Noninvasive blood pressure measurement method, device, equipment and storage medium

Abstract

The invention discloses a non-invasive blood pressure measurement method, device and equipment and a storage medium. The method comprises the following steps: preprocessing signal data of a pressure sensor; performing feature extraction on the envelope signal curve to obtain the maximum amplitude of the envelope signal curve, and calculating to obtain a plurality of first widths, a plurality of second widths, a plurality of first amplitudes and a plurality of second amplitudes according to the maximum amplitude; the extracted feature values are input into a classification model, the classification model classifies the envelope signal curve according to the input feature values, and the blood pressure type of the envelope signal curve is obtained; and calculating and acquiring a first ratio coefficient of systolic pressure and a second ratio coefficient of diastolic pressure of the blood pressure type by utilizing a least square method. The method can better adapt to processing of data such as large pulse pressure difference, arteriosclerosis and individual difference, the universality and accuracy of the method are improved, and the problem of measurement precision in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-user message sending, and in particular to a non-invasive blood pressure measurement method, device, equipment and storage medium. Background Art

[0002] Non-invasive blood pressure measurement is one of the most commonly used methods for monitoring physiological parameters in clinical practice. Traditional oscillometric methods, which use an automatically inflating blood pressure cuff to obtain blood pressure readings, can provide reliable estimates of mean arterial pressure. However, this method has significant uncertainty in estimating systolic blood pressure (SBP) and diastolic blood pressure (DBP), particularly in the following situations:

[0003] Pulse pressure variations: When a patient's pulse pressure (the difference between systolic and diastolic pressure) varies widely or narrowly, traditional oscillometric algorithms struggle to accurately capture these variations. For example, increased pulse pressure, common in the elderly, or low pulse pressure in certain pathological conditions (such as aortic regurgitation) can affect measurement accuracy.

[0004] Variations in arterial stiffness: Arterial stiffness reduces the elasticity of the blood vessel wall, thus altering the characteristics of the cuff pressure oscillation signal. Many existing algorithms are sensitive to variations in arterial stiffness, making their performance unstable across individuals. This is particularly true for patients with hypertension, diabetes, or other cardiovascular diseases, who may have stiffer arteries, further exacerbating measurement errors.

[0005] Individual differences: Each subject has unique physiological characteristics, including but not limited to age, gender, body mass index (BMI), and ethnicity. These factors influence arterial structure and function, leading to varying pressure curves. Therefore, empirical oscillation amplitude ratios based on fixed parameters are difficult to apply to all populations. Summary of the Invention

[0006] The purpose of the embodiments of the present application is to provide a non-invasive blood pressure measurement method, device, equipment and storage medium to solve the measurement accuracy problem in the prior art.

[0007] In order to solve the above technical problems, the present application provides a non-invasive blood pressure measurement method, which adopts the following technical solutions, including:

[0008] Step 100: Using PWM to control the air pump to perform rapid pressurization, slow and uniform deflation, and rapid deflation in sequence, obtain pressure sensor signal data, pre-process the pressure sensor signal data to obtain maximum and minimum points of the pressure sensor signal data and the intervals between the maximum and minimum points, and obtain an envelope signal curve using the maximum and minimum points;

[0009] Step 200: Extract features of the envelope signal curve to obtain a maximum amplitude of the envelope signal curve, and calculate based on the maximum amplitude a plurality of first widths of the maximum amplitude that differ from a starting point of the pressure curve to the left by a plurality of prescribed values, a plurality of second widths of the maximum amplitude that differ from a starting point of the pressure curve to the right by a plurality of prescribed values, a plurality of first amplitudes corresponding to the pressure change window envelope curve shifted sequentially by prescribed units to the left by the maximum amplitude, and a plurality of second amplitudes corresponding to the pressure change window envelope curve shifted sequentially by prescribed units to the right by the maximum amplitude;

[0010] Step 300: Determine whether the blood pressure measurement process is valid based on the maximum amplitude, the maximum point, the minimum point, the interval between the maximum points, the first width, and the second width. If the blood pressure measurement is valid, input the extracted feature value into a classification model. The classification model classifies the envelope signal curve based on the input feature value to obtain the blood pressure type of the envelope signal curve.

