Intelligent closed-loop hypertension management method and system based on wearable device and wearable device

Abstract

The invention belongs to the technical field of blood pressure management, and provides an intelligent closed-loop hypertension management method, system and equipment based on wearable equipment, and the method comprises the steps: applying controllable peripheral pressure to the body of a user through the wearable equipment, and inducing local blood flow change in a pressed area; according to the method, the peripheral pressure stimulation and blood pressure monitoring are combined, continuous blood pressure signals of a user are collected in real time, the instantaneous reference blood pressure value of the continuous blood pressure signals is calibrated, the system can dynamically adjust the peripheral pressure currently applied by the wearable device and regulation and control parameters after calibration, a self-adaptive closed loop is formed by peripheral pressure stimulation and blood pressure monitoring, and pressure stimulation can be applied again according to needs. According to the scheme, controllable peripheral pressure stimulation and undisturbed continuous blood pressure monitoring are combined, real-time self-adaptive hemodynamic adjustment and intelligent closed-loop control are achieved, a continuous and real-time intelligent closed-loop hypertension management mechanism is constructed, blood pressure management covering all time periods and all scenes can be achieved, and the blood pressure monitoring accuracy is improved. The composition is suitable for hypertension regulation and control, cardiovascular and cerebrovascular disease prevention and individualized treatment assistance.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of blood pressure management, and particularly relates to an intelligent closed-loop high blood pressure management method and system based on a wearable device and a wearable device. BACKGROUND

[0002] Abnormal blood pressure, especially high blood pressure, is a major risk factor for cardiovascular and cerebrovascular diseases, and long-term effective blood pressure monitoring and management is crucial for disease prevention, diagnosis and treatment. In terms of blood pressure regulation, existing methods mainly rely on long-term adjustment of drug therapy and lifestyle, which have a slow effect and are difficult to respond quickly to immediate fluctuations in blood pressure.

[0003] Recent studies have shown that a short-term ischemia-reperfusion process induced by intermittent and controllable local external pressure stimulation can promote vasodilation, improve microcirculation and endothelial function, and has a positive effect on blood pressure control and prevention of cardiovascular and cerebrovascular events, and has the advantages of non-invasiveness, safety and immediate response. However, existing external pressure stimulation devices and training methods still have the following shortcomings: 1. Lack of continuous monitoring capability of blood pressure and hemodynamics, unable to real-time perceive individual physiological state; 2. Unable to automatically adjust stimulation intensity, duration or rhythm according to individual immediate response to external pressure; 3. Lack of safety mechanism and quantitative evaluation method based on physiological feedback; 4. External pressure stimulation and continuous blood pressure monitoring are not linked, lacking adaptive closed-loop control capability.

[0004] At the same time, existing high blood pressure management systems often separate monitoring, intervention and evaluation, making it difficult to support dynamic blood flow regulation and individualized trend management based on immediate state. Therefore, it is necessary to build an intelligent closed-loop system that deeply integrates external pressure regulation and continuous blood pressure monitoring, and realizes adaptive parameter adjustment based on biological feedback, to more finely support long-term management and individualized regulation of high blood pressure. SUMMARY

[0005] In order to overcome the defects of the prior art, the application provides an intelligent closed-loop high blood pressure management method based on a wearable device, which comprises: In response to a pressure signal, a wearable device applies pressure to a specified area of a user's body based on preset regulation parameters, inducing local blood flow changes in the pressure area to regulate hemodynamic state; Real-time acquisition of continuous blood pressure signals and instantaneous reference blood pressure values of the user, and dynamic calibration of the continuous blood pressure signals by the instantaneous reference blood pressure values; dynamically adjusting the pressure currently applied by the wearable device and / or the regulation parameters based on the calibrated continuous blood pressure signal; the regulation parameters include pressure value, pressure duration and pressure interval time; making the wearable device perform the next stage of pressure application based on the updated regulation parameters, so as to form an adaptive closed-loop regulation of peripheral pressure stimulation and continuous blood pressure monitoring.

[0006] Specifically, the method further comprises: After applying pressure by the wearable device, detecting the pressure fluctuation characteristics in the pressure area to obtain deformation amplitude data of the pressure-time curve reflecting the elasticity of the tissue and the compliance of the blood vessels, pressure recovery speed data of the inflation and deflation process reflecting the local blood perfusion characteristics, and phase difference data and / or amplitude difference data of the physiological sensing signal reflecting the response degree of the blood vessels under the tissue to external pressure; the physiological sensing signal is one or more of optical signal, mechanical signal, electrical / impedance signal, acoustic signal or ultrasonic signal.

