An intelligent blood pressure measurement method and system based on the deflation oscillometric method

Abstract

The present application relates to an intelligent blood pressure measurement method and system based on the deflation oscillometric method, belonging to the field of medical detection technology. The measurement method includes: controlling an air pump to inflate a cuff on the wrist or upper arm of the subject until a preset initial air pressure value is reached; controlling a solenoid valve to release the gas in the cuff at a preset rate, and receiving the air pressure data and oscillatory wave signals in the cuff collected by a pressure sensor in real time; identifying and extracting key features from the oscillatory wave signals based on the eigenvalue method to obtain oscillatory wave characteristic parameters; calculating a preliminary blood pressure value based on a pre-established proportional coefficient model according to the air pressure data and the oscillatory wave characteristic parameters; inputting the oscillatory wave signals, the oscillatory wave characteristic parameters, and the preliminary blood pressure value into a pre-trained blood pressure value prediction model with a momentum term to obtain a final blood pressure value, and sending the final blood pressure value to a display module for output display. The present application improves the accuracy and stability of blood pressure measurement.

Description

Technical Field

[0001] This application relates to the field of medical detection technologies, and particularly to an intelligent blood pressure measurement method and system based on the deflation oscillometric method. Background Art

[0002] Blood pressure is one of the important physiological parameters for evaluating cardiovascular health status. Accurate and reliable blood pressure measurement is crucial for early disease diagnosis, monitoring of treatment effects, and personal health management. Traditional blood pressure measurement methods mainly include the auscultatory method and the oscillometric method. Among them, the auscultatory method determines systolic and diastolic blood pressures by a doctor listening to Korotkoff sounds using a stethoscope. Although this method is widely used clinically, it has some significant limitations. In contrast, the oscillometric method, as a non-invasive automated blood pressure measurement technology, has been widely used because of its simplicity and ease of use. The oscillometric method uses the air pressure change in the cuff to detect the oscillatory wave signals caused by the pulse, and calculates the blood pressure value by analyzing these signals.

[0003] However, due to the influence of environmental factors and individual differences, the measurement method of the oscillometric method still has problems such as insufficient accuracy and susceptibility to interference in signal processing and blood pressure value calculation. Especially when facing complex or abnormal physiological states, such as arrhythmia, vascular elasticity changes, etc., it is easy to cause large fluctuations in the results of the oscillometric sphygmomanometer during multiple measurements, and it is difficult to provide stable and reliable blood pressure readings. Summary of the Invention

[0004] In order to improve the accuracy and stability of blood pressure measurement, this application provides an intelligent blood pressure measurement method and system based on the deflation oscillometric method.

[0005] In the first aspect, this application provides an intelligent blood pressure measurement method based on the deflation oscillometric method, adopting the following technical solutions:

[0006] An intelligent blood pressure measurement method based on the deflation oscillometric method, which is applied to an intelligent blood pressure measurement system including an air pump, an electromagnetic valve, a pressure sensor, a microprocessor, a display module, and a cuff. The measurement method includes:

[0007] Controlling the air pump to inflate the cuff on the wrist or upper arm of the subject until a preset initial air pressure value is reached;

[0008] Controlling the electromagnetic valve to release the gas in the cuff at a preset rate, and receiving the air pressure data and oscillatory wave signals in the cuff collected by the pressure sensor in real time;

[0009] Identifying and extracting key features from the oscillatory wave signals based on the eigenvalue method to obtain oscillatory wave characteristic parameters;

[0010] Based on a pre-established proportional coefficient model, a preliminary blood pressure value is calculated according to the air pressure data and the oscillatory wave characteristic parameters; the oscillatory wave signal, the oscillatory wave characteristic parameters, and the preliminary blood pressure value are input into a pre-trained blood pressure value prediction model with a momentum term to obtain the final blood pressure value; wherein, the blood pressure value includes a systolic blood pressure value and a diastolic blood pressure value;

[0011] The final blood pressure value is sent to the display module for output display.

[0012] By adopting the above technical solution, from air pressure regulation to data analysis and then to output display, through the combination of the characteristic processing of the oscillatory wave and the deep learning of the neural network, the efficiency and accuracy of the intelligent blood pressure measurement process are realized. When facing complex physiological signals, the reliability and accuracy of the blood pressure measurement results can still be ensured, thereby providing a user with an efficient, convenient and reliable blood pressure monitoring solution, improving the user experience, and providing more accurate and stable data support for the medical detection field.

[0013] Optionally, the steps of identifying and extracting key features from the oscillatory wave signal based on the eigenvalue method to obtain the oscillatory wave characteristic parameters include:

[0014] Perform data preprocessing on the oscillatory wave signal;

[0015] The preprocessed oscillatory wave signal is segmented into multiple sub-segments according to different preset pressure ranges;

[0016] Perform peak detection and valley detection on the oscillatory wave signal in each sub-segment respectively, determine the peak position and the valley position, and calculate the characteristic parameters between each peak and valley to obtain the key characteristic parameters of the oscillatory wave signal in each sub-segment;

[0017] Based on the principal component analysis method, perform dimensionality reduction processing and feature selection on the key characteristic parameters of the oscillatory wave signal in each sub-segment, and perform normalization processing on the selected features to obtain the optimized oscillatory wave characteristic parameters.

[0018] By adopting the above technical solution, the system can efficiently and accurately extract the key characteristic parameters of the oscillatory wave signal. These steps not only improve the accuracy and stability of feature extraction, but also reduce data redundancy, enhance the robustness and scalability of the system.

