A device and method for measuring systolic blood pressure in fingers

Abstract

This invention discloses a finger systolic blood pressure measuring device and method. The device uses a finger sleeve to stably receive liquid pressure from a liquid delivery module, precisely compressing the finger's blood vessels. A strain gauge at the distal end sensitively captures blood flow recovery pulsation data, providing a reliable basis for systolic blood pressure calculation. A temperature control module maintains a suitable liquid temperature, reducing the impact of temperature on measurement results and improving measurement accuracy and stability. This ensures consistent performance under different ambient temperatures, enhancing applicability and reliability. The liquid delivery module automatically adjusts the water pressure, precisely controlling blood vessel compression and relaxation, simplifying manual operation and improving measurement efficiency and accuracy. A data processing module automatically collects and processes data, quickly calculating systolic blood pressure, reducing human error and increasing measurement speed.

Description

Technical Field

[0001] This invention relates to the field of finger vasopressor pressure measurement technology, and in particular to a finger vasopressor pressure measurement device and measurement method. Background Technology

[0002] In the field of medical diagnosis and health monitoring, blood pressure measurement has always held a pivotal position. Traditional methods of blood pressure measurement, such as using mercury sphygmomanometers or electronic sphygmomanometers to measure blood pressure in the upper arm, are widely used but still have many limitations. For example, they may not be suitable for all individuals, especially those with abnormal arm blood vessels or certain diseases. In addition, traditional measurement methods may not be convenient enough in some situations to meet the needs of real-time monitoring.

[0003] To overcome these limitations, finger systolic blood pressure measurement devices have emerged. These devices measure systolic blood pressure by compressing the blood vessels in the finger and monitoring the blood flow recovery process. Compared with traditional methods, finger systolic blood pressure measurement has advantages such as being non-invasive, convenient, and easy to operate, and is particularly suitable for home health monitoring, preliminary clinical screening, and blood pressure monitoring for special patient groups.

[0004] However, despite the many advantages of finger systolic blood pressure measurement devices, existing technologies still have some obvious shortcomings. First, in terms of measurement accuracy, existing devices are often severely affected by environmental and instrument noise, leading to significant errors in the measurement results. Second, in terms of measurement stability, due to the thinness of finger blood vessels and their susceptibility to external factors, existing devices often exhibit large fluctuations in measured values ​​during long-term measurements or continuous monitoring. Furthermore, existing devices are also insufficient in adapting to the different characteristics of finger blood vessels in different individuals, making it difficult to achieve accurate measurements for all individuals. Summary of the Invention

[0005] In view of this, the present invention proposes a finger vasopressor measurement device and method, which can effectively solve the defects of existing technologies such as large error, poor stability and difficulty in achieving accurate measurement for all individuals.

[0006] The technical solution of this invention is implemented as follows:

[0007] A finger systolic blood pressure measuring device, comprising:

[0008] A finger liner is placed on the finger being tested and connected to a liquid delivery module, which uses the pressure of the liquid to compress the blood vessels in the finger.

[0009] A strain gauge for the finger is placed at the distal end of the finger bushing to detect pulsation data during blood flow recovery;

[0010] The liquid delivery module, connected to the finger liner via a water pipe, is used to supply liquid at a specific water pressure to the finger liner to compress the blood vessels in the finger;

[0011] Temperature control module, used to provide temperature control function to regulate the temperature of the liquid flowing through the finger liner;

[0012] The data processing module is used to collect and process data from the finger strain gauge, liquid delivery module and temperature control module to calculate the vasoconstrictive pressure of the finger.

[0013] As a further optional embodiment of the finger vasopressor pressure measuring device, the data processing module collects and processes data from the finger strain gauge, the liquid delivery module, and the temperature control module to calculate the finger's vasopressor pressure, specifically including:

[0014] The signal acquisition host ensures that the finger strain gauge, liquid delivery module and temperature control module simultaneously acquire the pulse wave signal, blood vessel pressure signal and liquid temperature and pressure of the finger blood vessels;

[0015] Adaptive filtering technology is used to denoise the collected data.

[0016] The denoised pulse wave signal, vascular compression signal, and liquid temperature and pressure are converted into time series.