[0007] Specifically, the dynamically adjusting the pressure currently applied by the wearable device and / or the regulation parameters based on the calibrated continuous blood pressure signal comprises: when the calibrated continuous blood pressure signal is higher than a first preset threshold, reducing the pressure value of the preset pressure currently applied or stopping the preset pressure currently applied, and correspondingly prolonging the pressure interval time; when the calibrated continuous blood pressure signal is lower than a second preset threshold, correspondingly increasing the pressure value, correspondingly prolonging the pressure duration, and / or correspondingly shortening the pressure interval time; the second preset threshold is lower than the first preset threshold; and / or, based on the historical blood pressure data, the physiological signals obtained by the wearable device and / or the individual characteristics of the user, performing feature extraction and correlation analysis and completing a trained regulation model, establishing a mapping relationship between blood pressure change, the regulation parameters and individual response of the user through the regulation model, and adjusting the pressure currently applied by the wearable device and / or the regulation parameters based on the mapping relationship.

[0008] Specifically, the method of collecting the continuous blood pressure signal of the user and dynamically calibrating comprises: acquiring physiological signals collected by at least one of optical, pressure, electrical, impedance, strain, acoustic, ultrasonic sensors, which characterize the changes of tissue or blood vessels with cardiac cycle; preprocessing and feature extraction are performed on the physiological signals, and the features are input into a trained blood pressure signal conversion model; calibrating the blood pressure signal conversion model with the instantaneous reference blood pressure value as reference blood pressure information, so that the model outputs a blood pressure signal waveform representing continuous blood pressure changes as the calibrated continuous blood pressure signal.

[0009] Further, processing the electrical signal includes: preprocessing the physiological signal and the pressure application signal to generate time-synchronized time series signals; extracting features from the time series signals and mapping the extracted features to a unified feature space to form a feature signal; performing time series fusion, semantic fusion and / or hierarchical fusion on the feature signal based on a feature fusion mechanism to generate a fusion feature vector for input to a blood pressure signal conversion model.

[0010] Preferably, the method further includes: detecting pulse waveforms at at least two measurement points on the same arterial path of the user; obtaining distribution characteristics reflecting local blood perfusion, vascular reactivity and microcirculation perfusion state based on time domain differences, amplitude differences and / or waveform morphology differences between adjacent measurement points in each group; evaluating the local hemodynamic state of the arterial path according to the distribution characteristics, and dynamically adjusting the current applied pressure of the wearable device and / or the regulation parameters accordingly.

[0011] Preferably, the method further includes: obtaining individual characteristic parameters of the user; inputting the calibrated continuous blood pressure signal of the user, physiological response data related to applied pressure and individual characteristic parameters as input data into a trained intelligent analysis model; analyzing the blood pressure response relationship of the user under different external pressures and different drug doses through the intelligent analysis model, predicting the optimal drug administration combination, and outputting a personalized auxiliary prescription scheme including individualized drug dose, administration frequency, administration time, synergistic plan of drug and physical regulation, drug reminder information and / or physiotherapy reminder information; based on the personalized auxiliary scheme, providing drug or physiotherapy reminders, generating a synergistic execution scheme of antihypertensive drugs and physical regulation, and / or controlling a transdermal or microneedle automatic drug delivery device to administer drugs.

[0012] Optionally, the specified regions include upper arm regions, wrist regions, hand regions, foot regions and / or ankle regions, and each of the specified regions corresponds to independent regulation parameters.

[0013] The application further provides a wearable device-based intelligent closed-loop hypertension management system, which comprises: a peripheral pressure regulation module configured to respond to the pressure signal and apply pressure to a specified region of the user's body based on preset regulation parameters through the wearable device to induce local blood flow changes in the pressure region to regulate hemodynamic state; a blood pressure monitoring module configured to collect continuous blood pressure signals and instantaneous reference blood pressure values of the user in real time and dynamically calibrate the continuous blood pressure signals based on the instantaneous reference blood pressure values; an intelligent control module configured to dynamically adjust the pressure currently applied by the wearable device and / or the regulation parameters based on the calibrated continuous blood pressure signals and enable the wearable device to perform pressure application in the next stage based on the updated regulation parameters, so that peripheral pressure stimulation and continuous blood pressure monitoring form an adaptive closed-loop regulation; the regulation parameters include pressure value, pressure duration and pressure interval time.

[0014] The application further provides a wearable device, which applies the wearable device-based intelligent closed-loop hypertension management method as described above.

[0015] The application has at least the following beneficial effects: The scheme provided by the application can trigger pressure intervention at the initial stage of abnormal blood pressure fluctuation by monitoring blood pressure in real time and combining preset or learned regulation parameters, realizes closed-loop control from perception, decision-making to execution, changes passive management to active regulation, effectively makes up for the hysteresis of traditional methods, dynamically adjusts pressure value, duration and interval time based on continuously calibrated blood pressure data, matches intervention intensity with the current physiological state of the user, realizes individualized adaptive blood pressure management, avoids the problems of insufficient or excessive stimulation that may exist in the fixed parameter mode, improves individualized treatment accuracy and safety, can realize all-weather blood pressure management coverage, and greatly reduces the risk of high blood pressure at night; Further, the scheme provided by the application can simultaneously obtain dynamic indicators of vascular function and tissue characteristics, provide more abundant parameters for pressure regulation, realize individualized physiological response of individual users to specific pressure parameter combinations on the basis of standardized regulation by setting thresholds and training models combined with historical data, and thus improve the effectiveness of intervention, ensure the quality of signals through fine processing and model calibration of photoelectric signals, and can convert original signals into a fusion feature vector that can fully reflect the physiological state of blood pressure, provide input data with high information density, low noise and strong representation ability for the model, and greatly improve the continuous blood pressure measurement accuracy and long-term stability; In addition, the scheme provided by the application can also realize blood flow distribution evaluation by comparing the pulse wave arrival time and amplitude of different points on the same arterial path, and the scheme can set independent regulation parameters for different regions, perform regional optimization precise intervention, thereby realizing local dynamic microcirculation dynamic regulation, and the scheme can also generate an individualized auxiliary prescription by combining an intelligent analysis model, thereby realizing deep cooperation between physical therapy and drug therapy.

