In a blood pressure measuring device 1 that estimates blood pressure values ​​using pressure pulse wave data, in order to achieve the objective of enabling the measurement of the pressure pulse wave and the pressurization of the cuff 130 to be stopped at a desired position on the envelope, the proposed method introduces a "pressure level index P," which is an index representing the position relative to the envelope, and estimates this pressure level index P at a predetermined period while gradually pressurizing the cuff 130. Repeated estimation of the pressure level index P in this way is computationally intensive. Therefore, it is necessary to install a processor with high processing power, and there is also a possibility that power consumption will increase.

[0029] At this time, the pressure level index P has a constant relationship g(·) with the cuff pressure, and, For any index that can uniquely define an arbitrary cuff pressure, the index P = g(cuff pressure|parameter) is defined as cuff pressure = g -1An inverse function can be defined as (index P|parameter). Therefore, the parameter value of g(·) is predicted from the relationship between the history of the pressurization level index P and the cuff pressure. Then, using the inverse function of g(·) obtained in this way, the cuff pressure target value = g -1 (Pressure level index P target value | parameter) Cuff pressure to stop pressurization Predict the target value.

[0030] As described above, once the target cuff pressure can be predicted, the calculation of the pressurization level index P becomes unnecessary, thereby reducing the amount of computation required. Here, we have described the pressurization level index P, which has a certain relationship g(·) with cuff pressure and can uniquely define any cuff pressure. However, this is just one example and is not limited to this.

[0031] (Pressure level index P) Before explaining the cuff pressure prediction method proposed in this paper, we will first explain the pressurization level index P. Figure 1 illustrates the pressure level index P. A cuff 130 is attached to the part of the person being measured, and the cuff pressure is monitored by a sensor while the cuff 130 is gradually pressurized. The upper part of Figure 1 shows the sensor output signal. The sampling rate of the sensor output signal is, for example, about 250 Hz. The pressure pulse wave signal from the part of the person being measured is superimposed on the sensor output signal. The middle part of Figure 1 shows the pressure pulse wave signal extracted (separated) from the sensor output signal. For example, a high-pass filter can be used to extract the pressure pulse wave signal. The envelope is a curve formed by connecting the peak values ​​of the pulse waveforms (called "pulses") of each heartbeat in the pressure pulse wave signal. The lower part of Figure 1 shows the envelope obtained from the pressure pulse wave signal. Note that although the horizontal axis in Figure 1 is shown as time, since cuff pressure and time are correlated, the envelope may also be represented on a Cartesian coordinate plane with cuff pressure on the horizontal axis and pulse amplitude on the vertical axis.

[0032] The blood pressure measurement device 1 in this proposal estimates the value of the pressure level index P based on the pulse wave data (the portion enclosed by the dashed line) acquired up to the present time T while gradually pressurizing the cuff 130. This pressure level index P is a dimensionless index designed to represent the position at time T with respect to the expected envelope that is expected to be obtained if the pressurization of the cuff 130 is continued beyond time T. The pressure level index P represents a relative position with respect to, for example, the peak position of the expected envelope (the position where the amplitude is at its maximum). In the example in Figure 1, the pressure level index P is 0 at the peak position of the expected envelope, and the value of the pressure level index P at each position is set according to the ratio to the maximum amplitude value at the peak position. The pressure level index P takes a negative value before the peak and a positive value after the peak. For example, if the value of the pressure level index P is estimated to be -0.5 based on the pulse wave data acquired up to the present time T, the sign (positive or negative) of the pressure level index P indicates that the present time T is just before the peak of the envelope, and the absolute value of the pressure level index P indicates its relative position (distance) to the peak position of the envelope.

[0033] Figure 2 conceptually illustrates the technical meaning and effect of the pressure level index P. As shown on the left side of Figure 2, the envelope obtained from the measurement (with cuff pressure or time on the horizontal axis) differs in peak position and envelope width (spread) depending on the subject. Therefore, it is not easy to determine the position on the envelope from the current pulse amplitude value. The introduction of the pressure level index P has the effect of canceling out this variation in the envelope due to the subject being measured. That is, as shown on the right side of Figure 2, by taking the pressure level index P on the horizontal axis and scaling the envelope, the envelope is normalized with respect to the cuff pressure direction (time direction), making it possible to indicate the same position on the envelope using the value of the pressure level index P regardless of the subject being measured.