[0019] Optionally, the steps of calculating a preliminary blood pressure value according to the air pressure data and the oscillatory wave characteristic parameters based on a pre-established proportional coefficient model include:

[0020] Load the pre-established proportional coefficient model from the system storage;

[0021] Format the air pressure data and the oscillation wave characteristic parameters;

[0022] Map the oscillation wave characteristic parameters in each sub - segment to the corresponding input variables in the proportional coefficient model to obtain the mapped characteristic parameter set;

[0023] Perform calibration processing on the air pressure data, and align the calibrated air pressure data with the characteristic parameter set in terms of time to obtain the air pressure data set;

[0024] Input the characteristic parameter set and the air pressure data set into the proportional coefficient model, and calculate the preliminary systolic blood pressure value and diastolic blood pressure value.

[0025] By adopting the above - mentioned technical solution, based on the pre - established proportional coefficient relationship, using the air pressure data and the oscillation wave characteristic parameters to calculate the preliminary blood pressure value, this technical solution not only improves the accuracy and stability of the preliminary blood pressure estimation, but also provides a reliable data basis for the subsequent neural network optimization, significantly enhancing the accuracy and reliability of the overall blood pressure measurement.

[0026] Optionally, the relational expression of the proportional coefficient model is:

[0027] Systolic blood pressure = a1×Amplitude + b1×Frequency + c1×Air pressure + d1;

[0028] Diastolic blood pressure = a2×Amplitude + b2×Frequency + c2×Air pressure + d2;

[0029] In the above formula, a1, b1, c1, d1 and a2, b2, c2, d2 are pre - determined proportional coefficients.

[0030] Optionally, it further includes the training step of the blood pressure value prediction model, and the training step includes:

[0031] Obtain the sample data set and perform data pre - processing; among them, the sample data set includes oscillation wave signal sample data, oscillation wave characteristic parameter sample data, preliminary blood pressure sample values, and corresponding blood pressure value label data, and the blood pressure value label data are the actually measured systolic blood pressure and diastolic blood pressure;

[0032] Divide the sample data set into a training set, a validation set, and a test set;

[0033] Input the training set into the pre - constructed convolutional neural network model for iterative training, calculate the loss function of the model, calculate the gradient through the backpropagation algorithm, and optimize the model parameters;

[0034] Update the weights of the convolutional neural network model based on the optimization algorithm with momentum term until the loss function meets the preset conditions to obtain the trained convolutional neural network model;

[0035] Validate the convolutional neural network model based on the validation set, evaluate the performance of the convolutional neural network model, and adjust the hyperparameters of the model according to the validation results;

[0036] Test the prediction ability of the adjusted convolutional neural network model based on the test set to obtain the blood pressure value prediction model.

[0037] By adopting the above technical solution, the convolutional neural network model is iteratively trained using an optimization algorithm with a momentum term, and the model performance is evaluated and optimized through the validation set and the test set. This technical solution not only improves the accuracy of blood pressure measurement but also enhances the robustness of the model to abnormal situations. This optimization method significantly improves the accuracy and stability of blood pressure measurement, providing a more reliable and efficient solution for the medical detection field.

[0038] Optionally, after the step of sending the final blood pressure value to the display module for output display, the following steps are further included:

[0039] Determine whether the final blood pressure value exceeds the normal blood pressure range;

[0040] If so, generate a blood pressure warning prompt based on the final blood pressure value and send it to the corresponding medical staff terminal.

[0041] By adopting the above technical solution, after sending the final blood pressure value to the display module for output display, it is further determined whether the blood pressure value exceeds the normal range. If it exceeds the normal range, a corresponding warning prompt is generated and sent to the corresponding medical staff terminal. This technical solution can not only monitor the blood pressure status of users in real time but also notify medical staff in a timely manner when abnormalities are found, thereby improving the response speed and quality of medical services. Through this warning mechanism, patients can receive more timely medical intervention, reducing the risks caused by hypertension or hypotension and enhancing the safety and effectiveness of overall medical care.

[0042] In a second aspect, the present application provides an intelligent blood pressure measurement system based on the deflation oscillometric method, adopting the following technical solution:

[0043] An intelligent blood pressure measurement system based on the deflation oscillometric method, the intelligent blood pressure measurement system includes an air pump, a solenoid valve, a pressure sensor, a microprocessor, a display module, and a cuff wrapped around the wrist or upper arm of the measured person;

[0044] The air pump is used to fill the cuff with gas;

[0045] The solenoid valve is connected to the air pump and is used to control the gas inlet and outlet of the cuff;

[0046] The cuff is used to adjust the internal air pressure through the air pump and the solenoid valve;

[0047] The pressure sensor is connected to the cuff and is used to collect the air pressure data and oscillation wave signals inside the cuff in real time;

[0048] The microprocessor is connected to the air pump, the solenoid valve, and the pressure sensor, and is used to receive and process the air pressure data and oscillation wave signals collected by the pressure sensor, and calculate the final blood pressure value;

[0049] The display module is used to display the final blood pressure value calculated by the microprocessor.

[0050] Optionally, the microprocessor includes:

[0051] The air pump control unit is used to control the air pump to inflate the cuff on the wrist or upper arm of the subject until a preset initial air pressure value is reached;

[0052] The solenoid valve control unit is used to control the solenoid valve to release the gas in the cuff at a preset rate;

[0053] The data receiving unit is used to receive the air pressure data and oscillation wave signals inside the cuff collected by the pressure sensor in real time;

[0054] The feature extraction unit is used to identify and extract key features from the oscillation wave signals based on the eigenvalue method to obtain oscillation wave feature parameters;

[0055] The preliminary blood pressure value generation unit is used to calculate a preliminary blood pressure value based on a pre-established proportional coefficient model according to the air pressure data and oscillation wave feature parameters;

[0056] The final blood pressure value generation unit is used to input the oscillation wave signals, the oscillation wave feature parameters, and the preliminary blood pressure value into a pre-trained blood pressure value prediction model with a momentum term to obtain the final blood pressure value; wherein, the blood pressure value includes a systolic blood pressure value and a diastolic blood pressure value;

[0057] The final blood pressure value sending unit is used to send the final blood pressure value to the display module for output display.