[0017] Construct complex networks based on the similarity of time series data and calculate the topological features of the complex networks;

[0018] The calculated complex network topology features are input into a deep learning model, which then predicts the systolic blood pressure of the finger blood vessels based on the predicted topology features.

[0019] As a further optional feature of the finger systolic blood pressure measuring device, the step of using adaptive filtering technology to denoise the acquired data specifically includes:

[0020] Analyze the noise type and signal characteristics of the collected data;

[0021] Select the appropriate adaptive filter type based on the noise type and signal characteristics;

[0022] Set the filtering parameters of the adaptive filter;

[0023] The acquired data is filtered and denoised using an adaptive filter with pre-set filtering parameters.

[0024] As a further optional feature of the aforementioned finger systolic blood pressure measuring device, the conversion of the noise-reduced pulse wave signal, vascular pressure signal, and liquid temperature and pressure into a time series specifically includes:

[0025] The sampling frequency is determined based on the characteristics and analysis requirements of the denoised pulse wave signal, vascular compression signal, and liquid temperature and pressure.

[0026] Generate a corresponding timestamp for each sampling point;

[0027] Align the data for each sampling point;

[0028] The aligned pulse wave signal, vascular compression signal, and fluid temperature and pressure are arranged in the order of timestamps to form their respective time series.

[0029] As a further optional feature of the finger systolic blood pressure measuring device, the construction of a complex network based on time series similarity and the calculation of the topological features of the complex network specifically include:

[0030] Based on the Pearson correlation coefficient, the similarity value between each pair of time series is calculated;

[0031] Based on the similarity calculation results, a threshold is set, which is used to determine the similarity strength between time series;

[0032] Based on a set threshold, an adjacency matrix is ​​constructed, where each element in the adjacency matrix indicates whether there is a connection between two time series.

[0033] The adjacency matrix is ​​transformed into a complex network, where nodes represent time series and edges represent similar connections between time series.

[0034] Calculate the topological characteristic values ​​of complex networks, and obtain the topological characteristics of complex networks based on the topological characteristic values.

[0035] As a further optional feature of the finger systolic blood pressure measuring device, the temperature control module regulates the temperature of the liquid flowing through the finger liner, specifically including:

[0036] The temperature sensor in the temperature control module monitors the temperature of the liquid flowing through the finger liner in real time;

[0037] Temperature data is transmitted to the controller of the temperature control module;

[0038] The controller compares the real-time monitored temperature with the preset temperature range and makes a decision to adjust the temperature.

[0039] Based on the controller's decision, the temperature control module will activate the heating or cooling equipment;

[0040] Once the heating or cooling equipment starts working, it will gradually adjust the temperature of the liquid flowing through the finger liner.

[0041] A method for measuring systolic blood pressure in a finger, wherein the method utilizes any of the aforementioned finger systolic blood pressure measuring devices, specifically comprising:

[0042] The finger liner is placed on the finger being tested, and the finger liner is connected to the liquid delivery module via a water pipe.

[0043] A liquid at a specific pressure is supplied to the finger liner through a liquid delivery module to compress the blood vessels in the finger to block blood flow.

[0044] Gradually reduce the water pressure provided by the liquid delivery module until pulsation data of blood flow recovery is observed in the finger as detected by the strain gauge.

[0045] During the blood flow recovery process, pulsation data is continuously collected by a strain gauge using a finger, and this data, along with relevant data from the liquid delivery module and temperature control module, is sent to the data processing module.

[0046] The data processing module receives and processes data from the finger strain gauge, the liquid delivery module, and the temperature control module, and calculates the vasoconstrictive pressure of the finger according to a preset algorithm.

[0047] Output the calculated systolic blood pressure value of the finger.

[0048] A computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described finger systolic blood pressure measurement method.

[0049] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described finger vasopressor measurement method.

