Blood pressure measurement device, blood pressure measurement method, blood pressure measurement program, and method for generating classifier

Abstract

The present invention suppresses the occurrence of noise associated with switching of control and acquires a clean pressure pulse wave from a low pressure. This blood pressure measurement device comprises a cuff that is wound around a measurement site, a pressure detection unit that detects the cuff pressure in the cuff, a pressure control unit that controls the cuff pressure, a blood pressure calculation unit that performs a blood pressure calculation process for calculating the blood pressure of a subject on the basis of the detected cuff pressure, and a winding strength determination unit that performs a winding strength determination process for determining the winding strength with which the cuff is wound around the measurement site. The pressure control unit performs uniform rate pressurization control in which the cuff pressure is increased at a uniform rate through the winding strength determination process performed after the increasing of the cuff pressure is started and the blood pressure calculation process performed after the end of the winding strength determination process.

Description

Blood pressure measurement device, blood pressure measurement method, blood pressure measurement program, and classifier generation method

[0001] The present invention relates to a blood pressure measurement device, a blood pressure measurement method, a blood pressure measurement program, and a method for generating a classifier.

[0002] In recent years, health management has become commonplace by measuring information about an individual's physical and health, such as blood pressure, using a measuring device and recording and analyzing the measurement results. One example of such a measuring device is a blood pressure monitor that attaches a cuff to the subject's upper arm, wrist, or other part of the body to be measured and has a function for determining the wrapping strength of the cuff (see Patent Document 1).

[0003] In the blood pressure monitor disclosed in Patent Document 1, after the cuff is attached, a constant voltage is applied to the pump to drive it during initial inflation, and the wrapping strength of the cuff is determined from the cuff pressure-inflation time characteristic (cuff pressure curve) from the initial pressure until the pressure value reaches the initial inflation end pressure value, and then blood pressure is calculated.

[0004] However, when the wrapping strength is determined and the constant voltage drive is switched to constant speed inflation control, the inflation speed of the cuff changes suddenly, making it difficult to obtain a clear pressure pulse wave.

[0005] Patent No. 5408142

[0006] In view of the above-described conventional techniques, an object of the present invention is to provide a technique that can suppress the generation of noise that accompanies switching of control from determining the cuff wrapping strength to calculating blood pressure, and can acquire a clean pressure pulse wave even from low pressure.

[0007] In order to solve the above problems, the present invention provides a blood pressure measurement device comprising: a cuff that is wrapped around a part to be measured; a pressure detection unit that detects the cuff pressure in the cuff; a pressure control unit that controls the cuff pressure; a blood pressure calculation unit that performs blood pressure calculation processing that calculates the blood pressure of the person to be measured based on the detected cuff pressure; and a wrapping strength determination unit that performs wrapping strength determination processing that determines the wrapping strength of the cuff around the part to be measured, wherein the pressure control unit performs constant speed inflation control in which the cuff pressure is increased at a constant speed throughout the wrapping strength determination processing that is performed after the start of cuff pressure inflation and the blood pressure calculation processing that is performed after the wrapping strength determination processing is completed.

[0008] This allows constant velocity inflation control to be performed through the wrapping strength determination process and the subsequent blood pressure calculation process, thereby suppressing the generation of noise associated with control switching and enabling clear pressure pulse waves to be obtained even at low pressures during blood pressure measurement.

[0009] In the present invention, the wrapping strength determination unit may determine the wrapping strength based on a change over time in the cuff pressure and an inflation rate of the cuff pressure in the wrapping strength determination process.

[0010] In addition, in the present invention, the wrapping strength determination unit may determine the wrapping strength in the wrapping strength determination process using a trained classifier that classifies the wrapping strength based on the input cuff pressure and the change over time in the inflation rate of the cuff pressure.

[0011] In this way, by using a trained classifier, the wrapping strength of the cuff can be determined with greater accuracy.

[0012] The present invention may further include a determination condition determining unit that determines whether a condition for starting the wrapping strength determination process is met.