[0016] Therefore, the application provides an intelligent closed-loop hypertension management method and system based on a wearable device and a wearable device, the scheme provided by the application combines controllable peripheral pressure stimulation and disturbance-free continuous blood pressure monitoring, realizes real-time adaptive hemodynamic regulation and intelligent closed-loop control, constructs a continuous and real-time intelligent closed-loop hypertension management mechanism, and can realize blood pressure management covering all time periods and all scenes, and is suitable for hypertension regulation, cardiovascular and cerebrovascular disease prevention and individualized treatment assistance. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0018] Figure 1 The method flowchart of the intelligent closed-loop hypertension management method based on a wearable device provided for embodiment 1 is shown in the figure. Figure 2 The example diagram of the wearable device is shown in the figure. Figure 3 The example diagram of the wearable device worn by the user on multiple parts of the body is shown in the figure. Fig. 4(a)-Fig. 4(b) are schematic diagrams of the pressure sensor of the blood pressure monitoring sensor and the pressure regulation component in a separate distribution mode. Figure 5 The example diagram for realizing local microcirculation detection is shown in the figure. Figure 6 The example diagram of integrating multiple sensors on the same wearable device is shown in the figure. Figure 7 The method flowchart of collecting and calibrating continuous blood pressure signals is shown in the figure. Figure 8 The method flowchart for realizing drug management is shown in the figure. Figure 9 The overall architecture example diagram of the regulation system is shown in the figure. Figure 10 The module structure schematic diagram of the intelligent closed-loop hypertension management system based on a wearable device provided by embodiment 2 is shown in the figure. Figure 11 An APP interface diagram for realizing blood pressure management. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0020] Hereinafter, various embodiments of the present application will be described more fully. The present application can have various embodiments, and adjustments and changes can be made therein. However, it is understood that there is no intention to limit various embodiments of the present application to the specific embodiments disclosed herein, but the present application should be understood to encompass all adjustments, equivalents and / or alternatives falling within the spirit and scope of various embodiments of the present application.

[0021] Hereinafter, the term "include" or "may include" used in various embodiments of the present application indicates the presence of the disclosed functions, operations or elements, and does not limit the addition of one or more functions, operations or elements. In addition, as used in various embodiments of the present application, the terms "include", "have" and their synonyms only mean to indicate the presence of a specific feature, number, step, operation, element, component or combination of the foregoing, and should not be understood as first excluding the presence or addition of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing.

[0022] In various embodiments of the present application, the expression "or" or "at least one of A or / and B" includes any combination of the listed terms or all combinations thereof. For example, the expression "A or B" or "at least one of A or / and B" can include A, can include B, or can include both A and B.

[0023] The expressions (such as "first", "second", etc.) used in various embodiments of the present application can modify various constituent elements in various embodiments, but can not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only for the purpose of distinguishing one element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of various embodiments of the present application, a first element can be referred to as a second element, and likewise, a second element can be referred to as a first element.

[0024] It should be noted that in the present application, unless otherwise explicitly specified and defined, the terms such as "mounting", "connecting", "fixing" and the like should be understood in a broad sense, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be direct connection, or indirect connection through intermediate medium; it can be internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0025] In the present application, those skilled in the art need to understand that the terms indicating the orientation or positional relationship herein are based on the orientation or positional relationship shown in the drawings, which is only for the purpose of facilitating the description of the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0026] The terms used in various embodiments of the present application are used only for the purpose of describing specific embodiments and are not intended to limit various embodiments of the present application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly dictates otherwise. Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which various embodiments of the present application belong. The terms (such as those defined in a commonly used dictionary) will be interpreted to have the same meaning as the contextual meaning in the relevant technical field and will not be interpreted to have an idealized or overly formal meaning, unless clearly defined in various embodiments of the present application.

[0027] Embodiment 1 See Figure 1 The present embodiment proposes a smart closed-loop hypertension management method based on wearable devices. The method proposed in the present embodiment can realize hemodynamic regulation and intelligent closed-loop control by combining variable external pressure stimulation with continuous blood pressure monitoring, and is suitable for hypertension regulation, cardiovascular disease prevention and individualized treatment assistance. The method specifically comprises: S100: In response to the pressure signal, the wearable device applies pressure to the specified area of the user's body based on the preset regulation parameters, induces local blood flow changes in the pressure area to achieve regulation of hemodynamic state.