[0011] Step 400: Calculate a first ratio coefficient of the systolic pressure and a second ratio coefficient of the diastolic pressure of the blood pressure type using the least squares method, and estimate the systolic pressure and diastolic pressure of the blood pressure type based on the first ratio coefficient and the second ratio coefficient;

[0012] The first width and the second width are respectively the width from the maximum amplitude dividing line to the left and the width from the maximum amplitude dividing line to the right.

[0013] Furthermore, the step 100 includes:

[0014] Step 110: Use a bandpass filter to perform high-frequency filtering and low-frequency filtering on the pressure sensor signal data to obtain a pulse wave signal;

[0015] Step 120: Search and obtain the maximum value point, the minimum value point, and the distance between the maximum value points of the pulse wave signal, and extract the amplitude according to the maximum value point and the minimum value point;

[0016] Step 130 : interpolate according to the amplitude, and then perform low-pass filtering and zero-point calibration on the pulse wave signal to obtain the envelope signal curve.

[0017] Furthermore, the step 200 includes:

[0018] Step 210, respectively calculating the width to the left of the maximum amplitude dividing line when the maximum amplitude differs from the starting point of the pressure curve by 90%, 75%, 50%, 25%, and 10%, and the width to the right of the maximum amplitude dividing line when the maximum amplitude differs from the starting point of the pressure curve by 90%, 75%, 50%, 25%, and 10%.

[0019] Step 220: Calculate multiple first amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is moved 500 units to the left, and multiple second amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is moved 500 units to the right. The pressure change windows between the first amplitude values overlap by 200 units, and the pressure change windows between the second amplitude values overlap by 200 units.

[0020] Furthermore, step 300 includes:

[0021] Step 310: Compare the first number of the maximum points, the second number of the minimum points, and the spacing between the maximum points with a specified range, and compare the maximum amplitude, the first width, and the second width with a specified range;

[0022] Step 320: If the first number, the second number, and the distance between the maximum points are all within the specified range, and the maximum amplitude, the first width, and the second width are all within the specified range, then determine that the current blood pressure measurement is a valid measurement.

[0023] Furthermore, after step 320, step 300 also includes

[0024] Step 330: The classification model obtains the first width and the second width, the first amplitude and the second amplitude of each envelope signal curve;

[0025] Step 340: Classify the current blood pressure type into a normal blood pressure type, a critical blood pressure type, a sclerosis-grade hypertension type, or an arrhythmia combined with vascular sclerosis blood pressure type based on the first width and the second width, the first amplitude and the second amplitude.

[0026] Furthermore, the step 400 includes:

[0027] Step 410: Obtain the maximum amplitude of the blood pressure type, and construct a systolic blood pressure prediction function using the maximum amplitude and the first ratio coefficient parameter;

[0028] Step 420: Acquire actual systolic blood pressure parameters, and construct a systolic blood pressure least squares model using the systolic blood pressure prediction function and the actual systolic blood pressure parameters;

[0029] Step 430: Obtain a first ratio coefficient of the blood pressure type using the systolic blood pressure least squares model.

[0030] Furthermore, the step 400 further includes:

[0031] Step 440: Obtain the maximum amplitude of the blood pressure type, and construct a diastolic pressure prediction function using the maximum amplitude and the second ratio coefficient parameter;

[0032] Step 450: Acquire actual diastolic pressure parameters, and construct a diastolic pressure least squares model using the diastolic pressure prediction function and the actual diastolic pressure parameters;

[0033] Step 460: Obtain a second ratio coefficient of the blood pressure type using the diastolic pressure least squares model.