[0013] This allows the winding strength to be determined when the conditions for starting winding strength determination are satisfied, thereby enabling more accurate determination.

[0014] The present invention may further comprise a circumference determining unit that determines the circumference of the measurement target portion around which the cuff is wrapped.

[0015] This makes it possible to determine the winding strength taking into consideration the circumferential length of the part to be measured.

[0016] In the present invention, the blood pressure calculation unit may determine whether or not to perform the blood pressure calculation process depending on a result of the wrapping strength determination process.

[0017] This allows the blood pressure calculation process to be performed when the wrapping strength of the cuff is appropriate, thereby enabling more accurate blood pressure measurement.

[0018] In addition, in the present invention, the target value of the inflation speed of the cuff pressure in the constant speed inflation control when performing the wrapping strength determination process may be equal to the inflation speed of the cuff pressure in the constant speed inflation control when performing the blood pressure calculation process.

[0019] This allows constant-speed inflation control to be performed at the same inflation speed throughout the wrapping strength determination process and the subsequent blood pressure calculation process, thereby further reducing noise caused by switching between controls.

[0020] The present invention also provides a blood pressure measurement method comprising the steps of: detecting the cuff pressure in a cuff wrapped around a portion to be measured; performing constant-speed inflation control to maintain the inflation speed of the cuff pressure at a constant target value; performing a wrapping strength determination process to determine the wrapping strength around the portion to be measured during the constant-speed inflation control; and performing a blood pressure calculation process to calculate the blood pressure of the subject based on the cuff pressure during the constant-speed inflation control.

[0021] According to this, constant velocity inflation control is performed through the wrapping strength determination process and the blood pressure calculation process, which suppresses the generation of noise associated with control switching and enables a clear pressure pulse wave to be obtained even at low pressures during blood pressure measurement.

[0022] The present invention also provides a blood pressure measurement program that causes a computer to execute the following steps: detecting the cuff pressure in a cuff wrapped around a portion to be measured; performing constant-speed inflation control to maintain the inflation speed of the cuff pressure at a constant target value; performing a wrapping strength determination process to determine the wrapping strength around the portion to be measured during the constant-speed inflation control; and performing a blood pressure calculation process to calculate the blood pressure of the subject based on the cuff pressure during the constant-speed inflation control.

[0023] According to this, constant velocity inflation control is performed through the wrapping strength determination process and the blood pressure calculation process, which suppresses the generation of noise associated with control switching and enables a clear pressure pulse wave to be obtained even at low pressures during blood pressure measurement.

[0024] Furthermore, the present invention provides a method for generating a classifier used in the wrapping strength determination process in a blood pressure measurement program that causes a computer to execute the following steps: detecting the cuff pressure in a cuff wrapped around a portion to be measured; performing constant-speed inflation control to maintain the inflation rate of the cuff pressure at a constant target value; performing wrapping strength determination processing to determine the wrapping strength around the portion to be measured during the constant-speed inflation control; and performing blood pressure calculation processing to calculate the blood pressure of the subject based on the cuff pressure during the constant-speed inflation control, wherein the method trains a classifier by machine learning to generate the trained classifier, which uses the change in cuff pressure over time, the change in the inflation rate of the cuff pressure over time, and the wrapping strength around the portion to be measured as learning data, and outputs the wrapping strength around the portion to be classified as a classification result in response to input of the cuff pressure and the change in the inflation rate of the cuff pressure over time.

[0025] This makes it possible to provide classification that enables accurate classification of the wrapping strength of the cuff in blood pressure measurement.

[0026] According to the present invention, it is possible to suppress the generation of noise that accompanies switching of control from determining the wrapping strength of the cuff to calculating the blood pressure, and to acquire a clear pressure pulse wave even from low pressure.

