Data processing method and system for blood pressure electrical stimulator

Abstract

The invention relates to the technical field of biomedical signal data processing, and particularly discloses a data processing method and system for a blood pressure electrical stimulator, and the method comprises the steps: synchronously collecting an electrocardiosignal, a blood pressure waveform signal and an electrical stimulation parameter signal of a testee at a moment through multiple channels; extracting an electrical stimulation switch moment sequence; constructing a standardized individual response data vector; establishing an individualized physiological response curve model by adopting a generalized linear regression method; and next stimulation parameters are adjusted through a feedback adjustment mechanism. In the prior art, an electrical stimulation method which depends on a fixed rule or empirical parameter setting, especially in an application scene in which physiological response differences exist among individuals, high-resolution physiological response data modeling cannot be realized. Due to the fact that data segmentation, low-sample modeling and predictive regulation and control can be carried out based on event driving, an individualized stimulation and response model is constructed, and the flexibility and safety of control over the blood pressure electrical stimulator are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of biomedical signal data processing, and in particular to a data processing method and system for a blood pressure electrical stimulator. Background Art

[0002] Currently, blood pressure electrical stimulators are widely used to assist in regulating vascular tone and sympathetic nerve activity in patients with hypertension. Their core approach relies on electrical signals acting on specific neural pathways to achieve blood pressure regulation. However, existing technologies often use preset electrical stimulation parameters with fixed intensity, frequency, or period, or adjust them based on a small number of empirical rules. This lacks in-depth modeling of individual physiological differences, resulting in unstable control effects and even the induction of side effects when faced with dynamic blood pressure fluctuations or significant differences in individual response characteristics. For example, while some studies have introduced heart rate or blood pressure change indicators, these serve only as auxiliary triggering conditions and do not establish a mapping model between stimulation parameters and physiological responses, making it impossible to predict stimulation results or provide feedback on control. Furthermore, traditional systems often ignore the interconnected effects of electrical stimulation on complex nonlinear characteristics such as heart rate variability and short-term blood pressure dynamics, resulting in stimulation patterns that are neither interpretable nor adaptable. Existing technologies cannot fully meet the dynamic control needs of application scenarios with significant physiological differences between individuals, severe blood pressure fluctuations, or high target control precision requirements. Therefore, there is an urgent need for a data processing method and system for a blood pressure electrical stimulator that can realize data processing, modeling and feedback adjustment of the blood pressure stimulation response law, so as to improve the individual adaptability, control accuracy and clinical safety of the electrical stimulation system. Summary of the Invention

[0003] In response to the above-mentioned technical deficiencies, the purpose of the present invention is to propose a data processing method for a blood pressure electrical stimulator, aiming to solve the technical problem that high-resolution physiological response data modeling cannot be achieved in application scenarios where there are differences in physiological responses between individuals, because the electrical stimulation methods in the prior art mostly rely on fixed rules or empirical parameter settings.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a data processing method for a blood pressure electrical stimulator,

[0005] The data processing method for the blood pressure electrical stimulator comprises:

[0006] Step S10: synchronously collect the subject's physiological signals at time t through multiple channels, including the ECG signal s ECG (t), blood pressure waveform signal s BP (t) and the electrical stimulation parameter signal u(t), the three signals are synchronized at the hardware level using a common clock timestamp mechanism, and the electrical stimulation parameter signal u(t) is denoised and feature extracted to obtain the electrical stimulation on / off time sequence;

[0007] Step S20: Obtain the kth on-time from the electrical stimulation on-off time sequence and closing time And start time and closing time Centered and extended forward by Δt b seconds, expand backward Δt r seconds, forming the physiological response time window W locked to the stimulus event (k) , in each W (k) Extract the ECG signal after hardware-level synchronization ECG (t), blood pressure waveform signal s BP (t) and electrical stimulation parameter signal u(t), construct the response data set D for each stimulation (k) ;

[0008] Step S30: For each physiological response time window W (k) , for the constructed response data set D (k) Extract physiological response features and obtain heart rate variation feature ΔHR (k) , systolic blood pressure change rate characteristics ΔSBP (k) and stimulus intensity statistical characteristics The above features are vector normalized to form the individual response data vector x (k) ;

[0009] Step S40: Use the generalized linear regression method to construct a physiological response curve regression model, and transform the individual response data vector x (k) Mapped to blood pressure regulation response output value y (k) ;

[0010] Step S50: Input feature x for the k+1th electrical stimulation (k+1) , the fitted physiological response curve regression model is used to predict the k+1th blood pressure regulation response output value y (k+1) , when the blood pressure regulation response output value y (k+1) Less than the preset desired target threshold y target When the closed-loop feedback regulation mechanism is executed.