[0028] Specifically, the method proposed in this embodiment can detect the pressure fluctuation characteristics in the pressure area after applying pressure through the wearable device, to obtain the deformation amplitude data of the pressure-time curve reflecting the elasticity of the tissue and the compliance of the blood vessels, the inflation and deflation process pressure recovery speed data reflecting the local blood perfusion characteristics, and / or the phase difference data and / or amplitude difference data of the physiological sensing signal reflecting the response degree of the blood vessels under the tissue to external pressure. Optionally, the physiological sensing signal can include but is not limited to optical signal, mechanical signal, electrical / impedance signal, acoustic signal, ultrasonic signal.

[0029] Referring to Figure 2 In this embodiment, step S100 can be implemented by a cuff or other wearable device capable of applying pressure. The wearable device can provide the function of achieving diastolic and relaxation for the user through low-intensity periodic external pressure stimulation. In an optional embodiment, the wearable device can include a gas bag, a micropump or a motor actuating mechanism as a driving unit for driving the wearable device to apply pressure.

[0030] Optionally, referring to Figure 3 The specified area can include but is not limited to upper arm area, wrist area, hand area, foot area, ankle area, each specified area corresponding to independent control parameters, and the wearable devices arranged on different specified areas can work cooperatively or in a split interaction mode, thereby realizing the integrated function of continuous blood pressure monitoring and peripheral pressure regulation at different parts, and improving the signal stability and measurement accuracy.

[0031] S200: Real-time acquisition of continuous blood pressure signal and instantaneous reference blood pressure value of the user, and dynamic calibration of the continuous blood pressure signal through the instantaneous reference blood pressure value.

[0032] In this embodiment, step S200 can realize snapshot blood pressure measurement and obtain the instantaneous reference blood pressure value through the oscillation method, and dynamically calibrate the continuous blood pressure signal through the instantaneous reference blood pressure value, to realize the monitoring and error correction of the continuous blood pressure signal. Referring to FIG. 4(a)-4(b), in an optional embodiment, step S200 can be implemented by at least one continuous blood pressure monitoring sensor. The continuous blood pressure monitoring sensor can include but is not limited to a photoplethysmography sensor (PPG), a tonometry sensor, etc. The continuous blood pressure monitoring sensor can acquire physiological signals related to continuous blood pressure, obtain uncalibrated continuous blood pressure signals through modeling of the physiological signals, and then perform calibration processing on the continuous blood pressure signals to obtain calibrated continuous blood pressure signals.

[0033] S300: dynamically adjusting the pressure applied by the wearable device and / or the regulation parameters based on the calibrated continuous blood pressure signal, so that the wearable device performs the next stage of pressure application based on the updated regulation parameters, thereby forming an adaptive closed-loop regulation of the peripheral pressure stimulation and the continuous blood pressure monitoring.

[0034] In this embodiment, the regulation parameters include pressure value, pressure duration and pressure interval time. Through the feedback control of the process of applying and releasing pressure in step S300, dynamic and closed-loop blood pressure management and regulation can be achieved.

[0035] Specifically, the dynamic adjustment of the pressure applied by the wearable device and / or the regulation parameters based on the calibrated continuous blood pressure signal in step S300 includes: When the calibrated continuous blood pressure signal is higher than the first preset threshold, the pressure value of the preset pressure applied currently is reduced or the preset pressure applied currently is stopped, and the pressure interval time is correspondingly extended; When the calibrated continuous blood pressure signal is lower than the second preset threshold, the pressure value is correspondingly increased, the pressure duration is correspondingly extended, and / or the pressure interval time is correspondingly shortened; the second preset threshold is lower than the first preset threshold; And / or, based on the historical blood pressure data, the physiological signals obtained by the wearable device and / or the individual characteristics of the user, the feature extraction and correlation analysis are performed and the regulation model is trained, the mapping relationship between the blood pressure change, the regulation parameters and the individual response of the user is established through the regulation model, and the pressure applied by the wearable device and / or the regulation parameters are adjusted based on the mapping relationship.

[0036] Preferably, the method proposed in this embodiment can also upload data to the cloud, and continuously update and optimize the regulation model through the data of the cloud, realize long-term trend analysis and self-adaptation of individual differences, and thus better ensure that the blood pressure of the user can always be maintained within a certain range.

[0037] Preferably, referring to Figure 5 The method proposed in this embodiment can also detect pulse waveforms at at least two measurement points on the same arterial path of the user, obtain distribution characteristics reflecting local blood perfusion and vascular reactivity based on the time domain difference, amplitude difference and / or waveform morphology difference between adjacent measurement points in each group, and the distribution characteristics can also be used to reflect the microcirculation perfusion state; then the local hemodynamic state of the arterial path can be evaluated according to the distribution characteristics, and the pressure applied by the wearable device and / or the regulation parameters are dynamically adjusted accordingly; this method can replace the traditional double-finger palpation to realize microcirculation monitoring, and through multi-point signal input, peak detection and delay calculation, perfusion index and peak ratio parameters are output to reflect the local blood perfusion and reperfusion state.