[0058] In a third aspect, the present application provides a computer device, adopting the following technical solution:

[0059] A computer device includes a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the method described in the first aspect.

[0060] In a fourth aspect, the present application provides a computer-readable storage medium, adopting the following technical solution:

[0061] A computer-readable storage medium stores a computer program that can be loaded and executed by a processor to perform any of the methods in the first aspect.

[0062] In summary, the present application includes at least one of the following beneficial technical effects: from air pressure regulation to data analysis and then to output display, by combining the characteristic processing of oscillation waves and the deep learning of neural networks, the efficiency and accuracy of the intelligent blood pressure measurement process are realized. Even in the face of complex physiological signals, the reliability and accuracy of blood pressure measurement results can still be ensured, thus providing a user with an efficient, convenient and reliable blood pressure monitoring solution, improving the user experience, and providing more accurate and stable data support for the medical detection field. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 FIG. is a first flowchart of an intelligent blood pressure measurement method according to an embodiment of the present application.

[0064] Figure 2 FIG. is a second flowchart of an intelligent blood pressure measurement method according to an embodiment of the present application.

[0065] Figure 3 FIG. is a third flowchart of an intelligent blood pressure measurement method according to an embodiment of the present application.

[0066] Figure 4 FIG. is a fourth flowchart of an intelligent blood pressure measurement method according to an embodiment of the present application.

[0067] Figure 5 FIG. is a fifth flowchart of an intelligent blood pressure measurement method according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the following further describes the present application in detail with reference to the Figures 1-5 drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] An embodiment of the present application discloses an intelligent blood pressure measurement method based on the deflation oscillometric method.

[0070] Referring to Figure 1 , an intelligent blood pressure measurement method based on the deflation oscillometric method, which is applied to an intelligent blood pressure measurement system including an air pump, a solenoid valve, a pressure sensor, a microprocessor, a display module and a cuff, and the measurement method includes:

[0071] Step S101: Control the air pump to inflate the cuff on the wrist or upper arm of the subject until the preset initial air pressure value is reached. Specifically, during the inflation stage, the subject sits still with the arm at the same level as the heart, wears the cuff properly, and the microprocessor issues an instruction to control the air pump to inflate the cuff on the wrist or upper arm of the subject. The air pressure inside the cuff gradually increases until the preset initial air pressure value (such as about 180 mmHg) is reached. At this time, the arterial blood flow is blocked, and the pressure change inside the cuff is mainly composed of the oscillatory signal caused by the pulse. By quickly inflating to the predetermined pressure level, it is ensured that the blood flow can be completely blocked and a detectable oscillatory wave signal can be generated, providing a basis for subsequent blood pressure measurement.

[0072] It should be noted that in order to ensure the smoothness and stability of the inflation process, this application also introduces a momentum term parameter, which is similar to the integral term (I) and the derivative term (D) in the PID controller and is used to smooth the pressure change and reduce the fluctuation. Exemplarily, during the inflation stage, the target air pressure is set to 180 mmHg. Initially, the air pump works at full speed to quickly inflate. If the current air pressure is 170 mmHg and the deviation is 10 mmHg, the proportional term will increase the working intensity of the air pump; the integral term will accumulate the past deviations and gradually increase the working intensity of the air pump; the derivative term will adjust according to the rising speed of the air pressure to avoid overshoot, so as to achieve a more stable inflation process, reduce the air pressure fluctuation caused by rapid inflation, and thus improve the accuracy of subsequent measurement.

[0073] Step S102: Control the solenoid valve to release the gas in the cuff at a preset rate, and receive the air pressure data and oscillatory wave signal in the cuff collected by the pressure sensor in real time.

[0074] Specifically, during the deflation stage, the microprocessor controls the solenoid valve to release the gas in the cuff at a set speed (such as 5 - 10 mmHg / s). At the same time, the pressure sensor continuously monitors and records the air pressure change and oscillatory wave signal in the cuff, and a series of air pressure data and oscillatory waveform information changing with time can be obtained.

[0075] It should be noted that, in order to ensure the smoothness and stability of the deflation process, the present application also introduces a momentum term parameter, which is similar to the proportional term (P), integral term (I), and derivative term (D) in a PID controller and is used to adjust the deflation rate to make it smoother. Exemplarily, in the deflation stage, the deflation rate is set to 5 - 10 mmHg / s. Initially, the solenoid valve opens at the set speed to start deflation, and the PID controller adjusts according to the deviation between the current air pressure and the target air pressure to ensure a stable deflation rate. For example, if the current air pressure is 170 mmHg, the target air pressure is 160 mmHg, and the deviation is 10 mmHg, the proportional term will increase the opening degree of the solenoid valve; the integral term will accumulate past deviations and gradually increase the opening degree of the solenoid valve; the derivative term will adjust according to the speed of air pressure drop to avoid too rapid a drop in air pressure, so as to achieve a smoother deflation process, reduce air pressure fluctuations caused by uneven deflation rates, and thus improve the accuracy and stability of blood pressure measurement.

[0076] It can be understood that by slowly and evenly reducing the pressure in the cuff, the system can capture the characteristics of the oscillatory wave at different pressures, which is the key basis for calculating blood pressure values.

[0077] Step S103: Identify and extract key features from the oscillatory wave signal based on the eigenvalue method to obtain oscillatory wave characteristic parameters.

[0078] In some embodiments, the microprocessor uses the eigenvalue method to analyze the oscillatory wave signal, identify key points therein, such as wave peaks, wave valleys, etc., and at the same time obtains important parameters describing the shape of the oscillatory wave, including but not limited to wave amplitude, frequency, etc. By processing the original signal, the information that can best reflect the blood pressure state is extracted, providing reliable data support for the subsequent accurate calculation of blood pressure.