[0011] Preferably, in step S30, the heart rate variation characteristic in, represents the Δt after the kth electrical stimulation event is initiated r Average heart rate in seconds, Δt before the kth electrical stimulation event b Average heart rate within seconds; systolic blood pressure change rate characteristics in, is Δt after the kth electrical stimulation event is initiated r The average systolic blood pressure within a second, Δt before the kth electrical stimulation event b Average systolic blood pressure within seconds; statistical characteristics of stimulus intensity where |u(t)| is the instantaneous amplitude of the stimulus signal at time t before and after the kth event.

[0012] Preferably, in step S40, the blood pressure adjustment response output value y (k) =θ1·ΔHR (k) +θ2·

[0013] Among them, θ1, θ2, θ3 are individual response weight parameters, ε (k) is the modeling error term.

[0014] Preferably, in step S40, the physiological response curve regression model is used to characterize the blood pressure regulation response characteristics of the individual under different electrical stimulation doses; the individual response weight parameters θ1, θ2, θ3 are estimated by the least squares method, and the calculation formula is: in, are the individual response weight parameters θ1, θ2, θ3 to be solved; X is the input feature matrix, and each line is the standardized feature vector of the kth stimulus Y is the blood pressure regulation response output value y corresponding to each stimulus (k) Column vector of response results; is the Moore-Penrose pseudoinverse matrix of the least squares solution.

[0015] Preferably, in step S10, the step of performing denoising and feature extraction on the electrical stimulation parameter signal u(t) to obtain the electrical stimulation on / off time sequence specifically includes:

[0016] The first-order difference algorithm is used to detect the edge of the electrical stimulation parameter signal u(t), and the differential signal Δu(t) is defined as: Δu(t) = u(t) - u(t - δt), where δt is the preset sampling period;

[0017] Then set the enable threshold γ on >0 and turn off threshold γ off <0, when:

[0018] Δu(t)>γ on When

[0019] Δu(t)<γ off When the time is reached, it is recognized as the closing moment of an electrical stimulation.

[0020] Set the stimulus interval threshold T gap Post-process the recognition results, remove repeated recognition events to obtain effective trigger events, and extract them as the electrical stimulation switch time sequence in, are the kth opening time and closing time Used for subsequent physiological response time window construction.

[0021] Preferably, in step S50, the fitting data set in the fitting process of the physiological response curve regression model comes from the previous n completed electrical stimulation events in the historical data.

[0022] Preferably, in step S20,

[0023] The present invention also provides a data processing system for a blood pressure electrical stimulator, comprising:

[0024] Multi-channel synchronous acquisition and trigger recognition module, used to synchronously acquire the subject's physiological signals at time t through multiple channels, including the ECG signal s ECG (t), blood pressure waveform signal s BP (t) and the electrical stimulation parameter signal u(t), the three signals are synchronized at the hardware level using a common clock timestamp mechanism, and the electrical stimulation parameter signal u(t) is denoised and feature extracted to obtain the electrical stimulation on / off time sequence;

[0025] Response time window construction and data set generation module, used to obtain the kth on-off moment from the electrical stimulation on-off moment sequence and closing time And start time and closing time Centered and extended forward by Δt b seconds, expand backward Δt r seconds, forming the physiological response time window W locked to the stimulus event (k) , in each W (k) Extract the ECG signal after hardware-level synchronization ECG (t), blood pressure waveform signal s BP (t) and electrical stimulation parameter signal u(t), construct the response data set D for each stimulation (k) ;