[0034] In order to solve the above technical problems, the embodiment of the present application further provides a non-invasive blood pressure measurement device, which adopts the non-invasive blood pressure measurement method described in the first aspect, including:

[0035] a preprocessing module, configured to use PWM to control an air pump to sequentially perform rapid pressurization, slow and uniform deflation, and rapid deflation, obtain pressure sensor signal data, preprocess the pressure sensor signal data, obtain maximum and minimum points of the pressure sensor signal data, and intervals between the maximum and minimum points, and obtain an envelope signal curve using the maximum and minimum points;

[0036] a feature extraction module, configured to perform feature extraction on the envelope signal curve to obtain a maximum amplitude of the envelope signal curve, and calculate, based on the maximum amplitude, a plurality of first widths of the maximum amplitude that differ from a starting point of the pressure curve to the left by a plurality of prescribed values, a plurality of second widths of the maximum amplitude that differ from a starting point of the pressure curve to the right by a plurality of prescribed values, a plurality of first amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is sequentially shifted to the left by prescribed units, and a plurality of second amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is sequentially shifted to the right by prescribed units;

[0037] a classification module, configured to determine whether the blood pressure measurement process is valid based on the maximum amplitude, the maximum point, the minimum point, the interval between the maximum points, the first width, and the second width; if the blood pressure measurement is valid, inputting the extracted feature value into a classification model, and classifying the envelope signal curve based on the input feature value to obtain the blood pressure type of the envelope signal curve;

[0038] an estimation module, configured to calculate a first ratio coefficient of the systolic pressure and a second ratio coefficient of the diastolic pressure of the blood pressure type using a least squares method, and estimate the systolic pressure and the diastolic pressure of the blood pressure type based on the first ratio coefficient and the second ratio coefficient;

[0039] The first width and the second width are respectively the width from the maximum amplitude dividing line to the left and the width from the maximum amplitude dividing line to the right.

[0040] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, it implements the steps of the non-invasive blood pressure measurement method described above.

[0041] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the steps of the non-invasive blood pressure measurement method described above are implemented.

[0042] Compared with the existing technology, the embodiments of the present application mainly have the following technical effects: by using the decision tree model to classify the envelope signal, the envelopes of different people are divided into different blood pressure types, and the least squares method is used to determine the ratio coefficients of the mean pressure to the systolic pressure and diastolic pressure according to different blood pressure types, so that it can better adapt to the processing of data such as large pulse pressure difference, arteriosclerosis, and individual differences, improve the universality and accuracy of the method, and solve the measurement accuracy problem in the existing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 This is a flow chart of an embodiment of a non-invasive blood pressure measurement method of the present application;

[0045] Figure 2 yes Figure 1 A flowchart of a specific implementation of S100;

[0046] Figure 3 yes Figure 2 A flowchart of a specific implementation of S200;

[0047] Figure 4 yes Figure 1 A flowchart of a specific implementation of S300;

[0048] Figure 5 yes Figure 4 A flowchart of a specific implementation method after S320;

[0049] Figure 6 yes Figure 1 A flowchart of a specific implementation of S400;

[0050] Figure 7 yes Figure 6 A flowchart of another specific implementation of S400;

[0051] Figure 8 This is a schematic diagram of the module structure of a non-invasive blood pressure measurement device of the present application;

[0052] Figure 9 is a structural diagram of an embodiment of a computer device according to the present application;

[0053] Figure 10 This is a comparison chart of the changes in cuff pressure and pulse wave signal during the deflation process of this application;

[0054] Figure 11 is the envelope signal curve diagram in this application;

[0055] Figure 12 This is an envelope signal curve diagram for blood pressure type classification using a decision tree model in this application. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0057] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0059] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0060] The purpose of the embodiments of the present application is to provide a non-invasive blood pressure measurement method, device, equipment and storage medium to solve the measurement accuracy problem in the prior art.

[0061] In order to solve the above technical problems, the present invention provides a non-invasive blood pressure measurement method, which adopts the following technical solutions: Figure 1 , Figure 1 This is a flowchart of an embodiment of a non-invasive blood pressure measurement method of the present application, including: S100, using PWM to control the air pump to perform rapid pressurization, slow and uniform deflation, and rapid deflation in sequence, obtain pressure sensor signal data, preprocess the pressure sensor signal data, obtain the maximum point, minimum point and interval between the maximum points of the pressure sensor signal data, and use the maximum point and minimum point to obtain an envelope signal curve.