[0079] Step S104: Calculate a preliminary blood pressure value based on a pre-established proportional coefficient model according to the air pressure data and the oscillatory wave characteristic parameters.

[0080] Among them, the microprocessor can apply the proportional coefficient method to convert the characteristic parameters into preliminary systolic and diastolic blood pressure estimates based on the proportional coefficient model established according to clinical data and the oscillatory wave characteristic parameters obtained in the above steps, laying a foundation for further optimization.

[0081] Step S105: Input the oscillatory wave signal, the oscillatory wave characteristic parameters, and the preliminary blood pressure value into a pre-trained blood pressure value prediction model with a momentum term to obtain the final blood pressure value; where the blood pressure value includes the systolic blood pressure value and the diastolic blood pressure value; specifically, this model has learned from a large number of actual blood pressure measurement data sets and already has the ability to accurately predict blood pressure from complex signals, and can further optimize the preliminary blood pressure value.

[0082] It is understandable that by introducing machine learning algorithms, especially neural network models with momentum terms, the microprocessor can more precisely correct the results of the preliminary estimation, improve measurement accuracy, and enhance the robustness of the model against abnormal situations.

[0083] Step S106: Send the final blood pressure value to the display module for output display.

[0084] Among them, when the microprocessor sends the final blood pressure value to the display module, the user can see the clearly displayed systolic and diastolic blood pressure values on the screen, realizing the intuitive display of the blood pressure measurement results and facilitating the user to timely understand their own health status; for example, directly outputting "Systolic blood pressure is 120 mmHg, diastolic blood pressure is 80 mmHg" on the display screen.

[0085] In the above embodiments, from air pressure regulation to data analysis and then to output display, through the combination of the characteristic processing of the oscillatory wave and the deep learning of the neural network, the efficiency and precision of the intelligent blood pressure measurement process are realized, and the reliability and accuracy of the blood pressure measurement results can still be ensured when facing complex physiological signals, thereby providing the user with an efficient, convenient and reliable blood pressure monitoring solution, improving the user experience, and providing more accurate and stable data support for the medical detection field.

[0086] In addition, by introducing the momentum term parameter, the present application can achieve the smoothness and stability of the inflation and deflation processes. Specifically, the momentum term parameter is similar to the proportional, integral, and differential terms in a PID controller and is used to adjust the working states of the air pump and the solenoid valve, thereby achieving a more stable pressure change. This method not only improves the controllability of the inflation and deflation processes but also reduces the measurement errors caused by air pressure fluctuations, significantly enhancing the accuracy and stability of blood pressure measurement. Finally, this control strategy provides a high-quality data basis for subsequent signal processing and blood pressure calculation, further enhancing the reliability and performance of the entire system.

[0087] Referring to Figure 2 , as an implementation manner of step S103, the steps of identifying the oscillatory wave signal based on the eigenvalue method and extracting the key features to obtain the oscillatory wave characteristic parameters include:

[0088] Step S201: Perform data preprocessing on the oscillatory wave signal;

[0089] Specifically, the data preprocessing steps include filtering and baseline correction to reduce the influence of external noise and baseline drift and improve the accuracy of subsequent processing;

[0090] In some embodiments, for filtering processing, a low-pass filter (such as a Butterworth filter) can be used to remove high-frequency noise and retain useful low-frequency components. For example, a low-pass filter with a cut-off frequency of 5 Hz can be set to filter out noise above this frequency. Baseline correction can be achieved by calculating the average value over a period of time and subtracting it from the signal to eliminate baseline drift caused by changes in cuff position or other factors. For example, the average value of the signal in the previous few seconds can be calculated as the baseline, and this baseline value can be subtracted from the entire signal.

[0091] Step S202: Divide the preprocessed oscillatory wave signal into multiple sub-segments according to different preset pressure ranges.

[0092] Specifically, the signal can be divided into multiple sub-segments according to a preset pressure range (such as one sub-segment per 10 mmHg). Each sub-segment represents a specific pressure interval. By detecting the peak points in each sub-segment, the start and end points of each sub-segment can be determined. For example, during the deflation process, when the air pressure drops to the next preset pressure value, a new sub-segment begins.

[0093] It can be understood that dividing the signal into multiple sub-segments according to the inflation and deflation stages facilitates independent analysis within different pressure intervals, thereby improving the pertinence and accuracy of feature extraction.

[0094] Step S203: Perform peak detection and valley detection on the oscillatory wave signal in each sub-segment respectively to determine the peak positions and valley positions.

[0095] Specifically, for peak detection, a local maximum detection algorithm can be used to perform peak detection on the oscillatory wave signal in each sub-segment to find all obvious peak positions. For valley detection, based on the peak positions, the valley positions between adjacent peaks can be further determined. Step S204: Calculate the characteristic parameters between each peak and valley to obtain the key characteristic parameters of the oscillatory wave signal in each sub-segment.

[0096] Among them, the key characteristic parameters of the oscillatory wave signal in each sub-segment include, but are not limited to, peak positions, valley positions, amplitudes, frequencies, periods, rising edge slopes, and falling edge slopes, etc.

[0097] Specifically, after determining the peaks and valleys, calculate parameters such as the amplitude, frequency, and period between each peak and valley. For example, the amplitude can be calculated by the height difference between the peak and the valley, and the frequency can be estimated by the time interval between adjacent peaks. At the same time, identify and record other possible key features, such as the rising edge slope and falling edge slope of the waveform.

[0098] It can be understood that through detailed waveform feature extraction, the characteristics of the oscillatory wave signal can be more comprehensively described, providing rich information for subsequent blood pressure calculation.

[0099] Step S205: Based on the principal component analysis method, perform dimensionality reduction processing and feature selection on the key feature parameters of the oscillatory wave signals in each sub-segment, and perform normalization processing on the selected features to obtain optimized oscillatory wave feature parameters.