[0026] Response feature extraction and vector normalization module is used for each physiological response time window W (k) , for the constructed response data set D (k) Extract physiological response features and obtain heart rate variation feature ΔHR (k) , systolic blood pressure change rate characteristics ΔSBP (k)and stimulus intensity statistical characteristics The above features are vector normalized to form the individual response data vector x (k) ;

[0027] Physiological response modeling module is used to construct physiological response curve regression model by using generalized linear regression method, and transform individual response data vector x (k) Mapped to blood pressure regulation response output value y (k) ;

[0028] Closed-loop feedback control module for the k+1th electrical stimulation input feature x (k+1) , the fitted physiological response curve regression model is used to predict the k+1th blood pressure regulation response output value y (k+1) , when the blood pressure regulation response output value y (k+1) Less than the preset desired target threshold y target When the closed-loop feedback regulation mechanism is executed.

[0029] The present invention also provides a data processing device for a blood pressure electric stimulator, comprising: a memory, a processor, and a data processing program for the blood pressure electric stimulator stored in the memory and executable on the processor. When the data processing program for the blood pressure electric stimulator is executed by the processor, a data processing method for the blood pressure electric stimulator is implemented.

[0030] The present invention also provides a computer program product, comprising a data processing program for a blood pressure electric stimulator, wherein the data processing program for a blood pressure electric stimulator implements the data processing method for a blood pressure electric stimulator when executed by a processor.

[0031] The beneficial effects of the present invention are: providing a multimodal synchronous acquisition and modeling mechanism that integrates electrocardiogram, blood pressure, and electrical stimulation parameters. Based on event-driven data processing and segmentation and individual response vector construction, it is possible to complete efficient modeling of the subject's blood pressure regulation response even when the number of samples is limited, thereby enhancing the adaptability and precision control capabilities of the blood pressure electrical stimulator under conditions of biomedical individual differences;

[0032] By constructing a generalized linear regression model of the physiological response curve and introducing a feedback regulation mechanism to dynamically adjust the electrical stimulation parameters, a closed-loop control method combining data-driven and mechanism-guided control is achieved. Compared with traditional electrical stimulation strategies based on empirical rules, the method of the present invention is more suitable for the individualized and highly sensitive blood pressure regulation needs in biomedical scenarios, and helps to improve the safety of intervention and the stability of therapeutic efficacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 This is a flow chart of a first embodiment of a data processing method for a blood pressure electrical stimulator according to the present invention.

[0035] Figure 2 The present invention is a device schematic diagram of a data processing method for a blood pressure electrical stimulator. DETAILED DESCRIPTION

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0037] Example 1: Figure 1 2 is a flow chart of a first embodiment of a data processing method for a blood pressure electric stimulator according to the present invention, which provides a first embodiment of a data processing method for a blood pressure electric stimulator according to the present invention.

[0038] In a first embodiment, the data processing method for the blood pressure electrical stimulator includes:

[0039] Step S10: synchronously collect the subject's physiological signals at time t through multiple channels, including the ECG signal s ECG (t), blood pressure waveform signal s BP (t) and the electrical stimulation parameter signal u(t), the three signals are synchronized at the hardware level using a common clock timestamp mechanism, and the electrical stimulation parameter signal u(t) is denoised and feature extracted to obtain the electrical stimulation on / off time sequence;

[0040] It should be noted that in step S10, the step of performing denoising and feature extraction on the electrical stimulation parameter signal u(t) to obtain the electrical stimulation switch time sequence specifically includes: using a first-order difference algorithm to perform mutation edge detection on the electrical stimulation parameter signal u(t), defining the differential signal Δu(t) as: Δu(t) = u(t) - u(t - δt), where δt is a preset sampling period; and then setting the enabling threshold γ on >0 and turn off threshold γ off <0, when Δu(t)>γon When Δu(t)<γ off When the time is reached, it is recognized as the closing moment of an electrical stimulation. Set the stimulus interval threshold T gap Post-process the recognition results, remove repeated recognition events to obtain effective trigger events, and extract them as the electrical stimulation switch time sequence in, are the kth opening time and closing time Used for subsequent physiological response time window construction.