[0050] The beneficial effects of this invention are as follows: the finger liner allows the finger being tested to stably receive liquid pressure from the liquid delivery module, thereby ensuring precise compression of the finger's blood vessels. The strain gauge for the finger, located at the distal end of the finger liner, can sensitively capture pulsation data during blood flow recovery, providing a reliable basis for subsequent systolic pressure calculation. The presence of the temperature control module ensures that the temperature of the liquid flowing through the finger liner is always maintained within a suitable range, which helps reduce the influence of temperature on the measurement results and improves the accuracy and stability of the measurement. Temperature control also enables the device to maintain consistent measurement performance under different ambient temperatures, thereby improving its applicability and reliability. The liquid delivery module can automatically adjust the water pressure of the liquid as needed to achieve precise compression and relaxation of the finger's blood vessels, which reduces the complexity of manual operation and improves the efficiency and accuracy of the measurement. The data processing module can automatically collect and process data from various modules and calculate the systolic pressure of the finger's blood vessels. This automated processing not only improves the measurement speed but also reduces the possibility of human error. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a schematic diagram of the components of a finger vasopressor measuring device according to the present invention;

[0053] Figure 2 This is a flowchart illustrating a method for measuring systolic blood pressure in the fingers according to the present invention.

[0054] Figure 3 This is a schematic diagram of the composition of a computing device according to the present invention. Detailed Implementation

[0055] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] refer to Figures 1 to 3 A finger systolic blood pressure measuring device, comprising:

[0057] A finger liner is placed on the finger being tested and connected to a liquid delivery module, which uses the pressure of the liquid to compress the blood vessels in the finger.

[0058] A strain gauge for the finger is placed at the distal end of the finger bushing to detect pulsation data during blood flow recovery;

[0059] The liquid delivery module, connected to the finger liner via a water pipe, is used to supply liquid at a specific water pressure to the finger liner to compress the blood vessels in the finger;

[0060] Temperature control module, used to provide temperature control function to regulate the temperature of the liquid flowing through the finger liner;

[0061] The data processing module is used to collect and process data from the finger strain gauge, liquid delivery module and temperature control module to calculate the vasoconstrictive pressure of the finger.

[0062] In this embodiment, the finger liner allows the finger being tested to stably receive liquid pressure from the liquid delivery module, ensuring precise compression of the finger's blood vessels. A strain gauge located at the distal end of the finger liner sensitively captures pulsation data during blood flow recovery, providing a reliable basis for subsequent systolic blood pressure calculation. The temperature control module ensures that the temperature of the liquid flowing through the finger liner remains within a suitable range, helping to reduce the impact of temperature on measurement results and improve measurement accuracy and stability. Temperature control also enables the device to maintain consistent measurement performance under different ambient temperatures, thereby improving its applicability and reliability. The liquid delivery module can automatically adjust the water pressure as needed to achieve precise compression and relaxation of the finger's blood vessels, reducing the complexity of manual operation and improving measurement efficiency and accuracy. The data processing module can automatically collect and process data from various modules to calculate the finger's systolic blood pressure. This automated processing not only improves measurement speed but also reduces the possibility of human error.

[0063] Preferably, the data processing module collects and processes data from the finger strain gauge, the liquid delivery module, and the temperature control module to calculate the vasoconstrictive pressure of the finger, specifically including:

[0064] The signal acquisition host ensures that the finger strain gauge, liquid delivery module and temperature control module simultaneously acquire the pulse wave signal, blood vessel pressure signal and liquid temperature and pressure of the finger blood vessels;

[0065] Adaptive filtering technology is used to denoise the collected data.

[0066] The denoised pulse wave signal, vascular compression signal, and liquid temperature and pressure are converted into time series.

[0067] Construct complex networks based on the similarity of time series data and calculate the topological features of the complex networks;

[0068] The calculated complex network topology features are input into a deep learning model, which then predicts the systolic blood pressure of the finger blood vessels based on the predicted topology features.