[0100] Among them, by applying the principal component analysis method (PCA) to perform dimensionality reduction on the feature parameters, the most representative principal components can be extracted. For example, if there are 10 original features, through PCA, it may be reduced to 3 - 5 main features. Then, according to the results of PCA, select the most important several features; for example, the top three principal components with the largest contribution rate can be selected. Finally, perform normalization processing on the selected features to make them within the same scale range for subsequent processing. For example, the minimum - maximum normalization method can be used to scale the feature values to the interval [0, 1].

[0101] In the above - mentioned implementation manner, the system can efficiently and accurately extract the key feature parameters of the oscillatory wave signals. These steps not only improve the accuracy and stability of feature extraction, but also reduce data redundancy, enhancing the robustness and scalability of the system.

[0102] Refer to Figure 3 , as an implementation manner of step S104, the steps of calculating the preliminary blood pressure value based on the pre - established proportional coefficient model according to the air pressure data and the oscillatory wave feature parameters include:

[0103] Step S301: Load the pre - established proportional coefficient model from the system storage;

[0104] Specifically, this proportional coefficient model is trained based on a large amount of clinical data and describes the relationship between systolic blood pressure, diastolic blood pressure and the oscillatory wave feature parameters.

[0105] It should be noted that when loading, check the validity and version of the model to ensure that the latest or specified version of the model is used.

[0106] Step S302: Perform data formatting on the air pressure data and the oscillatory wave feature parameters;

[0107] Among them, convert the air pressure data and the oscillatory wave feature parameters into a unified data format, for example, convert all data into floating - point types to ensure the consistency and availability of the input data and provide an accurate basis for subsequent calculations.

[0108] Step S303: Map the oscillatory wave feature parameters in each sub - segment to the corresponding input variables in the proportional coefficient model to obtain a set of mapped feature parameters;

[0109] Among them, according to the requirements of the proportional coefficient model, the oscillatory wave characteristic parameters (such as amplitude, frequency, etc.) in each sub-segment are mapped to the corresponding input variables in the model; Exemplarily, assuming that the input variables required by the model include amplitude, frequency, and period, then these characteristic parameters in each sub-segment are respectively corresponding to the input variables of the model.

[0110] Step S304, perform calibration processing on the air pressure data, and perform time alignment on the calibrated air pressure data and the characteristic parameter set to obtain an air pressure data set;

[0111] Specifically, perform calibration processing on the air pressure data, for example, smooth the uneven changes by interpolation or other methods; then perform time alignment on the calibrated air pressure data and the mapped characteristic parameter set to ensure the data matching at the same time point.

[0112] Step S305, input the characteristic parameter set and the air pressure data set into the proportional coefficient model, and calculate the preliminary systolic blood pressure value and diastolic blood pressure value.

[0113] Specifically, substitute the characteristic parameter set and the air pressure data set into the proportional coefficient model, and calculate using the preset proportional coefficient formula.

[0114] In the above embodiments, based on the pre-established proportional coefficient relationship, the air pressure data and the oscillatory wave characteristic parameters are used to calculate the preliminary blood pressure value. This technical solution not only improves the accuracy and stability of the preliminary blood pressure estimation, but also provides a reliable data basis for the subsequent neural network optimization, significantly improving the accuracy and reliability of the overall blood pressure measurement.

[0115] In one embodiment of the present application, the relational expression of the proportional coefficient model is:

[0116] Systolic blood pressure = a1 × amplitude + b1 × frequency + c1 × air pressure + d1;

[0117] Diastolic blood pressure = a2 × amplitude + b2 × frequency + c2 × air pressure + d2;

[0118] In the above formula, a1, b1, c1, d1 and a2, b2, c2, d2 are pre-determined proportional coefficients; Since there is a linear relationship between the systolic blood pressure and diastolic blood pressure and the oscillatory wave characteristic parameters, the above linear regression model can be used to fit this relationship.

[0119] Specifically, in order to establish the above proportional coefficient model, a large amount of clinical data needs to be collected, and this data usually includes the following parts: blood pressure measurement sample data, such as systolic blood pressure and diastolic blood pressure; oscillatory wave signal sample parameters, such as amplitude, frequency, period, rising edge slope, and falling edge slope; air pressure sample data, that is, the real-time air pressure value in the cuff, recorded at different time points during inflation and deflation.

[0120] It should be noted that clinical data can be collected on a large scale in multiple medical institutions, and subjects of different ages, genders, and health conditions (such as hypertension, hypotension, and normal blood pressure) should be included as much as possible to cover a wide range of physiological conditions.

[0121] Referring to Figure 4 , a further embodiment of the present application further includes a training step of a blood pressure value prediction model, and the training step includes:

[0122] Step S401, obtaining a sample data set and performing data preprocessing;

[0123] Among them, the sample data set includes oscillatory wave signal sample data, oscillatory wave characteristic parameter sample data, preliminary blood pressure sample values, and corresponding blood pressure value label data, and the blood pressure value label data are the actually measured systolic and diastolic blood pressures;

[0124] Specifically, taking the actually measured systolic blood pressure value and diastolic blood pressure value as label data, and corresponding them to each group of oscillatory wave signal sample data, oscillatory wave characteristic parameter sample data, and the calculated preliminary blood pressure sample values, these data constitute the data basis for training the model.

[0125] In some embodiments, the preprocessing step includes data cleaning, data normalization, data augmentation, etc., to ensure the consistency and availability of the input data and provide a high-quality data basis for subsequent training. Specifically, data cleaning is to remove outliers and noise to ensure the quality of the data. For example, statistical methods (such as Z-score) can be used to detect and remove outliers; data normalization means normalizing all characteristic parameters and blood pressure values to the same scale range, such as [0, 1] or [-1, 1], which helps to improve the convergence speed and stability of the model; data augmentation such as random cropping, translation, scaling, etc., especially for oscillatory wave signals, can enhance the diversity of the data.