[0041] It can be understood that by performing first-order differential mutation detection on the electrical stimulation parameter signal in the above-mentioned way, and combining the threshold judgment and minimum interval screening mechanism, it is possible not only to accurately extract the start and end times of the electrical stimulation event under a complex noise background, but also to effectively eliminate the misidentification caused by signal jitter or pulse tails, thereby significantly improving the robustness of event positioning and the accuracy of timing annotation.

[0042] It should be understood that the extracted sequence of electrical stimulation on-off moments serves as the temporal anchor for subsequent physiological response modeling, affecting the accuracy of the response data window construction and the timeliness of feature extraction. This step establishes a data segmentation basis for event-driven modeling, ensuring that the subsequent fitting of individual response curves has clear causal boundaries and temporal continuity, meeting the practical requirements of biomedical data processing for high temporal resolution and low-error trigger identification.

[0043] Step S20: Obtain the kth on-time from the electrical stimulation on-off time sequence and closing time And start time and closing time Centered and extended forward by Δt b seconds, expand backward Δt r seconds, forming the physiological response time window W locked to the stimulus event (k) , in each W (k) Extract the ECG signal after hardware-level synchronization ECG (t), blood pressure waveform signal s BP (t) and electrical stimulation parameter signal u(t), construct the response data set D for each stimulation (k) ;

[0044] It should be noted that the physiological response window W (k) The construction method can flexibly configure the central reference point according to specific application requirements. For example, the "on time" of electrical stimulation is used as the anchor point to analyze the physiological changes immediately after the stimulation is triggered, or the "off time" is used as the anchor point to analyze the recovery process after the stimulation is terminated. The set Δtb (forward-looking duration) and Δt r (Backview duration) can be empirically tuned in combination with physiological response delay characteristics to ensure that the response process can be fully covered. Dataset D (k) The extracted multi-source signal segments maintain temporal consistency and channel alignment, ensuring a unified input basis for modeling.

[0045] It can be understood that by constructing a short time window with front and back buffers around each electrical stimulation event, not only can the local physiological response dynamics be effectively captured, but the original continuous signal can also be divided into structured segments, which is convenient for subsequent feature extraction, vector construction and model fitting; compared with the traditional whole-segment sliding window method, this event-driven time window segmentation method can achieve higher physiological relevance and computational efficiency.

[0046] It should be understood that the accuracy of constructing the stimulus-locked response time window, as the data structure unit for individual modeling, directly affects the accuracy and timeliness of physiological response feature extraction and serves as a critical input boundary for subsequent learning of individual response functions. The time window dataset constructed using this method not only has a unified time reference but also enhances the explicitness of causal relationships during model training, meeting the requirements of "time-dependent modeling" in biomedical signal processing.

[0047] Step S30: For each physiological response time window W (k) , for the constructed response data set D (k) Extract physiological response features and obtain heart rate variation feature ΔHR (k) , systolic blood pressure change rate characteristics ΔSBP (k) and stimulus intensity statistical characteristics The above features are vector normalized to form the individual response data vector x (k) ;

[0048] It should be noted that in step S30, the heart rate variation rate characteristic in, represents the Δt after the kth electrical stimulation event is initiated r Average heart rate in seconds, Δt before the kth electrical stimulation event b Average heart rate within seconds; systolic blood pressure change rate characteristics in, is Δt after the kth electrical stimulation event is initiated r The average systolic blood pressure within a second, Δt before the kth electrical stimulation event b Average systolic blood pressure within seconds; statistical characteristics of stimulus intensity where |u(t)| is the instantaneous amplitude of the stimulus signal at time t before and after the kth event.

[0049] It's understandable that by separately calculating the average heart rate and systolic blood pressure change rate before and after electrical stimulation, we can capture the macroscopic trend of the direct impact of stimulation on autonomic nervous system activity and hemodynamics. Introducing the time-averaged stimulus intensity as a dose indicator further establishes a quantitative mapping between physiological responses and input dose. Together, these three construct a low-dimensional yet highly interpretable individualized response vector, enabling stable modeling even with relatively small amounts of data.

[0050] It should be understood that this step significantly improves the specificity and versatility of data modeling by extracting and normalizing the target physiological change characteristics from the structured time window. The constructed individual response vector not only forms the input basis for the subsequent regression model but also possesses good generalizability and clinical interpretability, forming the foundation for the present invention's implementation of small-sample, multi-channel collaborative modeling in biomedicine.