[0062] In a preferred embodiment, Figure 2 , Figure 2 yes Figure 1 Flowchart of a specific implementation of S100; S100 includes: S110, using a bandpass filter to perform high-frequency filtering and low-frequency filtering on the pressure sensor signal data to obtain a pulse wave signal; S120, searching for the maximum point, minimum point, and the distance between the maximum points of the pulse wave signal, and extracting the amplitude based on the maximum point and the minimum point; S130, interpolating based on the amplitude, and then low-pass filtering and zero-point calibration of the pulse wave signal to obtain an envelope signal curve.

[0063] In this embodiment, the user's pressure sensor oscillation wave signal is first obtained. During this process, the PWM-controlled air pump quickly pressurizes the airbag, generally to 160-200 mmHg, and then the deflation valve slowly and evenly deflates the airbag, generally at a deflation rate of 3-5 mmHg / s. The airbag is deflated to a pressure of about 30-25 mmHg, and then rapidly deflated to ensure that a complete pressure sensor oscillation wave signal is obtained. The changes in the cuff pressure and pulse wave signal during the deflation process are shown in Figure 2. Figure 10 .

[0064] The raw data of the pressure sensor's oscillation wave signal is passed through a bandpass filter to remove high- and low-frequency signals, retaining the valid pulse wave. The maximum and minimum points are then searched. The distance between the maximum points is recorded as the RRI, which is used for signal validity assessment and pulse rate calculation. The amplitude is extracted based on the maximum and minimum points, and the amplitude is interpolated by 0.5 mmHg. The interpolated data is low-pass filtered to make it smoother and avoid the influence of waveform oscillation. The smoothed data is zero-calibrated to compensate for the signal delay caused by filtering delay, and the processed pulse wave envelope signal curve is output.

[0065] S200. Perform feature extraction on the envelope signal curve to obtain the maximum amplitude of the envelope signal curve, and calculate based on the maximum amplitude a plurality of first widths of the maximum amplitude that differ from the starting point of the pressure curve to the left by a plurality of specified values, a plurality of second widths of the maximum amplitude that differ from the starting point of the pressure curve to the right by a plurality of specified values, a plurality of first amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is sequentially shifted by specified units to the left, and a plurality of second amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is sequentially shifted by specified units to the right.

[0066] In a preferred embodiment, Figure 3 , Figure 3 yes Figure 2 A flowchart of a specific implementation of S200 in the embodiment; S200 includes S210, respectively calculating the width to the left of the maximum amplitude dividing line when the maximum amplitude differs from the starting point of the pressure curve by 90%, 75%, 50%, 25%, and 10%, and the width to the right of the maximum amplitude dividing line when the maximum amplitude differs from the starting point of the pressure curve by 90%, 75%, 50%, 25%, and 10%. S220, respectively calculating multiple first amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is shifted 500 units to the left and multiple second amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is shifted 500 units to the right, wherein the pressure change windows between the first amplitude values overlap by 200 units, and the pressure change windows between the second amplitude values overlap by 200 units.

[0067] In this embodiment, if Figure 11 Systolic blood pressure is generally Figure 11On the right side of the maximum amplitude MAP, SBW90, SBW75, SBW50, SBW25, and SBW10 are the widths from the MAP dividing line of 90%, 75%, 50%, 25%, and 10% of the difference Hm between MAP and the starting point of the pressure curve to the right pressure curve, respectively, and the width indicates the corresponding pressure change value; similarly, DBW90, DBW75, DBW50, DBW25, and DBW10 are the widths from the MAP dividing line of 90%, 75%, 50%, 25%, and 10% of the difference Hm between MAP and the starting point of the pressure curve to the left pressure curve, respectively, and the width indicates the corresponding pressure change value.

[0068] In this embodiment, if Figure 11 , apm represents the amplitude value corresponding to the envelope curve within the pressure change window 500 units to the left from the MAP point; bpm represents the amplitude value corresponding to the envelope curve of a 500-unit pressure change window that continues to move 300 units to the left based on the 500-unit pressure change window of apm (and the moving step of the front and rear windows is 300 units, and there is a 200-unit overlap between windows); cpm, dpm, and epm are obtained by analogy; similarly, the values of the fpm, gpm, hpm, ipm, jpm, and kpm features on the right are obtained.