[0034] By using such a pressure level index P, it is possible to measure the pressure pulse wave at a desired position on the envelope. It becomes possible to stop the pressurization of the cuff 130. For example, the estimation process of the pressurization level index P may be executed at a predetermined cycle while gradually pressurizing the cuff 130, and control may be performed to stop the pressurization of the cuff 130 when the value of the pressurization level index P reaches a predetermined threshold Pth. For example, in FIG. 1, if the threshold Pth is set to -0.5, the pressurization of the cuff 130 is stopped at time point T, and blood pressure estimation is executed based on the data of the pressure pulse wave signal acquired up to time point T. In this case, the value of the pressurization level index P may be provided as prior knowledge to the blood pressure estimation process, and the blood pressure estimation algorithm or the parameters used in the algorithm may be changed according to the value of the pressurization level index P. For example, three types of algorithms or parameters are prepared in advance: for the case of P < -0.3, for the case of -0.3 ≦ P ≦ 0.3, and for the case of 0.3 < P, and the algorithm or parameter to be used is changed according to the value of the pressurization level index P at the time when pressurization is stopped. With this configuration, high-accuracy and highly reliable blood pressure estimation can be expected regardless of whether an envelope before reaching the peak, an envelope including the peak, or an envelope beyond the peak is used.

[0035] <Configuration of Blood Pressure Measurement Device> FIG. 3 schematically shows an example of the hardware configuration of the blood pressure measurement device 1 according to the present embodiment. The blood pressure measurement device 1 according to the present embodiment includes a control unit 10, a storage unit 11, an oscillation circuit 121, a pump drive circuit 122, a valve drive circuit 123, a cuff 130, a pressure sensor 131, a pressurization pump 132, an exhaust valve 133, an air tube 134, an operation switch 14, a display unit 15, and a power source 16. The control unit 10 and the storage unit 11 are an example of the computer part of the blood pressure measurement device 1.

[0036] The cuff 130 includes an air bag 1301 that contains air. The cuff 130 is equipped with a pressure sensor 131, a pressurizing pump 132, and an exhaust valve 133 via an air tube 134. The pressure sensor 131 is configured to detect the pressure (cuff pressure) inside the air bag 1301 of the cuff 130. The pressurizing pump 132 is configured to supply air into the air bag 1301. The exhaust valve 133 is provided as a boundary between the internal and external spaces of the air bag 1301 and is configured to be openable and closable. By closing the exhaust valve 133, air can be trapped inside the air bag 1301 and the pressure inside the air bag 1301 can be maintained. On the other hand, by opening the exhaust valve 133, air can be released from the air bag 1301 and the pressure can be reduced.

[0037] The control unit 10 includes a hardware processor such as a CPU and is configured to perform information processing based on a program and various data. The control unit 10 (CPU) is an example of the processor resources of the estimation device. The oscillation circuit 121 outputs a signal with an oscillation frequency corresponding to the output value of the pressure sensor 131 to the control unit 10. In this embodiment, the control unit 10 processes the signal from the oscillation circuit 121 to obtain cuff pressure and pulse wave data. The pump drive circuit 122 is configured to control the drive of the pressurizing pump 132 based on a control signal output from the control unit 10. The valve drive circuit 123 is configured to control the opening and closing of the exhaust valve 133 based on a control signal output from the control unit 10.

[0038] The memory unit 11 may be composed of, for example, a semiconductor memory. The memory unit 11 is an example of a memory resource of the estimation device. In this embodiment, the memory unit 11 stores various information such as the program 110 and model data 111. The program 110 includes a program that causes the CPU of the blood pressure measuring device 1 to execute information processing (described later), such as pressurization control processing of the cuff 130, acquisition processing of pressure pulse waves, estimation processing of the pressurization level index P, estimation processing of blood pressure values, and display processing of measurement results. The program 110 includes a series of instructions for said information processing. Note that each process may be composed of a different program module, or all processes may be executed with a single program. The model data 111 is a trained model. The configuration of the model data 111 is not particularly limited and may be appropriately determined according to the embodiment, as long as the trained model can be reproduced when estimating the pressurization level index P or blood pressure. The model data 111 may be training result data. The model data 111 may be incorporated into the program 110. The memory unit 11 stores the results of blood pressure measurement (cuff pressure, pulse wave data, pressurization level index). Other information, such as the value of P and estimated blood pressure, may be retained as appropriate.

[0039] The operation switch 14 is used to perform operations such as starting blood pressure measurement. The operation switch 14 may consist of at least one of a physical switch and a virtual switch. The display unit 15 is configured to display various information such as the blood pressure measurement results. The operation switch 14 and the display unit 15 may be integrally configured as a touch panel display. The power supply 16 is configured to supply power to each part, such as the control unit 10.