[0051] Step S40: Use the generalized linear regression method to construct a physiological response curve regression model, and transform the individual response data vector x (k) Mapped to blood pressure regulation response output value y (k) ;

[0052] It should be noted that in step S40, the blood pressure adjustment response output value Among them, θ1, θ2, θ3 are individual response weight parameters, ε (k) is the modeling error term. The physiological response curve regression model is used to characterize the blood pressure regulation response characteristics of the individual under different electrical stimulation doses; the individual response weight parameters θ1, θ2, and θ3 are estimated using the least squares method, and the calculation formula is: in, are the individual response weight parameters θ1, θ2, θ3 to be solved; X is the input feature matrix, and each line is the standardized feature vector of the kth stimulus Y is the blood pressure regulation response output value y corresponding to each stimulus (k) Column vector of response results; is the Moore-Penrose pseudoinverse matrix of the least squares solution.

[0053] It is understandable that the use of generalized linear regression to construct a physiological response curve regression model can automatically learn the sensitivity and directionality of the subjects to changes in electrical stimulation intensity from the physiological response characteristics of the subjects. The resulting response weight parameters have clear biomedical interpretation within the model, corresponding to autonomic nervous system regulation, vascular reactivity and dose-effect intensity, respectively, and can effectively support subsequent prediction and control.

[0054] It should be understood that by using the least squares method for parameter fitting, this step can not only achieve rapid model convergence under the condition of a small number of samples, but also use historical response data to construct a stable individualized response function.

[0055] Step S50: Input feature x for the k+1th electrical stimulation (k+1) , the fitted physiological response curve regression model is used to predict the k+1th blood pressure regulation response output value y (k+1) , when the blood pressure regulation response output value y (k+1) Less than the preset desired target threshold y target When the closed-loop feedback regulation mechanism is executed.

[0056] It should be noted that, in step S50 , the fitting data set in the fitting process of the physiological response curve regression model comes from the previous n completed electrical stimulation events in the historical data.

[0057] It is understandable that by performing forward predictions based on individual models constructed based on historical response samples, it is possible to predict the trend of the current electrical stimulation control effect without adding additional physiological burden, thereby identifying inefficient responses in advance and actively intervening in regulation, thereby improving the timeliness and initiative of regulation.

[0058] It should be understood that this closed-loop feedback control mechanism is based on a predictive logic that combines data-driven and individual modeling, realizing a quantitative closed-loop mapping between stimulation parameters and blood pressure regulation effects. Compared with traditional fixed stimulation modes or manual parameter adjustment methods, it can continuously correct stimulation strategies in a dynamic environment, ensuring that the blood pressure regulation system has higher individual adaptability, robustness and long-term safety, and meeting the needs of personalized response regulation in biomedical scenarios.

[0059] Embodiment 2: In addition, the present invention provides a data processing system for a blood pressure electrical stimulator, which adopts a data processing method for a blood pressure electrical stimulator in the above embodiment, and can solve the technical problem of data processing for a blood pressure electrical stimulator. Compared with the prior art, the beneficial effects of the data processing system for a blood pressure electrical stimulator provided by the present invention are the same as the beneficial effects of the data processing method for a blood pressure electrical stimulator provided by the above embodiment, and the other technical features of the data processing system for a blood pressure electrical stimulator are the same as the features disclosed in the above embodiment method, which are not described in detail here.

[0060] Example 3: The present invention provides a data processing device for a blood pressure electrical stimulator, please refer to Figure 2A data processing device for a blood pressure electrostimulator includes at least one processor and a memory connected to the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the data processing method for a blood pressure electrostimulator in Embodiment 1. The data processing device for a blood pressure electrostimulator in the embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and car terminals (e.g., car navigation terminals), and fixed terminals such as digital TVs and desktop computers. The data processing device for a blood pressure electrostimulator is merely an example and should not limit the functions and use range of the embodiments of the present application. The data processing device for a blood pressure electrostimulator can include a processing device 1001 (e.g., a central processing unit, a graphic processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or loaded from a storage device 1003 to a random access memory (RAM) 1004. Various programs and data required for the operation of the data processing device for a blood pressure electrostimulator are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. In general, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication devices 1009 can allow the data processing device for a blood pressure electrostimulator to communicate with other devices wirelessly or by wire to exchange data. Although the data processing device for a blood pressure electrostimulator with various systems is shown in the figure, it should be understood that all the shown systems are not required to be implemented or provided. More or less systems can be alternatively implemented or provided.