[0069] S300. Determine whether the blood pressure measurement process is valid based on the maximum amplitude, the maximum point, the minimum point, the interval between the maximum points, the first width, and the second width. If the blood pressure measurement is valid, input the extracted eigenvalues into the classification model. The classification model classifies the envelope signal curve according to the input eigenvalues to obtain the blood pressure type of the envelope signal curve.

[0070] In a preferred embodiment, Figure 4 , Figure 4 yes Figure 1 Flowchart of a specific implementation of S300; S300 includes: S310, comparing the first number of maximum points, the second number of minimum points and the distance between the maximum points with the specified range, and comparing the maximum amplitude, the first width and the second width with the specified range; S320, if the first number, the second number and the distance between the maximum points are all within the specified range, and the maximum amplitude and the first width and the second width are within the specified range, then determine that this blood pressure measurement is a valid measurement.

[0071] In a preferred embodiment, Figure 5 , Figure 5 yes Figure 4 A flowchart of a specific implementation after S320; after S320, S300 also includes

[0072] S330. The classification model obtains the first width and the second width, the first amplitude and the second amplitude of each of the envelope signal curves; S340. The current blood pressure type is classified into a normal blood pressure type, a critical blood pressure type, a sclerosis-grade hypertension type, or an arrhythmia combined with vascular sclerosis blood pressure type according to the first width and the second width, the first amplitude and the second amplitude.

[0073] In this embodiment, the classification model adopts a decision tree model, which includes but is not limited to a maximum tree depth of 7, a minimum number of samples required for internal node re-division of 5, and a split decision including but not limited to randomly selecting a number of split points and selecting the best one. This process helps to introduce a certain degree of randomness and avoid overfitting. When looking for the best split, references include but are not limited to the square root of the number of features. The above parameters can also be defined in the form of a decision tree parameter grid, and the model parameters can be tuned and selected by traversing the grid parameters, and the best performing set of parameters can be output. In this S processing, the decision tree model divides the envelope waveform into the following: Figure 12 The four types of waveforms A, B, C, and D shown correspond to the physiological characteristics of normal blood pressure type, critical blood pressure type, sclerosis hypertension type, and arrhythmia combined with vascular sclerosis blood pressure type.

[0074] S400 , using the least squares method to calculate and obtain a first ratio coefficient of the systolic pressure and a second ratio coefficient of the diastolic pressure of the blood pressure type, and estimating the systolic pressure and the diastolic pressure of the blood pressure type according to the first ratio coefficient and the second ratio coefficient.

[0075] In a preferred embodiment, Figure 6 , Figure 6 yes Figure 1 A flowchart of a specific implementation of S400; 400 includes: S410, obtaining the maximum amplitude of the blood pressure type, and constructing a systolic pressure estimation function using the maximum amplitude and the first ratio coefficient parameter; S420, obtaining the actual systolic pressure parameter, and constructing a systolic pressure least squares model using the systolic pressure estimation function and the actual systolic pressure parameter; S430, obtaining the first ratio coefficient of the blood pressure type using the systolic pressure least squares model.

[0076] Assume that the ratio coefficient of the envelope systolic pressure of blood pressure type A is α A , the diastolic pressure ratio coefficient is β A , if the actual systolic blood pressure parameter is Pre i , then there exists α A So that:

[0077]

[0078] Get the minimum value.

[0079] Among them, Pre_Mi is the maximum amplitude of the oscillation wave, and the systolic pressure estimation function f() is the ratio coefficient of the envelope systolic pressure is α A With Pre_M i The function of blood pressure estimation, including but not limited to linear relationship, S(α A ) is the minimum residual sum of squares between the algorithm measurement value and the target value, where Pre_M of the same type (such as type A) envelope signal i and α A The functional relationship can be determined by using the same function, or by replacing Pre_M i Perform interval solving (for example Get the corresponding coefficient array α A .

[0080] In a preferred embodiment, Figure 7 , Figure 7 yes Figure 6 A flowchart of another specific implementation of S400; 400 also includes: S440, obtaining the maximum amplitude of the blood pressure type, and constructing a diastolic pressure prediction function using the maximum amplitude and the second ratio coefficient parameter; S450, obtaining the actual diastolic pressure parameter, and constructing a diastolic pressure least squares model using the diastolic pressure prediction function and the actual diastolic pressure parameter; S460, obtaining the second ratio coefficient of the blood pressure type using the diastolic pressure least squares model.