[0038] Specifically, referring toFigure 6 The step of detecting the pulse waveform at at least two measuring points on the same arterial path of the user can be realized by multi-point signal differential analysis of multiple photoplethysmogram sensors and / or tension sensors; Preferably, the method proposed in the embodiment can also collect pulse waveform signals at multiple local positions through array photoplethysmogram sensors or tension sensors, and realize two-dimensional imaging of local blood pressure and blood flow distribution through time delay, wave peak ratio and perfusion index analysis, thereby realizing the functions of evaluating vascular compliance, perfusion recovery efficiency and microcirculation functional state.

[0039] In an optional implementation, by detecting the wave peak arrival time, rising time, reflected wave delay and other key timing characteristics of the pulse waveform at each measuring point, the time difference between adjacent measuring points can be calculated And the pulse waveform peak value or pulsation amplitude difference between adjacent measuring points ; Among them, Can reflect the changes of local pulse wave propagation speed and vascular compliance, when the local vascular resistance increases or the blood perfusion is insufficient, the pulse wave propagation speed will slow down, Correspondingly increase, Then it can reflect the local blood vessel volume change and stroke volume distribution, when the local reperfusion is insufficient, the pulsation amplitude will decrease or the waveform will become blunt.

[0040] On this basis, the method proposed in the embodiment can calculate the local microcirculation perfusion index for judging the local perfusion and reperfusion state by joint analysis of And Thus, without additional pressure intervention, the quantitative evaluation of microcirculation state can be realized only by differential analysis of multi-point optical or tension signals, replacing the traditional empirical judgment of double finger palpation, and the formula for calculating the local microcirculation perfusion index can include:

[0041] Among them, Represents the local microcirculation perfusion index, Represents the reference amplitude value normalized to , Represents the reference time value normalized to , And Respectively represent And The contribution weight of the local microcirculation perfusion index.

[0042] Specifically, please refer to Figure 7, the method of acquiring the continuous blood pressure signal of the user and performing dynamic calibration in step S200 includes: S210: acquiring a physiological signal representing changes in tissue or blood vessels over a cardiac cycle, collected by at least one of an optical, pressure, electrical, impedance, strain, acoustic, and ultrasonic sensor.

[0043] Illustratively, step S210 can acquire an optical signal received by a photodetector in a photoplethysmographic sensor from a light-emitting device and converted into an electrical signal including a direct current component and an alternating current component. It should be noted that the direct current component contains information about tissue and average blood absorption, and the alternating current component contains information about blood volume fluctuations that change with the heart.

[0044] S220: pre-processing and feature extraction of the physiological signal, and inputting the features into the trained blood pressure signal conversion model.

[0045] Illustratively, the processing of the electrical signal in step S220 can specifically include: multi-layer filtering and synchronization processing of the electrical signal and the pressure signal to generate time-synchronized time series signals; extracting features of the time series signals, mapping numerical features with different physical units contained in the time series signals to the same interval, and encoding discrete variables contained in the time series signals to obtain feature signals; and then integrating the extracted features through a single-layer or multi-layer fusion mechanism of time series fusion, semantic fusion, and / or hierarchical fusion to generate a unified fusion feature vector as a processing result of the input blood pressure signal conversion model.

[0046] S230: dynamically parameterizing the blood pressure signal conversion model with the instantaneous reference blood pressure value as the reference blood pressure information, so that the model outputs a blood pressure signal waveform representing continuous blood pressure changes as the calibrated continuous blood pressure signal.

[0047] Preferably, referring to Figure 8 The method proposed in this embodiment further includes: S410: acquiring individual characteristic parameters of the user.

[0048] In this embodiment, the individual characteristic parameters of the user can include but are not limited to the user's age, gender, BMI, medication history, drug sensitivity, and the like.

[0049] S420: inputting the calibrated continuous blood pressure signal of the user, the physiological response data related to the applied pressure, and the individual characteristic parameters as input data into the trained intelligent analysis model.

[0050] In this embodiment, the intelligent analysis model used in step S420 can include the regulation model that establishes the mapping relationship between blood pressure changes, regulation parameters, and individual responses of the user in step S300.

[0051] S430: Analyzing the blood pressure response relationship of the user under different external pressures and different drug doses through the intelligent analysis model, predicting the optimal drug administration combination, and outputting the individualized auxiliary prescription scheme containing individualized drug dose, administration frequency, medication time, drug and physical regulation coordination plan, drug reminder information and / or physiotherapy reminder information.

[0052] S440: Providing drug or physiotherapy reminders based on the individualized auxiliary scheme, generating a coordinated execution scheme for antihypertensive drugs and physical regulation, and / or controlling the transdermal or microneedle automatic drug delivery device to administer the drug.

[0053] Illustratively, step S440 can provide oral drug administration reminders for the user, or automatically administer the drug through transdermal or microneedle.