[0061] Embodiment four: the application further provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of a data processing method for a blood pressure electrical stimulator as described above. The computer program product provided by the application can solve the technical problem of data processing for a blood pressure electrical stimulator. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the data processing method for a blood pressure electrical stimulator provided by the above-described embodiments, and are not described here.

[0062] In particular, according to the embodiments disclosed by the application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments disclosed by the application include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by a processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed by the application are executed.

[0063] It should be understood that various parts of the application disclosed can be realized in hardware, software, firmware or a combination thereof. In the description of the above-described embodiments, specific features, structures, materials or characteristics can be combined in any appropriate manner in any one or more embodiments or examples.

[0064] Obviously, those skilled in the art can make various modifications and variations to the application without departing from the spirit and scope of the application. Thus, if these modifications and variations of the application fall within the scope of the claims of the application and their equivalent technologies, the application also intends to include these modifications and variations.

Claims

1. A data processing method for a blood pressure electrical stimulator, characterized in that: Methods include: Step S10: synchronously collect the subject's physiological signals at time t through multiple channels, including the ECG signal s ECG (t), blood pressure waveform signal s BP (t) and the electrical stimulation parameter signal u(t), the three signals are synchronized at the hardware level using a common clock timestamp mechanism, and the electrical stimulation parameter signal u(t) is denoised and feature extracted to obtain the electrical stimulation on / off time sequence; Step S20: Obtain the kth on-time from the electrical stimulation on-off time sequence and closing time And start time and closing time Centered and extended forward by Δt b seconds, expand backward Δt r seconds, forming the physiological response time window W locked to the stimulus event (k) , in each W (k) Extract the ECG signal after hardware-level synchronization ECG (t), blood pressure waveform signal s BP (t) and electrical stimulation parameter signal u(t), construct the response data set D for each stimulation (k) ; Step S30: For each physiological response time window W (k) , for the constructed response data set D (k) Extract physiological response features and obtain heart rate variation feature ΔHR (k) , systolic blood pressure change rate characteristics ΔSBP (k) and stimulus intensity statistical characteristics The above features are vector normalized to form the individual response data vector x (k) ; Step S40: Use the generalized linear regression method to construct a physiological response curve regression model, and transform the individual response data vector x (k) Mapped to blood pressure regulation response output value y (k) ; Step S50: Input feature x for the k+1th electrical stimulation (k+1) , the fitted physiological response curve regression model is used to predict the k+1th blood pressure regulation response output value y (k+1) , when the blood pressure regulation response output value y (k+1) Less than the preset desired target threshold y target When the closed-loop feedback regulation mechanism is executed.

2. A data processing method for a blood pressure electrical stimulator according to claim 1, characterized in that: In step S30, the heart rate variation characteristic in, represents the Δt after the kth electrical stimulation event is initiated r Average heart rate in seconds, Δt before the kth electrical stimulation event b Average heart rate within seconds; systolic blood pressure change rate characteristics in, is Δt after the kth electrical stimulation event is initiated r The average systolic blood pressure within a second, Δt before the kth electrical stimulation event b Average systolic blood pressure within seconds; statistical characteristics of stimulus intensity where |u(t)| is the instantaneous amplitude of the stimulus signal at time t before and after the kth event.

3. The data processing method for a blood pressure electrical stimulator according to claim 1, wherein: In step S40, the blood pressure adjustment response output value Among them, θ1, θ2, θ3 are individual response weight parameters, ε (k) is the modeling error term.