[0040] Regarding the specific hardware configuration of the blood pressure measurement device 1, components can be omitted, replaced, and added as appropriate depending on the embodiment. For example, the control unit 10 may include multiple hardware processors. Hardware processors may consist of microprocessors, FPGAs, DSPs, ASICs, etc. The blood pressure measurement device 1 may be equipped with a communication interface. For example, the blood pressure measurement device 1 may be configured to communicate data with a user terminal such as a smartphone by including a proximity wireless communication module. This allows the blood pressure measurement device 1 to acquire arbitrary data via the user terminal. At least one of the program 110 and model data 111 may be stored on a storage medium of an external computer such as a NAS. The blood pressure measurement device 1 may acquire at least one of the program 110 and model data 111 from an external computer. The blood pressure measurement device 1 may acquire data directly from an external computer, or it may acquire data indirectly from an external computer via a user terminal. The blood pressure measurement device 1 may be configured as a general blood pressure monitor, or as a wearable device such as a wristwatch.

[0041] Figure 4 is a block diagram showing an example of the functional configuration of the blood pressure measuring device 1 according to this embodiment.

[0042] The blood pressure measuring device 1 has, as its main functions related to blood pressure measurement, a pressure detection unit 40, an index estimation unit 43, a target cuff pressure determination unit 45, a pressurization control unit 46, and a blood pressure estimation unit 47. These functions are realized by the CPU of the control unit 10 reading and executing a program stored in the memory unit 11.

[0043] The pressure detection unit 40 receives the signal from the oscillation circuit 121. The pressure detection unit 40 detects the oscillation frequency of the signal input from the oscillation circuit 121 and converts the detected oscillation frequency into a pressure value signal. The pressure detection unit 40 includes an HPF (High Pass Filter) unit 41 that extracts and outputs a pressure pulse wave signal by processing the pressure value signal with an HPF (High Pass Filter), and an LPF (Low Pass Filter) unit 42 that extracts and outputs a cuff pressure signal by processing the pressure value signal with an LPF (Low Pass Filter). The time-series data of the pressure pulse wave output from unit 41 and the time-series data of the cuff pressure output from LPF unit 42 are stored in the memory of the control unit 10. That is, HPF unit 41 functions as a pulse wave acquisition unit that acquires pulse wave data from the output signal of the pressure sensor 131, and LPF unit 42 functions as a cuff pressure acquisition unit that acquires cuff pressure data from the output signal of the pressure sensor 131. The sampling rate of the pulse wave and cuff pressure is, for example, about 250 Hz.

[0044] The index estimation unit 43 has the function of performing an index estimation process that estimates the pressure level index P based on the time-series data of the pressure pulse wave acquired up to the present while gradually pressurizing the cuff 130. The index estimation unit 43 repeatedly performs the index estimation process at a predetermined cycle once measurement (pressurization of the cuff 130) begins. The execution cycle of the index estimation process can be set arbitrarily, but it is preferable that the index is estimated and evaluated each time a new pulse is obtained, so in this embodiment, it is set to be about the same as or slightly faster than the average heart rate cycle (for example, about 1 Hz to several Hz).

[0045] The target cuff pressure determination unit 45 gradually pressurizes the cuff 130 and estimates the target cuff pressure based on the combination of the cuff pressure obtained up to that point and the estimated pressurization level index P. It has a function to perform a target cuff pressure determination process to determine the target cuff pressure. The target cuff pressure determination unit 45 includes a relationship estimation unit 451, a target cuff pressure estimation unit 452, and a precision determination unit 453, which will be described later.

[0046] The pressurization control unit 46 has the function of pressurizing and depressurizing the cuff 130 by sending control signals to the pump drive circuit 122 and the valve drive circuit 123 and controlling the operation of the pressurizing pump 132 and the exhaust valve 133.

[0047] The blood pressure estimation unit 476 has the function of reading time-series data of pulse waves from memory and estimating blood pressure values ​​using that data. The blood pressure values ​​to be estimated should include systolic blood pressure (SBP) and diastolic blood pressure (DBP).

[0048] In this embodiment, the functions shown in Figure 4 are implemented by a software program, but all or part of these functions may be replaced by circuits such as ASICs or FPGAs. Alternatively, the functions shown in Figure 4 may be implemented through collaboration with other computers connected via a network (such as a cloud server, a user's PC, or a smartphone).

[0049] <Operation of blood pressure measuring device> Figure 5 is a flowchart showing the overall processing steps of the blood pressure measurement method using the blood pressure measurement device 1. The processing shown in Figure 5 is achieved by the CPU of the control unit 10 reading and executing the program 110 from the memory unit 11. Note that all or part of the program 110 may be read into the blood pressure measurement device 1 from a computer-readable external storage medium (such as flash memory), or it may be acquired via a network.

[0050] When measuring blood pressure, the person being measured has already wrapped the cuff 130 around the part to be measured. The following explanation describes an example where the upper arm is the part to be measured, but the part to be measured is not limited to the upper arm; it may also be the wrist or other parts. Furthermore, it will be explained assuming that the person being measured has made the necessary settings using the operation switch 14 and has given the instruction to start blood pressure measurement. When the blood pressure measuring device 1 receives the instruction to start blood pressure measurement, it performs the necessary initialization, such as opening the exhaust valve 133 and setting the cuff pressure to atmospheric pressure (initial pressure).