[0054] In an optional embodiment, please refer to Figure 9 The method proposed in this embodiment can be implemented by a regulation system with a data input layer, a preprocessing and feature extraction fusion layer, a machine learning modeling layer, and an external pressure regulation execution layer; In the data input layer, the regulation system can collect multiple types of physiological and environmental data in real time through wearable devices, including blood pressure signals (such as snapshot blood pressure values, TAG signals), peripheral pressure parameters (such as pressure amplitude, duration, and pressure frequency), microcirculation characteristics (such as perfusion recovery time, compliance, and local resistance changes), and individual static parameters (such as age, gender, and drug use history). The above data can constitute cross-modal input, providing a rich basis for time series and individual information for subsequent intelligent modeling; In the preprocessing and feature extraction fusion layer, the regulation system can first perform multi-layer filtering and synchronization processing on signal-type data such as blood pressure and microcirculation signals, and perform data normalization and encoding, unifying different physical quantities such as mmHg, Hz, and s to the [0, 1] interval, and One-Hot encoding for discrete variables. Then, enter the feature extraction and layer fusion stage, automatically extract blood pressure waveform features (such as rise time, peak slope, reflection ratio, PTT), microcirculation features (such as perfusion recovery time, perfusion amplitude ratio, compliance index), external pressure features (such as pressure intensity, dP / dt, and pressure rhythm), and individualized features, and then integrate them through a "time series-semantic-hierarchical" three-layer fusion mechanism to generate a unified fusion feature vector X. In the machine learning modeling layer, the fusion feature vector X is input into the cross-modal machine learning network. The network can adopt a hybrid architecture, for example, a CNN module is used to extract local time-frequency features, an LSTM / GRU is used to capture blood pressure dynamic trends, or a Transformer / Attention structure is used to realize global semantic association between multi-modal features. The model establishes a mapping relationship between the blood pressure change and the peripheral pressure response parameters through supervised learning, and outputs control recommendation parameters including blood pressure change trend and peripheral pressure value , pressure duration , pressure frequency , etc., to provide decision basis for individualized blood pressure control. In the external pressure control execution layer, the control system can generate a control strategy according to the model output, determine the optimal pressure application scheme through the parameter self-adaptive adjustment module, and execute the peripheral pressure regulation operation through the wearable device. Real-time feedback of the execution result will be input into the system again to realize continuous learning and self-adaptive control, so that the blood pressure can be maintained stable within a safe range.

[0055] Embodiment 2 Please refer to Figure 10 , the embodiment proposes an intelligent closed-loop hypertension management system based on a wearable device, which is used to realize the intelligent closed-loop hypertension management method based on a wearable device as proposed in embodiment 1. The system includes: a peripheral pressure control module 10 for responding to a pressure signal and applying pressure to a specified region of a user's body through a wearable device based on preset control parameters to induce local blood flow changes in the pressure region to regulate hemodynamic state; a blood pressure monitoring module 20 for real-time acquisition of continuous blood pressure signals and instantaneous reference blood pressure values of a user, and dynamic calibration of the continuous blood pressure signals through the instantaneous reference blood pressure values; an intelligent control module 30 for dynamically adjusting the pressure applied by the wearable device and / or the control parameters based on the calibrated continuous blood pressure signals, and enabling the wearable device to perform pressure application in the next stage based on the updated control parameters, so that the peripheral pressure stimulation and continuous blood pressure monitoring form an adaptive closed-loop control; the control parameters include pressure value, pressure duration and pressure interval time.

[0056] Optionally, the specified region can include but is not limited to upper arm region, wrist region, hand region, foot region, ankle region, and each specified region corresponds to independent control parameters. The wearable devices arranged on different specified regions can work cooperatively or in a split interaction mode, so as to realize the integrated function of continuous blood pressure monitoring and peripheral pressure control in different parts, and improve signal stability and measurement accuracy.

[0057] Specifically, the intelligent control module 30 implements a manner of dynamically adjusting the current applied pressure and / or regulating parameters of the wearable device based on the calibrated continuous blood pressure signal, including: when the calibrated continuous blood pressure signal is higher than the first preset threshold, reducing the pressure value of the current applied preset pressure or stopping the current applied preset pressure, and correspondingly prolonging the pressure interval time; when the calibrated continuous blood pressure signal is lower than the second preset threshold, correspondingly increasing the pressure value, correspondingly prolonging the pressure duration, and / or correspondingly shortening the pressure interval time; And / or, based on the historical blood pressure data, physiological signals obtained by the wearable device, and / or individual characteristics of the user, feature extraction and correlation analysis are performed and a trained regulating model is completed, a mapping relationship between blood pressure changes, regulating parameters and individual responses of the user is established through the regulating model, and the current applied pressure and / or regulating parameters of the wearable device are adjusted based on the mapping relationship.

[0058] Specifically, the blood pressure monitoring module 20 can obtain physiological signals collected by at least one of optical, pressure, electrical, impedance, strain, acoustic, and ultrasonic sensors, which represent changes in tissue or blood vessels with the cardiac cycle, and pre-process and extract features from the physiological signals. The features are input into the trained blood pressure signal conversion model, so that the instantaneous reference blood pressure value is used as the reference blood pressure information to dynamically calibrate the blood pressure signal conversion model, so that the model outputs a blood pressure signal waveform representing continuous blood pressure changes as a calibrated continuous blood pressure signal.