[0027] FIG. 1 is a diagram illustrating an outline of the hardware configuration of a blood pressure measurement device according to a first embodiment. FIG. 2 is a functional block diagram of the blood pressure measurement device according to the first embodiment. FIG. 3 is a flowchart illustrating the overall processing procedure of the blood pressure measurement device according to the first embodiment. FIGS. 4A and 4B are graphs illustrating the changes over time in cuff pressure, inflation speed, and pulse wave amplitude for subjects with different arm circumferences in the blood pressure measurement device according to the first embodiment. FIG. 5 is a flowchart illustrating the procedures of a wrapping strength determination process in the blood pressure measurement device according to the first embodiment. FIG. 6 is a graph illustrating the changes over time in cuff pressure for each wrapping strength in the blood pressure measurement device according to the first embodiment. FIG. 7 is a functional block diagram of a blood pressure measurement device according to a second embodiment. FIG. 8 is a flowchart illustrating the procedures of an arm circumference determination and wrapping strength determination process in the blood pressure measurement device according to the second embodiment. FIG. 9 is a graph illustrating the changes over time in cuff pressure for each arm circumference and wrapping strength in the blood pressure measurement device according to the second embodiment.

[0028] Hereinafter, specific embodiments of the present invention will be described with reference to the drawings.

[0029] Example 1 An example of an embodiment of the present invention will be described below. However, unless otherwise specified, the dimensions, materials, shapes, relative positions, etc. of the components described in this example are not intended to limit the scope of the present invention to those only.

[0030] (Device Configuration) FIG. 1 is a schematic diagram of the hardware configuration of a blood pressure measurement device 1 according to this embodiment.

[0031] The blood pressure measurement device 1 includes a cuff 11, a pressure sensor 12, a pressure pump 13, an exhaust valve 14, an air tube 15, an oscillator circuit 21, a pump drive circuit 22, a valve drive circuit 23, a display unit 25, a memory 24, an operation switch 26, a power supply 27, and a CPU 100. The blood pressure measurement device 1 corresponds to the blood pressure measurement device of the present invention. The cuff 11 corresponds to the cuff of the present invention.

[0032] The cuff 11 includes an air bag 11a containing air. The cuff 11 is provided with a pressure sensor 12 for detecting the pressure in the air bag 11a of the cuff 11 (hereinafter referred to as "cuff pressure") via an air tube 15, a pressure pump 13 for supplying air to the air bag 11a, and an exhaust valve 14 that opens and closes to maintain the pressure in the air bag 11a or to exhaust the air from the air bag 11a.

[0033] Furthermore, the blood pressure measurement device 1 includes a CPU (Central Processing Unit) 100 for controlling each part of the device, a memory 24 for storing programs and parameters executed for determining the wrapping strength, including a trained classifier for determining the wrapping strength, which will be described later, programs executed for the blood pressure measurement process, and data such as the cuff pressure, inflation speed, and blood pressure measurement results, a display unit 25 for displaying various information such as the wrapping strength determination results and blood pressure measurement results, an operation switch 26 for inputting various instructions for measurement, and a power source 27 for supplying power to each part of the device, such as the CPU.

[0034] Furthermore, the oscillator circuit 21 outputs a signal having an oscillation frequency corresponding to the output value of the pressure sensor 12 to the CPU 100. The pump drive circuit 22 controls the drive of the pressure pump 13 based on a control signal output from the CPU 100. The valve drive circuit 23 controls the opening and closing of the exhaust valve 14 based on the control signal output from the CPU 100.

[0035] 2 is a functional block diagram of the blood pressure measurement device 1. The CPU 100 includes a pressure detection unit 110, a pressure control unit 120, a blood pressure calculation unit 130, a wrapping strength determination input value calculation unit 140, and a wrapping strength determination unit 150. The pressure detection unit 110, the pressure control unit 120, the blood pressure calculation unit 130, and the wrapping strength determination unit 150 correspond to the pressure detection unit, the pressure control unit, the blood pressure calculation unit, and the wrapping strength determination unit of the present invention, respectively.