[0126] Step S402, dividing the sample data set into a training set, a validation set, and a test set;

[0127] Among them, the data set is divided into a training set, a validation set, and a test set. Usually, 70% of the data is used as the training set, 15% as the validation set, and 15% as the test set. The data can be divided by using the method of random sampling to avoid data deviation and ensure the consistent data distribution in each subset at the same time.

[0128] Step S403, inputting the training set into a pre-constructed convolutional neural network model for iterative training, calculating the loss function of the model, calculating the gradient through the backpropagation algorithm, and optimizing the model parameters;

[0129] Among them, it is very effective to use a convolutional neural network (CNN) to process time series data or multi-dimensional data. Through multiple layers of convolution and pooling operations, features in the data are gradually extracted for subsequent decision-making in the fully connected layer.

[0130] In one embodiment of the present application, the pre-constructed convolutional neural network model includes an input layer, a convolutional layer, a fully connected layer, and an output layer; specifically, it is set that the input layer receives the processed oscillatory wave signal data and the preliminary blood pressure value, and splices them into a multi-dimensional array as the input; then several convolutional layers are constructed to extract high-order features in the oscillatory wave signal, and these features can reveal subtle changes in the signal; the output of the convolutional layer is passed through several fully connected layers to further process and fuse the preliminary input blood pressure value; finally, an output layer is set, which has two neurons, one for predicting the systolic blood pressure value and the other for predicting the diastolic blood pressure value. Through multiple rounds of iterative training, the weights and biases of the model are gradually optimized, enabling the model to accurately predict blood pressure values from complex signals.

[0131] Step S404, update the weights of the convolutional neural network model based on an optimization algorithm with a momentum term until the loss function meets the preset conditions, and obtain the trained convolutional neural network model;

[0132] Specifically, during model training, an optimization algorithm with a momentum term is selected, such as SGD with momentum. By introducing the momentum term, the gradient descent process is accelerated, oscillations are reduced, and the convergence speed and stability of the model are improved; then, according to the calculated gradient and momentum term, the weights of the model are updated. For example, when using SGD with momentum, the update formula is as follows:

[0133]

[0134] θ t =θ t-1 -v t

[0135] In the above formula, v t is the velocity (i.e., momentum) at the t-th step, γ is the momentum coefficient (for example, 0.9), η is the learning rate, is the gradient of the loss function J with respect to the parameter θ at θ t-1 .

[0136] As an implementation of the loss function, the mean square error (MSE) can be used as the loss function. The loss function is used to measure the difference between the model prediction value and the true value. The gradient of the loss function is calculated through the backpropagation algorithm, and the optimization algorithm is used to adjust the model parameters to minimize the loss function, enabling the model to effectively learn and adjust its own parameters, and improving the accuracy and robustness of the prediction.

[0137] Step S405: Validate the convolutional neural network model based on the validation set, evaluate the performance of the convolutional neural network model, and adjust the hyperparameters of the model according to the validation results;

[0138] Among them, input the validation set data into the trained convolutional neural network, calculate the predicted systolic blood pressure and diastolic blood pressure, and use evaluation metrics (such as MSE, MAE, R 2 score, etc.) to evaluate the performance of the model. Then, according to the performance evaluation results on the validation set, adjust the hyperparameters of the model (such as learning rate, batch size, momentum coefficient, etc.) to further optimize the model performance.

[0139] Step S406: Test the prediction ability of the adjusted convolutional neural network model based on the test set to obtain a blood pressure value prediction model.

[0140] Specifically, input the test set data into the adjusted convolutional neural network, calculate the predicted systolic blood pressure and diastolic blood pressure to evaluate its actual prediction ability and generalization performance. The performance metrics on the test set are the key criteria for measuring the practicality of the model. The mean square error (MSE), accuracy, and other relevant evaluation metrics of the model can be evaluated to ensure that the model effect meets the practical standards.

[0141] In the above embodiment, an optimization algorithm with a momentum term is used to iteratively train the convolutional neural network model, and the performance of the model is evaluated and optimized through the validation set and the test set. This technical solution not only improves the accuracy of blood pressure measurement but also enhances the robustness of the model to abnormal situations. This optimization method significantly improves the accuracy and stability of blood pressure measurement and provides a more reliable and efficient solution for the medical detection field.

[0142] Referring to Figure 5 , as a further embodiment of the intelligent blood pressure measurement method, after the step of sending the final blood pressure value to the display module for output display, the following steps are further included:

[0143] Step S501: Determine whether the final blood pressure value exceeds the normal blood pressure range; if so, jump to step S502; if not, do nothing.

[0144] In some embodiments, the normal blood pressure range can be defined according to medical standards; for example, the normal blood pressure range for adults is usually 90 - 120 mmHg for systolic blood pressure and 60 - 80 mmHg for diastolic blood pressure. By comparing the final blood pressure value with the defined normal blood pressure range, the blood pressure condition of the user can be accurately judged, and abnormal situations can be detected in a timely manner.

[0145] Step S502: Generate a blood pressure warning prompt according to the final blood pressure value and send it to the corresponding medical care terminal.

[0146] Among them, if the final blood pressure value exceeds the normal range, a corresponding warning prompt is generated. In some embodiments, the warning prompt may include the following content: the identity information of the measured person (such as name, ID number, etc.), the final blood pressure value, the warning type (hypertension or hypotension), and the recommended measures (such as recommending immediate medical treatment, close monitoring, etc.); the medical staff terminal can be a doctor's workstation, a nurse's handheld device, or other designated medical management systems.