[0051] When blood pressure measurement is started, the pressurization control unit 46 starts pressurization control to pressurize the cuff 130 (step S501). During pressurization control, the cuff pressure is increased at a constant rate.

[0052] The pressure detection unit 40 acquires the pressure pulse wave and cuff pressure while gradually increasing the cuff pressure (step S502). Here, the pressure detection unit 40 may monitor the cuff pressure and wait until the cuff pressure reaches a predetermined lower limit so that a reliable pulse wave can be measured. When the part to be measured begins to be compressed with a certain force by the cuff 130, the process may proceed to step S503.

[0053] If the target cuff pressure, which will be described later, has already been determined (Yes in step S503), the current cuff pressure is compared with the target cuff pressure (step S510). If the cuff pressure is equal to or greater than the target cuff pressure (Yes in step S510), the pressurization control unit 46 stops pressurizing the cuff 130 at that point (step S511). If the cuff pressure is less than the target cuff pressure (No in step S510), the process from step S502 onwards continues. If the target cuff pressure has not yet been determined (No in step S503), the process proceeds to step S504.

[0054] <Estimation process for pressure level index P> Step S504 is the indicator estimation process performed by the indicator estimation unit 43. Figure 6 is a flowchart of an example of the indicator estimation process. Figure 7 is a schematic diagram showing the flow of the indicator estimation process performed by the indicator estimation unit 43. An example of the indicator estimation process will be explained with reference to Figure 7 as well.

[0055] The indicator estimation process will be explained with reference to Figure 6. In step S601, the index estimation unit 43 obtains the envelope of the pulse wave up to the present time based on the pulse wave data for multiple heartbeats acquired up to that point. Known methods can be used to generate the envelope. For example, the envelope may be obtained by simply connecting the peak positions of the pulses of each heartbeat, or the envelope may be obtained by fitting a curve to the sequence of points of the peak positions of the pulses of each heartbeat. Although not shown in the figures, the index estimation unit 43 may also perform preprocessing such as noise reduction on the pulse wave data before obtaining the envelope.

[0056] In step S602, the index estimation unit 43 extracts "envelope features" using the envelope obtained in step S503, and also extracts "pulse features" using the pulse (pulse wave) of the most recent heartbeat. Examples of envelope features that can be used include the maximum amplitude of the envelope, the full width at half maximum of the envelope, the peak cuff pressure of the envelope (the cuff pressure at which the envelope amplitude is maximum), the area of ​​the envelope, the standard deviation of the envelope amplitude, the skewness of the envelope, the kurtosis of the envelope, and the parameters when a predetermined model (curve) is fitted to the envelope (for example, the parameters of the Gaussian function fitted to the envelope). In addition, examples of pulse features that can be used include the maximum amplitude of the pulse, the full width at half maximum of the pulse, the peak cuff pressure of the pulse, the area of ​​the pulse, the standard deviation of the pulse amplitude, the skewness of the pulse, and the kurtosis of the pulse. Note that the features listed here are just examples, and other features may be used.

[0057] In step S603, the index estimation unit 43 estimates the value of the pressure level index P based on the envelope features up to the present time and the features of the most recent heartbeat pulse. In this embodiment, as shown in Figure 6, a pre-trained model that has been machine-learned to output the value of the pressure level index P when given the envelope features and the features of one heartbeat pulse as input is used for the index estimation process (the learning process will be described later).

[0058] <Example of design for pressure level index P> Figures 8A and 8B show design example 1 of the pressurization level index P. In design example 1, the envelope is modeled using a Gaussian function, and the relationship between the pressurization level index P and cuff pressure is defined using the parameters of the Gaussian function.

[0059] First, prepare the pressure pulse wave data. As shown in Figure 8A, use the pressure pulse wave data for the range from cuff pressure less than the diastolic blood pressure (DBP) to cuff pressure exceeding the systolic blood pressure (SBP). Next, obtain the envelope from the pressure pulse wave. For example, you can obtain the envelope by connecting the peak points of the pulses for each heartbeat. Then, fit the envelope with a Gaussian function represented by equation (1) below. In equation (1), the variable x is the cuff pressure, and A, B, and C are parameters that define the shape of the Gaussian function. The pressurization level index P is defined as shown in equation (2) below, using the parameters B and C of the Gaussian function obtained by fitting. Equation (2) defines the relationship (conversion) between the pressurization level index P and the cuff pressure x.