[0036] The output signal of the oscillator circuit 21 is input to the pressure detection unit 110. The pressure detection unit 110 detects the oscillation frequency of the input signal and converts the detected oscillation frequency into a pressure value signal. The pressure detection unit 110 includes an HPF (High Pass Filter) unit that processes the pressure value signal through an HPF to extract and output a pressure pulse wave signal, and an LPF (Low Pass Filter) unit that processes the pressure value signal through an LPF to extract and output a cuff pressure signal. The cuff pressure signal, which indicates the cuff pressure detected in chronological order by the LPF unit of the pressure detection unit 110, is stored in a predetermined area of ​​the memory 24.

[0037] The pressure control unit 120 controls the operation of the pump drive circuit 22 and the valve drive circuit 23 to control the cuff pressure of the cuff 11 .

[0038] The blood pressure calculation unit 130 receives the pressure pulse wave signal extracted by the HPF unit of the pressure detection unit 110 and processes the received pressure pulse wave signal according to the oscillometric method to calculate the diastolic blood pressure (minimum blood pressure) and the systolic blood pressure (maximum blood pressure).

[0039] The wrapping strength determination input value calculation unit 140 receives a cuff pressure signal indicating the cuff pressure detected in time series from the LPF unit of the pressure detection unit 110. Based on the cuff pressure signal received in time series, the wrapping strength determination input value calculation unit 140 calculates a wrapping strength determination input value to be input to a trained classifier used for wrapping strength determination, which will be described later. The wrapping strength determination input value will be described later.

[0040] The wrapping strength determination unit 150 reads out a trained classifier for winding strength determination from the trained classifier storage unit 240 in the memory 24, and the winding strength determination input value calculated by the winding strength determination input value calculation unit 140 is input to this trained classifier for winding strength determination. The trained classifier for winding strength determination outputs a classification result of the input, indicating the winding strength as loose, tight, or tight. The winding strength determination method will be described in detail later.

[0041] (Blood pressure measurement method) Fig. 3 is a flowchart showing the procedure of the overall processing of the blood pressure measurement method by the blood pressure measurement device 1. The overall processing of blood pressure measurement shown in Fig. 3 is stored in advance in a predetermined area of ​​the memory 24 as a blood pressure measurement program, and is realized by the CPU 100 reading and executing the program from the memory 24. The program may be stored in a computer-readable storage medium and read into the blood pressure measurement device 1 from the storage medium.

[0042] When measuring blood pressure, the subject wraps the cuff 11 around the part to be measured in advance. In the following description, an example is given in which the part to be measured is the upper arm, but the part to be measured is not limited to this and may be the wrist, etc. The description also assumes that the subject performs predetermined settings using the operation switch 26 and issues a command to start blood pressure measurement. Upon receiving the command to start blood pressure measurement, the blood pressure measurement device 1 performs predetermined initialization, such as opening the exhaust valve 14 and setting the cuff pressure to atmospheric pressure (initial pressure).

[0043] When blood pressure measurement is started, the pressure control unit 120 starts constant-speed inflation control (step S1). At this time, the pressure control unit 120 controls the pump drive circuit 22 so that the inflation speed of the cuff pressure reaches a predetermined target value (referred to as "constant-speed inflation control"). This constant-speed inflation control can be performed by, for example, PID control, but the control method is not limited to this.

[0044] Figure 4(A) shows the changes over time in cuff pressure, inflation rate, and pulse wave amplitude under constant velocity inflation control for a subject with an upper arm circumference of 22 cm. Figure 4(B) shows the changes over time in cuff pressure, inflation rate, and pulse wave amplitude under constant velocity inflation control for a subject with an arm circumference of 36 cm. As shown in Figures 4(A) and 4(B), even when the same constant velocity inflation control is performed, the changes over time in cuff pressure and inflation rate vary depending on the circumference of the upper arm on which the subject wears blood pressure measurement device 1.