[0081] In this embodiment, the same principle as formula (1) can be used to obtain β A (or β A coefficient array). Where α A The value range of β is generally 0.46~0.64, A The value range is generally 0.43 to 0.73.

[0082] The first width and the second width are the widths from the maximum amplitude dividing line to the left and to the right, respectively. By using a decision tree model to classify the envelope signal, different people's envelopes are divided into different blood pressure types. The least squares method is used to determine the ratio coefficients of mean pressure to systolic pressure and diastolic pressure, respectively, according to different blood pressure types. This allows for better adaptation to data processing for large pulse pressure differences, arteriosclerosis, and individual differences, improving the universality and accuracy of the method and resolving measurement accuracy issues in existing technologies.

[0083] In order to solve the above technical problems, the embodiment of the present application further provides a non-invasive blood pressure measurement device 500, which adopts the non-invasive blood pressure measurement method of the first aspect, such as Figure 8 , Figure 8 This is a schematic diagram of the module structure of a non-invasive blood pressure measurement device of the present application; it includes:

[0084] A preprocessing module 501 is configured to use PWM to control an air pump to sequentially perform rapid pressurization, slow and uniform deflation, and rapid deflation, obtain pressure sensor signal data, preprocess the pressure sensor signal data, obtain maximum and minimum points of the pressure sensor signal data, and the intervals between the maximum and minimum points, and obtain an envelope signal curve using the maximum and minimum points;

[0085] a feature extraction module 502 configured to extract features from the envelope signal curve to obtain a maximum amplitude of the envelope signal curve, and calculate, based on the maximum amplitude, a plurality of first widths of the maximum amplitude that are a plurality of specified values away from the starting point of the pressure curve to the left, a plurality of second widths of the maximum amplitude that are a plurality of specified values away from the starting point of the pressure curve to the right, a plurality of first amplitudes corresponding to the pressure variation window envelope curve shifted sequentially by specified units to the left, and a plurality of second amplitudes corresponding to the pressure variation window envelope curve shifted sequentially by specified units to the right;

[0086] Classification module 503 is configured to determine whether the blood pressure measurement process is valid based on the maximum amplitude, the maximum point, the minimum point, the interval between the maximum points, the first width, and the second width. If the blood pressure measurement is valid, the extracted feature value is input into the classification model. The classification model classifies the envelope signal curve based on the input feature value to obtain the blood pressure type of the envelope signal curve;

[0087] an estimation module 504 for calculating a first ratio coefficient of systolic pressure and a second ratio coefficient of diastolic pressure of a blood pressure type using a least squares method, and estimating the systolic pressure and diastolic pressure of the blood pressure type based on the first ratio coefficient and the second ratio coefficient;

[0088] The first width and the second width are respectively the width from the maximum amplitude dividing line to the left and the width from the maximum amplitude dividing line to the right.

[0089] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the above non-invasive blood pressure measurement method are implemented.

[0090] The computer device adopts the following technical solution: it includes a processor, a network module and a memory, and the processor and the memory are connected to each other through the network module.

[0091] The computer device can be a computer, server, workstation or other device, or a mobile phone, tablet, vehicle-mounted mobile terminal or other device with program execution capability. The internal structure diagram of the computer device can be as follows: Figure 9 As shown, Figure 9This is a structural diagram of an embodiment of a computer device according to the present application. The computer device includes a processor, a memory, and a network module. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage medium stores an operating system, instructions or code. The internal memory provides an environment for the operation of the operating system and instructions or code in the non-volatile storage medium. When the instructions or code are executed by the processor, the functions or steps of a non-invasive blood pressure measurement method are implemented. The network module of the computer device may include a network interface and / or a wireless network module, and the computer device may communicate with other devices or service platforms through the network module. In addition, the computer device may also include a display screen and an input device.

[0092] The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions. When the processor executes the instructions or codes, the steps of the non-invasive blood pressure measurement method described above are implemented.

[0093] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the steps of the above-mentioned non-invasive blood pressure measurement method are implemented.