[0060]

number

number

[0061] Figure 8B shows the relationship between the value of the pressure level index P according to equation (2) and the amplitude of the envelope. The pressure level index P takes the value of 0 (first value) at the peak position where the amplitude of the envelope is at its maximum, and the absolute value of the pressure level index P is (2log2) at the position where the amplitude of the envelope is half of the maximum value. 1 / 2 It takes the second value, where log is the natural logarithm.

[0062] Statistically, it is known that the position where the envelope amplitude is half of its maximum value roughly corresponds to DBP and SBP. Therefore, when using the pressure level index P in design example 1, P = -(2log2) 1 / 2 The position of the arrow roughly indicates the position of DBP, and P = (2log2) 1 / 2The position of this point will roughly indicate the position of the SBP. Based on this knowledge, the desired pressurization stop threshold Pth can be determined.

[0063] Next, as an alternative example, we will explain design example 2 of the pressure level index P. In design example 2, the relationship between the pressure level index P and cuff pressure is defined by normalizing the envelope in the interval between the lowest blood pressure and the highest blood pressure.

[0064] Specifically, the true value of systolic blood pressure (SBP) gt and the true value of diastolic blood pressure (DBP) gt Using this, the relationship (conversion) between the pressurization level index P and the cuff pressure x can be defined as shown in equation (3) below. In the case of design example 2, since there is no need to calculate the envelope or fit the formula to the envelope as in design example 1, the relationship formula for the pressurization level index P can be obtained with a simple process.

[0065]

number

[0066] Figure 9 shows the relationship between the pressure level index P and cuff pressure x according to equation (3). Specifically, the pressure level index P takes a value of -1 (first value) at the position corresponding to the diastolic blood pressure DBP on the envelope, and a value of +1 (second value) at the position corresponding to the systolic blood pressure SBP on the envelope. Furthermore, by setting the envelope to peak midway between the diastolic and systolic blood pressures, the pressure level index P becomes 0 at the peak position of the envelope. Based on these findings, the desired threshold Pth can be determined.

[0067] Returning to the explanation of the flowchart shown in Figure 5. The pressurization control unit 46 compares the value of the pressurization level index P with a predetermined threshold Pth (step S505). The threshold Pth may be preset in the storage unit 11 of the blood pressure measuring device 1, or it may be changeable by the user.

[0068] If the value of the pressurization level index P has reached the threshold Pth (Yes in step S505), the pressurization control unit 46 stops pressurizing the cuff 130 at that point (step S511). However, even if the value of the pressurization level index P has not reached the threshold Pth (No in step S506), if the cuff pressure has reached a predetermined upper limit, it may be considered that some kind of abnormality has occurred, and pressurization of the cuff 130 may be stopped. If the value of the pressurization level index P has not reached the threshold Pth (No in step S505), proceed to step S506.

[0069] <Estimation of target cuff pressure> In step S506, the basic information storage unit 44 stores the cuff pressure acquired in step S502. Then, the pressurization level index P estimated in step S504 is obtained, and basic information including the combination of the corresponding cuff pressure and the estimated value of the pressurization level index P is stored and accumulated in a predetermined area of ​​the storage unit 11.

[0070] In step S507, the target cuff pressure determination unit 45 estimates the target cuff pressure. Figure 10 is a diagram illustrating the target cuff pressure estimation process, and Figure 11 is a flowchart detailing the procedure for the target cuff pressure estimation process in step S507.

[0071] In step S1101, the target cuff pressure determination unit 45 obtains the time-series changes of the cuff pressure and the estimated value of the pressurization level index P during the pressurization process from basic information including the combination of accumulated cuff pressure and the estimated value of the pressurization level index P. Each point in FIG. 10 indicates time-series changes of past cuff pressures obtained in this manner and estimated values of the pressurization level index P. For example, the point Pt1 corresponds to a combination of the pressurization level index P calculated based on pressure pulse waves and cuff pressures obtained up to the timing T1 which is the target cuff pressure estimation time indicated by the arrow, and the cuff pressure at the timing T1. Similarly, the point Pt2 corresponds to a combination of the pressurization level index P calculated based on pressure pulse waves and cuff pressures obtained up to the timing T2 which is the target cuff pressure estimation time indicated by the arrow, and the cuff pressure at the timing T2. Further, the point Pt3 corresponds to a combination of the pressurization level index P calculated based on pressure pulse waves and cuff pressures obtained up to the timing T3 which is the target cuff pressure estimation time indicated by the arrow, and the cuff pressure at the timing T3.

[0072] In step S1102, a relationship estimating unit 451 executes relationship estimation processing for estimating a relational expression between the cuff pressure and the pressurization level index P by applying curve approximation to time-series changes of past cuff pressures and estimated values of the pressurization level index P. When the envelope is approximated by the Gaussian function shown in formula (1), the pressurization level index P is defined by formula (2), that is, a linear function g(CP) with respect to the cuff pressure CP as shown in the following formula (4). [Mathematical expression] In formula (4), [Mathematical expression] is set.