[0045] In the process of the constant speed pressurization control, the wrapping strength determination unit 150 executes the wrapping strength determination process shown in Fig. 5 based on the determination input value calculated by the wrapping strength determination input value calculation unit 140 (step S3). In this way, the wrapping strength determination process is performed under the constant speed pressurization control.

[0046] In the wrapping strength determination process of step S3, the wrapping strength of the cuff 11 is determined to be one of three categories: loosely wrapped, tightly wrapped, or tightly wrapped. When the cuff 11 is wrapped around the measurement part, such as the upper arm, to form a cylinder, if the circumferential length of this cylinder is approximately equal to the circumferential length of the measurement part, the pressure applied to the measurement part by the cuff 11 is at an appropriate level for blood pressure measurement, and this state is considered to be tightly wrapped. If the circumferential length of the cylinder formed by the cuff 11 is shorter than the circumferential length of the measurement part, the cuff 11 is wrapped tightly around the measurement part, and the pressure applied to the measurement part by the cuff 11 is higher than the appropriate level, and this state is considered to be tightly wrapped. On the other hand, if the circumferential length of the cylinder formed by the cuff 11 is longer than the circumferential length of the measurement part, the cuff 11 is wrapped loosely around the measurement part, and the pressure applied to the measurement part by the cuff 11 is lower than the appropriate level, and this state is considered to be loosely wrapped.

[0047] The wrapping strength determination process will be described below with reference to Fig. 5. First, the wrapping strength determination input value calculation unit 140 calculates the time change ΔT1 in the cuff pressure when P1±ΔP1 is reached, i.e., the time ΔT1 required for the cuff pressure to change from P1-ΔP1 to P1+ΔP1, from the output from the LPF unit of the pressure detection unit 110 (which may be data read from the memory 24) (step S201).

[0048] Next, the wrapping strength determination input value calculation unit 140 calculates the time ΔT2 required for the inflation rate to change from Pd1-ΔPd1 to Pd1+Pd1 when the inflation rate (differential value of the cuff pressure) corresponding to the cuff pressure P1 is Pd1, from the output from the LPF unit of the pressure detection unit 110 (which may be data read from the memory 24) (step S202).

[0049] Then, ΔT1 and ΔT2 calculated by the wrapping strength determination input value calculation unit 140 are input to a trained classifier for wrapping strength determination read from the memory 24. This trained classifier for wrapping strength determination is a classifier generated by machine learning so that, in response to input of changes in cuff pressure and inflation speed, it classifies the wrapping strength into loose, tight, or tight, and outputs the result. The trained classifier for wrapping strength determination classifies the wrapping strength of the blood pressure measurement device 1 by the subject based on the input ΔT1 and ΔT2, thereby determining the wrapping strength (step S203).

[0050] This trained classifier for determining wrapping strength can be generated as follows: (1) First, ΔT indicating the change in cuff pressure over time and ΔT2 indicating the change in the inflation rate of the cuff pressure over time, as well as the wrapping strength of the cuff 11 at the time of measurement when such data was obtained, are acquired. (2) A classification model is prepared that uses the change in cuff pressure over time ΔT1 and the change in cuff pressure over time ΔT2 as inputs and classifies the wrapping strength into loose, tight, or tight, and outputs the result. (3) The acquired data are used as training data and the prepared classification model is trained by machine learning. Any appropriate model can be used as the classification model. Furthermore, any appropriate machine learning method, such as deep learning, can be used. Such a classifier may be generated or updated based on the data obtained by a learning device in an external system of the blood pressure measurement device 1 via a network, the learning device acquiring ΔT indicating the change in cuff pressure over time, ΔT2 indicating the change in the rate of inflation of the cuff pressure over time, and the wrapping strength of the cuff 11 during measurement from a plurality of blood pressure measurement devices 1, and the acquired learned classifier may be stored in the memory 24 of the blood pressure measurement device 1, or the classifier may be provided in a form that can be imported by the blood pressure measurement device 1 using a recording medium that stores the data including parameters, etc.