[0069] In this embodiment, the signal acquisition host ensures that the finger strain gauge, liquid delivery module, and temperature control module can acquire data synchronously. This synchronization is crucial for subsequent data processing and analysis because it ensures the consistency of all relevant data over time, thereby improving the accuracy and reliability of data analysis. Adaptive filtering technology is used to denoise the acquired data, effectively removing noise and interference, improving data purity and quality. This is essential for subsequent data analysis and systolic blood pressure calculation, as noise and interference can affect the accuracy of the results. Converting the denoised data into a time series helps to better understand and analyze the dynamic changes in the data. Time series analysis is the process of processing and analyzing time series data. An effective method can reveal hidden patterns and trends in data, providing strong support for subsequent analysis and prediction. Constructing complex networks based on the similarity of time series data and calculating their topological features is an innovative data processing method. By converting time series data into complex networks and calculating their topological features, it can reveal complex relationships and interactions between data, providing richer information for subsequent deep learning models. The calculated complex network topological features are then input into a deep learning model, which can predict the systolic blood pressure of finger veins based on these features. Deep learning models have powerful learning and prediction capabilities, and can handle complex and nonlinear data relationships, thus enabling more accurate prediction of systolic blood pressure in finger veins.

[0070] Preferably, the step of using adaptive filtering technology to denoise the acquired data specifically includes:

[0071] Analyze the noise type and signal characteristics of the collected data;

[0072] Select the appropriate adaptive filter type based on the noise type and signal characteristics;

[0073] Set the filtering parameters of the adaptive filter;

[0074] The acquired data is filtered and denoised using an adaptive filter with pre-set filtering parameters.

[0075] In this embodiment, the collected data is analyzed for noise type and signal characteristics. This is the foundation of denoising processing because only by accurately understanding the noise type and signal characteristics can the most suitable filtering method and parameters be selected. This precise analysis helps improve the targeting and effectiveness of denoising processing. Based on the noise type and signal characteristics, a corresponding adaptive filter type is selected. The adaptive filter can automatically adjust its filtering parameters according to changes in the input signal, thereby effectively suppressing different types of noise. This selective filtering method ensures that useful information of the original signal is preserved as much as possible while removing noise. The setting of filtering parameters directly affects the performance and effect of the filter. By accurately setting the filtering parameters, it can be ensured that the adaptive filter will not cause excessive distortion or loss to the original signal while removing noise. The collected data is filtered and denoised according to the adaptive filter with the set filtering parameters. This step is the actual denoising process. Because the adaptive filter has the ability to automatically adjust parameters, it can continuously adapt to changes in the input signal during processing, thereby achieving efficient and accurate denoising processing.

[0076] It's important to note that analyzing the noise type in the original data, such as Gaussian noise or impulse noise (salt and pepper noise), helps in selecting a suitable adaptive filtering algorithm. Understanding the characteristics of the signal to be processed, including its frequency range and amplitude variations, aids in designing more appropriate filter parameters. Based on the noise type and signal characteristics, a suitable adaptive filter type is selected, such as the Wiener adaptive filter or the LMS adaptive filter. Filter parameters are then set, including the filter order, step size factor (for the LMS algorithm), and regularization factor (for the NLMS algorithm). These parameters directly affect the filter's performance and convergence speed. Through iteration, the filter parameters are continuously adjusted based on the input signal and the desired signal (or error signal) to minimize the error between the output signal and the desired signal. The denoising effect of the filter is evaluated by observing the filtered output signal. Based on the evaluation results, the filter parameters may need to be adjusted to achieve better denoising results. Finally, the optimized adaptive filter is applied to a real-world environment to test its denoising performance and stability.

[0077] Preferably, the step of converting the denoised pulse wave signal, vascular pressure signal, and liquid temperature and pressure into a time series specifically includes:

[0078] The sampling frequency is determined based on the characteristics and analysis requirements of the denoised pulse wave signal, vascular compression signal, and liquid temperature and pressure.

[0079] Generate a corresponding timestamp for each sampling point;

[0080] Align the data for each sampling point;

[0081] The aligned pulse wave signal, vascular compression signal, and fluid temperature and pressure are arranged in the order of timestamps to form their respective time series.