[0073] At this time, both parameters a and b are based on the past cuff pressure CP past and the past estimated pressurization level index P past , from the relationship of [Mathematical expression] can be estimated. Note that a-hat and b-hat indicate estimated values of the respective parameters. In this way, a curve approximation (here, an approximation using a linear function) is applied to the past cuff pressure and pressure level index P estimates accumulated up to the present time (when the target cuff pressure is estimated). By doing so, we estimate g(CP), which shows the relationship between cuff pressure and the pressurization level index P.

[0074] The line L shown in Figure 10 corresponds to P=g(CP). In step S1103, the target pressurization stop level P is set for g(CP) estimated in step S1102. target If you set this, the corresponding target cuff pressure CP target teeth

number

[0075] Thus, the target cuff pressure estimation unit 452 estimates the target cuff pressure CP based on the pressure pulse wave and cuff pressure acquired up to the time of target cuff pressure estimation. target We estimate this.

[0076] Let's return to the explanation of the flowchart in Figure 5. In step S508, the accuracy determination unit 453 determines the estimated target cuff pressure CP target To determine whether the accuracy is sufficient, there is variability in the cuff pressure CP and pressurization level index P obtained over time, and the estimated target cuff pressure CP target This is because the accuracy may not be sufficient. As criteria for determining accuracy, for example, the absolute mean of the approximation error for the estimated value of the pressure level index P may be less than or equal to a predetermined threshold, the variability of the most recent estimated value of the pressure level index P may be less than or equal to a predetermined threshold, or the average value of the variability of the most recent few estimated values ​​of the pressure level index P may be less than or equal to a predetermined threshold. The criteria for determining accuracy are not limited to these, and combinations of these or other methods may be used.

[0077] Estimated target cuff pressure CP targetIf it is determined that the accuracy is insufficient (No. in step S508), the process returns to step S502, and the index estimation process and the target cuff pressure estimation process are repeatedly executed at predetermined intervals until a target cuff pressure with sufficient accuracy is estimated. Then, the estimated target cuff pressure CP target If it is determined that the accuracy is sufficient (Yes in step S508), the target cuff pressure determination unit 45 determines the target cuff pressure CP estimated in step S507. target This is determined as the target cuff pressure (step S509).

[0078] In step S510, the pressurization control unit 46 determines whether the current cuff pressure is equal to or greater than the determined target cuff pressure.

[0079] If it is determined that the current cuff pressure is less than the determined target cuff pressure (No in step S510), the process returns to step S502, and the acquisition of the pressure pulse wave and cuff pressure is repeated at predetermined intervals. At this point, since the target cuff pressure has been determined, it is determined to be Yes in step S503, and the process proceeds to step S510. When the target cuff pressure is determined at this time, the estimation process of the pressurization level index P in step S504 becomes unnecessary, thus reducing the amount of computation. If it is determined that the current cuff pressure is equal to or greater than the determined target cuff pressure (Yes in step S510), the pressurization control unit 46 stops pressurizing the cuff 130 at that point (step S511).

[0080] In step S512, the blood pressure estimation unit 47 estimates blood pressure values ​​(SBP, DBP) using information such as the envelope obtained from the pressure pulse wave data acquired before the pressurization of the cuff 130 is stopped. The measurement results (blood pressure values, heart rate, etc.) obtained from the above measurement process are displayed on the display unit 15 (step S513).

[0081] <Modified version of target cuff pressure estimation process> Figure 12 illustrates a modified version of the target cuff pressure estimation process. Detailed explanations of parts common to Figure 10 are omitted. Figure 13 is a flowchart detailing the steps of the target cuff pressure estimation process related to the modified version. Here, in step S504, when estimating the pressure level index P, the variability of the estimated value of the pressure level index P is also obtained, and in step S506, when storing the combination of cuff pressure and the estimated value of the pressure level index P, the variability of the estimated value of the pressure level index P is also stored and accumulated. Examples of the variability of the estimated value include, but are not limited to, the error and standard deviation of the estimated value.

[0082] In step S1301, the time-series changes of the estimated cuff pressure and the estimated pressure level index P (including the variability of the estimated value) during the pressurization process are obtained from the combination of the accumulated cuff pressure and the estimated pressure level index P (including the variability of the estimated value). In Figure 11, the variability of the estimated pressure level index P is shown by error bars Eb1 along with the display of point Pt1 (the same applies to other points).