[0051] Returning to the flowchart of Fig. 4, the overall process of blood pressure measurement will be described. If it is determined in step S203 that the wrapping strength is perfect, the blood pressure calculation unit 130 acquires a pressure pulse wave for blood pressure measurement from the HPF unit of the pressure detection unit 110 and performs a blood pressure calculation process to calculate blood pressure values ​​such as systolic blood pressure and diastolic blood pressure by the oscillometric method (step S4).

[0052] Here, following the end of the wrapping strength determination process in step S2, the blood pressure calculation process in step S4 is performed while maintaining constant velocity inflation control. This prevents noise caused by control switching after the end of the wrapping strength determination process, and allows for the acquisition of clear pressure pulse waves even from low pressures.

[0053] The CPU 100 displays the measurement results, such as the blood pressure value calculated in step S4, on the display unit 25 of the blood pressure measuring device 1 (step S5).The CPU 100 then records the measurement results, such as the blood pressure value calculated in step S4, in a predetermined area of ​​the memory 24 of the blood pressure measuring device 1 (step S6), and ends the blood pressure measurement process.

[0054] If the wrapping strength is determined to be insufficient in the wrapping strength determination process of step S2, i.e., if the wrapping strength is determined to be loose or tight, the blood pressure calculation unit 130 does not perform the blood pressure calculation process, and instead controls the valve drive circuit 23 via the pressure control unit 120 to open the exhaust valve 14 and discharge air from the air bag 11a of the cuff 11 (step S7).The CPU 100 then displays an error on the display unit 25 (step S8), and ends the blood pressure measurement process.

[0055] 7 is a functional block diagram of a blood pressure measurement device 2 according to Example 2. The configuration of the blood pressure measurement device 2, excluding the CPU 100A, is the same as that of the blood pressure measurement device 1 according to Example 1, and therefore detailed description thereof will be omitted. The blood pressure measurement device 2 has a function of determining the arm circumference of the upper arm on which the blood pressure measurement device 2 is worn, prior to the wrapping strength determination process.

[0056] The CPU 100A includes a pressure detection unit 110, a pressure control unit 120, a blood pressure calculation unit 130, a wrapping strength determination input value calculation unit 140, a wrapping strength determination unit 150, as well as a wrapping strength determination condition judgment unit 160, an arm circumference discrimination input value calculation unit 170, and an arm circumference discrimination unit 180.

[0057] The winding strength determination condition determining unit 160 determines whether the conditions for determining the winding strength are met. The conditions for determining the winding strength will be described later.

[0058] The arm circumference discrimination input value calculation unit 170 receives a cuff pressure signal indicating the cuff pressure detected in time series from the LPF unit of the pressure detection unit 110. Based on the cuff pressure signal received in time series, the arm circumference discrimination input value calculation unit 170 calculates an arm circumference discrimination input value to be input to a trained classifier used for arm circumference discrimination, which will be described later. The arm circumference discrimination input value will be described later.

[0059] The arm circumference discrimination unit 180 reads out a trained classifier for arm circumference discrimination from the trained classifier storage unit 240 in the memory 24, and the arm number discrimination input value calculated by the arm circumference discrimination input value calculation unit 170 is input to this trained classifier for arm circumference discrimination. The trained classifier for arm circumference discrimination discriminates and outputs the arm circumference for the input. The arm circumference discrimination method will be described in detail later. Here, the arm circumference discrimination unit 180 corresponds to the circumference discrimination unit of the present invention.

[0060] The wrapping strength determination process in the blood pressure measurement device according to Example 2 will be described with reference to Fig. 8. Fig. 9 is a graph showing the change over time in cuff pressure for each arm circumference and wrapping strength.

[0061] First, the arm circumference discrimination input value calculation unit 170 calculates the time change ΔT3 in the cuff pressure when P'1±ΔP'1 is reached, that is, the time change ΔT3 from P'1-ΔP'1 to P'1+ΔP'1, from the output from the LPF unit of the pressure detection unit 110 (which may be data read from the memory 24) (step S211). Here, a value corresponding to the initial rise in cuff pressure during constant velocity inflation control is set as the cuff pressure P'. The cuff pressure P'1 may be the same as P1 described in the first embodiment.