[0082] In this embodiment, based on the characteristics of the denoised pulse wave signal, vascular compression signal, and the temperature and pressure of the liquid, and the analysis requirements, the sampling frequency is precisely determined. The choice of sampling frequency directly affects the resolution and accuracy of the time series. By selecting an appropriate sampling frequency, it can be ensured that the time series can accurately reflect the dynamic changes of the original signal. A corresponding timestamp is generated for each sampling point, and data alignment is performed on each sampling point. The generation of timestamps ensures that each sampling point has a clear time marker, which facilitates subsequent time series analysis and processing. Data alignment ensures the temporal consistency between different signals, that is, different signal values ​​at the same time point can be correlated. The data-aligned pulse wave signal, The vascular pressure signal, fluid temperature, and pressure are arranged in time stamp order to form their respective time series. The formation of time series gives the data a clear time dimension, making it easier to observe and analyze the changing trends and characteristics of the data at different time points. Through a series of steps, including accurately determining the sampling frequency, generating timestamps, aligning data, and forming time series, this technical solution successfully converts the denoised data into a time series. This conversion not only improves the readability and analyzability of the data but also provides strong support for subsequent data processing and analysis. Time series analysis can reveal hidden patterns and trends in the data, providing a more accurate and reliable basis for the calculation and prediction of finger vascular systolic pressure.

[0083] It should be noted that for pulse wave signals and vascular compression signals, since they usually contain high-frequency components (such as heart rate variability), a higher sampling frequency is required to capture these changes. For the temperature and pressure of liquids, if their changes are relatively slow, a lower sampling frequency can be selected. The generation of timestamps is usually based on a stable clock source (such as a system clock or a high-precision timer). The timestamps of each sampling point should be continuous and consistent with the sampling frequency. Data alignment can be achieved through interpolation, resampling, or time synchronization. A time series is a collection of data arranged in chronological order, reflecting the changes of a signal over time. Each time series contains two parts of information: timestamps and data values.

[0084] Preferably, the construction of complex networks based on time series similarity and the calculation of the topological features of the complex networks specifically include:

[0085] Based on the Pearson correlation coefficient, the similarity value between each pair of time series is calculated;

[0086] Based on the similarity calculation results, a threshold is set, which is used to determine the similarity strength between time series;

[0087] Based on a set threshold, an adjacency matrix is ​​constructed, where each element in the adjacency matrix indicates whether there is a connection between two time series.

[0088] The adjacency matrix is ​​transformed into a complex network, where nodes represent time series and edges represent similar connections between time series.

[0089] Calculate the topological characteristic values ​​of complex networks, and obtain the topological characteristics of complex networks based on the topological characteristic values.

[0090] In this embodiment, the similarity value between each pair of time series is calculated using the Pearson correlation coefficient. This technique accurately quantifies the linear correlation between time series. The Pearson correlation coefficient is a commonly used statistic that measures the degree of linear correlation between two variables, thus exhibiting good applicability in time series analysis. By setting a threshold to determine the similarity strength between time series, this technique flexibly controls which time series are considered similar and constitute a connection. This flexibility allows the technique to adapt to different application scenarios and data analysis needs. By constructing an adjacency matrix and converting it into a complex network, this technique can intuitively express the connection relationships between time series. In the complex network, nodes represent time series, and edges represent similarity connections between time series. This representation facilitates visualization and further analysis. By calculating the topological characteristic values ​​of complex networks, this technical solution can reveal the structural characteristics of complex systems. Topological characteristic values, such as degree distribution, clustering coefficient, and average path length, can reflect the overall structure and local characteristics of complex networks. Extending time series analysis to the field of complex networks provides a new perspective and method for time series analysis. By transforming the similarity between time series into connectivity relationships in complex networks, complex network theory and methods can be used to analyze the potential structure and dynamic behavior of time series data. Constructing complex networks based on time series data supports the dynamic analysis of complex systems. By comparing the topological characteristics of complex networks at different time points or under different conditions, the dynamic changes and evolutionary laws of complex systems can be revealed.

[0091] It should be noted that, based on the similarity calculation results, a threshold is set to determine which time series should be connected. Based on this threshold, an adjacency matrix is ​​constructed, where each element represents whether a connection exists between two time series. This adjacency matrix is ​​then transformed into a complex network, where nodes represent time series and edges represent similarity connections between them. Depending on the research objective and the characteristics of the complex network, appropriate topological feature parameters are selected, such as degree, clustering coefficient, average path length, network diameter, maximum connected subgraph size, kernel number, and betweenness number. Using relevant algorithms and tools, the specific values ​​of the selected topological feature parameters are calculated. The calculated topological feature values ​​are then analyzed to reveal the intrinsic structure and characteristics of the complex network.