[0083] Then, in step S1302, when estimating the relationship between cuff pressure and the pressure level index P by applying curve approximation to the time-series changes of past cuff pressure and estimated pressure level index P, the variability of the estimated pressure level index P is used as the weighting for regression (fitting). For example, if the variability of the estimated pressure level index P is large, the weighting can be made small, and if the variability of the estimated pressure level index P is small, the weighting can be made large, but the method of weighting is not limited to this. The process in step S1303 is the same as in step S1103, so it is omitted.

[0084] <Learning the pressure level index P> Figure 14 is a schematic diagram illustrating the training process of a machine learning model used for indicator estimation. This training process can be performed by the control unit 10 of the blood pressure measurement device 1, but typically it is performed by a separate training device. The training device consists of a general-purpose computer equipped with a CPU, GPU, memory, storage, etc., and the training process described below is realized by loading the training program stored in storage into memory and executing the program using the CPU and GPU. Any machine learning algorithm can be used, such as multiple regression, random forest, neural network, support vector regression, Lasso regression, Ridge regression, or Naive Bayes (Gaussian distribution).

[0085] First, the learning device acquires training data, specifically pressure pulse wave data (step S130). It is advisable to prepare a large amount of pressure pulse wave data obtained from multiple subjects.

[0086] The learning device first selects one pulse wave data point and determines the relationship between the pressure level index P and cuff pressure for that data point (step S141). If the pressure level index P from design example 1 is adopted, relationship (2) is obtained; if the pressure level index P from design example 2 is adopted, relationship (3) is obtained.

[0087] The learning device extracts the target pressure pulse wave data at an arbitrary cuff pressure (step S142). This cuff pressure is hereafter referred to as the "cut cuff pressure." This extraction process simulates the state in which measurements have been taken up to the point of the cut cuff pressure.

[0088] The learning device extracts envelope features and pulse features from the pressure pulse wave data extracted in step S142 (step S143). Then, these features are used by the machine being trained. The data is input into the learning model to obtain an estimate of the pressure level index P (step S144).

[0089] On the other hand, the learning device calculates the true value of the pressurization level index P by substituting the cut cuff pressure into the relational expression obtained in step S141 (step S145). The learning device calculates the difference between the estimated value and the true value of the pressurization level index P obtained in step S144 (step S146), and uses that difference to modify the machine learning model (step S147).

[0090] By repeating steps S142-S147 while varying the cut cuff pressure, the correlation between the pressure level index P and the position on the envelope in the target pressure pulse wave data can be learned. By repeating this for multiple given pressure pulse wave data, a general-purpose trained model can be obtained.

[0091] <Other> The above embodiments are merely illustrative examples illustrating the configuration of the present invention. The present invention is not limited to the above specific forms, and various modifications are possible within the scope of its technical concept. In the above embodiments, envelope features and pulse features for one heartbeat were used in the index inference process, but other features can also be used in the index inference process. For example, envelope features and pulse features for multiple recent heartbeats may be used in the index inference process. Alternatively, only envelope features may be used in the index inference process, or pulse features for multiple recent heartbeats may be used in the index inference process. Furthermore, the above design examples 1 and 2 are merely examples, and any definition may be used as long as the relationship (conversion) between the pressurization level index P and cuff pressure can be defined. [Explanation of symbols]

[0092] 1: Blood pressure measuring device

Claims

1. In a blood pressure measuring device having a blood pressure estimation unit that performs a blood pressure estimation process to estimate blood pressure values ​​using pulse wave data, A cuff for compressing the area to be measured, A sensor for detecting the pressure of the cuff, A pulse wave acquisition unit that acquires pulse wave data from the output signal of the aforementioned sensor, An index estimation unit performs an index estimation process that estimates an index representing the current position relative to the predicted envelope expected to be obtained if the pressure on the cuff is continued, based on the pulse wave data acquired up to the present while gradually pressurizing the cuff. A basic information storage unit stores basic information including the value of the index estimated by the index estimation process and the pressure of the cuff at the time of the index estimation. A relationship estimation unit performs a relationship estimation process to estimate the relationship between the index and the pressure of the cuff based on the basic information accumulated up to the present while gradually pressurizing the cuff. A target cuff pressure determination unit performs a target cuff pressure determination process to determine a target cuff pressure, which is the pressure of the cuff corresponding to the target value of the index for which the pressurization of the cuff should be stopped, based on the relationship estimated by the relationship estimation unit. A pressure control unit that stops pressurizing the cuff when the pressure of the cuff reaches the target cuff pressure determined by the target cuff pressure determination process, It has, The index estimation unit is a blood pressure measuring device that performs the index estimation process at predetermined intervals until the target cuff pressure is determined by the target cuff pressure determination unit.

2. The aforementioned relationship estimation unit, The relationship is estimated based on the basic information and the variability in the values ​​of the indicators included in the basic information when they are estimated by the indicator estimation process. The blood pressure measuring device according to claim 1.