[0062] Next, ΔT3 calculated by the arm circumference discrimination input value calculation unit 170 is input to the trained classifier for arm circumference discrimination read from the trained classifier storage unit 240 of the memory 24. This trained classifier for arm circumference discrimination is a classifier generated by machine learning to discriminate and output an arm circumference in response to an input of a change in the waveform of the first rising edge during constant velocity inflation control. Based on the input ΔT3, the trained classifier for arm circumference discrimination discriminates the arm circumference of the subject wearing the blood pressure measurement device 1 (step S212). An appropriate method such as deep learning can be used as the machine learning method.

[0063] Next, wrapping strength determination input value calculation unit 140 calculates the change in cuff pressure P2±ΔP2 (ΔT4) over time, that is, the change in cuff pressure P2 from P2−ΔP2 to P2+ΔP2, from the output of the LPF unit of pressure detection unit 110 (which may be data read from memory 24) (step S213). Cuff pressure P2 may be set according to the arm circumference determined in step S212.

[0064] The wrapping strength determination condition determining unit 160 then determines whether the wrapping strength determination condition, that is, whether the inflation rate Sp2 is equal to or less than ±X1 mmHg / sec and whether the cuff pressure P2 is equal to or greater than X2 mmHg, is met at the time of the cuff pressure P2. This wrapping strength determination condition is essentially for determining whether the inflation rate is stable and whether the information necessary for determining the wrapping strength has been obtained. X1 and X2 are set from this perspective and stored in the memory 24, and the wrapping strength determination condition determining unit 160 reads them and makes a determination. For example, X2 can be set to a value approximately twice the value of P1. Here, the wrapping strength determination condition determining unit 160 corresponds to the determination condition determining unit of the present invention.

[0065] If it is determined in step S214 that the winding strength determination condition is not satisfied, the process returns to step S213, and the processes of steps S213 and S214 are repeated for the new P2.

[0066] If it is determined in step S214 that the wrapping strength determination condition is satisfied, the process proceeds to step S215. Here, ΔT4 calculated by the wrapping strength determination input value calculation unit 140 in step S213 is input to the trained classifier for wrapping strength determination read from the trained classifier storage unit 240 in the memory 24. This trained classifier for wrapping strength determination is a classifier generated by machine learning to classify and output the input of a change in cuff pressure as a wrapping strength of loose, tight, or tight. The trained classifier for wrapping strength determination classifies the input ΔT4 as the wrapping strength of the blood pressure measurement device 1 by the subject, thereby determining the wrapping strength. Here, a trained classifier for wrapping strength determination that determines the wrapping strength using the change in cuff pressure as input is used. However, a trained classifier for wrapping strength determination that determines the wrapping strength using the input including the arm circumference determined in step S212 may also be used. The trained classifier for wrapping strength determination can be generated in a manner similar to that of Example 1.

[0067] The blood pressure measurement process and the like in the blood pressure measurement device 2 after the wrapping strength determination process is completed are the same as steps S4 to S8 described for the blood pressure measurement device 1 according to Example 1 with reference to the flowchart in Figure 3. In this example, following the completion of the wrapping strength determination process in step S2, the blood pressure calculation process in step S4 is performed while maintaining constant velocity inflation control. This prevents noise caused by control switching after the completion of the wrapping strength determination process, and enables a clear pressure pulse wave to be acquired even from low pressures.

[0068] In this embodiment, the arm circumference determination process and the wrapping strength determination process are performed for the cuff pressures P1' and P2, respectively, but they may be performed for a plurality of cuff pressures. Also, the wrapping strength determination process according to the first embodiment may be adopted as the wrapping strength determination process.