[0092] Preferably, the temperature control module regulates the temperature of the liquid flowing through the finger liner, specifically including:

[0093] The temperature sensor in the temperature control module monitors the temperature of the liquid flowing through the finger liner in real time;

[0094] Temperature data is transmitted to the controller of the temperature control module;

[0095] The controller compares the real-time monitored temperature with the preset temperature range and makes a decision to adjust the temperature.

[0096] Based on the controller's decision, the temperature control module will activate the heating or cooling equipment;

[0097] Once the heating or cooling equipment starts working, it will gradually adjust the temperature of the liquid flowing through the finger liner.

[0098] In this embodiment, the temperature sensor in the temperature control module can monitor the temperature of the liquid flowing through the finger liner in real time. This real-time monitoring ensures that the system can respond quickly to temperature changes. The controller compares the real-time monitored temperature with a preset temperature range to make precise temperature adjustment decisions. This precise control helps maintain a stable temperature of the liquid inside the finger liner, avoiding the impact of temperature fluctuations on applications such as finger vasopressor measurement. Based on the controller's decision, the temperature control module automatically starts the heating or cooling equipment. This automated adjustment not only improves response speed but also reduces the need for manual intervention, making it more efficient and energy-saving. By precisely controlling the start and stop of the heating or cooling equipment, temperature requirements can be met while minimizing [the impact of temperature fluctuations]. Energy consumption; After the heating or cooling equipment starts working, it gradually adjusts the temperature of the liquid flowing through the finger liner until it reaches the preset temperature range. This gradual adjustment helps avoid discomfort caused by sudden temperature changes to the fingers, while ensuring the temperature stability of the liquid inside the finger liner. A stable temperature environment is crucial for measuring physiological parameters such as vasoconstriction in the fingers, helping to improve the accuracy and reliability of the measurements. By adjusting the preset temperature range, it can adapt to different application scenarios and user needs. For example, in cold environments, a higher temperature range can be set to keep the fingers warm; in hot environments, a lower temperature range can be set to avoid overheating the fingers. This flexibility and adaptability make this technology solution have broad application prospects.

[0099] A method for measuring systolic blood pressure in a finger, wherein the method utilizes any of the aforementioned finger systolic blood pressure measuring devices, specifically comprising:

[0100] The finger liner is placed on the finger being tested, and the finger liner is connected to the liquid delivery module via a water pipe.

[0101] A liquid at a specific pressure is supplied to the finger liner through a liquid delivery module to compress the blood vessels in the finger to block blood flow.

[0102] Gradually reduce the water pressure provided by the liquid delivery module until pulsation data of blood flow recovery is observed in the finger as detected by the strain gauge.

[0103] During the blood flow recovery process, pulsation data is continuously collected by a strain gauge using a finger, and this data, along with relevant data from the liquid delivery module and temperature control module, is sent to the data processing module.

[0104] The data processing module receives and processes data from the finger strain gauge, the liquid delivery module, and the temperature control module, and calculates the vasoconstrictive pressure of the finger according to a preset algorithm.

[0105] Output the calculated systolic blood pressure value of the finger.

[0106] A computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described finger systolic blood pressure measurement method.

[0107] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described finger vasopressor measurement method.