[0147] In the above embodiment, after the final blood pressure value is sent to the display module for output display, it is further determined whether the blood pressure value exceeds the normal range. If it exceeds the normal range, a corresponding warning prompt is generated and sent to the corresponding medical staff terminal. This technical solution can not only monitor the user's blood pressure status in real time, but also notify the medical staff in time when abnormalities are found, thus improving the response speed and quality of medical services. Through this warning mechanism, patients can receive more timely medical intervention, reducing the risks caused by hypertension or hypotension and enhancing the safety and effectiveness of overall medical care.

[0148] The embodiment of the present application also discloses an intelligent blood pressure measurement system based on the deflation oscillometric method.

[0149] An intelligent blood pressure measurement system based on the deflation oscillometric method, the intelligent blood pressure measurement system includes an air pump, a solenoid valve, a pressure sensor, a microprocessor, a display module, and a cuff wrapped around the wrist or upper arm of the measured person;

[0150] The air pump is used to fill the cuff with gas;

[0151] The solenoid valve is connected to the air pump and is used to control the gas inlet and outlet of the cuff;

[0152] The cuff is used to adjust the internal air pressure through the air pump and the solenoid valve;

[0153] The pressure sensor is connected to the cuff and is used to collect the air pressure data and oscillation wave signals inside the cuff in real time;

[0154] The microprocessor is connected to the air pump, the solenoid valve, and the pressure sensor, and is used to receive and process the air pressure data and oscillation wave signals collected by the pressure sensor, and calculate the final blood pressure value;

[0155] The display module is used to display the final blood pressure value calculated by the microprocessor.

[0156] Based on the above intelligent blood pressure measurement system, during the actual operation process, first ensure that hardware devices such as the air pump, solenoid valve, and pressure sensor are correctly connected to the microprocessor and perform system initialization; after the subject wears the cuff according to the instructions, start the measurement program, and the microprocessor controls the air pump and solenoid valve to complete the inflation process until the blood flow is blocked and the subsequent deflation process; during this process, the pressure sensor continuously collects air pressure and oscillometric wave signals, and the microprocessor preprocesses and extracts features from these signals; next, the proportional coefficient method is applied to calculate the preliminary blood pressure value, and then the preliminary result is optimized through a pre-trained neural network model to improve the measurement accuracy; finally, the final blood pressure value is displayed on the screen, and data can be selectively stored or transmitted for further analysis and management; this system combines the traditional oscillometric method with advanced signal processing and machine learning technologies to achieve efficient, accurate, and reliable blood pressure measurement.

[0157] As an implementation of the microprocessor, the microprocessor includes:

[0158] An air pump control unit for controlling the air pump to inflate the cuff on the subject's wrist or upper arm until a preset initial air pressure value is reached;

[0159] A solenoid valve control unit for controlling the solenoid valve to release the gas in the cuff at a preset rate;

[0160] A data receiving unit for receiving the air pressure data and oscillometric wave signals in the cuff continuously collected by the pressure sensor;

[0161] A feature extraction unit for identifying and extracting key features from the oscillometric wave signals based on the eigenvalue method to obtain oscillometric wave feature parameters;

[0162] A preliminary blood pressure value generation unit for calculating a preliminary blood pressure value based on a pre-established proportional coefficient model according to the air pressure data and oscillometric wave feature parameters;

[0163] A final blood pressure value generation unit for inputting the oscillometric wave signals, oscillometric wave feature parameters, and preliminary blood pressure value into a pre-trained blood pressure value prediction model with a momentum term to obtain the final blood pressure value; where the blood pressure value includes the systolic blood pressure value and the diastolic blood pressure value;

[0164] A final blood pressure value sending unit for sending the final blood pressure value to the display module for output display.

[0165] The intelligent blood pressure measurement system based on the deflation oscillometric method in the embodiments of the present application can implement any one of the above intelligent blood pressure measurement methods, and the specific working processes of each module in the intelligent blood pressure measurement system can refer to the corresponding processes in the above method embodiments.

[0166] In several embodiments provided by the present application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for example, the division of a certain module is only a logical function division, and there may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0167] The embodiments of the present application also disclose a computer device.

[0168] The computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent blood pressure measurement method based on the deflation oscillometric method as described above.

[0169] The embodiments of the present application also disclose a computer-readable storage medium.

[0170] The computer-readable storage medium stores a computer program that can be loaded and executed by a processor to implement any one of the intelligent blood pressure measurement methods based on the deflation oscillometric method as described above.

[0171] Among them, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component; the program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination of the above.

[0172] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0173] The above are all the preferred embodiments of the present application. The protection scope of the present application is not limited by this. Any feature disclosed in this specification (including the abstract and drawings), unless specifically described, can be replaced by other equivalent or similar-purpose alternative features. That is, unless specifically described, each feature is only an example in a series of equivalent or similar features.

Claims

1. An intelligent blood pressure measurement method based on deflation oscillometric method, applied to an intelligent blood pressure measurement system including an air pump, a solenoid valve, a pressure sensor, a microprocessor, a display module and a cuff, characterized in that: The measuring method comprises: Controlling the air pump to inflate air into the cuff on the wrist or upper arm of the subject until a preset initial air pressure value is reached; Controlling the solenoid valve to release the gas in the cuff at a preset rate, and receiving the air pressure data and oscillation wave signal in the cuff collected in real time by the pressure sensor; Identify the oscillation wave signal and extract key features based on the eigenvalue method to obtain oscillation wave characteristic parameters; Based on a pre-established proportional coefficient model, a preliminary blood pressure value is calculated according to the air pressure data and the oscillation wave characteristic parameters; Inputting the oscillation wave signal, the oscillation wave characteristic parameter and the preliminary blood pressure value into a pre-trained blood pressure value prediction model with a momentum term to obtain a final blood pressure value; wherein the blood pressure value includes a systolic pressure value and a diastolic pressure value; The final blood pressure value is sent to the display module for output display; the steps of identifying the oscillation wave signal and extracting key features based on the eigenvalue method to obtain oscillation wave characteristic parameters include: Performing data preprocessing on the oscillation wave signal; The preprocessed oscillation wave signal is divided into a plurality of sub-segments according to different preset pressure ranges; wherein the signal is divided into a plurality of sub-segments according to the difference between the inflation stage and the deflation stage, and each sub-segment represents a specific pressure interval; Performing peak detection and trough detection on the oscillation wave signal in each sub-segment, determining the peak position and the trough position, and calculating the characteristic parameters between each peak and the trough, to obtain the key characteristic parameters of the oscillation wave signal in each sub-segment; wherein the key characteristic parameters include the peak position, the trough position, the amplitude, the frequency, the period, the rising edge slope and the falling edge slope; Based on the principal component analysis method, dimension reduction processing and feature selection are performed on the key characteristic parameters of the oscillation wave signal in each sub-segment, and the selected features are normalized to obtain the optimized characteristic parameters of the oscillation wave.