[0059] Exemplarily, the blood pressure monitoring module 20 can obtain an optical signal received by a photoelectric detector in a photoplethysmographic pulse wave sensor through a light emitting device, and convert it into an electrical signal including a direct current component and an alternating current component. The processing of the electrical signal can specifically include: performing multi-layer filtering and synchronous processing on the electrical signal and the pressure signal to generate time-synchronized time series signals; extracting features of the time series signals, mapping numerical features with different physical units contained in the time series signals to the same interval, and encoding discrete variables contained in the time series signals to obtain feature signals; and then integrating the extracted features through a single-layer or multi-layer fusion mechanism of time series fusion, semantic fusion and / or hierarchical fusion to generate a unified fusion feature vector as a processing result of the input blood pressure signal conversion model.

[0060] Preferably, the system proposed in the embodiment further comprises: The intelligent drug delivery module 40 is used to obtain individual characteristic parameters of a user, input the calibrated continuous blood pressure signal of the user, physiological response data related to the applied pressure and the individual characteristic parameters into the intelligent analysis model which is completed training as input data, analyze the blood pressure response relationship of the user under different applied pressures and different drug doses through the intelligent analysis model, predict the optimal drug delivery combination, and output a personalized auxiliary prescription scheme including individualized drug dose, drug delivery frequency, drug use time, synergistic plan of drug and physical regulation, drug reminder information and / or physiotherapy reminder information, finally provide drug or physiotherapy reminders based on the personalized auxiliary scheme, generate a synergistic execution scheme of the antihypertensive drug and the physical regulation, and / or control the transdermal or microneedle automatic drug delivery device to deliver drugs.

[0061] The microcirculation detection module 50 is used to detect pulse waveforms at at least two measurement points on the same arterial path of the user, obtain distribution characteristics reflecting local blood perfusion, vascular reactivity and microcirculation perfusion state based on time domain differences, amplitude differences and / or waveform morphology differences between each group of adjacent measurement points, evaluate the local hemodynamic state of the arterial path according to the distribution characteristics, and dynamically adjust the pressure and / or regulation parameters currently applied by the wearable device; in this way, the microcirculation monitoring can be realized by replacing the traditional double-finger palpation, the peak detection and delay calculation are performed through multi-point signal input, and parameters such as perfusion index and peak ratio are output to reflect the local blood perfusion and reperfusion state.

[0062] Embodiment 3 The embodiment provides a wearable device, and the wearable device provided in the embodiment applies the intelligent closed-loop hypertension management method based on the wearable device as provided in the embodiment 1.

[0063] Preferably, referring to Figure 11 The wearable device provided in the embodiment can be in communication connection with a terminal such as a smart phone, so that a real-time blood pressure display area, a blood pressure trend chart, a peripheral pressure regulation control area, a massage and snapshot measurement function area, a microcirculation detection function area and a drug management module are displayed on the interface of the terminal, the user can view the real-time blood pressure and trend change, adjust the applied pressure parameters, obtain a drug reminder and upload data through the interface, so that an integrated operation of monitoring, intervention and management is realized.

[0064] In conclusion, the present application provides an intelligent closed-loop hypertension management method, system and wearable device based on a wearable device, the scheme provided in the present application combines the controllable peripheral pressure stimulation with the undisturbed continuous blood pressure monitoring, realizes the real-time adaptive hemodynamic regulation and intelligent closed-loop control, constructs a continuous and real-time intelligent closed-loop hypertension management mechanism, can realize the blood pressure management covering all time periods and all scenes, and is suitable for hypertension regulation, cardiovascular and cerebrovascular disease prevention and individualized treatment assistance.

[0065] The above description is only the preferred embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A smart closed-loop hypertension management method based on wearable devices, characterized in that, The method includes: In response to a pressure signal, pressure is applied to a designated area of ​​the user's body via a wearable device based on preset control parameters, inducing local blood flow changes in the pressure area to regulate hemodynamic state; The system collects the user's continuous blood pressure signal and instantaneous reference blood pressure value in real time, and dynamically calibrates the continuous blood pressure signal using the instantaneous reference blood pressure value. The wearable device dynamically adjusts the pressure currently applied and / or the control parameters based on the calibrated continuous blood pressure signal; the control parameters include pressure value, pressure application duration, and pressure application interval. The wearable device is then able to apply pressure in the next stage based on the updated control parameters, thereby enabling an adaptive closed-loop control between peripheral pressure stimulation and continuous blood pressure monitoring.

2. The intelligent closed-loop hypertension management method based on wearable devices according to claim 1, characterized in that, The method further includes: After pressure is applied through the wearable device, the pressure fluctuation characteristics within the pressure area are detected to obtain data on the deformation amplitude of the pressure-time curve reflecting tissue elasticity and vascular compliance, data on the pressure recovery rate during the inflation and deflation process reflecting local blood perfusion characteristics, and phase difference data and / or amplitude difference data of physiological sensor signals reflecting the degree of response of blood vessels beneath the tissue to external pressure; the physiological sensor signals are one or more of optical signals, mechanical signals, electrical / impedance signals, acoustic signals, or ultrasound signals.