4. A data processing method for a blood pressure electrical stimulator according to claim 3, characterized in that: In step S40, the physiological response curve regression model is used to characterize the blood pressure regulation response characteristics of the individual under different electrical stimulation doses; the individual response weight parameters θ1, θ2, θ3 are estimated by the least squares method, and the calculation formula is: in, are the individual response weight parameters θ1, θ2, θ3 to be solved; X is the input feature matrix, and each line is the standardized feature vector of the kth stimulus Y is the blood pressure regulation response output value y corresponding to each stimulus (k) Column vector of response results; is the Moore-Penrose pseudoinverse matrix of the least squares solution.

5. The data processing method for a blood pressure electrical stimulator according to claim 1, wherein: In step S10, the steps of performing denoising and feature extraction on the electrical stimulation parameter signal u(t) to obtain the electrical stimulation on / off time sequence specifically include: The first-order difference algorithm is used to detect the edge of the electrical stimulation parameter signal u(t). The differential signal Δu(t) is defined as: Δu(t) = u(t) - u(t - δt), where δt is the preset sampling period and u(t - δt) is the differential signal at time t - δt. Then set the enable threshold γ on >0 and turn off threshold γ off <0, when: Δu(t)>γ on When Δu(t)<γ off When the time is reached, it is recognized as the closing moment of an electrical stimulation. Set the stimulus interval threshold T gap Post-process the recognition results, remove repeated recognition events to obtain effective trigger events, and extract them as the electrical stimulation switch time sequence in, are the kth opening time and closing time Used for subsequent physiological response time window construction.

6. The data processing method for a blood pressure electrical stimulator according to claim 1, wherein: In step S50 , the fitting data set in the fitting process of the physiological response curve regression model comes from the previous n completed electrical stimulation events in the historical data.

7. The data processing method for a blood pressure electrical stimulator according to claim 1, wherein: In step S20, 8. A data processing system for a blood pressure electrical stimulator, applied to a data processing method for a blood pressure electrical stimulator according to any one of claims 1 to 7, characterized in that: The data processing system for the blood pressure electrical stimulator comprises: Multi-channel synchronous acquisition and trigger recognition module, used to synchronously acquire the subject's physiological signals at time t through multiple channels, including the ECG signal s ECG (t), blood pressure waveform signal s BP (t) and the electrical stimulation parameter signal u(t), the three signals are synchronized at the hardware level using a common clock timestamp mechanism, and the electrical stimulation parameter signal u(t) is denoised and feature extracted to obtain the electrical stimulation on / off time sequence; Response time window construction and data set generation module, used to obtain the kth on-off moment from the electrical stimulation on-off moment sequence and closing time And start time and closing time Centered and extended forward by Δt b seconds, expand backward Δt r seconds, forming the physiological response time window W locked to the stimulus event (k) , in each W (k) Extract the ECG signal after hardware-level synchronization ECG (t), blood pressure waveform signal s BP (t) and electrical stimulation parameter signal u(t), construct the response data set D for each stimulation (k) ; Response feature extraction and vector normalization module is used for each physiological response time window W (k) , for the constructed response data set D (k) Extract physiological response features and obtain heart rate variation feature ΔHR (k0 , systolic blood pressure change rate characteristics ΔSBP (k) and stimulus intensity statistical characteristics The above features are vector normalized to form the individual response data vector x (k) ; Physiological response modeling module is used to construct physiological response curve regression model by using generalized linear regression method, and transform individual response data vector x (k) Mapped to blood pressure regulation response output value y (k) ; Closed-loop feedback control module for the k+1th electrical stimulation input feature x (k+1) , the fitted physiological response curve regression model is used to predict the k+1th blood pressure regulation response output value y (k+1) , when the blood pressure regulation response output value y (k+1) Less than the preset desired target threshold y target When the closed-loop feedback regulation mechanism is executed.

9. A data processing device for a blood pressure electrical stimulator, characterized in that: The data processing device for the blood pressure electric stimulator includes: a memory, a processor, and a data processing program for the blood pressure electric stimulator stored in the memory and executable on the processor. When the data processing program for the blood pressure electric stimulator is executed by the processor, a data processing method for the blood pressure electric stimulator according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The computer program product includes a data processing program for a blood pressure electrical stimulator, and when the data processing program for a blood pressure electrical stimulator is executed by a processor, a data processing method for a blood pressure electrical stimulator according to any one of claims 1 to 7 is implemented.

Images