[0094] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the steps of the above-mentioned non-invasive blood pressure measurement method are implemented.

[0095] The computer readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by the processor, Figures 1 to 7 The non-invasive blood pressure measurement method provided in each step can be specifically referred to the implementation methods provided in the above steps, which will not be repeated here.

[0096] The computer-readable storage medium may be an internal storage unit of a non-invasive blood pressure measurement device or a terminal device provided in any of the aforementioned embodiments, such as a hard disk or memory of a computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., provided on the computer device.

[0097] Furthermore, the computer-readable storage medium may include both an internal storage unit of the computer device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0098] However, it should be understood that implementation of all illustrated components is not required, and more or fewer components may be implemented instead. Those skilled in the art will appreciate that a computer device herein is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, and the like.

[0099] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0100] Compared with the existing technology, the embodiments of the present application mainly have the following technical effects: by using the decision tree model to classify the envelope signal, the envelopes of different people are divided into different blood pressure types, and the least squares method is used to determine the ratio coefficients of the mean pressure to the systolic pressure and diastolic pressure according to different blood pressure types, so that it can better adapt to the processing of data such as large pulse pressure difference, arteriosclerosis, and individual differences, improve the universality and accuracy of the method, and solve the measurement accuracy problem in the existing technology.

[0101] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A non-invasive blood pressure measurement method, comprising: Step 100: Using PWM to control the air pump to perform rapid pressurization, slow and uniform deflation, and rapid deflation in sequence, obtain pressure sensor signal data, pre-process the pressure sensor signal data to obtain maximum and minimum points of the pressure sensor signal data and the intervals between the maximum and minimum points, and obtain an envelope signal curve using the maximum and minimum points; Step 200: Extract features of the envelope signal curve to obtain a maximum amplitude of the envelope signal curve, and calculate based on the maximum amplitude a plurality of first widths of the maximum amplitude that differ from a starting point of the pressure curve to the left by a plurality of prescribed values, a plurality of second widths of the maximum amplitude that differ from a starting point of the pressure curve to the right by a plurality of prescribed values, a plurality of first amplitudes corresponding to the pressure change window envelope curve shifted sequentially by prescribed units to the left by the maximum amplitude, and a plurality of second amplitudes corresponding to the pressure change window envelope curve shifted sequentially by prescribed units to the right by the maximum amplitude; Step 300: Determine whether the blood pressure measurement process is valid based on the maximum amplitude, the maximum point, the minimum point, the interval between the maximum points, the first width, and the second width. If the blood pressure measurement is valid, input the extracted feature value into a classification model. The classification model classifies the envelope signal curve based on the input feature value to obtain the blood pressure type of the envelope signal curve. Step 400: Calculate a first ratio coefficient of the systolic pressure and a second ratio coefficient of the diastolic pressure of the blood pressure type using the least squares method, and estimate the systolic pressure and diastolic pressure of the blood pressure type based on the first ratio coefficient and the second ratio coefficient; The first width and the second width are respectively the width from the maximum amplitude dividing line to the left and the width from the maximum amplitude dividing line to the right.

2. The non-invasive blood pressure measurement method according to claim 1, wherein: The step 100 includes: Step 110: Use a bandpass filter to perform high-frequency filtering and low-frequency filtering on the pressure sensor signal data to obtain a pulse wave signal; Step 120: Search and obtain the maximum value point, the minimum value point, and the distance between the maximum value points of the pulse wave signal, and extract the amplitude according to the maximum value point and the minimum value point; Step 130 : interpolate according to the amplitude, and then perform low-pass filtering and zero-point calibration on the pulse wave signal to obtain the envelope signal curve.

3. The non-invasive blood pressure measurement method according to claim 1, wherein: The step 200 includes: Step 210, respectively calculating the width to the left of the maximum amplitude dividing line when the maximum amplitude differs from the starting point of the pressure curve by 90%, 75%, 50%, 25%, and 10%, and the width to the right of the maximum amplitude dividing line when the maximum amplitude differs from the starting point of the pressure curve by 90%, 75%, 50%, 25%, and 10%. Step 220: Calculate multiple first amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is moved 500 units to the left, and multiple second amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is moved 500 units to the right. The pressure change windows between the first amplitude values overlap by 200 units, and the pressure change windows between the second amplitude values overlap by 200 units.