3. The intelligent closed-loop hypertension management method based on wearable devices according to claim 1, characterized in that, The dynamic adjustment of the pressure currently applied by the wearable device and / or the control parameters based on the calibrated continuous blood pressure signal includes: When the calibrated continuous blood pressure signal is higher than a first preset threshold, the pressure value of the currently applied preset pressure is reduced or the currently applied preset pressure is stopped, and the pressure application interval is extended accordingly. When the calibrated continuous blood pressure signal is lower than the second preset threshold, the pressure value is increased accordingly, the pressure application duration is extended accordingly, and / or the pressure application interval is shortened accordingly; the second preset threshold is lower than the first preset threshold. And / or, based on historical blood pressure data, physiological signals acquired by the wearable device, and / or the user's individual characteristics, a regulation model is trained by performing feature extraction and correlation analysis. The regulation model establishes a mapping relationship between blood pressure changes, the regulation parameters, and the user's individual response, so as to adjust the pressure currently applied by the wearable device and / or the regulation parameters based on the mapping relationship.

4. The intelligent closed-loop hypertension management method based on wearable devices according to claim 1 or 3, characterized in that, The method for acquiring the user's continuous blood pressure signal and performing dynamic calibration includes: Acquire physiological signals characterizing changes in tissues or blood vessels during the cardiac cycle, collected by at least one of optical, pressure, electrical, impedance, strain, acoustic, and ultrasonic sensors. The physiological signals are preprocessed and features are extracted, and the features are input into the trained blood pressure signal conversion model; The instantaneous reference blood pressure value is used as reference blood pressure information to dynamically calibrate the blood pressure signal conversion model so that the model outputs a blood pressure signal waveform that represents continuous blood pressure changes, which is then used as the calibrated continuous blood pressure signal.

5. The intelligent closed-loop hypertension management method based on wearable devices according to claim 4, characterized in that, Processing the physiological signals includes: The physiological signals and the pressure signals are preprocessed to generate time-synchronized time-series signals; The time-series signal is subjected to feature extraction, and the obtained features are mapped to a unified feature space to form a feature signal; The feature signals are fused temporally, semantically, and / or hierarchically based on a feature fusion mechanism to generate a fused feature vector for input to a blood pressure signal conversion model.

6. The intelligent closed-loop hypertension management method based on wearable devices according to claim 1, characterized in that, The method further includes: Pulse waveforms are detected at at least two measurement points along the same arterial pathway of the user; Based on the temporal, amplitude and / or waveform morphology differences between adjacent measurement points in each group, distribution characteristics reflecting local blood perfusion, vascular reactivity and microcirculation perfusion status are obtained. The local hemodynamic state of the arterial pathway is assessed based on the distribution characteristics, and the pressure currently applied by the wearable device and / or the regulation parameters are dynamically adjusted accordingly.

7. The intelligent closed-loop hypertension management method based on wearable devices according to claim 1 or 2, characterized in that, The method further includes: Obtain the individual characteristic parameters of the user; The intelligent analysis model is trained by inputting the user's calibrated continuous blood pressure signal, physiological response data related to applied pressure, and individual characteristic parameters as input data. The intelligent analysis model analyzes the user's blood pressure response under different external pressures and drug dosages, predicts the optimal drug dosing combination, and outputs a personalized auxiliary prescription plan that includes individualized drug dosage, dosing frequency, medication time, synergistic plan of drug and physical regulation, drug reminder information and / or physical therapy reminder information. Based on the personalized assistance plan, medication or physical therapy reminders are provided, a synergistic execution plan for antihypertensive drugs and physical regulation is generated, and / or, a transdermal or microneedle automated drug delivery device is controlled to administer medication.

8. The intelligent closed-loop hypertension management method based on wearable devices according to claim 1, characterized in that, The designated areas include the upper arm area, wrist area, hand area, foot area and / or ankle area, and each designated area corresponds to an independent control parameter.

9. A smart closed-loop hypertension management system based on wearable devices, characterized in that, The system includes: The peripheral pressure regulation module is used to respond to pressure signals and apply pressure to a designated area of ​​the user's body through a wearable device based on preset regulation parameters, thereby inducing local blood flow changes in the pressure area to regulate hemodynamic state. The blood pressure monitoring module is used to collect the user's continuous blood pressure signal and instantaneous reference blood pressure value in real time, and to dynamically calibrate the continuous blood pressure signal using the instantaneous reference blood pressure value; The intelligent control module is used to dynamically adjust the pressure currently applied by the wearable device and / or the control parameters based on the calibrated continuous blood pressure signal, and to enable the wearable device to perform the next stage of pressure application based on the updated control parameters, thereby forming an adaptive closed-loop control between peripheral pressure stimulation and continuous blood pressure monitoring; the control parameters include pressure value, pressure application duration, and pressure application interval.

10. A wearable device, characterized in that, The intelligent closed-loop hypertension management method based on wearable devices as described in any one of claims 1-8 is applied.

Images