2. The intelligent blood pressure measurement method based on the deflation oscillometric method according to claim 1, characterized in that: Based on the pre-established proportional coefficient model, the step of calculating the preliminary blood pressure value according to the air pressure data and the oscillation wave characteristic parameters includes: Load a pre-built scale factor model from system storage; Formatting the air pressure data and oscillation wave characteristic parameters; Mapping the oscillation wave characteristic parameters in each sub-segment to corresponding input variables in the proportional coefficient model to obtain a mapped characteristic parameter set; Correcting the air pressure data, and time-aligning the corrected air pressure data with the characteristic parameter set to obtain an air pressure data set; The characteristic parameter set and the air pressure data set are input into a proportional coefficient model to calculate preliminary systolic pressure value and diastolic pressure value.

3. The intelligent blood pressure measurement method based on the deflation oscillometric method according to claim 2, characterized in that: The relationship of the proportional coefficient model is: Systolic blood pressure = a1×amplitude+b1×frequency+c1×pressure+d1; Diastolic pressure = a2×amplitude+b2×frequency+c2×pressure+d2; In the above formula, a1, b1, c1, d1 and a2, b2, c2, d2 are predetermined proportional coefficients.

4. The intelligent blood pressure measurement method based on the deflation oscillometric method according to claim 1, characterized in that: The method further includes a training step of the blood pressure value prediction model, wherein the training step includes: Acquire a sample data set and perform data preprocessing; wherein the sample data set includes oscillation wave signal sample data, oscillation wave characteristic parameter sample data, preliminary blood pressure sample values ​​and corresponding blood pressure value label data, and the blood pressure value label data is the actually measured systolic and diastolic pressure; Dividing the sample data set into a training set, a validation set and a test set; Inputting the training set into a pre-built convolutional neural network model for iterative training, calculating the loss function of the model, calculating the gradient through a back-propagation algorithm, and optimizing the model parameters; The weights of the convolutional neural network model are updated based on an optimization algorithm with a momentum term until the loss function meets a preset condition, thereby obtaining a trained convolutional neural network model; Validating the convolutional neural network model based on the validation set, evaluating the performance of the convolutional neural network model and adjusting the hyperparameters of the model according to the validation results; The prediction ability of the adjusted convolutional neural network model is tested based on the test set to obtain the blood pressure value prediction model.

5. The intelligent blood pressure measurement method based on the deflation oscillometric method according to any one of claims 1 to 4, characterized in that: After the step of sending the final blood pressure value to the display module for output display, the method further includes: Determining whether the final blood pressure value exceeds a normal blood pressure range; If so, a blood pressure warning prompt is generated according to the final blood pressure value and sent to the corresponding medical terminal.

6. An intelligent blood pressure measurement system based on deflation oscillometric method, characterized in that: Used to perform the intelligent blood pressure measurement method based on the deflation oscillometric method according to any one of claims 1 to 5, the intelligent blood pressure measurement system comprising an air pump, a solenoid valve, a pressure sensor, a microprocessor, a display module, and a cuff wrapped around the wrist or upper arm of the subject; The air pump is used to fill the cuff with gas; The solenoid valve is connected to the air pump and is used to control the inflow and outflow of gas in the cuff; The cuff is used to adjust the internal air pressure through the air pump and the solenoid valve; The pressure sensor is connected to the cuff and is used to collect air pressure data and oscillation wave signals in the cuff in real time; The microprocessor is connected to the air pump, the solenoid valve and the pressure sensor, and is used to receive and process the air pressure data and the oscillation wave signal collected by the pressure sensor, and calculate the final blood pressure value; The display module is used to display the final blood pressure value calculated by the microprocessor.

7. The intelligent blood pressure measurement system based on the deflation oscillometric method according to claim 6, characterized in that: The microprocessor comprises: An air pump control unit, used for controlling the air pump to inflate air into the cuff of the wrist or upper arm of the subject until a preset initial air pressure value is reached; A solenoid valve control unit, used for controlling the solenoid valve to release the gas in the cuff at a preset rate; A data receiving unit, used for receiving the air pressure data and oscillation wave signal in the cuff collected in real time by the pressure sensor; A feature extraction unit, used to identify the oscillation wave signal and extract key features based on a eigenvalue method to obtain oscillation wave feature parameters; a preliminary blood pressure value generating unit, configured to calculate the preliminary blood pressure value according to the air pressure data and the oscillation wave characteristic parameters based on a pre-established proportional coefficient model; A final blood pressure value generating unit, used for inputting the oscillation wave signal, the oscillation wave characteristic parameter and the preliminary blood pressure value into a pre-trained blood pressure value prediction model with a momentum term to obtain a final blood pressure value; wherein the blood pressure value includes a systolic pressure value and a diastolic pressure value; The final blood pressure value sending unit is used to send the final blood pressure value to the display module for output display.

8. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 5 when executing the program.

9. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 5.

Images