[0069] DESCRIPTION OF SYMBOLS 1, 2... Blood pressure measurement device 11... Cuff 110... Pressure detection unit 120... Pressure control unit 130... Blood pressure calculation unit 150... Wrapping strength determination unit

Claims

1. A blood pressure measuring device comprising: a cuff that is wrapped around a part to be measured; a pressure detection unit that detects the cuff pressure in the cuff; a pressure control unit that controls the cuff pressure; a blood pressure calculation unit that performs blood pressure calculation processing that calculates the blood pressure of the person to be measured based on the detected cuff pressure; and a wrapping strength determination unit that performs wrapping strength determination processing to determine the strength of wrapping of the cuff around the part to be measured, wherein the pressure control unit performs constant speed inflation control in which the cuff pressure is increased at a constant speed throughout the wrapping strength determination processing that is performed after the start of cuff pressure inflation and the blood pressure calculation processing that is performed after the wrapping strength determination processing is completed.

2. The blood pressure measuring device according to claim 1, characterized in that the wrapping strength determination unit determines the wrapping strength based on the change over time in the cuff pressure and the inflation rate of the cuff pressure during the wrapping strength determination process.

3. The blood pressure measuring device described in claim 2, characterized in that the wrapping strength determination unit determines the wrapping strength using a trained classifier that classifies the wrapping strength based on the input cuff pressure and the change over time in the inflation rate of the cuff pressure during the wrapping strength determination process.

4. The blood pressure measuring device according to any one of claims 1 to 3, further comprising a determination condition determining unit that determines whether or not a condition for starting the wrapping strength determination process is met.

5. A blood pressure measuring device according to any one of claims 1 to 3, characterized in that it comprises a circumference determining unit that determines the circumference of the measurement part around which the cuff is wrapped.

6. A blood pressure measurement device as described in any one of claims 1 to 3, characterized in that the blood pressure calculation unit determines whether or not to perform the blood pressure calculation process depending on the result of the wrapping strength determination process.

7. A blood pressure measuring device as described in any one of claims 1 to 3, characterized in that the target value of the cuff pressure inflation speed in the constant speed inflation control when performing the wrapping strength determination process is equal to the cuff pressure inflation speed in the constant speed inflation control when performing the blood pressure calculation process.

8. A blood pressure measurement method comprising the steps of: detecting the cuff pressure in a cuff wrapped around a part to be measured; performing constant-speed inflation control to maintain the inflation speed of the cuff pressure at a constant target value; performing a wrapping strength determination process to determine the wrapping strength around the part to be measured during the constant-speed inflation control; and performing a blood pressure calculation process to calculate the blood pressure of the person to be measured based on the cuff pressure during the constant-speed inflation control.

9. A blood pressure measurement program that causes a computer to execute the following steps: detecting the cuff pressure in a cuff wrapped around a part to be measured; performing constant-speed inflation control to maintain the inflation speed of the cuff pressure at a constant target value; performing a wrapping strength determination process to determine the wrapping strength around the part to be measured during the constant-speed inflation control; and performing a blood pressure calculation process to calculate the blood pressure of the person to be measured based on the cuff pressure during the constant-speed inflation control.

10. A method for generating a classifier used in the wrapping strength determination process in a blood pressure measurement program that causes a computer to execute the following steps: detecting the cuff pressure in a cuff wrapped around a part to be measured; performing constant-speed inflation control to maintain the inflation speed of the cuff pressure at a constant target value; performing wrapping strength determination processing to determine the wrapping strength around the part to be measured during the constant-speed inflation control; and performing blood pressure calculation processing to calculate the blood pressure of the subject based on the cuff pressure during the constant-speed inflation control, the method comprising: machine learning a classifier that uses the change in cuff pressure over time, the change in the inflation speed of the cuff pressure over time, and the wrapping strength around the part to be measured as learning data, and outputs the wrapping strength around the part to be classified as a result in response to input of the change in cuff pressure and the inflation speed of the cuff pressure; and generating the trained classifier.

Images