[0108] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A finger systolic blood pressure measuring device, characterized in that, include: A finger liner is placed on the finger being tested and connected to a liquid delivery module, which uses the pressure of the liquid to compress the blood vessels in the finger. A strain gauge for the finger is placed at the distal end of the finger bushing to detect pulsation data during blood flow recovery; The liquid delivery module, connected to the finger liner via a water pipe, is used to supply liquid at a specific water pressure to the finger liner to compress the blood vessels in the finger to a state of blood flow blockage. The temperature control module provides temperature control functionality to regulate the temperature of the liquid flowing through the finger liner; The data processing module is used to collect and process data from the finger strain gauge, liquid delivery module and temperature control module to calculate the vasoconstrictive pressure of the finger; The data processing module collects and processes data from the finger strain gauge, the liquid delivery module, and the temperature control module to calculate the vasoconstrictive pressure of the finger, specifically including: As the water pressure provided by the liquid delivery module is gradually reduced to restore blood flow, the signal acquisition host ensures that the finger strain gauge, liquid delivery module, and temperature control module simultaneously acquire the pulse wave signal, vascular pressure signal, and liquid temperature and pressure of the finger blood vessels. Adaptive filtering technology is used to denoise the collected data. The denoised pulse wave signal, vascular compression signal, and liquid temperature and pressure are converted into time series. Construct complex networks based on the similarity of time series data and calculate the topological features of the complex networks; The calculated complex network topology features are input into a deep learning model, which then predicts the systolic blood pressure of the finger blood vessels based on the predicted topology features.

2. The finger systolic blood pressure measuring device according to claim 1, characterized in that, The process of denoising the collected data using adaptive filtering technology specifically includes: Analyze the noise type and signal characteristics of the collected data; Select the appropriate adaptive filter type based on the noise type and signal characteristics; Set the filtering parameters of the adaptive filter; The acquired data is filtered and denoised using an adaptive filter with pre-set filtering parameters.

3. The finger systolic blood pressure measuring device according to claim 2, characterized in that, The process of converting the denoised pulse wave signal, vascular pressure signal, and liquid temperature and pressure into a time series specifically includes: The sampling frequency is determined based on the characteristics and analysis requirements of the denoised pulse wave signal, vascular compression signal, and liquid temperature and pressure. Generate a corresponding timestamp for each sampling point; Align the data for each sampling point; The aligned pulse wave signal, vascular compression signal, and fluid temperature and pressure are arranged in the order of timestamps to form their respective time series.

4. The finger systolic blood pressure measuring device according to claim 3, characterized in that, The construction of complex networks based on time-series similarity and the calculation of the topological features of the complex networks specifically include: Based on the Pearson correlation coefficient, the similarity value between each pair of time series is calculated; Based on the similarity calculation results, a threshold is set, which is used to determine the similarity strength between time series; Based on a set threshold, an adjacency matrix is ​​constructed, where each element in the adjacency matrix indicates whether there is a connection between two time series. The adjacency matrix is ​​transformed into a complex network, where nodes represent time series and edges represent similar connections between time series. Calculate the topological characteristic values ​​of complex networks, and obtain the topological characteristics of complex networks based on the topological characteristic values.

5. A finger systolic blood pressure measuring device according to claim 4, characterized in that, The temperature control module regulates the temperature of the liquid flowing through the finger liner, specifically including: The temperature sensor in the temperature control module monitors the temperature of the liquid flowing through the finger liner in real time; Temperature data is transmitted to the controller of the temperature control module; The controller compares the real-time monitored temperature with the preset temperature range and makes a decision to adjust the temperature. Based on the controller's decision, the temperature control module will activate the heating or cooling equipment; Once the heating or cooling equipment starts working, it will gradually adjust the temperature of the liquid flowing through the finger liner.

6. A method for measuring systolic blood pressure in a finger, characterized in that, The method utilizes any one of the finger vasopressor measuring devices according to claims 1-5, specifically including: The finger liner is placed on the finger being tested, and the finger liner is connected to the liquid delivery module via a water pipe. A liquid at a specific pressure is supplied to the finger liner through a liquid delivery module to compress the blood vessels in the finger to block blood flow. Gradually reduce the water pressure provided by the liquid delivery module until pulsation data of blood flow recovery is observed in the finger as detected by the strain gauge. During the blood flow recovery process, pulsation data is continuously collected by a strain gauge using a finger, and this data, along with relevant data from the liquid delivery module and temperature control module, is sent to the data processing module. The data processing module receives and processes data from the finger strain gauge, the liquid delivery module, and the temperature control module, and calculates the vasoconstrictive pressure of the finger according to a preset algorithm. Output the calculated systolic blood pressure value of the finger.

7. A computing device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the finger vasopressor measurement method of claim 6.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the finger vasopressor measurement method of claim 6.

Images