3. The aforementioned relationship estimation unit, The relationship described above is estimated by curve approximation. The blood pressure measuring device according to claim 1.

4. The target cuff pressure determination unit is, A target cuff pressure estimation unit performs a target cuff pressure estimation process to estimate the target cuff pressure based on the relationship estimated by the relationship estimation unit, A precision determination unit determines the target cuff pressure based on the precision of the estimated value of the target cuff pressure estimated by the target cuff pressure estimation process, Having, A blood pressure measuring device according to any one of claims 1 to 3.

5. The blood pressure estimation unit performs the blood pressure estimation process, which estimates the blood pressure value using the envelope obtained from the pulse wave data acquired before the pressurization of the cuff is stopped. The blood pressure measuring device according to claim 1.

6. The aforementioned index is designed to take a first value at the position where the amplitude of the predicted envelope is at its maximum value, and a second value at the position where the amplitude of the predicted envelope is at a predetermined ratio to the maximum value. The blood pressure measuring device according to claim 1.

7. The predetermined ratio is 1 / 2 of the maximum value. The blood pressure measuring device according to claim 6.

8. The aforementioned index is designed to take a first value at the position corresponding to the lowest blood pressure in the predicted envelope and a second value at the position corresponding to the highest blood pressure in the predicted envelope. The blood pressure measuring device according to claim 1.

9. The aforementioned index estimation unit, From the pulse wave data acquired up to the present time, the envelope up to the present time and the pulse wave for the most recent heartbeat are obtained. The value of the index is estimated based on the envelope characteristics up to the present time and the pulse wave characteristics of the most recent heartbeat. The blood pressure measuring device according to claim 1.

10. The index estimation unit performs the index estimation process using a pre-trained model that has been trained to output the value of the index when given the envelope feature quantities up to the present time and the pulse wave feature quantities for the most recent heartbeat as input. The blood pressure measuring device according to claim 9.

11. The aforementioned index estimation unit, From the pulse wave data acquired up to the present time, the envelope up to the present time and the pulse waves for the most recent multiple heartbeats are obtained. The value of the index is estimated based on the envelope characteristics up to the present time and the pulse wave characteristics for the most recent multiple heartbeats. The blood pressure measuring device according to claim 1.

12. The index estimation unit performs the index estimation process using a pre-trained model that has been trained to output the index value when given the envelope feature quantities up to the present time and the pulse wave feature quantities for the most recent multiple heartbeats as input. The blood pressure measuring device according to claim 11.

13. A method for controlling the pressure of a blood pressure measuring device that estimates blood pressure values ​​using pulse wave data, The process involves gradually increasing the pressure on the cuff and, based on the pulse wave data acquired up to this point, performing an index estimation process to estimate an index representing the current position relative to the predicted envelope that is expected to be obtained if the pressure on the cuff is continued. The system stores basic information including the value of the index estimated by the index estimation process and the pressure of the cuff at the time of the index estimation. The process involves gradually pressurizing the cuff while performing a relationship estimation process to estimate the relationship between the index and the pressure of the cuff based on the basic information accumulated up to that point, Based on the relationship estimated by the relationship estimation process, a target cuff pressure determination process is performed to determine the target cuff pressure, which is the pressure of the cuff corresponding to the target value of the index for which the pressurization of the cuff should be stopped. The pressurization of the cuff is stopped when the pressure of the cuff reaches the target cuff pressure determined by the target cuff pressure determination process. Includes, A pressurization control method that performs the index estimation process at predetermined intervals until the target cuff pressure is determined by the target cuff pressure determination process.

14. The processor of a blood pressure measuring device that estimates blood pressure values ​​using pulse wave data, The process involves gradually increasing the pressure on the cuff and, based on the pulse wave data acquired up to this point, performing an index estimation process to estimate an index representing the current position relative to the predicted envelope that is expected to be obtained if the pressure on the cuff is continued. The system stores basic information including the value of the index estimated by the index estimation process and the pressure of the cuff at the time of the index estimation. The process involves gradually pressurizing the cuff while performing a relationship estimation process to estimate the relationship between the index and the pressure of the cuff based on the basic information accumulated up to that point, Based on the relationship estimated by the relationship estimation process, a target cuff pressure determination process is performed to determine the target cuff pressure, which is the pressure of the cuff corresponding to the target value of the index for which the pressurization of the cuff should be stopped. The pressurization of the cuff is stopped when the pressure of the cuff reaches the target cuff pressure determined by the target cuff pressure determination process. Includes, A program for performing pressurization control, which involves executing the index estimation process at predetermined intervals until the target cuff pressure is determined by the target cuff pressure determination process.

Images