4. The non-invasive blood pressure measurement method according to claim 1, wherein: Step 300 includes: Step 310: Compare the first number of the maximum points, the second number of the minimum points, and the spacing between the maximum points with a specified range, and compare the maximum amplitude, the first width, and the second width with a specified range; Step 320: If the first number, the second number, and the distance between the maximum points are all within the specified range, and the maximum amplitude, the first width, and the second width are all within the specified range, then determine that the current blood pressure measurement is a valid measurement.

5. The non-invasive blood pressure measurement method according to claim 4, characterized in that: After step 320, step 300 further includes Step 330: The classification model obtains the first width and the second width, the first amplitude and the second amplitude of each envelope signal curve; Step 340: Classify the current blood pressure type into a normal blood pressure type, a critical blood pressure type, a sclerosis-grade hypertension type, or an arrhythmia combined with vascular sclerosis blood pressure type based on the first width and the second width, the first amplitude and the second amplitude.

6. The non-invasive blood pressure measurement method according to claim 1, wherein: The 400 includes: Step 410: Obtain the maximum amplitude of the blood pressure type, and construct a systolic blood pressure prediction function using the maximum amplitude and the first ratio coefficient parameter; Step 420: Acquire actual systolic blood pressure parameters, and construct a systolic blood pressure least squares model using the systolic blood pressure prediction function and the actual systolic blood pressure parameters; Step 430: Obtain a first ratio coefficient of the blood pressure type using the systolic blood pressure least squares model.

7. The non-invasive blood pressure measurement method according to claim 1, wherein: The 400 includes: Step 440: Obtain the maximum amplitude of the blood pressure type, and construct a diastolic pressure prediction function using the maximum amplitude and the second ratio coefficient parameter; Step 450: Acquire actual diastolic pressure parameters, and construct a diastolic pressure least squares model using the diastolic pressure prediction function and the actual diastolic pressure parameters; Step 460: Obtain a second ratio coefficient of the blood pressure type using the diastolic pressure least squares model.

8. A non-invasive blood pressure measurement device, using the non-invasive blood pressure measurement method according to any one of claims 1 to 7, characterized in that: include: a preprocessing module, configured to use PWM to control an air pump to sequentially perform rapid pressurization, slow and uniform deflation, and rapid deflation, obtain pressure sensor signal data, preprocess the pressure sensor signal data, obtain maximum and minimum points of the pressure sensor signal data, and intervals between the maximum and minimum points, and obtain an envelope signal curve using the maximum and minimum points; a feature extraction module, configured to perform feature extraction on the envelope signal curve to obtain a maximum amplitude of the envelope signal curve, and calculate, based on the maximum amplitude, a plurality of first widths of the maximum amplitude that differ from a starting point of the pressure curve to the left by a plurality of prescribed values, a plurality of second widths of the maximum amplitude that differ from a starting point of the pressure curve to the right by a plurality of prescribed values, a plurality of first amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is sequentially shifted to the left by prescribed units, and a plurality of second amplitudes corresponding to the pressure change window envelope curve when the maximum amplitude is sequentially shifted to the right by prescribed units; a classification module, configured to determine whether the blood pressure measurement process is valid based on the maximum amplitude, the maximum point, the minimum point, the interval between the maximum points, the first width, and the second width; if the blood pressure measurement is valid, inputting the extracted feature value into a classification model, and classifying the envelope signal curve based on the input feature value to obtain the blood pressure type of the envelope signal curve; an estimation module, configured to calculate a first ratio coefficient of the systolic pressure and a second ratio coefficient of the diastolic pressure of the blood pressure type using a least squares method, and estimate the systolic pressure and the diastolic pressure of the blood pressure type based on the first ratio coefficient and the second ratio coefficient; The first width and the second width are respectively the width from the maximum amplitude dividing line to the left and the width from the maximum amplitude dividing line to the right.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the non-invasive blood pressure measurement method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the non-invasive blood pressure measurement method according to any one of claims 1 to 7.

Images